1410 files changed, 57863 insertions, 27728 deletions

diff --git a/.mailmap b/.mailmap
index 9ad98690876a..074082ce9299 100644
--- a/.mailmap
+++ b/.mailmap
@@ -135,6 +135,7 @@ Ben Widawsky <bwidawsk@kernel.org> <benjamin.widawsky@intel.com>
 Benjamin Poirier <benjamin.poirier@gmail.com> <bpoirier@suse.de>
 Benjamin Tissoires <bentiss@kernel.org> <benjamin.tissoires@gmail.com>
 Benjamin Tissoires <bentiss@kernel.org> <benjamin.tissoires@redhat.com>
+Benno Lossin <lossin@kernel.org> <benno.lossin@proton.me>
 Bingwu Zhang <xtex@aosc.io> <xtexchooser@duck.com>
 Bingwu Zhang <xtex@aosc.io> <xtex@xtexx.eu.org>
 Bjorn Andersson <andersson@kernel.org> <bjorn@kryo.se>
@@ -419,6 +420,8 @@ Krishna Manikandan <quic_mkrishn@quicinc.com> <mkrishn@codeaurora.org>
 Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com>
 Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com>
 Krzysztof Kozlowski <krzk@kernel.org> <krzysztof.kozlowski@canonical.com>
+Krzysztof Wilczyński <kwilczynski@kernel.org> <krzysztof.wilczynski@linux.com>
+Krzysztof Wilczyński <kwilczynski@kernel.org> <kw@linux.com>
 Kshitiz Godara <quic_kgodara@quicinc.com> <kgodara@codeaurora.org>
 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 Kuogee Hsieh <quic_khsieh@quicinc.com> <khsieh@codeaurora.org>
@@ -461,6 +464,7 @@ Maheshwar Ajja <quic_majja@quicinc.com> <majja@codeaurora.org>
 Malathi Gottam <quic_mgottam@quicinc.com> <mgottam@codeaurora.org>
 Manikanta Pubbisetty <quic_mpubbise@quicinc.com> <mpubbise@codeaurora.org>
 Manivannan Sadhasivam <mani@kernel.org> <manivannanece23@gmail.com>
+Manivannan Sadhasivam <mani@kernel.org> <manivannan.sadhasivam@linaro.org>
 Manoj Basapathi <quic_manojbm@quicinc.com> <manojbm@codeaurora.org>
 Marcin Nowakowski <marcin.nowakowski@mips.com> <marcin.nowakowski@imgtec.com>
 Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com>
diff --git a/Documentation/ABI/testing/debugfs-pcie-ptm b/Documentation/ABI/testing/debugfs-pcie-ptm
new file mode 100644
index 000000000000..602d41363571
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-pcie-ptm
@@ -0,0 +1,70 @@
+What:		/sys/kernel/debug/pcie_ptm_*/local_clock
+Date:		May 2025
+Contact:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+Description:
+		(RO) PTM local clock in nanoseconds. Applicable for both Root
+		Complex and Endpoint controllers.
+
+What:		/sys/kernel/debug/pcie_ptm_*/master_clock
+Date:		May 2025
+Contact:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+Description:
+		(RO) PTM master clock in nanoseconds. Applicable only for
+		Endpoint controllers.
+
+What:		/sys/kernel/debug/pcie_ptm_*/t1
+Date:		May 2025
+Contact:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+Description:
+		(RO) PTM T1 timestamp in nanoseconds. Applicable only for
+		Endpoint controllers.
+
+What:		/sys/kernel/debug/pcie_ptm_*/t2
+Date:		May 2025
+Contact:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+Description:
+		(RO) PTM T2 timestamp in nanoseconds. Applicable only for
+		Root Complex controllers.
+
+What:		/sys/kernel/debug/pcie_ptm_*/t3
+Date:		May 2025
+Contact:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+Description:
+		(RO) PTM T3 timestamp in nanoseconds. Applicable only for
+		Root Complex controllers.
+
+What:		/sys/kernel/debug/pcie_ptm_*/t4
+Date:		May 2025
+Contact:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+Description:
+		(RO) PTM T4 timestamp in nanoseconds. Applicable only for
+		Endpoint controllers.
+
+What:		/sys/kernel/debug/pcie_ptm_*/context_update
+Date:		May 2025
+Contact:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+Description:
+		(RW) Control the PTM context update mode. Applicable only for
+		Endpoint controllers.
+
+		Following values are supported:
+
+		* auto = PTM context auto update trigger for every 10ms
+
+		* manual = PTM context manual update. Writing 'manual' to this
+			   file triggers PTM context update (default)
+
+What:		/sys/kernel/debug/pcie_ptm_*/context_valid
+Date:		May 2025
+Contact:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+Description:
+		(RW) Control the PTM context validity (local clock timing).
+		Applicable only for Root Complex controllers. PTM context is
+		invalidated by hardware if the Root Complex enters low power
+		mode or changes link frequency.
+
+		Following values are supported:
+
+		* 0 = PTM context invalid (default)
+
+		* 1 = PTM context valid
diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl
index 99bb3faf7a0e..6b4e8c7a963d 100644
--- a/Documentation/ABI/testing/sysfs-bus-cxl
+++ b/Documentation/ABI/testing/sysfs-bus-cxl
@@ -242,7 +242,7 @@ Description:
 		decoding a Host Physical Address range. Note that this number
 		may be elevated without any regionX objects active or even
 		enumerated, as this may be due to decoders established by
-		platform firwmare or a previous kernel (kexec).
+		platform firmware or a previous kernel (kexec).
 
 
 What:		/sys/bus/cxl/devices/decoderX.Y
@@ -572,7 +572,7 @@ Description:
 
 
 What:		/sys/bus/cxl/devices/regionZ/accessY/read_bandwidth
-		/sys/bus/cxl/devices/regionZ/accessY/write_banwidth
+		/sys/bus/cxl/devices/regionZ/accessY/write_bandwidth
 Date:		Jan, 2024
 KernelVersion:	v6.9
 Contact:	linux-cxl@vger.kernel.org
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer
index d1f67bb81d5d..5ed284523956 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer
@@ -117,3 +117,47 @@ Date:		July 2018
 KernelVersion:	4.19.0
 Contact:	linux-pci@vger.kernel.org, rajatja@google.com
 Description:	Total number of ERR_NONFATAL messages reported to rootport.
+
+PCIe AER ratelimits
+-------------------
+
+These attributes show up under all the devices that are AER capable.
+They represent configurable ratelimits of logs per error type.
+
+See Documentation/PCI/pcieaer-howto.rst for more info on ratelimits.
+
+What:		/sys/bus/pci/devices/<dev>/aer/correctable_ratelimit_interval_ms
+Date:		May 2025
+KernelVersion:	6.16.0
+Contact:	linux-pci@vger.kernel.org
+Description:	Writing 0 disables AER correctable error log ratelimiting.
+		Writing a positive value sets the ratelimit interval in ms.
+		Default is DEFAULT_RATELIMIT_INTERVAL (5000 ms).
+
+What:		/sys/bus/pci/devices/<dev>/aer/correctable_ratelimit_burst
+Date:		May 2025
+KernelVersion:	6.16.0
+Contact:	linux-pci@vger.kernel.org
+Description:	Ratelimit burst for correctable error logs. Writing a value
+		changes the number of errors (burst) allowed per interval
+		before ratelimiting. Reading gets the current ratelimit
+		burst. Default is DEFAULT_RATELIMIT_BURST (10).
+
+What:		/sys/bus/pci/devices/<dev>/aer/nonfatal_ratelimit_interval_ms
+Date:		May 2025
+KernelVersion:	6.16.0
+Contact:	linux-pci@vger.kernel.org
+Description:	Writing 0 disables AER non-fatal uncorrectable error log
+		ratelimiting. Writing a positive value sets the ratelimit
+		interval in ms. Default is DEFAULT_RATELIMIT_INTERVAL
+		(5000 ms).
+
+What:		/sys/bus/pci/devices/<dev>/aer/nonfatal_ratelimit_burst
+Date:		May 2025
+KernelVersion:	6.16.0
+Contact:	linux-pci@vger.kernel.org
+Description:	Ratelimit burst for non-fatal uncorrectable error logs.
+		Writing a value changes the number of errors (burst)
+		allowed per interval before ratelimiting. Reading gets the
+		current ratelimit burst. Default is DEFAULT_RATELIMIT_BURST
+		(10).
diff --git a/Documentation/ABI/testing/sysfs-class-led b/Documentation/ABI/testing/sysfs-class-led
index 2e24ac3bd7ef..0313b82644f2 100644
--- a/Documentation/ABI/testing/sysfs-class-led
+++ b/Documentation/ABI/testing/sysfs-class-led
@@ -72,6 +72,12 @@ Description:
 		/sys/class/leds/<led> once a given trigger is selected. For
 		their documentation see `sysfs-class-led-trigger-*`.
 
+		Writing "none" removes the trigger for this LED.
+
+		Writing "default" sets the trigger to the LED's default trigger
+		(which would often be configured in the device tree for the
+		hardware).
+
 What:		/sys/class/leds/<led>/inverted
 Date:		January 2011
 KernelVersion:	2.6.38
diff --git a/Documentation/PCI/controller/index.rst b/Documentation/PCI/controller/index.rst
new file mode 100644
index 000000000000..c2ce9ccdcfa0
--- /dev/null
+++ b/Documentation/PCI/controller/index.rst
@@ -0,0 +1,10 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================================
+PCI Native Host Bridge and Endpoint Drivers
+===========================================
+
+.. toctree::
+   :maxdepth: 2
+
+   rcar-pcie-firmware
diff --git a/Documentation/PCI/controller/rcar-pcie-firmware.rst b/Documentation/PCI/controller/rcar-pcie-firmware.rst
new file mode 100644
index 000000000000..67d3bf66e315
--- /dev/null
+++ b/Documentation/PCI/controller/rcar-pcie-firmware.rst
@@ -0,0 +1,32 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=================================================
+Firmware of PCIe controller for Renesas R-Car V4H
+=================================================
+
+Renesas R-Car V4H (r8a779g0) has a PCIe controller, requiring a specific
+firmware download during startup.
+
+However, Renesas currently cannot distribute the firmware free of charge.
+
+The firmware file "104_PCIe_fw_addr_data_ver1.05.txt" (note that the file name
+might be different between different datasheet revisions) can be found in the
+datasheet encoded as text, and as such, the file's content must be converted
+back to binary form. This can be achieved using the following example script:
+
+.. code-block:: sh
+
+	$ awk '/^\s*0x[0-9A-Fa-f]{4}\s+0x[0-9A-Fa-f]{4}/ { print substr($2,5,2) substr($2,3,2) }' \
+		104_PCIe_fw_addr_data_ver1.05.txt | \
+			xxd -p -r > rcar_gen4_pcie.bin
+
+Once the text content has been converted into a binary firmware file, verify
+its checksum as follows:
+
+.. code-block:: sh
+
+	$ sha1sum rcar_gen4_pcie.bin
+	1d0bd4b189b4eb009f5d564b1f93a79112994945  rcar_gen4_pcie.bin
+
+The resulting binary file called "rcar_gen4_pcie.bin" should be placed in the
+"/lib/firmware" directory before the driver runs.
diff --git a/Documentation/PCI/endpoint/pci-nvme-function.rst b/Documentation/PCI/endpoint/pci-nvme-function.rst
index df57b8e7d066..a68015317f7f 100644
--- a/Documentation/PCI/endpoint/pci-nvme-function.rst
+++ b/Documentation/PCI/endpoint/pci-nvme-function.rst
@@ -8,6 +8,6 @@ PCI NVMe Function
 
 The PCI NVMe endpoint function implements a PCI NVMe controller using the NVMe
 subsystem target core code. The driver for this function resides with the NVMe
-subsystem as drivers/nvme/target/nvmet-pciep.c.
+subsystem as drivers/nvme/target/pci-epf.c.
 
 See Documentation/nvme/nvme-pci-endpoint-target.rst for more details.
diff --git a/Documentation/PCI/index.rst b/Documentation/PCI/index.rst
index 5e7c4e6e726b..5d720d2a415e 100644
--- a/Documentation/PCI/index.rst
+++ b/Documentation/PCI/index.rst
@@ -17,5 +17,6 @@ PCI Bus Subsystem
    pci-error-recovery
    pcieaer-howto
    endpoint/index
+   controller/index
    boot-interrupts
    tph
diff --git a/Documentation/PCI/pcieaer-howto.rst b/Documentation/PCI/pcieaer-howto.rst
index f013f3b27c82..4b71e2f43ca7 100644
--- a/Documentation/PCI/pcieaer-howto.rst
+++ b/Documentation/PCI/pcieaer-howto.rst
@@ -85,12 +85,27 @@ In the example, 'Requester ID' means the ID of the device that sent
 the error message to the Root Port. Please refer to PCIe specs for other
 fields.
 
+AER Ratelimits
+--------------
+
+Since error messages can be generated for each transaction, we may see
+large volumes of errors reported. To prevent spammy devices from flooding
+the console/stalling execution, messages are throttled by device and error
+type (correctable vs. non-fatal uncorrectable).  Fatal errors, including
+DPC errors, are not ratelimited.
+
+AER uses the default ratelimit of DEFAULT_RATELIMIT_BURST (10 events) over
+DEFAULT_RATELIMIT_INTERVAL (5 seconds).
+
+Ratelimits are exposed in the form of sysfs attributes and configurable.
+See Documentation/ABI/testing/sysfs-bus-pci-devices-aer.
+
 AER Statistics / Counters
 -------------------------
 
 When PCIe AER errors are captured, the counters / statistics are also exposed
 in the form of sysfs attributes which are documented at
-Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
+Documentation/ABI/testing/sysfs-bus-pci-devices-aer.
 
 Developer Guide
 ===============
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index bd98ea3175ec..0cc35a14afbe 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1732,6 +1732,12 @@ The following nested keys are defined.
 	  numa_hint_faults (npn)
 		Number of NUMA hinting faults.
 
+	  numa_task_migrated (npn)
+		Number of task migration by NUMA balancing.
+
+	  numa_task_swapped (npn)
+		Number of task swap by NUMA balancing.
+
 	  pgdemote_kswapd
 		Number of pages demoted by kswapd.
 
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a3ea40b22fb9..f1f2c0874da9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -458,6 +458,9 @@
 	arm64.nomops	[ARM64] Unconditionally disable Memory Copy and Memory
 			Set instructions support
 
+	arm64.nompam	[ARM64] Unconditionally disable Memory Partitioning And
+			Monitoring support
+
 	arm64.nomte	[ARM64] Unconditionally disable Memory Tagging Extension
 			support
 
diff --git a/Documentation/devicetree/bindings/arm/atmel,sama5d2-secumod.yaml b/Documentation/devicetree/bindings/arm/atmel,sama5d2-secumod.yaml
new file mode 100644
index 000000000000..ad4a98a4ee67
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/atmel,sama5d2-secumod.yaml
@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/arm/atmel,sama5d2-secumod.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Microchip AT91 Security Module (SECUMOD)
+
+maintainers:
+  - Nicolas Ferre <nicolas.ferre@microchip.com>
+
+description:
+  The Security Module also offers the PIOBU pins which can be used as GPIO pins.
+  Note that they maintain their voltage during Backup/Self-refresh.
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - const: atmel,sama5d2-secumod
+          - const: syscon
+      - items:
+          - enum:
+              - microchip,sama7d65-secumod
+              - microchip,sama7g5-secumod
+          - const: atmel,sama5d2-secumod
+          - const: syscon
+  reg:
+    maxItems: 1
+
+  gpio-controller: true
+
+  "#gpio-cells":
+    const: 2
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    security-module@fc040000 {
+      compatible = "atmel,sama5d2-secumod", "syscon";
+      reg = <0xfc040000 0x100>;
+      gpio-controller;
+      #gpio-cells = <2>;
+    };
diff --git a/Documentation/devicetree/bindings/arm/atmel-sysregs.txt b/Documentation/devicetree/bindings/arm/atmel-sysregs.txt
index d3821f651e72..5ce54f9befe6 100644
--- a/Documentation/devicetree/bindings/arm/atmel-sysregs.txt
+++ b/Documentation/devicetree/bindings/arm/atmel-sysregs.txt
@@ -46,28 +46,3 @@ Examples:
 		reg = <0xffffe800 0x200>;
 	};
 
-Security Module (SECUMOD)
-
-The Security Module macrocell provides all necessary secure functions to avoid
-voltage, temperature, frequency and mechanical attacks on the chip. It also
-embeds secure memories that can be scrambled.
-
-The Security Module also offers the PIOBU pins which can be used as GPIO pins.
-Note that they maintain their voltage during Backup/Self-refresh.
-
-required properties:
-- compatible: Should be "atmel,<chip>-secumod", "syscon".
-  <chip> can be "sama5d2".
-- reg: Should contain registers location and length
-- gpio-controller:	Marks the port as GPIO controller.
-- #gpio-cells:		There are 2. The pin number is the
-			first, the second represents additional
-			parameters such as GPIO_ACTIVE_HIGH/LOW.
-
-
-	secumod@fc040000 {
-		compatible = "atmel,sama5d2-secumod", "syscon";
-		reg = <0xfc040000 0x100>;
-		gpio-controller;
-		#gpio-cells = <2>;
-	};
diff --git a/Documentation/devicetree/bindings/ata/ahci-dm816.txt b/Documentation/devicetree/bindings/ata/ahci-dm816.txt
deleted file mode 100644
index f8c535f3541f..000000000000
--- a/Documentation/devicetree/bindings/ata/ahci-dm816.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-Device tree binding for the TI DM816 AHCI SATA Controller
----------------------------------------------------------
-
-Required properties:
-  - compatible: must be "ti,dm816-ahci"
-  - reg: physical base address and size of the register region used by
-         the controller (as defined by the AHCI 1.1 standard)
-  - interrupts: interrupt specifier (refer to the interrupt binding)
-  - clocks: list of phandle and clock specifier pairs (or only
-            phandles for clock providers with '0' defined for
-            #clock-cells); two clocks must be specified: the functional
-            clock and an external reference clock
-
-Example:
-
-	sata: sata@4a140000 {
-		compatible = "ti,dm816-ahci";
-		reg = <0x4a140000 0x10000>;
-		interrupts = <16>;
-		clocks = <&sysclk5_ck>, <&sata_refclk>;
-	};
diff --git a/Documentation/devicetree/bindings/ata/ahci-st.txt b/Documentation/devicetree/bindings/ata/ahci-st.txt
deleted file mode 100644
index 909c9935360d..000000000000
--- a/Documentation/devicetree/bindings/ata/ahci-st.txt
+++ /dev/null
@@ -1,35 +0,0 @@
-STMicroelectronics STi SATA controller
-
-This binding describes a SATA device.
-
-Required properties:
- - compatible	   : Must be "st,ahci"
- - reg		   : Physical base addresses and length of register sets
- - interrupts	   : Interrupt associated with the SATA device
- - interrupt-names :   Associated name must be; "hostc"
- - clocks	   : The phandle for the clock
- - clock-names	   :   Associated name must be; "ahci_clk"
- - phys		   : The phandle for the PHY port
- - phy-names	   :   Associated name must be; "ahci_phy"
-
-Optional properties:
- - resets	   : The power-down, soft-reset and power-reset lines of SATA IP
- - reset-names	   :   Associated names must be; "pwr-dwn", "sw-rst" and "pwr-rst"
-
-Example:
-
-	/* Example for stih407 family silicon */
-	sata0: sata@9b20000 {
-		compatible	= "st,ahci";
-		reg		= <0x9b20000 0x1000>;
-		interrupts	= <GIC_SPI 159 IRQ_TYPE_NONE>;
-		interrupt-names	= "hostc";
-		phys		= <&phy_port0 PHY_TYPE_SATA>;
-		phy-names	= "ahci_phy";
-		resets		= <&powerdown STIH407_SATA0_POWERDOWN>,
-				  <&softreset STIH407_SATA0_SOFTRESET>,
-				  <&softreset STIH407_SATA0_PWR_SOFTRESET>;
-		reset-names	= "pwr-dwn", "sw-rst", "pwr-rst";
-		clocks		= <&clk_s_c0_flexgen CLK_ICN_REG>;
-		clock-names	= "ahci_clk";
-	};
diff --git a/Documentation/devicetree/bindings/ata/apm,xgene-ahci.yaml b/Documentation/devicetree/bindings/ata/apm,xgene-ahci.yaml
new file mode 100644
index 000000000000..7dc942808656
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/apm,xgene-ahci.yaml
@@ -0,0 +1,58 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ata/apm,xgene-ahci.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: APM X-Gene 6.0 Gb/s SATA host controller
+
+maintainers:
+  - Rob Herring <robh@kernel.org>
+
+allOf:
+  - $ref: ahci-common.yaml#
+
+properties:
+  compatible:
+    enum:
+      - apm,xgene-ahci
+      - apm,xgene-ahci-pcie
+
+  reg:
+    minItems: 4
+    items:
+      - description: AHCI memory resource
+      - description: Host controller core
+      - description: Host controller diagnostic
+      - description: Host controller AXI
+      - description: Host controller MUX
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - clocks
+  - phys
+  - phy-names
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    sata@1a400000 {
+        compatible = "apm,xgene-ahci";
+        reg = <0x1a400000 0x1000>,
+              <0x1f220000 0x1000>,
+              <0x1f22d000 0x1000>,
+              <0x1f22e000 0x1000>,
+              <0x1f227000 0x1000>;
+        clocks = <&sataclk 0>;
+        dma-coherent;
+        interrupts = <0x0 0x87 0x4>;
+        phys = <&phy2 0>;
+        phy-names = "sata-phy";
+    };
diff --git a/Documentation/devicetree/bindings/ata/apm-xgene.txt b/Documentation/devicetree/bindings/ata/apm-xgene.txt
deleted file mode 100644
index 02e690a675db..000000000000
--- a/Documentation/devicetree/bindings/ata/apm-xgene.txt
+++ /dev/null
@@ -1,77 +0,0 @@
-* APM X-Gene 6.0 Gb/s SATA host controller nodes
-
-SATA host controller nodes are defined to describe on-chip Serial ATA
-controllers. Each SATA controller (pair of ports) have its own node.
-
-Required properties:
-- compatible		: Shall contain:
-  * "apm,xgene-ahci"
-- reg			: First memory resource shall be the AHCI memory
-			  resource.
-			  Second memory resource shall be the host controller
-			  core memory resource.
-			  Third memory resource shall be the host controller
-			  diagnostic memory resource.
-			  4th memory resource shall be the host controller
-			  AXI memory resource.
-			  5th optional memory resource shall be the host
-			  controller MUX memory resource if required.
-- interrupts		: Interrupt-specifier for SATA host controller IRQ.
-- clocks		: Reference to the clock entry.
-- phys			: A list of phandles + phy-specifiers, one for each
-			  entry in phy-names.
-- phy-names		: Should contain:
-  * "sata-phy" for the SATA 6.0Gbps PHY
-
-Optional properties:
-- dma-coherent		: Present if dma operations are coherent
-- status		: Shall be "ok" if enabled or "disabled" if disabled.
-			  Default is "ok".
-
-Example:
-		sataclk: sataclk {
-			compatible = "fixed-clock";
-			#clock-cells = <1>;
-			clock-frequency = <100000000>;
-			clock-output-names = "sataclk";
-		};
-
-		phy2: phy@1f22a000 {
-			compatible = "apm,xgene-phy";
-			reg = <0x0 0x1f22a000 0x0 0x100>;
-			#phy-cells = <1>;
-		};
-
-		phy3: phy@1f23a000 {
-			compatible = "apm,xgene-phy";
-			reg = <0x0 0x1f23a000 0x0 0x100>;
-			#phy-cells = <1>;
-		};
-
-		sata2: sata@1a400000 {
-			compatible = "apm,xgene-ahci";
-			reg = <0x0 0x1a400000 0x0 0x1000>,
-			      <0x0 0x1f220000 0x0 0x1000>,
-			      <0x0 0x1f22d000 0x0 0x1000>,
-			      <0x0 0x1f22e000 0x0 0x1000>,
-			      <0x0 0x1f227000 0x0 0x1000>;
-			interrupts = <0x0 0x87 0x4>;
-			dma-coherent;
-			clocks = <&sataclk 0>;
-			phys = <&phy2 0>;
-			phy-names = "sata-phy";
-		};
-
-		sata3: sata@1a800000 {
-			compatible = "apm,xgene-ahci-pcie";
-			reg = <0x0 0x1a800000 0x0 0x1000>,
-			      <0x0 0x1f230000 0x0 0x1000>,
-			      <0x0 0x1f23d000 0x0 0x1000>,
-			      <0x0 0x1f23e000 0x0 0x1000>,
-			      <0x0 0x1f237000 0x0 0x1000>;
-			interrupts = <0x0 0x88 0x4>;
-			dma-coherent;
-			clocks = <&sataclk 0>;
-			phys = <&phy3 0>;
-			phy-names = "sata-phy";
-		};
diff --git a/Documentation/devicetree/bindings/ata/arasan,cf-spear1340.yaml b/Documentation/devicetree/bindings/ata/arasan,cf-spear1340.yaml
new file mode 100644
index 000000000000..4d7017452dda
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/arasan,cf-spear1340.yaml
@@ -0,0 +1,70 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ata/arasan,cf-spear1340.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Arasan PATA Compact Flash Controller
+
+maintainers:
+  - Viresh Kumar <viresh.kumar@linaro.org>
+
+properties:
+  compatible:
+    const: arasan,cf-spear1340
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  arasan,broken-udma:
+    description: UDMA mode is unusable
+    type: boolean
+
+  arasan,broken-mwdma:
+    description: MWDMA mode is unusable
+    type: boolean
+
+  arasan,broken-pio:
+    description: PIO mode is unusable
+    type: boolean
+
+  dmas:
+    maxItems: 1
+
+  dma-names:
+    items:
+      - const: data
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+additionalProperties: false
+
+allOf:
+  - if:
+      not:
+        required:
+          - arasan,broken-udma
+          - arasan,broken-mwdma
+    then:
+      required:
+        - dmas
+        - dma-names
+
+examples:
+  - |
+    cf@fc000000 {
+        compatible = "arasan,cf-spear1340";
+        reg = <0xfc000000 0x1000>;
+        interrupts = <12>;
+        dmas = <&dma 23>;
+        dma-names = "data";
+    };
diff --git a/Documentation/devicetree/bindings/ata/cavium,ebt3000-compact-flash.yaml b/Documentation/devicetree/bindings/ata/cavium,ebt3000-compact-flash.yaml
new file mode 100644
index 000000000000..349f289b81e6
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/cavium,ebt3000-compact-flash.yaml
@@ -0,0 +1,59 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ata/cavium,ebt3000-compact-flash.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Cavium Compact Flash
+
+maintainers:
+  - Rob Herring <robh@kernel.org>
+
+description:
+  The Cavium Compact Flash device is connected to the Octeon Boot Bus, and is
+  thus a child of the Boot Bus device.  It can read and write industry standard
+  compact flash devices.
+
+properties:
+  compatible:
+    const: cavium,ebt3000-compact-flash
+
+  reg:
+    description: The base address of the CF chip select banks.
+    items:
+      - description: CF chip select bank 0
+      - description: CF chip select bank 1
+
+  cavium,bus-width:
+    description: The width of the connection to the CF devices.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [8, 16]
+
+  cavium,true-ide:
+    description: True IDE mode when present.
+    type: boolean
+
+  cavium,dma-engine-handle:
+    description: A phandle for the DMA Engine connected to this device.
+    $ref: /schemas/types.yaml#/definitions/phandle
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    bus {
+        #address-cells = <2>;
+        #size-cells = <1>;
+
+        compact-flash@5,0 {
+            compatible = "cavium,ebt3000-compact-flash";
+            reg = <5 0 0x10000>, <6 0 0x10000>;
+            cavium,bus-width = <16>;
+            cavium,true-ide;
+            cavium,dma-engine-handle = <&dma0>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/ata/cavium-compact-flash.txt b/Documentation/devicetree/bindings/ata/cavium-compact-flash.txt
deleted file mode 100644
index 3bacc8e0931e..000000000000
--- a/Documentation/devicetree/bindings/ata/cavium-compact-flash.txt
+++ /dev/null
@@ -1,30 +0,0 @@
-* Compact Flash
-
-The Cavium Compact Flash device is connected to the Octeon Boot Bus,
-and is thus a child of the Boot Bus device.  It can read and write
-industry standard compact flash devices.
-
-Properties:
-- compatible: "cavium,ebt3000-compact-flash";
-
-  Compatibility with many Cavium evaluation boards.
-
-- reg: The base address of the CF chip select banks.  Depending on
-  the device configuration, there may be one or two banks.
-
-- cavium,bus-width: The width of the connection to the CF devices.  Valid
-  values are 8 and 16.
-
-- cavium,true-ide: Optional, if present the CF connection is in True IDE mode.
-
-- cavium,dma-engine-handle: Optional, a phandle for the DMA Engine connected
-  to this device.
-
-Example:
-	compact-flash@5,0 {
-		compatible = "cavium,ebt3000-compact-flash";
-		reg = <5 0 0x10000>, <6 0 0x10000>;
-		cavium,bus-width = <16>;
-		cavium,true-ide;
-		cavium,dma-engine-handle = <&dma0>;
-	};
diff --git a/Documentation/devicetree/bindings/ata/marvell,orion-sata.yaml b/Documentation/devicetree/bindings/ata/marvell,orion-sata.yaml
new file mode 100644
index 000000000000..f656ea9223d6
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/marvell,orion-sata.yaml
@@ -0,0 +1,83 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ata/marvell,orion-sata.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Marvell Orion SATA
+
+maintainers:
+  - Andrew Lunn <andrew@lunn.ch>
+  - Gregory Clement <gregory.clement@bootlin.com>
+
+allOf:
+  - $ref: sata-common.yaml#
+
+properties:
+  compatible:
+    enum:
+      - marvell,orion-sata
+      - marvell,armada-370-sata
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+    maxItems: 8
+
+  clock-names:
+    minItems: 1
+    items:
+      - const: '0'
+      - const: '1'
+      - const: '2'
+      - const: '3'
+      - const: '4'
+      - const: '5'
+      - const: '6'
+      - const: '7'
+
+  interrupts:
+    maxItems: 1
+
+  nr-ports:
+    description:
+      Number of SATA ports in use.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    maximum: 8
+
+  phys:
+    minItems: 1
+    maxItems: 8
+
+  phy-names:
+    minItems: 1
+    items:
+      - const: port0
+      - const: port1
+      - const: port2
+      - const: port3
+      - const: port4
+      - const: port5
+      - const: port6
+      - const: port7
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - nr-ports
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    sata@80000 {
+        compatible = "marvell,orion-sata";
+        reg = <0x80000 0x5000>;
+        interrupts = <21>;
+        phys = <&sata_phy0>, <&sata_phy1>;
+        phy-names = "port0", "port1";
+        nr-ports = <2>;
+    };
diff --git a/Documentation/devicetree/bindings/ata/marvell.txt b/Documentation/devicetree/bindings/ata/marvell.txt
deleted file mode 100644
index b460edd12766..000000000000
--- a/Documentation/devicetree/bindings/ata/marvell.txt
+++ /dev/null
@@ -1,22 +0,0 @@
-* Marvell Orion SATA
-
-Required Properties:
-- compatibility : "marvell,orion-sata" or "marvell,armada-370-sata"
-- reg           : Address range of controller
-- interrupts    : Interrupt controller is using
-- nr-ports      : Number of SATA ports in use.
-
-Optional Properties:
-- phys		: List of phandles to sata phys
-- phy-names	: Should be "0", "1", etc, one number per phandle
-
-Example:
-
-	sata@80000 {
-		compatible = "marvell,orion-sata";
-		reg = <0x80000 0x5000>;
-		interrupts = <21>;
-		phys = <&sata_phy0>, <&sata_phy1>;
-		phy-names = "0", "1";
-		nr-ports = <2>;
-	}
diff --git a/Documentation/devicetree/bindings/ata/pata-arasan.txt b/Documentation/devicetree/bindings/ata/pata-arasan.txt
deleted file mode 100644
index 872edc105680..000000000000
--- a/Documentation/devicetree/bindings/ata/pata-arasan.txt
+++ /dev/null
@@ -1,37 +0,0 @@
-* ARASAN PATA COMPACT FLASH CONTROLLER
-
-Required properties:
-- compatible: "arasan,cf-spear1340"
-- reg: Address range of the CF registers
-- interrupt: Should contain the CF interrupt number
-- clock-frequency: Interface clock rate, in Hz, one of
-       25000000
-       33000000
-       40000000
-       50000000
-       66000000
-       75000000
-      100000000
-      125000000
-      150000000
-      166000000
-      200000000
-
-Optional properties:
-- arasan,broken-udma: if present, UDMA mode is unusable
-- arasan,broken-mwdma: if present, MWDMA mode is unusable
-- arasan,broken-pio: if present, PIO mode is unusable
-- dmas: one DMA channel, as described in bindings/dma/dma.txt
-  required unless both UDMA and MWDMA mode are broken
-- dma-names: the corresponding channel name, must be "data"
-
-Example:
-
-	cf@fc000000 {
-		compatible = "arasan,cf-spear1340";
-		reg = <0xfc000000 0x1000>;
-		interrupt-parent = <&vic1>;
-		interrupts = <12>;
-		dmas = <&dma-controller 23>;
-		dma-names = "data";
-	};
diff --git a/Documentation/devicetree/bindings/ata/rockchip,dwc-ahci.yaml b/Documentation/devicetree/bindings/ata/rockchip,dwc-ahci.yaml
index 13eaa8d9a16e..b5ecaabfe2e2 100644
--- a/Documentation/devicetree/bindings/ata/rockchip,dwc-ahci.yaml
+++ b/Documentation/devicetree/bindings/ata/rockchip,dwc-ahci.yaml
@@ -20,6 +20,7 @@ select:
       contains:
         enum:
           - rockchip,rk3568-dwc-ahci
+          - rockchip,rk3576-dwc-ahci
           - rockchip,rk3588-dwc-ahci
   required:
     - compatible
@@ -29,6 +30,7 @@ properties:
     items:
       - enum:
           - rockchip,rk3568-dwc-ahci
+          - rockchip,rk3576-dwc-ahci
           - rockchip,rk3588-dwc-ahci
       - const: snps,dwc-ahci
 
@@ -83,6 +85,7 @@ allOf:
           contains:
             enum:
               - rockchip,rk3568-dwc-ahci
+              - rockchip,rk3576-dwc-ahci
     then:
       properties:
         clocks:
diff --git a/Documentation/devicetree/bindings/ata/st,ahci.yaml b/Documentation/devicetree/bindings/ata/st,ahci.yaml
new file mode 100644
index 000000000000..6e8e4b4f3d6c
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/st,ahci.yaml
@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ata/st,ahci.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STMicroelectronics STi SATA controller
+
+maintainers:
+  - Patrice Chotard <patrice.chotard@foss.st.com>
+
+allOf:
+  - $ref: ahci-common.yaml#
+
+properties:
+  compatible:
+    const: st,ahci
+
+  interrupt-names:
+    items:
+      - const: hostc
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    items:
+      - const: ahci_clk
+
+  resets:
+    items:
+      - description: Power-down line
+      - description: Soft-reset line
+      - description: Power-reset line
+
+  reset-names:
+    items:
+      - const: pwr-dwn
+      - const: sw-rst
+      - const: pwr-rst
+
+required:
+  - compatible
+  - interrupt-names
+  - phys
+  - phy-names
+  - clocks
+  - clock-names
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/phy/phy.h>
+    #include <dt-bindings/reset/stih407-resets.h>
+    #include <dt-bindings/clock/stih407-clks.h>
+
+    sata@9b20000 {
+        compatible    = "st,ahci";
+        reg           = <0x9b20000 0x1000>;
+        interrupts    = <GIC_SPI 159 IRQ_TYPE_NONE>;
+        interrupt-names = "hostc";
+        phys          = <&phy_port0 PHY_TYPE_SATA>;
+        phy-names     = "sata-phy";
+        resets        = <&powerdown STIH407_SATA0_POWERDOWN>,
+                         <&softreset STIH407_SATA0_SOFTRESET>,
+                         <&softreset STIH407_SATA0_PWR_SOFTRESET>;
+        reset-names   = "pwr-dwn", "sw-rst", "pwr-rst";
+        clocks        = <&clk_s_c0_flexgen CLK_ICN_REG>;
+        clock-names   = "ahci_clk";
+    };
diff --git a/Documentation/devicetree/bindings/ata/ti,dm816-ahci.yaml b/Documentation/devicetree/bindings/ata/ti,dm816-ahci.yaml
new file mode 100644
index 000000000000..d0ff9e78afe6
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/ti,dm816-ahci.yaml
@@ -0,0 +1,43 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ata/ti,dm816-ahci.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: TI DM816 AHCI SATA Controller
+
+maintainers:
+  - Bartosz Golaszewski <brgl@bgdev.pl>
+
+allOf:
+  - $ref: ahci-common.yaml#
+
+properties:
+  compatible:
+    const: ti,dm816-ahci
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: functional clock
+      - description: external reference clock
+
+  ti,hwmods:
+    const: sata
+
+required:
+  - compatible
+  - clocks
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    sata@4a140000 {
+        compatible = "ti,dm816-ahci";
+        reg = <0x4a140000 0x10000>;
+        interrupts = <16>;
+        clocks = <&sysclk5_ck>, <&sata_refclk>;
+    };
diff --git a/Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml b/Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml
index a8d40c766dcd..0bea4f5287ce 100644
--- a/Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml
+++ b/Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml
@@ -10,8 +10,8 @@ maintainers:
   - Saurabh Sengar <ssengar@linux.microsoft.com>
 
 description:
-  VMBus is a software bus that implement the protocols for communication
-  between the root or host OS and guest OSs (virtual machines).
+  VMBus is a software bus that implements the protocols for communication
+  between the root or host OS and guest OS'es (virtual machines).
 
 properties:
   compatible:
@@ -25,9 +25,16 @@ properties:
   '#size-cells':
     const: 1
 
+  dma-coherent: true
+
+  interrupts:
+    maxItems: 1
+    description: Interrupt is used to report a message from the host.
+
 required:
   - compatible
   - ranges
+  - interrupts
   - '#address-cells'
   - '#size-cells'
 
@@ -35,6 +42,8 @@ additionalProperties: false
 
 examples:
   - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
     soc {
         #address-cells = <2>;
         #size-cells = <1>;
@@ -49,6 +58,9 @@ examples:
                 #address-cells = <2>;
                 #size-cells = <1>;
                 ranges = <0x0f 0xf0000000 0x0f 0xf0000000 0x10000000>;
+                dma-coherent;
+                interrupt-parent = <&gic>;
+                interrupts = <GIC_PPI 2 IRQ_TYPE_EDGE_RISING>;
             };
         };
     };
diff --git a/Documentation/devicetree/bindings/dma/arm,dma-350.yaml b/Documentation/devicetree/bindings/dma/arm,dma-350.yaml
new file mode 100644
index 000000000000..429f682f15d8
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/arm,dma-350.yaml
@@ -0,0 +1,44 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/arm,dma-350.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Arm CoreLink DMA-350 Controller
+
+maintainers:
+  - Robin Murphy <robin.murphy@arm.com>
+
+allOf:
+  - $ref: dma-controller.yaml#
+
+properties:
+  compatible:
+    const: arm,dma-350
+
+  reg:
+    items:
+      - description: Base and size of the full register map
+
+  interrupts:
+    minItems: 1
+    items:
+      - description: Channel 0 interrupt
+      - description: Channel 1 interrupt
+      - description: Channel 2 interrupt
+      - description: Channel 3 interrupt
+      - description: Channel 4 interrupt
+      - description: Channel 5 interrupt
+      - description: Channel 6 interrupt
+      - description: Channel 7 interrupt
+
+  "#dma-cells":
+    const: 1
+    description: The cell is the trigger input number
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+unevaluatedProperties: false
diff --git a/Documentation/devicetree/bindings/dma/fsl,edma.yaml b/Documentation/devicetree/bindings/dma/fsl,edma.yaml
index 950e8fa4f4ab..fa4248e2f1b9 100644
--- a/Documentation/devicetree/bindings/dma/fsl,edma.yaml
+++ b/Documentation/devicetree/bindings/dma/fsl,edma.yaml
@@ -48,11 +48,11 @@ properties:
 
   interrupts:
     minItems: 1
-    maxItems: 64
+    maxItems: 65
 
   interrupt-names:
     minItems: 1
-    maxItems: 64
+    maxItems: 65
 
   "#dma-cells":
     description: |
diff --git a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
index d3f8c269916c..da0235e451d6 100644
--- a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
+++ b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
@@ -19,6 +19,7 @@ properties:
       - enum:
           - nvidia,tegra210-adma
           - nvidia,tegra186-adma
+          - nvidia,tegra264-adma
       - items:
           - enum:
               - nvidia,tegra234-adma
@@ -92,6 +93,7 @@ allOf:
           contains:
             enum:
               - nvidia,tegra186-adma
+              - nvidia,tegra264-adma
     then:
       anyOf:
         - properties:
diff --git a/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml b/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml
index 3ad0d9b1fbc5..f2f87f0f545b 100644
--- a/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml
+++ b/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml
@@ -42,6 +42,8 @@ properties:
   interrupts:
     maxItems: 1
 
+  dma-coherent: true
+
   iommus:
     minItems: 1
     maxItems: 6
diff --git a/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml b/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
index b356251de5a8..92b12762c472 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
+++ b/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml
@@ -11,19 +11,23 @@ maintainers:
 
 properties:
   compatible:
-    items:
-      - enum:
-          - renesas,r7s72100-dmac # RZ/A1H
-          - renesas,r9a07g043-dmac # RZ/G2UL and RZ/Five
-          - renesas,r9a07g044-dmac # RZ/G2{L,LC}
-          - renesas,r9a07g054-dmac # RZ/V2L
-          - renesas,r9a08g045-dmac # RZ/G3S
-      - const: renesas,rz-dmac
+    oneOf:
+      - items:
+          - enum:
+              - renesas,r7s72100-dmac # RZ/A1H
+              - renesas,r9a07g043-dmac # RZ/G2UL and RZ/Five
+              - renesas,r9a07g044-dmac # RZ/G2{L,LC}
+              - renesas,r9a07g054-dmac # RZ/V2L
+              - renesas,r9a08g045-dmac # RZ/G3S
+          - const: renesas,rz-dmac
+
+      - const: renesas,r9a09g057-dmac # RZ/V2H(P)
 
   reg:
     items:
       - description: Control and channel register block
       - description: DMA extended resource selector block
+    minItems: 1
 
   interrupts:
     maxItems: 17
@@ -52,6 +56,7 @@ properties:
     items:
       - description: DMA main clock
       - description: DMA register access clock
+    minItems: 1
 
   clock-names:
     items:
@@ -61,10 +66,10 @@ properties:
   '#dma-cells':
     const: 1
     description:
-      The cell specifies the encoded MID/RID values of the DMAC port
-      connected to the DMA client and the slave channel configuration
-      parameters.
-      bits[0:9] - Specifies MID/RID value
+      The cell specifies the encoded MID/RID or the REQ No values of
+      the DMAC port connected to the DMA client and the slave channel
+      configuration parameters.
+      bits[0:9] - Specifies the MID/RID or the REQ No value
       bit[10] - Specifies DMA request high enable (HIEN)
       bit[11] - Specifies DMA request detection type (LVL)
       bits[12:14] - Specifies DMAACK output mode (AM)
@@ -80,12 +85,26 @@ properties:
     items:
       - description: Reset for DMA ARESETN reset terminal
       - description: Reset for DMA RST_ASYNC reset terminal
+    minItems: 1
 
   reset-names:
     items:
       - const: arst
       - const: rst_async
 
+  renesas,icu:
+    description:
+      It must contain the phandle to the ICU and the index of the DMAC as seen
+      from the ICU.
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      - items:
+          - description: Phandle to the ICU node.
+          - description:
+              The number of the DMAC as seen from the ICU, i.e. parameter k from
+              register ICU_DMkSELy. This may differ from the actual DMAC instance
+              number.
+
 required:
   - compatible
   - reg
@@ -98,13 +117,25 @@ allOf:
   - $ref: dma-controller.yaml#
 
   - if:
-      not:
-        properties:
-          compatible:
-            contains:
-              enum:
-                - renesas,r7s72100-dmac
+      properties:
+        compatible:
+          contains:
+            enum:
+              - renesas,r9a07g043-dmac
+              - renesas,r9a07g044-dmac
+              - renesas,r9a07g054-dmac
+              - renesas,r9a08g045-dmac
     then:
+      properties:
+        reg:
+          minItems: 2
+        clocks:
+          minItems: 2
+        resets:
+          minItems: 2
+
+        renesas,icu: false
+
       required:
         - clocks
         - clock-names
@@ -112,6 +143,46 @@ allOf:
         - resets
         - reset-names
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: renesas,r7s72100-dmac
+    then:
+      properties:
+        reg:
+          minItems: 2
+
+        clocks: false
+        clock-names: false
+        power-domains: false
+        resets: false
+        reset-names: false
+        renesas,icu: false
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: renesas,r9a09g057-dmac
+    then:
+      properties:
+        reg:
+          maxItems: 1
+        clocks:
+          maxItems: 1
+        resets:
+          maxItems: 1
+
+        clock-names: false
+        reset-names: false
+
+      required:
+        - clocks
+        - power-domains
+        - renesas,icu
+        - resets
+
 additionalProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/hwmon/pmbus/adi,lt3074.yaml b/Documentation/devicetree/bindings/hwmon/pmbus/adi,lt3074.yaml
new file mode 100644
index 000000000000..bf028a8718f1
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/pmbus/adi,lt3074.yaml
@@ -0,0 +1,50 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/hwmon/pmbus/adi,lt3074.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Analog Devices LT3074 voltage regulator
+
+maintainers:
+  - Cedric Encarnacion <cedricjustine.encarnacion@analog.com>
+
+description: |
+  The LT3074 is a low voltage, ultra-low noise and ultra-fast transient
+  response linear regulator. It allows telemetry for input/output voltage,
+  output current and temperature through the PMBus serial interface.
+
+  Datasheet:
+    https://www.analog.com/en/products/lt3074.html
+
+allOf:
+  - $ref: /schemas/regulator/regulator.yaml#
+
+properties:
+  compatible:
+    enum:
+      - adi,lt3074
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        regulator@6d {
+            compatible = "adi,lt3074";
+            reg = <0x6d>;
+            regulator-name = "vout";
+            regulator-max-microvolt = <1250000>;
+            regulator-min-microvolt = <1150000>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/hwmon/pmbus/mps,mpq8785.yaml b/Documentation/devicetree/bindings/hwmon/pmbus/mps,mpq8785.yaml
new file mode 100644
index 000000000000..90970a0433e9
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/pmbus/mps,mpq8785.yaml
@@ -0,0 +1,74 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/hwmon/pmbus/mps,mpq8785.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Monolithic Power Systems Multiphase Voltage Regulators with PMBus
+
+maintainers:
+  - Charles Hsu <ythsu0511@gmail.com>
+
+description:
+  Monolithic Power Systems digital multiphase voltage regulators with PMBus.
+
+properties:
+  compatible:
+    enum:
+      - mps,mpm3695
+      - mps,mpm3695-25
+      - mps,mpm82504
+      - mps,mpq8785
+
+  reg:
+    maxItems: 1
+
+  mps,vout-fb-divider-ratio-permille:
+    description:
+      The feedback resistor divider ratio, expressed in permille
+      (Vfb / Vout * 1000). This value is written to the PMBUS_VOUT_SCALE_LOOP
+      register and is required for correct output voltage presentation.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 1
+    maximum: 4095
+    default: 706
+
+required:
+  - compatible
+  - reg
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          enum:
+            - mps,mpm3695
+            - mps,mpm82504
+    then:
+      properties:
+        mps,vout-fb-divider-ratio-permille:
+          maximum: 1023
+
+  - if:
+      properties:
+        compatible:
+          const: mps,mpq8785
+    then:
+      properties:
+        mps,vout-fb-divider-ratio-permille:
+          maximum: 2047
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      pmic@30 {
+        compatible = "mps,mpm82504";
+        reg = <0x30>;
+        mps,vout-fb-divider-ratio-permille = <600>;
+      };
+    };
diff --git a/Documentation/devicetree/bindings/hwmon/sophgo,sg2042-hwmon-mcu.yaml b/Documentation/devicetree/bindings/hwmon/sophgo,sg2042-hwmon-mcu.yaml
index f0667ac41d75..b76805d39427 100644
--- a/Documentation/devicetree/bindings/hwmon/sophgo,sg2042-hwmon-mcu.yaml
+++ b/Documentation/devicetree/bindings/hwmon/sophgo,sg2042-hwmon-mcu.yaml
@@ -11,7 +11,11 @@ maintainers:
 
 properties:
   compatible:
-    const: sophgo,sg2042-hwmon-mcu
+    oneOf:
+      - items:
+          - const: sophgo,sg2044-hwmon-mcu
+          - const: sophgo,sg2042-hwmon-mcu
+      - const: sophgo,sg2042-hwmon-mcu
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/hwmon/ti,amc6821.yaml b/Documentation/devicetree/bindings/hwmon/ti,amc6821.yaml
index 5d33f1a23d03..9ca7356760a7 100644
--- a/Documentation/devicetree/bindings/hwmon/ti,amc6821.yaml
+++ b/Documentation/devicetree/bindings/hwmon/ti,amc6821.yaml
@@ -28,6 +28,17 @@ properties:
   i2c-mux:
     type: object
 
+  fan:
+    $ref: fan-common.yaml#
+    unevaluatedProperties: false
+
+  "#pwm-cells":
+    const: 2
+    description: |
+      Number of cells in a PWM specifier.
+      - cell 0: PWM period in nanoseconds
+      - cell 1: PWM polarity: 0 or PWM_POLARITY_INVERTED
+
 required:
   - compatible
   - reg
@@ -50,9 +61,14 @@ examples:
         #address-cells = <1>;
         #size-cells = <0>;
 
-        fan@18 {
+        fan_controller: fan@18 {
             compatible = "ti,amc6821";
             reg = <0x18>;
+            #pwm-cells = <2>;
+
+            fan {
+                pwms = <&fan_controller 40000 0>;
+            };
         };
     };
 
diff --git a/Documentation/devicetree/bindings/hwmon/ti,ina2xx.yaml b/Documentation/devicetree/bindings/hwmon/ti,ina2xx.yaml
index bc03781342c0..d1fb7b9abda0 100644
--- a/Documentation/devicetree/bindings/hwmon/ti,ina2xx.yaml
+++ b/Documentation/devicetree/bindings/hwmon/ti,ina2xx.yaml
@@ -19,6 +19,7 @@ description: |
 properties:
   compatible:
     enum:
+      - silergy,sq52206
       - silergy,sy24655
       - ti,ina209
       - ti,ina219
@@ -58,6 +59,9 @@ properties:
       shunt voltage, and a value of 4 maps to ADCRANGE=0 such that a wider
       voltage range is used.
 
+      For SQ52206,the shunt-gain value 1 mapps to ADCRANGE=10/11, the value 2
+      mapps to ADCRANGE=01, and the value 4 mapps to ADCRANGE=00.
+
       The default value is device dependent, and is defined by the reset value
       of PGA/ADCRANGE in the respective configuration registers.
     $ref: /schemas/types.yaml#/definitions/uint32
@@ -97,6 +101,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - silergy,sq52206
               - silergy,sy24655
               - ti,ina209
               - ti,ina219
diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml
index 7e5b62a0215d..4c89448eba0d 100644
--- a/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml
+++ b/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml
@@ -23,6 +23,9 @@ properties:
   "#thermal-sensor-cells":
     const: 1
 
+  vcc-supply:
+    description: Power supply for tmp102
+
 required:
   - compatible
   - reg
@@ -42,6 +45,7 @@ examples:
             reg = <0x48>;
             interrupt-parent = <&gpio7>;
             interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
+            vcc-supply = <&supply>;
             #thermal-sensor-cells = <1>;
         };
     };
diff --git a/Documentation/devicetree/bindings/leds/ti,tps61310.yaml b/Documentation/devicetree/bindings/leds/ti,tps61310.yaml
new file mode 100644
index 000000000000..118f9c8bfdf7
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/ti,tps61310.yaml
@@ -0,0 +1,120 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/leds/ti,tps61310.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments TPS6131X flash LED driver
+
+maintainers:
+  - Matthias Fend <matthias.fend@emfend.at>
+
+description: |
+  The TPS61310/TPS61311 is a flash LED driver with I2C interface.
+  Its power stage is capable of supplying a maximum total current of roughly 1500mA.
+  The TPS6131x provides three constant-current sinks, capable of sinking
+  up to 2 x 400mA (LED1 and LED3) and 800mA (LED2) in flash mode.
+  In torch mode, each sink (LED1, LED2, LED3) supports currents up to 175mA.
+  Since the three current sinks share most of the control components such as
+  flash timer, control logic, safety timer and the operating mode, they cannot
+  be used completely independently of each other. Therefore, only one LED is
+  supported, but the current sinks can be combined accordingly.
+
+  The data sheet can be found at:
+    https://www.ti.com/lit/ds/symlink/tps61310.pdf
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - ti,tps61311
+          - const: ti,tps61310
+      - items:
+          - const: ti,tps61310
+
+  reg:
+    maxItems: 1
+
+  reset-gpios:
+    maxItems: 1
+    description: GPIO connected to NRESET pin
+
+  ti,valley-current-limit:
+    type: boolean
+    description:
+      Reduce the valley peak current limit from 1750mA to 1250mA (TPS61310) or
+      from 2480mA to 1800mA (TPS61311).
+
+  led:
+    type: object
+    $ref: common.yaml#
+    unevaluatedProperties: false
+
+    properties:
+      led-sources:
+        minItems: 1
+        maxItems: 3
+        items:
+          enum: [1, 2, 3]
+
+      led-max-microamp:
+        oneOf:
+          - minimum: 50000
+            maximum: 350000
+            multipleOf: 50000
+          - minimum: 25000
+            maximum: 525000
+            multipleOf: 25000
+
+      flash-max-microamp:
+        oneOf:
+          - minimum: 50000
+            maximum: 800000
+            multipleOf: 50000
+          - minimum: 25000
+            maximum: 1500000
+            multipleOf: 25000
+
+      flash-max-timeout-us:
+        enum: [ 5300, 10700, 16000, 21300, 26600, 32000, 37300, 68200, 71500,
+                102200, 136300, 170400, 204500, 340800, 579300, 852000 ]
+
+    required:
+      - led-sources
+      - led-max-microamp
+      - flash-max-microamp
+      - flash-max-timeout-us
+
+required:
+  - compatible
+  - reg
+  - led
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/leds/common.h>
+    #include <dt-bindings/gpio/gpio.h>
+
+    i2c {
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      led-controller@33 {
+        compatible = "ti,tps61311", "ti,tps61310";
+        reg = <0x33>;
+
+        reset-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;
+
+        led {
+          function = LED_FUNCTION_FLASH;
+          color = <LED_COLOR_ID_WHITE>;
+          led-sources = <1>, <2>, <3>;
+          led-max-microamp = <525000>;
+          flash-max-microamp = <1500000>;
+          flash-max-timeout-us = <852000>;
+        };
+      };
+    };
diff --git a/Documentation/devicetree/bindings/mfd/atmel,at91sam9260-gpbr.yaml b/Documentation/devicetree/bindings/mfd/atmel,at91sam9260-gpbr.yaml
index f805545aa62a..f6f47999c6c1 100644
--- a/Documentation/devicetree/bindings/mfd/atmel,at91sam9260-gpbr.yaml
+++ b/Documentation/devicetree/bindings/mfd/atmel,at91sam9260-gpbr.yaml
@@ -19,6 +19,7 @@ properties:
       - items:
           - enum:
               - atmel,at91sam9260-gpbr
+              - microchip,sama7d65-gpbr
           - const: syscon
       - items:
           - enum:
diff --git a/Documentation/devicetree/bindings/mfd/brcm,bcm59056.txt b/Documentation/devicetree/bindings/mfd/brcm,bcm59056.txt
deleted file mode 100644
index be51a15e05f9..000000000000
--- a/Documentation/devicetree/bindings/mfd/brcm,bcm59056.txt
+++ /dev/null
@@ -1,39 +0,0 @@
--------------------------------
-BCM590xx Power Management Units
--------------------------------
-
-Required properties:
-- compatible: "brcm,bcm59056"
-- reg: I2C slave address
-- interrupts: interrupt for the PMU. Generic interrupt client node bindings
-  are described in interrupt-controller/interrupts.txt
-
-------------------
-Voltage Regulators
-------------------
-
-Optional child nodes:
-- regulators: container node for regulators following the generic
-  regulator binding in regulator/regulator.txt
-
-  The valid regulator node names for BCM59056 are:
-  	rfldo, camldo1, camldo2, simldo1, simldo2, sdldo, sdxldo,
-	mmcldo1, mmcldo2, audldo, micldo, usbldo, vibldo,
-	csr, iosr1, iosr2, msr, sdsr1, sdsr2, vsr,
-	gpldo1, gpldo2, gpldo3, gpldo4, gpldo5, gpldo6,
-	vbus
-
-Example:
-	pmu: bcm59056@8 {
-		compatible = "brcm,bcm59056";
-		reg = <0x08>;
-		interrupts = <GIC_SPI 215 IRQ_TYPE_LEVEL_HIGH>;
-		regulators {
-			rfldo_reg: rfldo {
-				regulator-min-microvolt = <1200000>;
-				regulator-max-microvolt = <3300000>;
-			};
-
-			...
-		};
-	};
diff --git a/Documentation/devicetree/bindings/mfd/brcm,bcm59056.yaml b/Documentation/devicetree/bindings/mfd/brcm,bcm59056.yaml
new file mode 100644
index 000000000000..b67d7a723fc2
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/brcm,bcm59056.yaml
@@ -0,0 +1,76 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mfd/brcm,bcm59056.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Broadcom BCM590xx Power Management Units
+
+maintainers:
+  - Artur Weber <aweber.kernel@gmail.com>
+
+properties:
+  compatible:
+    enum:
+      - brcm,bcm59054
+      - brcm,bcm59056
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  regulators:
+    type: object
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+additionalProperties: false
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: brcm,bcm59054
+    then:
+      properties:
+        regulators:
+          $ref: /schemas/regulator/brcm,bcm59054.yaml#
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: brcm,bcm59056
+    then:
+      properties:
+        regulators:
+          $ref: /schemas/regulator/brcm,bcm59056.yaml#
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pmic@8 {
+            compatible = "brcm,bcm59056";
+            reg = <0x08>;
+            interrupts = <GIC_SPI 215 IRQ_TYPE_LEVEL_HIGH>;
+
+            regulators {
+                rfldo {
+                    regulator-min-microvolt = <1200000>;
+                    regulator-max-microvolt = <3300000>;
+                };
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/mfd/iqs62x.yaml b/Documentation/devicetree/bindings/mfd/iqs62x.yaml
index e79ce447a800..f242dd0e18fd 100644
--- a/Documentation/devicetree/bindings/mfd/iqs62x.yaml
+++ b/Documentation/devicetree/bindings/mfd/iqs62x.yaml
@@ -60,43 +60,34 @@ examples:
     #include <dt-bindings/interrupt-controller/irq.h>
 
     i2c {
-            #address-cells = <1>;
-            #size-cells = <0>;
-
-            iqs620a@44 {
-                    compatible = "azoteq,iqs620a";
-                    reg = <0x44>;
-                    interrupt-parent = <&gpio>;
-                    interrupts = <17 IRQ_TYPE_LEVEL_LOW>;
-
-                    keys {
-                            compatible = "azoteq,iqs620a-keys";
-
-                            linux,keycodes = <KEY_SELECT>,
-                                             <KEY_MENU>,
-                                             <KEY_OK>,
-                                             <KEY_MENU>;
-
-                            hall-switch-south {
-                                    linux,code = <SW_LID>;
-                                    azoteq,use-prox;
-                            };
-                    };
-
-                    iqs620a_pwm: pwm {
-                            compatible = "azoteq,iqs620a-pwm";
-                            #pwm-cells = <2>;
-                    };
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        iqs620a@44 {
+            compatible = "azoteq,iqs620a";
+            reg = <0x44>;
+            interrupt-parent = <&gpio>;
+            interrupts = <17 IRQ_TYPE_LEVEL_LOW>;
+
+            keys {
+                compatible = "azoteq,iqs620a-keys";
+
+                linux,keycodes = <KEY_SELECT>,
+                                 <KEY_MENU>,
+                                 <KEY_OK>,
+                                 <KEY_MENU>;
+
+                hall-switch-south {
+                    linux,code = <SW_LID>;
+                    azoteq,use-prox;
+                };
             };
-    };
-
-    pwmleds {
-            compatible = "pwm-leds";
 
-            led-1 {
-                    pwms = <&iqs620a_pwm 0 1000000>;
-                    max-brightness = <255>;
+            iqs620a_pwm: pwm {
+                compatible = "azoteq,iqs620a-pwm";
+                #pwm-cells = <2>;
             };
+        };
     };
 
   - |
@@ -105,37 +96,37 @@ examples:
     #include <dt-bindings/interrupt-controller/irq.h>
 
     i2c {
-            #address-cells = <1>;
-            #size-cells = <0>;
-
-            iqs620a@44 {
-                    compatible = "azoteq,iqs620a";
-                    reg = <0x44>;
-                    interrupt-parent = <&gpio>;
-                    interrupts = <17 IRQ_TYPE_LEVEL_LOW>;
-
-                    firmware-name = "iqs620a_coil.bin";
-
-                    keys {
-                            compatible = "azoteq,iqs620a-keys";
-
-                            linux,keycodes = <0>,
-                                             <0>,
-                                             <0>,
-                                             <0>,
-                                             <0>,
-                                             <0>,
-                                             <KEY_MUTE>;
-
-                            hall-switch-north {
-                                    linux,code = <SW_DOCK>;
-                            };
-
-                            hall-switch-south {
-                                    linux,code = <SW_TABLET_MODE>;
-                            };
-                    };
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        iqs620a@44 {
+            compatible = "azoteq,iqs620a";
+            reg = <0x44>;
+            interrupt-parent = <&gpio>;
+            interrupts = <17 IRQ_TYPE_LEVEL_LOW>;
+
+            firmware-name = "iqs620a_coil.bin";
+
+            keys {
+                compatible = "azoteq,iqs620a-keys";
+
+                linux,keycodes = <0>,
+                                 <0>,
+                                 <0>,
+                                 <0>,
+                                 <0>,
+                                 <0>,
+                                 <KEY_MUTE>;
+
+                hall-switch-north {
+                    linux,code = <SW_DOCK>;
+                };
+
+                hall-switch-south {
+                    linux,code = <SW_TABLET_MODE>;
+                };
             };
+        };
     };
 
   - |
@@ -144,36 +135,36 @@ examples:
     #include <dt-bindings/interrupt-controller/irq.h>
 
     i2c {
-            #address-cells = <1>;
-            #size-cells = <0>;
-
-            iqs624@44 {
-                    compatible = "azoteq,iqs624";
-                    reg = <0x44>;
-                    interrupt-parent = <&gpio>;
-                    interrupts = <17 IRQ_TYPE_LEVEL_LOW>;
-
-                    keys {
-                            compatible = "azoteq,iqs624-keys";
-
-                            linux,keycodes = <BTN_0>,
-                                             <0>,
-                                             <BTN_1>,
-                                             <0>,
-                                             <0>,
-                                             <0>,
-                                             <0>,
-                                             <0>,
-                                             <0>,
-                                             <0>,
-                                             <0>,
-                                             <0>,
-                                             <0>,
-                                             <0>,
-                                             <KEY_VOLUMEUP>,
-                                             <KEY_VOLUMEDOWN>;
-                    };
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        iqs624@44 {
+            compatible = "azoteq,iqs624";
+            reg = <0x44>;
+            interrupt-parent = <&gpio>;
+            interrupts = <17 IRQ_TYPE_LEVEL_LOW>;
+
+            keys {
+                compatible = "azoteq,iqs624-keys";
+
+                linux,keycodes = <BTN_0>,
+                                 <0>,
+                                 <BTN_1>,
+                                 <0>,
+                                 <0>,
+                                 <0>,
+                                 <0>,
+                                 <0>,
+                                 <0>,
+                                 <0>,
+                                 <0>,
+                                 <0>,
+                                 <0>,
+                                 <0>,
+                                 <KEY_VOLUMEUP>,
+                                 <KEY_VOLUMEDOWN>;
             };
+        };
     };
 
 ...
diff --git a/Documentation/devicetree/bindings/mfd/mediatek,mt8195-scpsys.yaml b/Documentation/devicetree/bindings/mfd/mediatek,mt8195-scpsys.yaml
index 768390b92682..0e1d43c96fb9 100644
--- a/Documentation/devicetree/bindings/mfd/mediatek,mt8195-scpsys.yaml
+++ b/Documentation/devicetree/bindings/mfd/mediatek,mt8195-scpsys.yaml
@@ -18,6 +18,7 @@ properties:
   compatible:
     items:
       - enum:
+          - mediatek,mt6893-scpsys
           - mediatek,mt8167-scpsys
           - mediatek,mt8173-scpsys
           - mediatek,mt8183-scpsys
diff --git a/Documentation/devicetree/bindings/mfd/mscc,ocelot.yaml b/Documentation/devicetree/bindings/mfd/mscc,ocelot.yaml
index 8bd1abfc44d9..b613da83dca4 100644
--- a/Documentation/devicetree/bindings/mfd/mscc,ocelot.yaml
+++ b/Documentation/devicetree/bindings/mfd/mscc,ocelot.yaml
@@ -76,12 +76,6 @@ additionalProperties: false
 
 examples:
   - |
-    ocelot_clock: ocelot-clock {
-          compatible = "fixed-clock";
-          #clock-cells = <0>;
-          clock-frequency = <125000000>;
-      };
-
     spi {
         #address-cells = <1>;
         #size-cells = <0>;
diff --git a/Documentation/devicetree/bindings/mfd/netronix,ntxec.yaml b/Documentation/devicetree/bindings/mfd/netronix,ntxec.yaml
index 59a630025f52..37fbb953ea12 100644
--- a/Documentation/devicetree/bindings/mfd/netronix,ntxec.yaml
+++ b/Documentation/devicetree/bindings/mfd/netronix,ntxec.yaml
@@ -48,29 +48,18 @@ examples:
   - |
     #include <dt-bindings/interrupt-controller/irq.h>
     i2c {
-            #address-cells = <1>;
-            #size-cells = <0>;
-
-            ec: embedded-controller@43 {
-                    pinctrl-names = "default";
-                    pinctrl-0 = <&pinctrl_ntxec>;
-
-                    compatible = "netronix,ntxec";
-                    reg = <0x43>;
-                    system-power-controller;
-                    interrupt-parent = <&gpio4>;
-                    interrupts = <11 IRQ_TYPE_EDGE_FALLING>;
-                    #pwm-cells = <2>;
-            };
-    };
-
-    backlight {
-            compatible = "pwm-backlight";
-            pwms = <&ec 0 50000>;
-            power-supply = <&backlight_regulator>;
-    };
-
-    backlight_regulator: regulator-dummy {
-            compatible = "regulator-fixed";
-            regulator-name = "backlight";
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        ec: embedded-controller@43 {
+                pinctrl-names = "default";
+                pinctrl-0 = <&pinctrl_ntxec>;
+
+                compatible = "netronix,ntxec";
+                reg = <0x43>;
+                system-power-controller;
+                interrupt-parent = <&gpio4>;
+                interrupts = <11 IRQ_TYPE_EDGE_FALLING>;
+                #pwm-cells = <2>;
+        };
     };
diff --git a/Documentation/devicetree/bindings/mfd/rohm,bd9571mwv.yaml b/Documentation/devicetree/bindings/mfd/rohm,bd9571mwv.yaml
index 534cf03f36bb..47611c2a982c 100644
--- a/Documentation/devicetree/bindings/mfd/rohm,bd9571mwv.yaml
+++ b/Documentation/devicetree/bindings/mfd/rohm,bd9571mwv.yaml
@@ -99,29 +99,29 @@ examples:
     #include <dt-bindings/interrupt-controller/irq.h>
 
     i2c {
-          #address-cells = <1>;
-          #size-cells = <0>;
-
-          pmic: pmic@30 {
-                  compatible = "rohm,bd9571mwv";
-                  reg = <0x30>;
-                  interrupt-parent = <&gpio2>;
-                  interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
-                  interrupt-controller;
-                  #interrupt-cells = <2>;
-                  gpio-controller;
-                  #gpio-cells = <2>;
-                  rohm,ddr-backup-power = <0xf>;
-                  rohm,rstbmode-pulse;
-
-                  regulators {
-                          dvfs: dvfs {
-                                  regulator-name = "dvfs";
-                                  regulator-min-microvolt = <750000>;
-                                  regulator-max-microvolt = <1030000>;
-                                  regulator-boot-on;
-                                  regulator-always-on;
-                          };
-                  };
-          };
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pmic: pmic@30 {
+            compatible = "rohm,bd9571mwv";
+            reg = <0x30>;
+            interrupt-parent = <&gpio2>;
+            interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+            interrupt-controller;
+            #interrupt-cells = <2>;
+            gpio-controller;
+            #gpio-cells = <2>;
+            rohm,ddr-backup-power = <0xf>;
+            rohm,rstbmode-pulse;
+
+            regulators {
+                dvfs: dvfs {
+                    regulator-name = "dvfs";
+                    regulator-min-microvolt = <750000>;
+                    regulator-max-microvolt = <1030000>;
+                    regulator-boot-on;
+                    regulator-always-on;
+                };
+            };
+        };
     };
diff --git a/Documentation/devicetree/bindings/mfd/rohm,bd96801-pmic.yaml b/Documentation/devicetree/bindings/mfd/rohm,bd96801-pmic.yaml
index efee3de0d9ad..0e06570483ae 100644
--- a/Documentation/devicetree/bindings/mfd/rohm,bd96801-pmic.yaml
+++ b/Documentation/devicetree/bindings/mfd/rohm,bd96801-pmic.yaml
@@ -4,19 +4,21 @@
 $id: http://devicetree.org/schemas/mfd/rohm,bd96801-pmic.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: ROHM BD96801 Scalable Power Management Integrated Circuit
+title: ROHM BD96801/BD96805 Scalable Power Management Integrated Circuit
 
 maintainers:
   - Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
 
 description:
-  BD96801 is an automotive grade single-chip power management IC.
-  It integrates 4 buck converters and 3 LDOs with safety features like
+  BD96801 and BD96805 are automotive grade, single-chip power management ICs.
+  They both integrate 4 buck converters and 3 LDOs with safety features like
   over-/under voltage and over current detection and a watchdog.
 
 properties:
   compatible:
-    const: rohm,bd96801
+    enum:
+      - rohm,bd96801
+      - rohm,bd96805
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/mfd/rohm,bd96802-pmic.yaml b/Documentation/devicetree/bindings/mfd/rohm,bd96802-pmic.yaml
new file mode 100644
index 000000000000..6cbea796d12f
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/rohm,bd96802-pmic.yaml
@@ -0,0 +1,101 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mfd/rohm,bd96802-pmic.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ROHM BD96802 / BD96806 Scalable Power Management Integrated Circuit
+
+maintainers:
+  - Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
+
+description: |
+  BD96802Qxx-C and BD96806 are automotive grade configurable Power Management
+  Integrated Circuits supporting Functional Safety features for application
+  processors, SoCs and FPGAs
+
+properties:
+  compatible:
+    enum:
+      - rohm,bd96802
+      - rohm,bd96806
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    description:
+      The PMIC provides intb and errb IRQ lines. The errb IRQ line is used
+      for fatal IRQs which will cause the PMIC to shut down power outputs.
+      In many systems this will shut down the SoC contolling the PMIC and
+      connecting/handling the errb can be omitted. However, there are cases
+      where the SoC is not powered by the PMIC or has a short time backup
+      energy to handle shutdown of critical hardware. In that case it may be
+      useful to connect the errb and handle errb events.
+    minItems: 1
+    maxItems: 2
+
+  interrupt-names:
+    minItems: 1
+    items:
+      - enum: [intb, errb]
+      - const: errb
+
+  regulators:
+    $ref: ../regulator/rohm,bd96802-regulator.yaml
+    description:
+      List of child nodes that specify the regulators.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - interrupt-names
+  - regulators
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/leds/common.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        pmic: pmic@62 {
+            reg = <0x62>;
+            compatible = "rohm,bd96802";
+            interrupt-parent = <&gpio1>;
+            interrupts = <29 IRQ_TYPE_LEVEL_LOW>, <6 IRQ_TYPE_LEVEL_LOW>;
+            interrupt-names = "intb", "errb";
+
+            regulators {
+                buck1 {
+                    regulator-name = "buck1";
+                    regulator-ramp-delay = <1250>;
+                    /* 0.5V min INITIAL - 150 mV tune */
+                    regulator-min-microvolt = <350000>;
+                    /* 3.3V + 150mV tune */
+                    regulator-max-microvolt = <3450000>;
+
+                    /* These can be set only when PMIC is in STBY */
+                    rohm,initial-voltage-microvolt = <500000>;
+                    regulator-ov-error-microvolt = <230000>;
+                    regulator-uv-error-microvolt = <230000>;
+                    regulator-temp-protection-kelvin = <1>;
+                    regulator-temp-warn-kelvin = <0>;
+                };
+                buck2 {
+                    regulator-name = "buck2";
+                    regulator-min-microvolt = <350000>;
+                    regulator-max-microvolt = <3450000>;
+
+                    rohm,initial-voltage-microvolt = <3000000>;
+                    regulator-ov-error-microvolt = <18000>;
+                    regulator-uv-error-microvolt = <18000>;
+                    regulator-temp-protection-kelvin = <1>;
+                    regulator-temp-warn-kelvin = <1>;
+                };
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml b/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml
index ac5d0c149796..d6b9e2914796 100644
--- a/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml
+++ b/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml
@@ -20,6 +20,7 @@ description: |
 properties:
   compatible:
     enum:
+      - samsung,s2mpg10-pmic
       - samsung,s2mps11-pmic
       - samsung,s2mps13-pmic
       - samsung,s2mps14-pmic
@@ -58,11 +59,12 @@ properties:
       reset (setting buck voltages to default values).
     type: boolean
 
+  system-power-controller: true
+
   wakeup-source: true
 
 required:
   - compatible
-  - reg
   - regulators
 
 additionalProperties: false
@@ -72,6 +74,28 @@ allOf:
       properties:
         compatible:
           contains:
+            const: samsung,s2mpg10-pmic
+    then:
+      properties:
+        reg: false
+        samsung,s2mps11-acokb-ground: false
+        samsung,s2mps11-wrstbi-ground: false
+
+      oneOf:
+        - required: [interrupts]
+        - required: [interrupts-extended]
+
+    else:
+      properties:
+        system-power-controller: false
+
+      required:
+        - reg
+
+  - if:
+      properties:
+        compatible:
+          contains:
             const: samsung,s2mps11-pmic
     then:
       properties:
diff --git a/Documentation/devicetree/bindings/mfd/st,stm32-lptimer.yaml b/Documentation/devicetree/bindings/mfd/st,stm32-lptimer.yaml
index d41308856408..4eabafb8079d 100644
--- a/Documentation/devicetree/bindings/mfd/st,stm32-lptimer.yaml
+++ b/Documentation/devicetree/bindings/mfd/st,stm32-lptimer.yaml
@@ -21,7 +21,12 @@ maintainers:
 
 properties:
   compatible:
-    const: st,stm32-lptimer
+    oneOf:
+      - items:
+          - const: st,stm32mp25-lptimer
+          - const: st,stm32-lptimer
+      - items:
+          - const: st,stm32-lptimer
 
   reg:
     maxItems: 1
@@ -48,13 +53,21 @@ properties:
     minItems: 1
     maxItems: 2
 
+  power-domains:
+    maxItems: 1
+
   pwm:
     type: object
     additionalProperties: false
 
     properties:
       compatible:
-        const: st,stm32-pwm-lp
+        oneOf:
+          - items:
+              - const: st,stm32mp25-pwm-lp
+              - const: st,stm32-pwm-lp
+          - items:
+              - const: st,stm32-pwm-lp
 
       "#pwm-cells":
         const: 3
@@ -69,7 +82,12 @@ properties:
 
     properties:
       compatible:
-        const: st,stm32-lptimer-counter
+        oneOf:
+          - items:
+              - const: st,stm32mp25-lptimer-counter
+              - const: st,stm32-lptimer-counter
+          - items:
+              - const: st,stm32-lptimer-counter
 
     required:
       - compatible
@@ -80,7 +98,12 @@ properties:
 
     properties:
       compatible:
-        const: st,stm32-lptimer-timer
+        oneOf:
+          - items:
+              - const: st,stm32mp25-lptimer-timer
+              - const: st,stm32-lptimer-timer
+          - items:
+              - const: st,stm32-lptimer-timer
 
     required:
       - compatible
@@ -92,13 +115,18 @@ patternProperties:
 
     properties:
       compatible:
-        const: st,stm32-lptimer-trigger
+        oneOf:
+          - items:
+              - const: st,stm32mp25-lptimer-trigger
+              - const: st,stm32-lptimer-trigger
+          - items:
+              - const: st,stm32-lptimer-trigger
 
       reg:
         description: Identify trigger hardware block.
         items:
           minimum: 0
-          maximum: 2
+          maximum: 4
 
     required:
       - compatible
diff --git a/Documentation/devicetree/bindings/mfd/syscon.yaml b/Documentation/devicetree/bindings/mfd/syscon.yaml
index c6bbb19c3e3e..27672adeb1fe 100644
--- a/Documentation/devicetree/bindings/mfd/syscon.yaml
+++ b/Documentation/devicetree/bindings/mfd/syscon.yaml
@@ -84,6 +84,7 @@ select:
           - mediatek,mt2701-pctl-a-syscfg
           - mediatek,mt2712-pctl-a-syscfg
           - mediatek,mt6397-pctl-pmic-syscfg
+          - mediatek,mt7988-topmisc
           - mediatek,mt8135-pctl-a-syscfg
           - mediatek,mt8135-pctl-b-syscfg
           - mediatek,mt8173-pctl-a-syscfg
@@ -98,6 +99,8 @@ select:
           - mstar,msc313-pmsleep
           - nuvoton,ma35d1-sys
           - nuvoton,wpcm450-shm
+          - qcom,apq8064-mmss-sfpb
+          - qcom,apq8064-sps-sic
           - rockchip,px30-qos
           - rockchip,rk3036-qos
           - rockchip,rk3066-qos
@@ -187,9 +190,11 @@ properties:
           - mediatek,mt2701-pctl-a-syscfg
           - mediatek,mt2712-pctl-a-syscfg
           - mediatek,mt6397-pctl-pmic-syscfg
+          - mediatek,mt7988-topmisc
           - mediatek,mt8135-pctl-a-syscfg
           - mediatek,mt8135-pctl-b-syscfg
           - mediatek,mt8173-pctl-a-syscfg
+          - mediatek,mt8365-infracfg-nao
           - mediatek,mt8365-syscfg
           - microchip,lan966x-cpu-syscon
           - microchip,mpfs-sysreg-scb
@@ -201,6 +206,8 @@ properties:
           - mstar,msc313-pmsleep
           - nuvoton,ma35d1-sys
           - nuvoton,wpcm450-shm
+          - qcom,apq8064-mmss-sfpb
+          - qcom,apq8064-sps-sic
           - rockchip,px30-qos
           - rockchip,rk3036-qos
           - rockchip,rk3066-qos
diff --git a/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml b/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml
index 3f7661bdd202..45f015d63df1 100644
--- a/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml
+++ b/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml
@@ -316,106 +316,106 @@ additionalProperties: false
 
 examples:
   - |
-      i2c {
-          #address-cells = <1>;
-          #size-cells = <0>;
-
-          pmic@30 {
-              compatible = "x-powers,axp152";
-              reg = <0x30>;
-              interrupts = <0>;
-              interrupt-controller;
-              #interrupt-cells = <1>;
-          };
-      };
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pmic@30 {
+            compatible = "x-powers,axp152";
+            reg = <0x30>;
+            interrupts = <0>;
+            interrupt-controller;
+            #interrupt-cells = <1>;
+        };
+    };
 
   - |
-      #include <dt-bindings/interrupt-controller/irq.h>
-
-      i2c {
-          #address-cells = <1>;
-          #size-cells = <0>;
-
-          pmic@34 {
-              compatible = "x-powers,axp209";
-              reg = <0x34>;
-              interrupt-parent = <&nmi_intc>;
-              interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
-              interrupt-controller;
-              #interrupt-cells = <1>;
-
-              ac_power_supply: ac-power {
-                  compatible = "x-powers,axp202-ac-power-supply";
-              };
-
-              axp_adc: adc {
-                  compatible = "x-powers,axp209-adc";
-                  #io-channel-cells = <1>;
-              };
-
-              axp_gpio: gpio {
-                  compatible = "x-powers,axp209-gpio";
-                  gpio-controller;
-                  #gpio-cells = <2>;
-
-                  gpio0-adc-pin {
-                      pins = "GPIO0";
-                      function = "adc";
-                  };
-              };
-
-              battery_power_supply: battery-power {
-                  compatible = "x-powers,axp209-battery-power-supply";
-              };
-
-              regulators {
-                  /* Default work frequency for buck regulators */
-                  x-powers,dcdc-freq = <1500>;
-
-                  reg_dcdc2: dcdc2 {
-                      regulator-always-on;
-                      regulator-min-microvolt = <1000000>;
-                      regulator-max-microvolt = <1450000>;
-                      regulator-name = "vdd-cpu";
-                  };
-
-                  reg_dcdc3: dcdc3 {
-                      regulator-always-on;
-                      regulator-min-microvolt = <1000000>;
-                      regulator-max-microvolt = <1400000>;
-                      regulator-name = "vdd-int-dll";
-                  };
-
-                  reg_ldo1: ldo1 {
-                      /* LDO1 is a fixed output regulator */
-                      regulator-always-on;
-                      regulator-min-microvolt = <1300000>;
-                      regulator-max-microvolt = <1300000>;
-                      regulator-name = "vdd-rtc";
-                  };
-
-                  reg_ldo2: ldo2 {
-                      regulator-always-on;
-                      regulator-min-microvolt = <3000000>;
-                      regulator-max-microvolt = <3000000>;
-                      regulator-name = "avcc";
-                  };
-
-                  reg_ldo3: ldo3 {
-                      regulator-name = "ldo3";
-                  };
-
-                  reg_ldo4: ldo4 {
-                      regulator-name = "ldo4";
-                  };
-
-                  reg_ldo5: ldo5 {
-                      regulator-name = "ldo5";
-                  };
-              };
-
-              usb_power_supply: usb-power {
-                  compatible = "x-powers,axp202-usb-power-supply";
-              };
-          };
-      };
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pmic@34 {
+            compatible = "x-powers,axp209";
+            reg = <0x34>;
+            interrupt-parent = <&nmi_intc>;
+            interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+            interrupt-controller;
+            #interrupt-cells = <1>;
+
+            ac_power_supply: ac-power {
+                compatible = "x-powers,axp202-ac-power-supply";
+            };
+
+            axp_adc: adc {
+                compatible = "x-powers,axp209-adc";
+                #io-channel-cells = <1>;
+            };
+
+            axp_gpio: gpio {
+                compatible = "x-powers,axp209-gpio";
+                gpio-controller;
+                #gpio-cells = <2>;
+
+                gpio0-adc-pin {
+                    pins = "GPIO0";
+                    function = "adc";
+                };
+            };
+
+            battery_power_supply: battery-power {
+                compatible = "x-powers,axp209-battery-power-supply";
+            };
+
+            regulators {
+                /* Default work frequency for buck regulators */
+                x-powers,dcdc-freq = <1500>;
+
+                reg_dcdc2: dcdc2 {
+                    regulator-always-on;
+                    regulator-min-microvolt = <1000000>;
+                    regulator-max-microvolt = <1450000>;
+                    regulator-name = "vdd-cpu";
+                };
+
+                reg_dcdc3: dcdc3 {
+                    regulator-always-on;
+                    regulator-min-microvolt = <1000000>;
+                    regulator-max-microvolt = <1400000>;
+                    regulator-name = "vdd-int-dll";
+                };
+
+                reg_ldo1: ldo1 {
+                    /* LDO1 is a fixed output regulator */
+                    regulator-always-on;
+                    regulator-min-microvolt = <1300000>;
+                    regulator-max-microvolt = <1300000>;
+                    regulator-name = "vdd-rtc";
+                };
+
+                reg_ldo2: ldo2 {
+                    regulator-always-on;
+                    regulator-min-microvolt = <3000000>;
+                    regulator-max-microvolt = <3000000>;
+                    regulator-name = "avcc";
+                };
+
+                reg_ldo3: ldo3 {
+                    regulator-name = "ldo3";
+                };
+
+                reg_ldo4: ldo4 {
+                    regulator-name = "ldo4";
+                };
+
+                reg_ldo5: ldo5 {
+                    regulator-name = "ldo5";
+                };
+            };
+
+            usb_power_supply: usb-power {
+                compatible = "x-powers,axp202-usb-power-supply";
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/pci/apple,pcie.yaml b/Documentation/devicetree/bindings/pci/apple,pcie.yaml
index c8775f9cb071..c0852be04f6d 100644
--- a/Documentation/devicetree/bindings/pci/apple,pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/apple,pcie.yaml
@@ -17,6 +17,10 @@ description: |
   implements its root ports.  But the ATU found on most DesignWare
   PCIe host bridges is absent.
 
+  On systems derived from T602x, the PHY registers are in a region
+  separate from the port registers. In that case, there is one PHY
+  register range per port register range.
+
   All root ports share a single ECAM space, but separate GPIOs are
   used to take the PCI devices on those ports out of reset.  Therefore
   the standard "reset-gpios" and "max-link-speed" properties appear on
@@ -30,16 +34,18 @@ description: |
 
 properties:
   compatible:
-    items:
-      - enum:
-          - apple,t8103-pcie
-          - apple,t8112-pcie
-          - apple,t6000-pcie
-      - const: apple,pcie
+    oneOf:
+      - items:
+          - enum:
+              - apple,t8103-pcie
+              - apple,t8112-pcie
+              - apple,t6000-pcie
+          - const: apple,pcie
+      - const: apple,t6020-pcie
 
   reg:
     minItems: 3
-    maxItems: 6
+    maxItems: 10
 
   reg-names:
     minItems: 3
@@ -50,6 +56,10 @@ properties:
       - const: port1
       - const: port2
       - const: port3
+      - const: phy0
+      - const: phy1
+      - const: phy2
+      - const: phy3
 
   ranges:
     minItems: 2
@@ -98,6 +108,15 @@ allOf:
           maxItems: 5
         interrupts:
           maxItems: 3
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: apple,t6020-pcie
+    then:
+      properties:
+        reg-names:
+          minItems: 10
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml b/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
index 29f0e1eb5096..c4f9674e8695 100644
--- a/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
@@ -186,49 +186,48 @@ examples:
     #include <dt-bindings/interrupt-controller/arm-gic.h>
 
     scb {
-            #address-cells = <2>;
-            #size-cells = <1>;
-            pcie0: pcie@7d500000 {
-                    compatible = "brcm,bcm2711-pcie";
-                    reg = <0x0 0x7d500000 0x9310>;
-                    device_type = "pci";
-                    #address-cells = <3>;
-                    #size-cells = <2>;
-                    #interrupt-cells = <1>;
-                    interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
-                                 <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
-                    interrupt-names = "pcie", "msi";
-                    interrupt-map-mask = <0x0 0x0 0x0 0x7>;
-                    interrupt-map = <0 0 0 1 &gicv2 GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH
-                                     0 0 0 2 &gicv2 GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH
-                                     0 0 0 3 &gicv2 GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH
-                                     0 0 0 4 &gicv2 GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>;
-
-                    msi-parent = <&pcie0>;
-                    msi-controller;
-                    ranges = <0x02000000 0x0 0xf8000000 0x6 0x00000000 0x0 0x04000000>;
-                    dma-ranges = <0x42000000 0x1 0x00000000 0x0 0x40000000 0x0 0x80000000>,
-                                 <0x42000000 0x1 0x80000000 0x3 0x00000000 0x0 0x80000000>;
-                    brcm,enable-ssc;
-                    brcm,scb-sizes =  <0x0000000080000000 0x0000000080000000>;
-
-                    /* PCIe bridge, Root Port */
-                    pci@0,0 {
-                            #address-cells = <3>;
-                            #size-cells = <2>;
-                            reg = <0x0 0x0 0x0 0x0 0x0>;
-                            compatible = "pciclass,0604";
-                            device_type = "pci";
-                            vpcie3v3-supply = <&vreg7>;
-                            ranges;
-
-                            /* PCIe endpoint */
-                            pci-ep@0,0 {
-                                    assigned-addresses =
-                                        <0x82010000 0x0 0xf8000000 0x6 0x00000000 0x0 0x2000>;
-                                    reg = <0x0 0x0 0x0 0x0 0x0>;
-                                    compatible = "pci14e4,1688";
-                            };
-                    };
+        #address-cells = <2>;
+        #size-cells = <1>;
+        pcie0: pcie@7d500000 {
+            compatible = "brcm,bcm2711-pcie";
+            reg = <0x0 0x7d500000 0x9310>;
+            device_type = "pci";
+            #address-cells = <3>;
+            #size-cells = <2>;
+            #interrupt-cells = <1>;
+            interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+            interrupt-names = "pcie", "msi";
+            interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+            interrupt-map = <0 0 0 1 &gicv2 GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH
+                             0 0 0 2 &gicv2 GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH
+                             0 0 0 3 &gicv2 GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH
+                             0 0 0 4 &gicv2 GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>;
+
+            msi-parent = <&pcie0>;
+            msi-controller;
+            ranges = <0x02000000 0x0 0xf8000000 0x6 0x00000000 0x0 0x04000000>;
+            dma-ranges = <0x42000000 0x1 0x00000000 0x0 0x40000000 0x0 0x80000000>,
+                         <0x42000000 0x1 0x80000000 0x3 0x00000000 0x0 0x80000000>;
+            brcm,enable-ssc;
+            brcm,scb-sizes =  <0x0000000080000000 0x0000000080000000>;
+
+            /* PCIe bridge, Root Port */
+            pci@0,0 {
+                #address-cells = <3>;
+                #size-cells = <2>;
+                reg = <0x0 0x0 0x0 0x0 0x0>;
+                compatible = "pciclass,0604";
+                device_type = "pci";
+                vpcie3v3-supply = <&vreg7>;
+                ranges;
+
+                /* PCIe endpoint */
+                pci-ep@0,0 {
+                    assigned-addresses = <0x82010000 0x0 0xf8000000 0x6 0x00000000 0x0 0x2000>;
+                    reg = <0x0 0x0 0x0 0x0 0x0>;
+                    compatible = "pci14e4,1688";
+                };
             };
+        };
     };
diff --git a/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.yaml b/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.yaml
index 98651ab22103..8735293962ee 100644
--- a/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.yaml
+++ b/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.yaml
@@ -37,14 +37,14 @@ examples:
         #size-cells = <2>;
 
         pcie-ep@fc000000 {
-                compatible = "cdns,cdns-pcie-ep";
-                reg = <0x0 0xfc000000 0x0 0x01000000>,
-                      <0x0 0x80000000 0x0 0x40000000>;
-                reg-names = "reg", "mem";
-                cdns,max-outbound-regions = <16>;
-                max-functions = /bits/ 8 <8>;
-                phys = <&pcie_phy0>;
-                phy-names = "pcie-phy";
+            compatible = "cdns,cdns-pcie-ep";
+            reg = <0x0 0xfc000000 0x0 0x01000000>,
+                  <0x0 0x80000000 0x0 0x40000000>;
+            reg-names = "reg", "mem";
+            cdns,max-outbound-regions = <16>;
+            max-functions = /bits/ 8 <8>;
+            phys = <&pcie_phy0>;
+            phy-names = "pcie-phy";
         };
     };
 ...
diff --git a/Documentation/devicetree/bindings/pci/intel,keembay-pcie-ep.yaml b/Documentation/devicetree/bindings/pci/intel,keembay-pcie-ep.yaml
index 730e63fd7669..b19f61ae72fb 100644
--- a/Documentation/devicetree/bindings/pci/intel,keembay-pcie-ep.yaml
+++ b/Documentation/devicetree/bindings/pci/intel,keembay-pcie-ep.yaml
@@ -53,17 +53,17 @@ examples:
     #include <dt-bindings/interrupt-controller/arm-gic.h>
     #include <dt-bindings/interrupt-controller/irq.h>
     pcie-ep@37000000 {
-          compatible = "intel,keembay-pcie-ep";
-          reg = <0x37000000 0x00001000>,
-                <0x37100000 0x00001000>,
-                <0x37300000 0x00001000>,
-                <0x36000000 0x01000000>,
-                <0x37800000 0x00000200>;
-          reg-names = "dbi", "dbi2", "atu", "addr_space", "apb";
-          interrupts = <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>,
-                       <GIC_SPI 108 IRQ_TYPE_EDGE_RISING>,
-                       <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>,
-                       <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
-          interrupt-names = "pcie", "pcie_ev", "pcie_err", "pcie_mem_access";
-          num-lanes = <2>;
+        compatible = "intel,keembay-pcie-ep";
+        reg = <0x37000000 0x00001000>,
+              <0x37100000 0x00001000>,
+              <0x37300000 0x00001000>,
+              <0x36000000 0x01000000>,
+              <0x37800000 0x00000200>;
+        reg-names = "dbi", "dbi2", "atu", "addr_space", "apb";
+        interrupts = <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 108 IRQ_TYPE_EDGE_RISING>,
+                     <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
+        interrupt-names = "pcie", "pcie_ev", "pcie_err", "pcie_mem_access";
+        num-lanes = <2>;
     };
diff --git a/Documentation/devicetree/bindings/pci/intel,keembay-pcie.yaml b/Documentation/devicetree/bindings/pci/intel,keembay-pcie.yaml
index 1fd557504b10..dd71e3d6bf94 100644
--- a/Documentation/devicetree/bindings/pci/intel,keembay-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/intel,keembay-pcie.yaml
@@ -75,23 +75,23 @@ examples:
     #define KEEM_BAY_A53_PCIE
     #define KEEM_BAY_A53_AUX_PCIE
     pcie@37000000 {
-          compatible = "intel,keembay-pcie";
-          reg = <0x37000000 0x00001000>,
-                <0x37300000 0x00001000>,
-                <0x36e00000 0x00200000>,
-                <0x37800000 0x00000200>;
-          reg-names = "dbi", "atu", "config", "apb";
-          #address-cells = <3>;
-          #size-cells = <2>;
-          device_type = "pci";
-          ranges = <0x02000000 0 0x36000000 0x36000000 0 0x00e00000>;
-          interrupts = <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>,
-                       <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>,
-                       <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>;
-          interrupt-names = "pcie", "pcie_ev", "pcie_err";
-          clocks = <&scmi_clk KEEM_BAY_A53_PCIE>,
-                   <&scmi_clk KEEM_BAY_A53_AUX_PCIE>;
-          clock-names = "master", "aux";
-          reset-gpios = <&pca2 9 GPIO_ACTIVE_LOW>;
-          num-lanes = <2>;
+        compatible = "intel,keembay-pcie";
+        reg = <0x37000000 0x00001000>,
+              <0x37300000 0x00001000>,
+              <0x36e00000 0x00200000>,
+              <0x37800000 0x00000200>;
+        reg-names = "dbi", "atu", "config", "apb";
+        #address-cells = <3>;
+        #size-cells = <2>;
+        device_type = "pci";
+        ranges = <0x02000000 0 0x36000000 0x36000000 0 0x00e00000>;
+        interrupts = <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>;
+        interrupt-names = "pcie", "pcie_ev", "pcie_err";
+        clocks = <&scmi_clk KEEM_BAY_A53_PCIE>,
+                 <&scmi_clk KEEM_BAY_A53_AUX_PCIE>;
+        clock-names = "master", "aux";
+        reset-gpios = <&pca2 9 GPIO_ACTIVE_LOW>;
+        num-lanes = <2>;
     };
diff --git a/Documentation/devicetree/bindings/pci/marvell,armada8k-pcie.yaml b/Documentation/devicetree/bindings/pci/marvell,armada8k-pcie.yaml
new file mode 100644
index 000000000000..f3ba9230ce2a
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/marvell,armada8k-pcie.yaml
@@ -0,0 +1,100 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/marvell,armada8k-pcie.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Marvell Armada 7K/8K PCIe interface
+
+maintainers:
+  - Thomas Petazzoni <thomas.petazzoni@bootlin.com>
+
+description:
+  This PCIe host controller is based on the Synopsys DesignWare PCIe IP.
+
+select:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - marvell,armada8k-pcie
+  required:
+    - compatible
+
+allOf:
+  - $ref: snps,dw-pcie.yaml#
+
+properties:
+  compatible:
+    items:
+      - enum:
+          - marvell,armada8k-pcie
+      - const: snps,dw-pcie
+
+  reg:
+    maxItems: 2
+
+  reg-names:
+    items:
+      - const: ctrl
+      - const: config
+
+  clocks:
+    minItems: 1
+    maxItems: 2
+
+  clock-names:
+    items:
+      - const: core
+      - const: reg
+
+  interrupts:
+    maxItems: 1
+
+  msi-parent:
+    maxItems: 1
+
+  phys:
+    minItems: 1
+    maxItems: 4
+
+  phy-names:
+    minItems: 1
+    maxItems: 4
+
+  marvell,reset-gpio:
+    maxItems: 1
+    deprecated: true
+
+required:
+  - interrupt-map
+  - clocks
+  - msi-parent
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    pcie@f2600000 {
+        compatible = "marvell,armada8k-pcie", "snps,dw-pcie";
+        reg = <0xf2600000 0x10000>, <0xf6f00000 0x80000>;
+        reg-names = "ctrl", "config";
+        #address-cells = <3>;
+        #size-cells = <2>;
+        #interrupt-cells = <1>;
+        device_type = "pci";
+        dma-coherent;
+        msi-parent = <&gic_v2m0>;
+
+        ranges = <0x81000000 0 0xf9000000 0xf9000000 0 0x10000>,  /* downstream I/O */
+                 <0x82000000 0 0xf6000000 0xf6000000 0 0xf00000>;  /* non-prefetchable memory */
+        interrupt-map-mask = <0 0 0 0>;
+        interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+        interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+        num-lanes = <1>;
+        clocks = <&cpm_syscon0 1 13>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/pci/marvell,kirkwood-pcie.yaml b/Documentation/devicetree/bindings/pci/marvell,kirkwood-pcie.yaml
new file mode 100644
index 000000000000..7be695320ddf
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/marvell,kirkwood-pcie.yaml
@@ -0,0 +1,277 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/marvell,kirkwood-pcie.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Marvell EBU PCIe interfaces
+
+maintainers:
+  - Thomas Petazzoni <thomas.petazzoni@bootlin.com>
+  - Pali Rohár <pali@kernel.org>
+
+allOf:
+  - $ref: /schemas/pci/pci-host-bridge.yaml#
+
+properties:
+  compatible:
+    enum:
+      - marvell,armada-370-pcie
+      - marvell,armada-xp-pcie
+      - marvell,dove-pcie
+      - marvell,kirkwood-pcie
+
+  ranges:
+    description: >
+      The ranges describing the MMIO registers have the following layout:
+
+        0x82000000 0 r MBUS_ID(0xf0, 0x01) r 0 s
+
+      where:
+
+        * r is a 32-bits value that gives the offset of the MMIO registers of
+        this PCIe interface, from the base of the internal registers.
+
+        * s is a 32-bits value that give the size of this MMIO registers area.
+        This range entry translates the '0x82000000 0 r' PCI address into the
+        'MBUS_ID(0xf0, 0x01) r' CPU address, which is part of the internal
+        register window (as identified by MBUS_ID(0xf0, 0x01)).
+
+      The ranges describing the MBus windows have the following layout:
+
+          0x8t000000 s 0     MBUS_ID(w, a) 0 1 0
+
+      where:
+
+        * t is the type of the MBus window (as defined by the standard PCI DT
+        bindings), 1 for I/O and 2 for memory.
+
+        * s is the PCI slot that corresponds to this PCIe interface
+
+        * w is the 'target ID' value for the MBus window
+
+        * a the 'attribute' value for the MBus window.
+
+      Since the location and size of the different MBus windows is not fixed in
+      hardware, and only determined in runtime, those ranges cover the full first
+      4 GB of the physical address space, and do not translate into a valid CPU
+      address.
+
+  msi-parent:
+    maxItems: 1
+
+patternProperties:
+  '^pcie@':
+    type: object
+    allOf:
+      - $ref: /schemas/pci/pci-bus-common.yaml#
+      - $ref: /schemas/pci/pci-device.yaml#
+    unevaluatedProperties: false
+
+    properties:
+      clocks:
+        maxItems: 1
+
+      interrupts:
+        minItems: 1
+        maxItems: 2
+
+      interrupt-names:
+        minItems: 1
+        items:
+          - const: intx
+          - const: error
+
+      reset-delay-us:
+        default: 100000
+        description: todo
+
+      marvell,pcie-port:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        maximum: 3
+        description: todo
+
+      marvell,pcie-lane:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        maximum: 3
+        description: todo
+
+      interrupt-controller:
+        type: object
+        additionalProperties: false
+
+        properties:
+          interrupt-controller: true
+
+          '#interrupt-cells':
+            const: 1
+
+    required:
+      - assigned-addresses
+      - clocks
+      - interrupt-map
+      - marvell,pcie-port
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #define MBUS_ID(target,attributes) (((target) << 24) | ((attributes) << 16))
+
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        pcie@f001000000000000 {
+            compatible = "marvell,armada-xp-pcie";
+            device_type = "pci";
+
+            #address-cells = <3>;
+            #size-cells = <2>;
+
+            bus-range = <0x00 0xff>;
+            msi-parent = <&mpic>;
+
+            ranges =
+                  <0x82000000 0 0x40000 MBUS_ID(0xf0, 0x01) 0x40000 0 0x00002000  /* Port 0.0 registers */
+                    0x82000000 0 0x42000 MBUS_ID(0xf0, 0x01) 0x42000 0 0x00002000  /* Port 2.0 registers */
+                    0x82000000 0 0x44000 MBUS_ID(0xf0, 0x01) 0x44000 0 0x00002000  /* Port 0.1 registers */
+                    0x82000000 0 0x48000 MBUS_ID(0xf0, 0x01) 0x48000 0 0x00002000  /* Port 0.2 registers */
+                    0x82000000 0 0x4c000 MBUS_ID(0xf0, 0x01) 0x4c000 0 0x00002000  /* Port 0.3 registers */
+                    0x82000000 0 0x80000 MBUS_ID(0xf0, 0x01) 0x80000 0 0x00002000  /* Port 1.0 registers */
+                    0x82000000 0 0x82000 MBUS_ID(0xf0, 0x01) 0x82000 0 0x00002000  /* Port 3.0 registers */
+                    0x82000000 0 0x84000 MBUS_ID(0xf0, 0x01) 0x84000 0 0x00002000  /* Port 1.1 registers */
+                    0x82000000 0 0x88000 MBUS_ID(0xf0, 0x01) 0x88000 0 0x00002000  /* Port 1.2 registers */
+                    0x82000000 0 0x8c000 MBUS_ID(0xf0, 0x01) 0x8c000 0 0x00002000  /* Port 1.3 registers */
+                    0x82000000 0x1 0     MBUS_ID(0x04, 0xe8) 0 1 0 /* Port 0.0 MEM */
+                    0x81000000 0x1 0     MBUS_ID(0x04, 0xe0) 0 1 0 /* Port 0.0 IO  */
+                    0x82000000 0x2 0     MBUS_ID(0x04, 0xd8) 0 1 0 /* Port 0.1 MEM */
+                    0x81000000 0x2 0     MBUS_ID(0x04, 0xd0) 0 1 0 /* Port 0.1 IO  */
+                    0x82000000 0x3 0     MBUS_ID(0x04, 0xb8) 0 1 0 /* Port 0.2 MEM */
+                    0x81000000 0x3 0     MBUS_ID(0x04, 0xb0) 0 1 0 /* Port 0.2 IO  */
+                    0x82000000 0x4 0     MBUS_ID(0x04, 0x78) 0 1 0 /* Port 0.3 MEM */
+                    0x81000000 0x4 0     MBUS_ID(0x04, 0x70) 0 1 0 /* Port 0.3 IO  */
+
+                    0x82000000 0x5 0     MBUS_ID(0x08, 0xe8) 0 1 0 /* Port 1.0 MEM */
+                    0x81000000 0x5 0     MBUS_ID(0x08, 0xe0) 0 1 0 /* Port 1.0 IO  */
+                    0x82000000 0x6 0     MBUS_ID(0x08, 0xd8) 0 1 0 /* Port 1.1 MEM */
+                    0x81000000 0x6 0     MBUS_ID(0x08, 0xd0) 0 1 0 /* Port 1.1 IO  */
+                    0x82000000 0x7 0     MBUS_ID(0x08, 0xb8) 0 1 0 /* Port 1.2 MEM */
+                    0x81000000 0x7 0     MBUS_ID(0x08, 0xb0) 0 1 0 /* Port 1.2 IO  */
+                    0x82000000 0x8 0     MBUS_ID(0x08, 0x78) 0 1 0 /* Port 1.3 MEM */
+                    0x81000000 0x8 0     MBUS_ID(0x08, 0x70) 0 1 0 /* Port 1.3 IO  */
+
+                    0x82000000 0x9 0     MBUS_ID(0x04, 0xf8) 0 1 0 /* Port 2.0 MEM */
+                    0x81000000 0x9 0     MBUS_ID(0x04, 0xf0) 0 1 0 /* Port 2.0 IO  */
+
+                    0x82000000 0xa 0     MBUS_ID(0x08, 0xf8) 0 1 0 /* Port 3.0 MEM */
+                    0x81000000 0xa 0     MBUS_ID(0x08, 0xf0) 0 1 0 /* Port 3.0 IO  */>;
+
+            pcie@1,0 {
+                device_type = "pci";
+                assigned-addresses = <0x82000800 0 0x40000 0 0x2000>;
+                reg = <0x0800 0 0 0 0>;
+                #address-cells = <3>;
+                #size-cells = <2>;
+                #interrupt-cells = <1>;
+                ranges = <0x82000000 0 0 0x82000000 0x1 0 1 0
+                    0x81000000 0 0 0x81000000 0x1 0 1 0>;
+                interrupt-map-mask = <0 0 0 0>;
+                interrupt-map = <0 0 0 0 &mpic 58>;
+                marvell,pcie-port = <0>;
+                marvell,pcie-lane = <0>;
+                num-lanes = <1>;
+                /* low-active PERST# reset on GPIO 25 */
+                reset-gpios = <&gpio0 25 1>;
+                /* wait 20ms for device settle after reset deassertion */
+                reset-delay-us = <20000>;
+                clocks = <&gateclk 5>;
+            };
+
+            pcie@2,0 {
+                device_type = "pci";
+                assigned-addresses = <0x82001000 0 0x44000 0 0x2000>;
+                reg = <0x1000 0 0 0 0>;
+                #address-cells = <3>;
+                #size-cells = <2>;
+                #interrupt-cells = <1>;
+                ranges = <0x82000000 0 0 0x82000000 0x2 0 1 0
+                    0x81000000 0 0 0x81000000 0x2 0 1 0>;
+                interrupt-map-mask = <0 0 0 0>;
+                interrupt-map = <0 0 0 0 &mpic 59>;
+                marvell,pcie-port = <0>;
+                marvell,pcie-lane = <1>;
+                num-lanes = <1>;
+                clocks = <&gateclk 6>;
+            };
+
+            pcie@3,0 {
+                device_type = "pci";
+                assigned-addresses = <0x82001800 0 0x48000 0 0x2000>;
+                reg = <0x1800 0 0 0 0>;
+                #address-cells = <3>;
+                #size-cells = <2>;
+                #interrupt-cells = <1>;
+                ranges = <0x82000000 0 0 0x82000000 0x3 0 1 0
+                    0x81000000 0 0 0x81000000 0x3 0 1 0>;
+                interrupt-map-mask = <0 0 0 0>;
+                interrupt-map = <0 0 0 0 &mpic 60>;
+                marvell,pcie-port = <0>;
+                marvell,pcie-lane = <2>;
+                num-lanes = <1>;
+                clocks = <&gateclk 7>;
+            };
+
+            pcie@4,0 {
+                device_type = "pci";
+                assigned-addresses = <0x82002000 0 0x4c000 0 0x2000>;
+                reg = <0x2000 0 0 0 0>;
+                #address-cells = <3>;
+                #size-cells = <2>;
+                #interrupt-cells = <1>;
+                ranges = <0x82000000 0 0 0x82000000 0x4 0 1 0
+                    0x81000000 0 0 0x81000000 0x4 0 1 0>;
+                interrupt-map-mask = <0 0 0 0>;
+                interrupt-map = <0 0 0 0 &mpic 61>;
+                marvell,pcie-port = <0>;
+                marvell,pcie-lane = <3>;
+                num-lanes = <1>;
+                clocks = <&gateclk 8>;
+            };
+
+            pcie@5,0 {
+                device_type = "pci";
+                assigned-addresses = <0x82002800 0 0x80000 0 0x2000>;
+                reg = <0x2800 0 0 0 0>;
+                #address-cells = <3>;
+                #size-cells = <2>;
+                #interrupt-cells = <1>;
+                ranges = <0x82000000 0 0 0x82000000 0x5 0 1 0
+                    0x81000000 0 0 0x81000000 0x5 0 1 0>;
+                interrupt-map-mask = <0 0 0 0>;
+                interrupt-map = <0 0 0 0 &mpic 62>;
+                marvell,pcie-port = <1>;
+                marvell,pcie-lane = <0>;
+                num-lanes = <1>;
+                clocks = <&gateclk 9>;
+            };
+
+            pcie@6,0 {
+                device_type = "pci";
+                assigned-addresses = <0x82003000 0 0x84000 0 0x2000>;
+                reg = <0x3000 0 0 0 0>;
+                #address-cells = <3>;
+                #size-cells = <2>;
+                #interrupt-cells = <1>;
+                ranges = <0x82000000 0 0 0x82000000 0x6 0 1 0
+                    0x81000000 0 0 0x81000000 0x6 0 1 0>;
+                interrupt-map-mask = <0 0 0 0>;
+                interrupt-map = <0 0 0 0 &mpic 63>;
+                marvell,pcie-port = <1>;
+                marvell,pcie-lane = <1>;
+                num-lanes = <1>;
+                clocks = <&gateclk 10>;
+            };
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/pci/microchip,pcie-host.yaml b/Documentation/devicetree/bindings/pci/microchip,pcie-host.yaml
index 103574d18dbc..47b0bad690d5 100644
--- a/Documentation/devicetree/bindings/pci/microchip,pcie-host.yaml
+++ b/Documentation/devicetree/bindings/pci/microchip,pcie-host.yaml
@@ -50,7 +50,7 @@ properties:
     items:
       pattern: '^fic[0-3]$'
 
-  dma-coherent: true
+  dma-noncoherent: true
 
   ranges:
     minItems: 1
@@ -65,33 +65,33 @@ unevaluatedProperties: false
 examples:
   - |
     soc {
-            #address-cells = <2>;
+        #address-cells = <2>;
+        #size-cells = <2>;
+        pcie0: pcie@2030000000 {
+            compatible = "microchip,pcie-host-1.0";
+            reg = <0x0 0x70000000 0x0 0x08000000>,
+                  <0x0 0x43008000 0x0 0x00002000>,
+                  <0x0 0x4300a000 0x0 0x00002000>;
+            reg-names = "cfg", "bridge", "ctrl";
+            device_type = "pci";
+            #address-cells = <3>;
             #size-cells = <2>;
-            pcie0: pcie@2030000000 {
-                    compatible = "microchip,pcie-host-1.0";
-                    reg = <0x0 0x70000000 0x0 0x08000000>,
-                          <0x0 0x43008000 0x0 0x00002000>,
-                          <0x0 0x4300a000 0x0 0x00002000>;
-                    reg-names = "cfg", "bridge", "ctrl";
-                    device_type = "pci";
-                    #address-cells = <3>;
-                    #size-cells = <2>;
-                    #interrupt-cells = <1>;
-                    interrupts = <119>;
-                    interrupt-map-mask = <0x0 0x0 0x0 0x7>;
-                    interrupt-map = <0 0 0 1 &pcie_intc0 0>,
-                                    <0 0 0 2 &pcie_intc0 1>,
-                                    <0 0 0 3 &pcie_intc0 2>,
-                                    <0 0 0 4 &pcie_intc0 3>;
-                    interrupt-parent = <&plic0>;
-                    msi-parent = <&pcie0>;
-                    msi-controller;
-                    bus-range = <0x00 0x7f>;
-                    ranges = <0x03000000 0x0 0x78000000 0x0 0x78000000 0x0 0x04000000>;
-                    pcie_intc0: interrupt-controller {
-                        #address-cells = <0>;
-                        #interrupt-cells = <1>;
-                        interrupt-controller;
-                    };
+            #interrupt-cells = <1>;
+            interrupts = <119>;
+            interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+            interrupt-map = <0 0 0 1 &pcie_intc0 0>,
+                            <0 0 0 2 &pcie_intc0 1>,
+                            <0 0 0 3 &pcie_intc0 2>,
+                            <0 0 0 4 &pcie_intc0 3>;
+            interrupt-parent = <&plic0>;
+            msi-parent = <&pcie0>;
+            msi-controller;
+            bus-range = <0x00 0x7f>;
+            ranges = <0x03000000 0x0 0x78000000 0x0 0x78000000 0x0 0x04000000>;
+            pcie_intc0: interrupt-controller {
+                #address-cells = <0>;
+                #interrupt-cells = <1>;
+                interrupt-controller;
             };
+        };
     };
diff --git a/Documentation/devicetree/bindings/pci/mvebu-pci.txt b/Documentation/devicetree/bindings/pci/mvebu-pci.txt
deleted file mode 100644
index 6d022a9d36ee..000000000000
--- a/Documentation/devicetree/bindings/pci/mvebu-pci.txt
+++ /dev/null
@@ -1,310 +0,0 @@
-* Marvell EBU PCIe interfaces
-
-Mandatory properties:
-
-- compatible: one of the following values:
-    marvell,armada-370-pcie
-    marvell,armada-xp-pcie
-    marvell,dove-pcie
-    marvell,kirkwood-pcie
-- #address-cells, set to <3>
-- #size-cells, set to <2>
-- #interrupt-cells, set to <1>
-- bus-range: PCI bus numbers covered
-- device_type, set to "pci"
-- ranges: ranges describing the MMIO registers to control the PCIe
-  interfaces, and ranges describing the MBus windows needed to access
-  the memory and I/O regions of each PCIe interface.
-- msi-parent: Link to the hardware entity that serves as the Message
-  Signaled Interrupt controller for this PCI controller.
-
-The ranges describing the MMIO registers have the following layout:
-
-    0x82000000 0 r MBUS_ID(0xf0, 0x01) r 0 s
-
-where:
-
-  * r is a 32-bits value that gives the offset of the MMIO
-  registers of this PCIe interface, from the base of the internal
-  registers.
-
-  * s is a 32-bits value that give the size of this MMIO
-  registers area. This range entry translates the '0x82000000 0 r' PCI
-  address into the 'MBUS_ID(0xf0, 0x01) r' CPU address, which is part
-  of the internal register window (as identified by MBUS_ID(0xf0,
-  0x01)).
-
-The ranges describing the MBus windows have the following layout:
-
-    0x8t000000 s 0     MBUS_ID(w, a) 0 1 0
-
-where:
-
-   * t is the type of the MBus window (as defined by the standard PCI DT
-   bindings), 1 for I/O and 2 for memory.
-
-   * s is the PCI slot that corresponds to this PCIe interface
-
-   * w is the 'target ID' value for the MBus window
-
-   * a the 'attribute' value for the MBus window.
-
-Since the location and size of the different MBus windows is not fixed in
-hardware, and only determined in runtime, those ranges cover the full first
-4 GB of the physical address space, and do not translate into a valid CPU
-address.
-
-In addition, the device tree node must have sub-nodes describing each
-PCIe interface, having the following mandatory properties:
-
-- reg: used only for interrupt mapping, so only the first four bytes
-  are used to refer to the correct bus number and device number.
-- assigned-addresses: reference to the MMIO registers used to control
-  this PCIe interface.
-- clocks: the clock associated to this PCIe interface
-- marvell,pcie-port: the physical PCIe port number
-- status: either "disabled" or "okay"
-- device_type, set to "pci"
-- #address-cells, set to <3>
-- #size-cells, set to <2>
-- #interrupt-cells, set to <1>
-- ranges, translating the MBus windows ranges of the parent node into
-  standard PCI addresses.
-- interrupt-map-mask and interrupt-map, standard PCI properties to
-  define the mapping of the PCIe interface to interrupt numbers.
-
-and the following optional properties:
-- marvell,pcie-lane: the physical PCIe lane number, for ports having
-  multiple lanes. If this property is not found, we assume that the
-  value is 0.
-- num-lanes: number of SerDes PCIe lanes for this link (1 or 4)
-- reset-gpios: optional GPIO to PERST#
-- reset-delay-us: delay in us to wait after reset de-assertion, if not
-  specified will default to 100ms, as required by the PCIe specification.
-- interrupt-names: list of interrupt names, supported are:
-   - "intx" - interrupt line triggered by one of the legacy interrupt
-- interrupts or interrupts-extended: List of the interrupt sources which
-  corresponding to the "interrupt-names". If non-empty then also additional
-  'interrupt-controller' subnode must be defined.
-
-Example:
-
-pcie-controller {
-	compatible = "marvell,armada-xp-pcie";
-	device_type = "pci";
-
-	#address-cells = <3>;
-	#size-cells = <2>;
-
-	bus-range = <0x00 0xff>;
-	msi-parent = <&mpic>;
-
-	ranges =
-	       <0x82000000 0 0x40000 MBUS_ID(0xf0, 0x01) 0x40000 0 0x00002000	/* Port 0.0 registers */
-		0x82000000 0 0x42000 MBUS_ID(0xf0, 0x01) 0x42000 0 0x00002000	/* Port 2.0 registers */
-		0x82000000 0 0x44000 MBUS_ID(0xf0, 0x01) 0x44000 0 0x00002000	/* Port 0.1 registers */
-		0x82000000 0 0x48000 MBUS_ID(0xf0, 0x01) 0x48000 0 0x00002000	/* Port 0.2 registers */
-		0x82000000 0 0x4c000 MBUS_ID(0xf0, 0x01) 0x4c000 0 0x00002000	/* Port 0.3 registers */
-		0x82000000 0 0x80000 MBUS_ID(0xf0, 0x01) 0x80000 0 0x00002000	/* Port 1.0 registers */
-		0x82000000 0 0x82000 MBUS_ID(0xf0, 0x01) 0x82000 0 0x00002000	/* Port 3.0 registers */
-		0x82000000 0 0x84000 MBUS_ID(0xf0, 0x01) 0x84000 0 0x00002000	/* Port 1.1 registers */
-		0x82000000 0 0x88000 MBUS_ID(0xf0, 0x01) 0x88000 0 0x00002000	/* Port 1.2 registers */
-		0x82000000 0 0x8c000 MBUS_ID(0xf0, 0x01) 0x8c000 0 0x00002000	/* Port 1.3 registers */
-		0x82000000 0x1 0     MBUS_ID(0x04, 0xe8) 0 1 0 /* Port 0.0 MEM */
-		0x81000000 0x1 0     MBUS_ID(0x04, 0xe0) 0 1 0 /* Port 0.0 IO  */
-		0x82000000 0x2 0     MBUS_ID(0x04, 0xd8) 0 1 0 /* Port 0.1 MEM */
-		0x81000000 0x2 0     MBUS_ID(0x04, 0xd0) 0 1 0 /* Port 0.1 IO  */
-		0x82000000 0x3 0     MBUS_ID(0x04, 0xb8) 0 1 0 /* Port 0.2 MEM */
-		0x81000000 0x3 0     MBUS_ID(0x04, 0xb0) 0 1 0 /* Port 0.2 IO  */
-		0x82000000 0x4 0     MBUS_ID(0x04, 0x78) 0 1 0 /* Port 0.3 MEM */
-		0x81000000 0x4 0     MBUS_ID(0x04, 0x70) 0 1 0 /* Port 0.3 IO  */
-
-		0x82000000 0x5 0     MBUS_ID(0x08, 0xe8) 0 1 0 /* Port 1.0 MEM */
-		0x81000000 0x5 0     MBUS_ID(0x08, 0xe0) 0 1 0 /* Port 1.0 IO  */
-		0x82000000 0x6 0     MBUS_ID(0x08, 0xd8) 0 1 0 /* Port 1.1 MEM */
-		0x81000000 0x6 0     MBUS_ID(0x08, 0xd0) 0 1 0 /* Port 1.1 IO  */
-		0x82000000 0x7 0     MBUS_ID(0x08, 0xb8) 0 1 0 /* Port 1.2 MEM */
-		0x81000000 0x7 0     MBUS_ID(0x08, 0xb0) 0 1 0 /* Port 1.2 IO  */
-		0x82000000 0x8 0     MBUS_ID(0x08, 0x78) 0 1 0 /* Port 1.3 MEM */
-		0x81000000 0x8 0     MBUS_ID(0x08, 0x70) 0 1 0 /* Port 1.3 IO  */
-
-		0x82000000 0x9 0     MBUS_ID(0x04, 0xf8) 0 1 0 /* Port 2.0 MEM */
-		0x81000000 0x9 0     MBUS_ID(0x04, 0xf0) 0 1 0 /* Port 2.0 IO  */
-
-		0x82000000 0xa 0     MBUS_ID(0x08, 0xf8) 0 1 0 /* Port 3.0 MEM */
-		0x81000000 0xa 0     MBUS_ID(0x08, 0xf0) 0 1 0 /* Port 3.0 IO  */>;
-
-	pcie@1,0 {
-		device_type = "pci";
-		assigned-addresses = <0x82000800 0 0x40000 0 0x2000>;
-		reg = <0x0800 0 0 0 0>;
-		#address-cells = <3>;
-		#size-cells = <2>;
-		#interrupt-cells = <1>;
-		ranges = <0x82000000 0 0 0x82000000 0x1 0 1 0
-			  0x81000000 0 0 0x81000000 0x1 0 1 0>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &mpic 58>;
-		marvell,pcie-port = <0>;
-		marvell,pcie-lane = <0>;
-		num-lanes = <1>;
-		/* low-active PERST# reset on GPIO 25 */
-		reset-gpios = <&gpio0 25 1>;
-		/* wait 20ms for device settle after reset deassertion */
-		reset-delay-us = <20000>;
-		clocks = <&gateclk 5>;
-	};
-
-	pcie@2,0 {
-		device_type = "pci";
-		assigned-addresses = <0x82001000 0 0x44000 0 0x2000>;
-		reg = <0x1000 0 0 0 0>;
-		#address-cells = <3>;
-		#size-cells = <2>;
-		#interrupt-cells = <1>;
-		ranges = <0x82000000 0 0 0x82000000 0x2 0 1 0
-			  0x81000000 0 0 0x81000000 0x2 0 1 0>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &mpic 59>;
-		marvell,pcie-port = <0>;
-		marvell,pcie-lane = <1>;
-		num-lanes = <1>;
-		clocks = <&gateclk 6>;
-	};
-
-	pcie@3,0 {
-		device_type = "pci";
-		assigned-addresses = <0x82001800 0 0x48000 0 0x2000>;
-		reg = <0x1800 0 0 0 0>;
-		#address-cells = <3>;
-		#size-cells = <2>;
-		#interrupt-cells = <1>;
-		ranges = <0x82000000 0 0 0x82000000 0x3 0 1 0
-			  0x81000000 0 0 0x81000000 0x3 0 1 0>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &mpic 60>;
-		marvell,pcie-port = <0>;
-		marvell,pcie-lane = <2>;
-		num-lanes = <1>;
-		clocks = <&gateclk 7>;
-	};
-
-	pcie@4,0 {
-		device_type = "pci";
-		assigned-addresses = <0x82002000 0 0x4c000 0 0x2000>;
-		reg = <0x2000 0 0 0 0>;
-		#address-cells = <3>;
-		#size-cells = <2>;
-		#interrupt-cells = <1>;
-		ranges = <0x82000000 0 0 0x82000000 0x4 0 1 0
-			  0x81000000 0 0 0x81000000 0x4 0 1 0>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &mpic 61>;
-		marvell,pcie-port = <0>;
-		marvell,pcie-lane = <3>;
-		num-lanes = <1>;
-		clocks = <&gateclk 8>;
-	};
-
-	pcie@5,0 {
-		device_type = "pci";
-		assigned-addresses = <0x82002800 0 0x80000 0 0x2000>;
-		reg = <0x2800 0 0 0 0>;
-		#address-cells = <3>;
-		#size-cells = <2>;
-		#interrupt-cells = <1>;
-		ranges = <0x82000000 0 0 0x82000000 0x5 0 1 0
-			  0x81000000 0 0 0x81000000 0x5 0 1 0>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &mpic 62>;
-		marvell,pcie-port = <1>;
-		marvell,pcie-lane = <0>;
-		num-lanes = <1>;
-		clocks = <&gateclk 9>;
-	};
-
-	pcie@6,0 {
-		device_type = "pci";
-		assigned-addresses = <0x82003000 0 0x84000 0 0x2000>;
-		reg = <0x3000 0 0 0 0>;
-		#address-cells = <3>;
-		#size-cells = <2>;
-		#interrupt-cells = <1>;
-		ranges = <0x82000000 0 0 0x82000000 0x6 0 1 0
-			  0x81000000 0 0 0x81000000 0x6 0 1 0>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &mpic 63>;
-		marvell,pcie-port = <1>;
-		marvell,pcie-lane = <1>;
-		num-lanes = <1>;
-		clocks = <&gateclk 10>;
-	};
-
-	pcie@7,0 {
-		device_type = "pci";
-		assigned-addresses = <0x82003800 0 0x88000 0 0x2000>;
-		reg = <0x3800 0 0 0 0>;
-		#address-cells = <3>;
-		#size-cells = <2>;
-		#interrupt-cells = <1>;
-		ranges = <0x82000000 0 0 0x82000000 0x7 0 1 0
-			  0x81000000 0 0 0x81000000 0x7 0 1 0>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &mpic 64>;
-		marvell,pcie-port = <1>;
-		marvell,pcie-lane = <2>;
-		num-lanes = <1>;
-		clocks = <&gateclk 11>;
-	};
-
-	pcie@8,0 {
-		device_type = "pci";
-		assigned-addresses = <0x82004000 0 0x8c000 0 0x2000>;
-		reg = <0x4000 0 0 0 0>;
-		#address-cells = <3>;
-		#size-cells = <2>;
-		#interrupt-cells = <1>;
-		ranges = <0x82000000 0 0 0x82000000 0x8 0 1 0
-			  0x81000000 0 0 0x81000000 0x8 0 1 0>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &mpic 65>;
-		marvell,pcie-port = <1>;
-		marvell,pcie-lane = <3>;
-		num-lanes = <1>;
-		clocks = <&gateclk 12>;
-	};
-
-	pcie@9,0 {
-		device_type = "pci";
-		assigned-addresses = <0x82004800 0 0x42000 0 0x2000>;
-		reg = <0x4800 0 0 0 0>;
-		#address-cells = <3>;
-		#size-cells = <2>;
-		#interrupt-cells = <1>;
-		ranges = <0x82000000 0 0 0x82000000 0x9 0 1 0
-			  0x81000000 0 0 0x81000000 0x9 0 1 0>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &mpic 99>;
-		marvell,pcie-port = <2>;
-		marvell,pcie-lane = <0>;
-		num-lanes = <1>;
-		clocks = <&gateclk 26>;
-	};
-
-	pcie@a,0 {
-		device_type = "pci";
-		assigned-addresses = <0x82005000 0 0x82000 0 0x2000>;
-		reg = <0x5000 0 0 0 0>;
-		#address-cells = <3>;
-		#size-cells = <2>;
-		#interrupt-cells = <1>;
-		ranges = <0x82000000 0 0 0x82000000 0xa 0 1 0
-			  0x81000000 0 0 0x81000000 0xa 0 1 0>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &mpic 103>;
-		marvell,pcie-port = <3>;
-		marvell,pcie-lane = <0>;
-		num-lanes = <1>;
-		clocks = <&gateclk 27>;
-	};
-};
diff --git a/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie-ep.yaml b/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie-ep.yaml
index a24fb8307d29..6d6052a2748f 100644
--- a/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie-ep.yaml
+++ b/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie-ep.yaml
@@ -74,7 +74,7 @@ properties:
 
   reset-gpios:
     description: Must contain a phandle to a GPIO controller followed by GPIO
-      that is being used as PERST input signal. Please refer to pci.txt.
+      that is being used as PERST input signal.
 
   phys:
     minItems: 1
diff --git a/Documentation/devicetree/bindings/pci/pci-armada8k.txt b/Documentation/devicetree/bindings/pci/pci-armada8k.txt
deleted file mode 100644
index ff25a134befa..000000000000
--- a/Documentation/devicetree/bindings/pci/pci-armada8k.txt
+++ /dev/null
@@ -1,48 +0,0 @@
-* Marvell Armada 7K/8K PCIe interface
-
-This PCIe host controller is based on the Synopsys DesignWare PCIe IP
-and thus inherits all the common properties defined in snps,dw-pcie.yaml.
-
-Required properties:
-- compatible: "marvell,armada8k-pcie"
-- reg: must contain two register regions
-   - the control register region
-   - the config space region
-- reg-names:
-   - "ctrl" for the control register region
-   - "config" for the config space region
-- interrupts: Interrupt specifier for the PCIe controller
-- clocks: reference to the PCIe controller clocks
-- clock-names: mandatory if there is a second clock, in this case the
-   name must be "core" for the first clock and "reg" for the second
-   one
-
-Optional properties:
-- phys: phandle(s) to PHY node(s) following the generic PHY bindings.
-	Either 1, 2 or 4 PHYs might be needed depending on the number of
-	PCIe lanes.
-- phy-names: names of the PHYs corresponding to the number of lanes.
-	Must be "cp0-pcie0-x4-lane0-phy", "cp0-pcie0-x4-lane1-phy" for
-	2 PHYs.
-
-Example:
-
-	pcie@f2600000 {
-		compatible = "marvell,armada8k-pcie", "snps,dw-pcie";
-		reg = <0 0xf2600000 0 0x10000>, <0 0xf6f00000 0 0x80000>;
-		reg-names = "ctrl", "config";
-		#address-cells = <3>;
-		#size-cells = <2>;
-		#interrupt-cells = <1>;
-		device_type = "pci";
-		dma-coherent;
-
-		bus-range = <0 0xff>;
-		ranges = <0x81000000 0 0xf9000000 0  0xf9000000 0 0x10000	/* downstream I/O */
-			  0x82000000 0 0xf6000000 0  0xf6000000 0 0xf00000>;	/* non-prefetchable memory */
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &gic 0 GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
-		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
-		num-lanes = <1>;
-		clocks = <&cpm_syscon0 1 13>;
-	};
diff --git a/Documentation/devicetree/bindings/pci/pci-iommu.txt b/Documentation/devicetree/bindings/pci/pci-iommu.txt
deleted file mode 100644
index 0def586fdcdf..000000000000
--- a/Documentation/devicetree/bindings/pci/pci-iommu.txt
+++ /dev/null
@@ -1,171 +0,0 @@
-This document describes the generic device tree binding for describing the
-relationship between PCI(e) devices and IOMMU(s).
-
-Each PCI(e) device under a root complex is uniquely identified by its Requester
-ID (AKA RID). A Requester ID is a triplet of a Bus number, Device number, and
-Function number.
-
-For the purpose of this document, when treated as a numeric value, a RID is
-formatted such that:
-
-* Bits [15:8] are the Bus number.
-* Bits [7:3] are the Device number.
-* Bits [2:0] are the Function number.
-* Any other bits required for padding must be zero.
-
-IOMMUs may distinguish PCI devices through sideband data derived from the
-Requester ID. While a given PCI device can only master through one IOMMU, a
-root complex may split masters across a set of IOMMUs (e.g. with one IOMMU per
-bus).
-
-The generic 'iommus' property is insufficient to describe this relationship,
-and a mechanism is required to map from a PCI device to its IOMMU and sideband
-data.
-
-For generic IOMMU bindings, see
-Documentation/devicetree/bindings/iommu/iommu.txt.
-
-
-PCI root complex
-================
-
-Optional properties
--------------------
-
-- iommu-map: Maps a Requester ID to an IOMMU and associated IOMMU specifier
-  data.
-
-  The property is an arbitrary number of tuples of
-  (rid-base,iommu,iommu-base,length).
-
-  Any RID r in the interval [rid-base, rid-base + length) is associated with
-  the listed IOMMU, with the IOMMU specifier (r - rid-base + iommu-base).
-
-- iommu-map-mask: A mask to be applied to each Requester ID prior to being
-  mapped to an IOMMU specifier per the iommu-map property.
-
-
-Example (1)
-===========
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	iommu: iommu@a {
-		reg = <0xa 0x1>;
-		compatible = "vendor,some-iommu";
-		#iommu-cells = <1>;
-	};
-
-	pci: pci@f {
-		reg = <0xf 0x1>;
-		compatible = "vendor,pcie-root-complex";
-		device_type = "pci";
-
-		/*
-		 * The sideband data provided to the IOMMU is the RID,
-		 * identity-mapped.
-		 */
-		iommu-map = <0x0 &iommu 0x0 0x10000>;
-	};
-};
-
-
-Example (2)
-===========
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	iommu: iommu@a {
-		reg = <0xa 0x1>;
-		compatible = "vendor,some-iommu";
-		#iommu-cells = <1>;
-	};
-
-	pci: pci@f {
-		reg = <0xf 0x1>;
-		compatible = "vendor,pcie-root-complex";
-		device_type = "pci";
-
-		/*
-		 * The sideband data provided to the IOMMU is the RID with the
-		 * function bits masked out.
-		 */
-		iommu-map = <0x0 &iommu 0x0 0x10000>;
-		iommu-map-mask = <0xfff8>;
-	};
-};
-
-
-Example (3)
-===========
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	iommu: iommu@a {
-		reg = <0xa 0x1>;
-		compatible = "vendor,some-iommu";
-		#iommu-cells = <1>;
-	};
-
-	pci: pci@f {
-		reg = <0xf 0x1>;
-		compatible = "vendor,pcie-root-complex";
-		device_type = "pci";
-
-		/*
-		 * The sideband data provided to the IOMMU is the RID,
-		 * but the high bits of the bus number are flipped.
-		 */
-		iommu-map = <0x0000 &iommu 0x8000 0x8000>,
-			    <0x8000 &iommu 0x0000 0x8000>;
-	};
-};
-
-
-Example (4)
-===========
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	iommu_a: iommu@a {
-		reg = <0xa 0x1>;
-		compatible = "vendor,some-iommu";
-		#iommu-cells = <1>;
-	};
-
-	iommu_b: iommu@b {
-		reg = <0xb 0x1>;
-		compatible = "vendor,some-iommu";
-		#iommu-cells = <1>;
-	};
-
-	iommu_c: iommu@c {
-		reg = <0xc 0x1>;
-		compatible = "vendor,some-iommu";
-		#iommu-cells = <1>;
-	};
-
-	pci: pci@f {
-		reg = <0xf 0x1>;
-		compatible = "vendor,pcie-root-complex";
-		device_type = "pci";
-
-		/*
-		 * Devices with bus number 0-127 are mastered via IOMMU
-		 * a, with sideband data being RID[14:0].
-		 * Devices with bus number 128-255 are mastered via
-		 * IOMMU b, with sideband data being RID[14:0].
-		 * No devices master via IOMMU c.
-		 */
-		iommu-map = <0x0000 &iommu_a 0x0000 0x8000>,
-			    <0x8000 &iommu_b 0x0000 0x8000>;
-	};
-};
diff --git a/Documentation/devicetree/bindings/pci/pci-msi.txt b/Documentation/devicetree/bindings/pci/pci-msi.txt
deleted file mode 100644
index b73d839657b6..000000000000
--- a/Documentation/devicetree/bindings/pci/pci-msi.txt
+++ /dev/null
@@ -1,220 +0,0 @@
-This document describes the generic device tree binding for describing the
-relationship between PCI devices and MSI controllers.
-
-Each PCI device under a root complex is uniquely identified by its Requester ID
-(AKA RID). A Requester ID is a triplet of a Bus number, Device number, and
-Function number.
-
-For the purpose of this document, when treated as a numeric value, a RID is
-formatted such that:
-
-* Bits [15:8] are the Bus number.
-* Bits [7:3] are the Device number.
-* Bits [2:0] are the Function number.
-* Any other bits required for padding must be zero.
-
-MSIs may be distinguished in part through the use of sideband data accompanying
-writes. In the case of PCI devices, this sideband data may be derived from the
-Requester ID. A mechanism is required to associate a device with both the MSI
-controllers it can address, and the sideband data that will be associated with
-its writes to those controllers.
-
-For generic MSI bindings, see
-Documentation/devicetree/bindings/interrupt-controller/msi.txt.
-
-
-PCI root complex
-================
-
-Optional properties
--------------------
-
-- msi-map: Maps a Requester ID to an MSI controller and associated
-  msi-specifier data. The property is an arbitrary number of tuples of
-  (rid-base,msi-controller,msi-base,length), where:
-
-  * rid-base is a single cell describing the first RID matched by the entry.
-
-  * msi-controller is a single phandle to an MSI controller
-
-  * msi-base is an msi-specifier describing the msi-specifier produced for the
-    first RID matched by the entry.
-
-  * length is a single cell describing how many consecutive RIDs are matched
-    following the rid-base.
-
-  Any RID r in the interval [rid-base, rid-base + length) is associated with
-  the listed msi-controller, with the msi-specifier (r - rid-base + msi-base).
-
-- msi-map-mask: A mask to be applied to each Requester ID prior to being mapped
-  to an msi-specifier per the msi-map property.
-
-- msi-parent: Describes the MSI parent of the root complex itself. Where
-  the root complex and MSI controller do not pass sideband data with MSI
-  writes, this property may be used to describe the MSI controller(s)
-  used by PCI devices under the root complex, if defined as such in the
-  binding for the root complex.
-
-
-Example (1)
-===========
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	msi: msi-controller@a {
-		reg = <0xa 0x1>;
-		compatible = "vendor,some-controller";
-		msi-controller;
-		#msi-cells = <1>;
-	};
-
-	pci: pci@f {
-		reg = <0xf 0x1>;
-		compatible = "vendor,pcie-root-complex";
-		device_type = "pci";
-
-		/*
-		 * The sideband data provided to the MSI controller is
-		 * the RID, identity-mapped.
-		 */
-		msi-map = <0x0 &msi_a 0x0 0x10000>,
-	};
-};
-
-
-Example (2)
-===========
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	msi: msi-controller@a {
-		reg = <0xa 0x1>;
-		compatible = "vendor,some-controller";
-		msi-controller;
-		#msi-cells = <1>;
-	};
-
-	pci: pci@f {
-		reg = <0xf 0x1>;
-		compatible = "vendor,pcie-root-complex";
-		device_type = "pci";
-
-		/*
-		 * The sideband data provided to the MSI controller is
-		 * the RID, masked to only the device and function bits.
-		 */
-		msi-map = <0x0 &msi_a 0x0 0x100>,
-		msi-map-mask = <0xff>
-	};
-};
-
-
-Example (3)
-===========
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	msi: msi-controller@a {
-		reg = <0xa 0x1>;
-		compatible = "vendor,some-controller";
-		msi-controller;
-		#msi-cells = <1>;
-	};
-
-	pci: pci@f {
-		reg = <0xf 0x1>;
-		compatible = "vendor,pcie-root-complex";
-		device_type = "pci";
-
-		/*
-		 * The sideband data provided to the MSI controller is
-		 * the RID, but the high bit of the bus number is
-		 * ignored.
-		 */
-		msi-map = <0x0000 &msi 0x0000 0x8000>,
-			  <0x8000 &msi 0x0000 0x8000>;
-	};
-};
-
-
-Example (4)
-===========
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	msi: msi-controller@a {
-		reg = <0xa 0x1>;
-		compatible = "vendor,some-controller";
-		msi-controller;
-		#msi-cells = <1>;
-	};
-
-	pci: pci@f {
-		reg = <0xf 0x1>;
-		compatible = "vendor,pcie-root-complex";
-		device_type = "pci";
-
-		/*
-		 * The sideband data provided to the MSI controller is
-		 * the RID, but the high bit of the bus number is
-		 * negated.
-		 */
-		msi-map = <0x0000 &msi 0x8000 0x8000>,
-			  <0x8000 &msi 0x0000 0x8000>;
-	};
-};
-
-
-Example (5)
-===========
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	msi_a: msi-controller@a {
-		reg = <0xa 0x1>;
-		compatible = "vendor,some-controller";
-		msi-controller;
-		#msi-cells = <1>;
-	};
-
-	msi_b: msi-controller@b {
-		reg = <0xb 0x1>;
-		compatible = "vendor,some-controller";
-		msi-controller;
-		#msi-cells = <1>;
-	};
-
-	msi_c: msi-controller@c {
-		reg = <0xc 0x1>;
-		compatible = "vendor,some-controller";
-		msi-controller;
-		#msi-cells = <1>;
-	};
-
-	pci: pci@f {
-		reg = <0xf 0x1>;
-		compatible = "vendor,pcie-root-complex";
-		device_type = "pci";
-
-		/*
-		 * The sideband data provided to MSI controller a is the
-		 * RID, but the high bit of the bus number is negated.
-		 * The sideband data provided to MSI controller b is the
-		 * RID, identity-mapped.
-		 * MSI controller c is not addressable.
-		 */
-		msi-map = <0x0000 &msi_a 0x8000 0x08000>,
-			  <0x8000 &msi_a 0x0000 0x08000>,
-			  <0x0000 &msi_b 0x0000 0x10000>;
-	};
-};
diff --git a/Documentation/devicetree/bindings/pci/pci.txt b/Documentation/devicetree/bindings/pci/pci.txt
deleted file mode 100644
index 6a8f2874a24d..000000000000
--- a/Documentation/devicetree/bindings/pci/pci.txt
+++ /dev/null
@@ -1,84 +0,0 @@
-PCI bus bridges have standardized Device Tree bindings:
-
-PCI Bus Binding to: IEEE Std 1275-1994
-https://www.devicetree.org/open-firmware/bindings/pci/pci2_1.pdf
-
-And for the interrupt mapping part:
-
-Open Firmware Recommended Practice: Interrupt Mapping
-https://www.devicetree.org/open-firmware/practice/imap/imap0_9d.pdf
-
-Additionally to the properties specified in the above standards a host bridge
-driver implementation may support the following properties:
-
-- linux,pci-domain:
-   If present this property assigns a fixed PCI domain number to a host bridge,
-   otherwise an unstable (across boots) unique number will be assigned.
-   It is required to either not set this property at all or set it for all
-   host bridges in the system, otherwise potentially conflicting domain numbers
-   may be assigned to root buses behind different host bridges.  The domain
-   number for each host bridge in the system must be unique.
-- max-link-speed:
-   If present this property specifies PCI gen for link capability.  Host
-   drivers could add this as a strategy to avoid unnecessary operation for
-   unsupported link speed, for instance, trying to do training for
-   unsupported link speed, etc.  Must be '4' for gen4, '3' for gen3, '2'
-   for gen2, and '1' for gen1. Any other values are invalid.
-- reset-gpios:
-   If present this property specifies PERST# GPIO. Host drivers can parse the
-   GPIO and apply fundamental reset to endpoints.
-- supports-clkreq:
-   If present this property specifies that CLKREQ signal routing exists from
-   root port to downstream device and host bridge drivers can do programming
-   which depends on CLKREQ signal existence. For example, programming root port
-   not to advertise ASPM L1 Sub-States support if there is no CLKREQ signal.
-
-PCI-PCI Bridge properties
--------------------------
-
-PCIe root ports and switch ports may be described explicitly in the device
-tree, as children of the host bridge node. Even though those devices are
-discoverable by probing, it might be necessary to describe properties that
-aren't provided by standard PCIe capabilities.
-
-Required properties:
-
-- reg:
-   Identifies the PCI-PCI bridge. As defined in the IEEE Std 1275-1994
-   document, it is a five-cell address encoded as (phys.hi phys.mid
-   phys.lo size.hi size.lo). phys.hi should contain the device's BDF as
-   0b00000000 bbbbbbbb dddddfff 00000000. The other cells should be zero.
-
-   The bus number is defined by firmware, through the standard bridge
-   configuration mechanism. If this port is a switch port, then firmware
-   allocates the bus number and writes it into the Secondary Bus Number
-   register of the bridge directly above this port. Otherwise, the bus
-   number of a root port is the first number in the bus-range property,
-   defaulting to zero.
-
-   If firmware leaves the ARI Forwarding Enable bit set in the bridge
-   above this port, then phys.hi contains the 8-bit function number as
-   0b00000000 bbbbbbbb ffffffff 00000000. Note that the PCIe specification
-   recommends that firmware only leaves ARI enabled when it knows that the
-   OS is ARI-aware.
-
-Optional properties:
-
-- external-facing:
-   When present, the port is external-facing. All bridges and endpoints
-   downstream of this port are external to the machine. The OS can, for
-   example, use this information to identify devices that cannot be
-   trusted with relaxed DMA protection, as users could easily attach
-   malicious devices to this port.
-
-Example:
-
-pcie@10000000 {
-	compatible = "pci-host-ecam-generic";
-	...
-	pcie@0008 {
-		/* Root port 00:01.0 is external-facing */
-		reg = <0x00000800 0 0 0 0>;
-		external-facing;
-	};
-};
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sa8775p.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sa8775p.yaml
index efde49d1bef8..e3fa232da2ca 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie-sa8775p.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sa8775p.yaml
@@ -45,9 +45,10 @@ properties:
 
   interrupts:
     minItems: 8
-    maxItems: 8
+    maxItems: 9
 
   interrupt-names:
+    minItems: 8
     items:
       - const: msi0
       - const: msi1
@@ -57,6 +58,7 @@ properties:
       - const: msi5
       - const: msi6
       - const: msi7
+      - const: global
 
   resets:
     maxItems: 1
@@ -129,7 +131,8 @@ examples:
                          <GIC_SPI 313 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 314 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+                         <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
             interrupt-names = "msi0",
                               "msi1",
                               "msi2",
@@ -137,7 +140,8 @@ examples:
                               "msi4",
                               "msi5",
                               "msi6",
-                              "msi7";
+                              "msi7",
+                              "global";
             #interrupt-cells = <1>;
             interrupt-map-mask = <0 0 0 0x7>;
             interrupt-map = <0 0 0 1 &intc GIC_SPI 434 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sc7280.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sc7280.yaml
index 76cb9fbfd476..ff508f592a1a 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie-sc7280.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sc7280.yaml
@@ -54,9 +54,10 @@ properties:
 
   interrupts:
     minItems: 8
-    maxItems: 8
+    maxItems: 9
 
   interrupt-names:
+    minItems: 8
     items:
       - const: msi0
       - const: msi1
@@ -66,6 +67,7 @@ properties:
       - const: msi5
       - const: msi6
       - const: msi7
+      - const: global
 
   resets:
     maxItems: 1
@@ -149,9 +151,10 @@ examples:
                          <GIC_SPI 313 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 314 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+                         <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
             interrupt-names = "msi0", "msi1", "msi2", "msi3",
-                              "msi4", "msi5", "msi6", "msi7";
+                              "msi4", "msi5", "msi6", "msi7", "global";
             #interrupt-cells = <1>;
             interrupt-map-mask = <0 0 0 0x7>;
             interrupt-map = <0 0 0 1 &intc 0 0 0 434 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sc8180x.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sc8180x.yaml
index baf1813ec0ac..331fc25d7a17 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie-sc8180x.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sc8180x.yaml
@@ -49,9 +49,10 @@ properties:
 
   interrupts:
     minItems: 8
-    maxItems: 8
+    maxItems: 9
 
   interrupt-names:
+    minItems: 8
     items:
       - const: msi0
       - const: msi1
@@ -61,6 +62,7 @@ properties:
       - const: msi5
       - const: msi6
       - const: msi7
+      - const: global
 
   resets:
     maxItems: 1
@@ -136,7 +138,8 @@ examples:
                          <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+                         <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
             interrupt-names = "msi0",
                           "msi1",
                           "msi2",
@@ -144,7 +147,8 @@ examples:
                           "msi4",
                           "msi5",
                           "msi6",
-                          "msi7";
+                          "msi7",
+                          "global";
             #interrupt-cells = <1>;
             interrupt-map-mask = <0 0 0 0x7>;
             interrupt-map = <0 0 0 1 &intc 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8150.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8150.yaml
index 9d569644fda9..a604f2a79de3 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8150.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8150.yaml
@@ -49,9 +49,10 @@ properties:
 
   interrupts:
     minItems: 8
-    maxItems: 8
+    maxItems: 9
 
   interrupt-names:
+    minItems: 8
     items:
       - const: msi0
       - const: msi1
@@ -61,6 +62,7 @@ properties:
       - const: msi5
       - const: msi6
       - const: msi7
+      - const: global
 
   resets:
     maxItems: 1
@@ -128,9 +130,10 @@ examples:
                          <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+                         <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
             interrupt-names = "msi0", "msi1", "msi2", "msi3",
-                              "msi4", "msi5", "msi6", "msi7";
+                              "msi4", "msi5", "msi6", "msi7", "global";
             #interrupt-cells = <1>;
             interrupt-map-mask = <0 0 0 0x7>;
             interrupt-map = <0 0 0 1 &intc 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8250.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8250.yaml
index 4d060bce6f9d..af4dae68d508 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8250.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8250.yaml
@@ -61,9 +61,10 @@ properties:
 
   interrupts:
     minItems: 8
-    maxItems: 8
+    maxItems: 9
 
   interrupt-names:
+    minItems: 8
     items:
       - const: msi0
       - const: msi1
@@ -73,6 +74,7 @@ properties:
       - const: msi5
       - const: msi6
       - const: msi7
+      - const: global
 
   resets:
     maxItems: 1
@@ -143,9 +145,10 @@ examples:
                          <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+                         <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
             interrupt-names = "msi0", "msi1", "msi2", "msi3",
-                              "msi4", "msi5", "msi6", "msi7";
+                              "msi4", "msi5", "msi6", "msi7", "global";
             #interrupt-cells = <1>;
             interrupt-map-mask = <0 0 0 0x7>;
             interrupt-map = <0 0 0 1 &intc 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8350.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8350.yaml
index 2a4cc41fc710..dde3079adbb3 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8350.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8350.yaml
@@ -51,9 +51,10 @@ properties:
 
   interrupts:
     minItems: 8
-    maxItems: 8
+    maxItems: 9
 
   interrupt-names:
+    minItems: 8
     items:
       - const: msi0
       - const: msi1
@@ -63,6 +64,7 @@ properties:
       - const: msi5
       - const: msi6
       - const: msi7
+      - const: global
 
   resets:
     maxItems: 1
@@ -132,9 +134,10 @@ examples:
                          <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+                         <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
             interrupt-names = "msi0", "msi1", "msi2", "msi3",
-                              "msi4", "msi5", "msi6", "msi7";
+                              "msi4", "msi5", "msi6", "msi7", "global";
             #interrupt-cells = <1>;
             interrupt-map-mask = <0 0 0 0x7>;
             interrupt-map = <0 0 0 1 &intc 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
index 8f628939209e..0e1808105a81 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
@@ -21,6 +21,7 @@ properties:
           - qcom,pcie-apq8064
           - qcom,pcie-apq8084
           - qcom,pcie-ipq4019
+          - qcom,pcie-ipq5018
           - qcom,pcie-ipq6018
           - qcom,pcie-ipq8064
           - qcom,pcie-ipq8064-v2
@@ -168,6 +169,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,pcie-ipq5018
               - qcom,pcie-ipq6018
               - qcom,pcie-ipq8074-gen3
               - qcom,pcie-ipq9574
@@ -175,14 +177,16 @@ allOf:
       properties:
         reg:
           minItems: 5
-          maxItems: 5
+          maxItems: 6
         reg-names:
+          minItems: 5
           items:
             - const: dbi # DesignWare PCIe registers
             - const: elbi # External local bus interface registers
             - const: atu # ATU address space
             - const: parf # Qualcomm specific registers
             - const: config # PCIe configuration space
+            - const: mhi # MHI registers
 
   - if:
       properties:
@@ -327,6 +331,53 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,pcie-ipq5018
+    then:
+      properties:
+        clocks:
+          minItems: 6
+          maxItems: 6
+        clock-names:
+          items:
+            - const: iface # PCIe to SysNOC BIU clock
+            - const: axi_m # AXI Master clock
+            - const: axi_s # AXI Slave clock
+            - const: ahb # AHB clock
+            - const: aux # Auxiliary clock
+            - const: axi_bridge # AXI bridge clock
+        resets:
+          minItems: 8
+          maxItems: 8
+        reset-names:
+          items:
+            - const: pipe # PIPE reset
+            - const: sleep # Sleep reset
+            - const: sticky # Core sticky reset
+            - const: axi_m # AXI master reset
+            - const: axi_s # AXI slave reset
+            - const: ahb # AHB reset
+            - const: axi_m_sticky # AXI master sticky reset
+            - const: axi_s_sticky # AXI slave sticky reset
+        interrupts:
+          minItems: 9
+          maxItems: 9
+        interrupt-names:
+          items:
+            - const: msi0
+            - const: msi1
+            - const: msi2
+            - const: msi3
+            - const: msi4
+            - const: msi5
+            - const: msi6
+            - const: msi7
+            - const: global
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
               - qcom,pcie-msm8996
     then:
       properties:
@@ -562,6 +613,7 @@ allOf:
               enum:
                 - qcom,pcie-apq8064
                 - qcom,pcie-ipq4019
+                - qcom,pcie-ipq5018
                 - qcom,pcie-ipq8064
                 - qcom,pcie-ipq8064v2
                 - qcom,pcie-ipq8074
@@ -589,7 +641,11 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,pcie-ipq6018
+              - qcom,pcie-ipq8074
+              - qcom,pcie-ipq8074-gen3
               - qcom,pcie-msm8996
+              - qcom,pcie-msm8998
               - qcom,pcie-sdm845
     then:
       oneOf:
@@ -602,8 +658,9 @@ allOf:
         - properties:
             interrupts:
               minItems: 8
-              maxItems: 8
+              maxItems: 9
             interrupt-names:
+              minItems: 8
               items:
                 - const: msi0
                 - const: msi1
@@ -613,6 +670,7 @@ allOf:
                 - const: msi5
                 - const: msi6
                 - const: msi7
+                - const: global
 
   - if:
       properties:
@@ -622,11 +680,8 @@ allOf:
               - qcom,pcie-apq8064
               - qcom,pcie-apq8084
               - qcom,pcie-ipq4019
-              - qcom,pcie-ipq6018
               - qcom,pcie-ipq8064
               - qcom,pcie-ipq8064-v2
-              - qcom,pcie-ipq8074
-              - qcom,pcie-ipq8074-gen3
               - qcom,pcie-qcs404
     then:
       properties:
diff --git a/Documentation/devicetree/bindings/pci/rcar-pci-ep.yaml b/Documentation/devicetree/bindings/pci/rcar-pci-ep.yaml
index 32a3b7665ff5..6b91581c30ae 100644
--- a/Documentation/devicetree/bindings/pci/rcar-pci-ep.yaml
+++ b/Documentation/devicetree/bindings/pci/rcar-pci-ep.yaml
@@ -73,21 +73,21 @@ examples:
     #include <dt-bindings/interrupt-controller/arm-gic.h>
     #include <dt-bindings/power/r8a774c0-sysc.h>
 
-     pcie0_ep: pcie-ep@fe000000 {
-            compatible = "renesas,r8a774c0-pcie-ep",
-                         "renesas,rcar-gen3-pcie-ep";
-            reg = <0xfe000000 0x80000>,
-                  <0xfe100000 0x100000>,
-                  <0xfe200000 0x200000>,
-                  <0x30000000 0x8000000>,
-                  <0x38000000 0x8000000>;
-            reg-names = "apb-base", "memory0", "memory1", "memory2", "memory3";
-            interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>;
-            resets = <&cpg 319>;
-            power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>;
-            clocks = <&cpg CPG_MOD 319>;
-            clock-names = "pcie";
-            max-functions = /bits/ 8 <1>;
+    pcie0_ep: pcie-ep@fe000000 {
+        compatible = "renesas,r8a774c0-pcie-ep",
+                     "renesas,rcar-gen3-pcie-ep";
+        reg = <0xfe000000 0x80000>,
+              <0xfe100000 0x100000>,
+              <0xfe200000 0x200000>,
+              <0x30000000 0x8000000>,
+              <0x38000000 0x8000000>;
+        reg-names = "apb-base", "memory0", "memory1", "memory2", "memory3";
+        interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>;
+        resets = <&cpg 319>;
+        power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>;
+        clocks = <&cpg CPG_MOD 319>;
+        clock-names = "pcie";
+        max-functions = /bits/ 8 <1>;
     };
diff --git a/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml b/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml
index 666f013e3af8..7896576920aa 100644
--- a/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml
+++ b/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml
@@ -113,27 +113,27 @@ examples:
         pcie: pcie@fe000000 {
             compatible = "renesas,pcie-r8a7791", "renesas,pcie-rcar-gen2";
             reg = <0 0xfe000000 0 0x80000>;
-             #address-cells = <3>;
-             #size-cells = <2>;
-             bus-range = <0x00 0xff>;
-             device_type = "pci";
-             ranges = <0x01000000 0 0x00000000 0 0xfe100000 0 0x00100000>,
-                      <0x02000000 0 0xfe200000 0 0xfe200000 0 0x00200000>,
-                      <0x02000000 0 0x30000000 0 0x30000000 0 0x08000000>,
-                      <0x42000000 0 0x38000000 0 0x38000000 0 0x08000000>;
-             dma-ranges = <0x42000000 0 0x40000000 0 0x40000000 0 0x40000000>,
-                          <0x42000000 2 0x00000000 2 0x00000000 0 0x40000000>;
-             interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
-                          <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>,
-                          <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>;
-             #interrupt-cells = <1>;
-             interrupt-map-mask = <0 0 0 0>;
-             interrupt-map = <0 0 0 0 &gic GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>;
-             clocks = <&cpg CPG_MOD 319>, <&pcie_bus_clk>;
-             clock-names = "pcie", "pcie_bus";
-             power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
-             resets = <&cpg 319>;
-             vpcie3v3-supply = <&pcie_3v3>;
-             vpcie12v-supply = <&pcie_12v>;
-         };
+            #address-cells = <3>;
+            #size-cells = <2>;
+            bus-range = <0x00 0xff>;
+            device_type = "pci";
+            ranges = <0x01000000 0 0x00000000 0 0xfe100000 0 0x00100000>,
+                     <0x02000000 0 0xfe200000 0 0xfe200000 0 0x00200000>,
+                     <0x02000000 0 0x30000000 0 0x30000000 0 0x08000000>,
+                     <0x42000000 0 0x38000000 0 0x38000000 0 0x08000000>;
+            dma-ranges = <0x42000000 0 0x40000000 0 0x40000000 0 0x40000000>,
+                         <0x42000000 2 0x00000000 2 0x00000000 0 0x40000000>;
+            interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>;
+            #interrupt-cells = <1>;
+            interrupt-map-mask = <0 0 0 0>;
+            interrupt-map = <0 0 0 0 &gic GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>;
+            clocks = <&cpg CPG_MOD 319>, <&pcie_bus_clk>;
+            clock-names = "pcie", "pcie_bus";
+            power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
+            resets = <&cpg 319>;
+            vpcie3v3-supply = <&pcie_3v3>;
+            vpcie12v-supply = <&pcie_12v>;
+        };
     };
diff --git a/Documentation/devicetree/bindings/pci/rockchip-dw-pcie-common.yaml b/Documentation/devicetree/bindings/pci/rockchip-dw-pcie-common.yaml
index cc9adfc7611c..fde9b87508b3 100644
--- a/Documentation/devicetree/bindings/pci/rockchip-dw-pcie-common.yaml
+++ b/Documentation/devicetree/bindings/pci/rockchip-dw-pcie-common.yaml
@@ -65,7 +65,11 @@ properties:
           tx_cpl_timeout, cor_err_sent, nf_err_sent, f_err_sent, cor_err_rx,
           nf_err_rx, f_err_rx, radm_qoverflow
       - description:
-          eDMA write channel 0 interrupt
+          If the matching interrupt name is "msi", then this is the combined
+          MSI line interrupt, which is to support MSI interrupts output to GIC
+          controller via GIC SPI interrupt instead of GIC ITS interrupt.
+          If the matching interrupt name is "dma0", then this is the eDMA write
+          channel 0 interrupt.
       - description:
           eDMA write channel 1 interrupt
       - description:
@@ -81,7 +85,9 @@ properties:
       - const: msg
       - const: legacy
       - const: err
-      - const: dma0
+      - enum:
+          - msi
+          - dma0
       - const: dma1
       - const: dma2
       - const: dma3
diff --git a/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml b/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml
index 550d8a684af3..6c6d828ce964 100644
--- a/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml
@@ -16,16 +16,14 @@ description: |+
   PCIe IP and thus inherits all the common properties defined in
   snps,dw-pcie.yaml.
 
-allOf:
-  - $ref: /schemas/pci/snps,dw-pcie.yaml#
-  - $ref: /schemas/pci/rockchip-dw-pcie-common.yaml#
-
 properties:
   compatible:
     oneOf:
       - const: rockchip,rk3568-pcie
       - items:
           - enum:
+              - rockchip,rk3562-pcie
+              - rockchip,rk3576-pcie
               - rockchip,rk3588-pcie
           - const: rockchip,rk3568-pcie
 
@@ -71,8 +69,58 @@ properties:
 
   vpcie3v3-supply: true
 
-required:
-  - msi-map
+allOf:
+  - $ref: /schemas/pci/snps,dw-pcie.yaml#
+  - $ref: /schemas/pci/rockchip-dw-pcie-common.yaml#
+  - if:
+      not:
+        properties:
+          compatible:
+            contains:
+              enum:
+                - rockchip,rk3562-pcie
+                - rockchip,rk3576-pcie
+    then:
+      required:
+        - msi-map
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - rockchip,rk3562-pcie
+              - rockchip,rk3576-pcie
+    then:
+      properties:
+        interrupts:
+          minItems: 6
+          maxItems: 6
+        interrupt-names:
+          items:
+            - const: sys
+            - const: pmc
+            - const: msg
+            - const: legacy
+            - const: err
+            - const: msi
+    else:
+      properties:
+        interrupts:
+          minItems: 5
+        interrupt-names:
+          minItems: 5
+          items:
+            - const: sys
+            - const: pmc
+            - const: msg
+            - const: legacy
+            - const: err
+            - const: dma0
+            - const: dma1
+            - const: dma2
+            - const: dma3
+
 
 unevaluatedProperties: false
 
diff --git a/Documentation/devicetree/bindings/pci/sifive,fu740-pcie.yaml b/Documentation/devicetree/bindings/pci/sifive,fu740-pcie.yaml
index 844fc7142302..d35ff807936b 100644
--- a/Documentation/devicetree/bindings/pci/sifive,fu740-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/sifive,fu740-pcie.yaml
@@ -81,10 +81,10 @@ unevaluatedProperties: false
 
 examples:
   - |
+    #include <dt-bindings/clock/sifive-fu740-prci.h>
     bus {
         #address-cells = <2>;
         #size-cells = <2>;
-        #include <dt-bindings/clock/sifive-fu740-prci.h>
 
         pcie@e00000000 {
             compatible = "sifive,fu740-pcie";
diff --git a/Documentation/devicetree/bindings/pci/snps,dw-pcie-common.yaml b/Documentation/devicetree/bindings/pci/snps,dw-pcie-common.yaml
index dc05761c5cf9..34594972d8db 100644
--- a/Documentation/devicetree/bindings/pci/snps,dw-pcie-common.yaml
+++ b/Documentation/devicetree/bindings/pci/snps,dw-pcie-common.yaml
@@ -115,7 +115,7 @@ properties:
             above for new bindings.
           oneOf:
             - description: See native 'dbi' clock for details
-              enum: [ pcie, pcie_apb_sys, aclk_dbi ]
+              enum: [ pcie, pcie_apb_sys, aclk_dbi, reg ]
             - description: See native 'mstr/slv' clock for details
               enum: [ pcie_bus, pcie_inbound_axi, pcie_aclk, aclk_mst, aclk_slv ]
             - description: See native 'pipe' clock for details
@@ -201,6 +201,7 @@ properties:
           oneOf:
             - pattern: '^pcie(-?phy[0-9]*)?$'
             - pattern: '^p2u-[0-7]$'
+            - pattern: '^cp[01]-pcie[0-2]-x[124](-lane[0-3])?-phy$'  # marvell,armada8k-pcie
 
   reset-gpio:
     deprecated: true
diff --git a/Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml b/Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml
index 1117a86fb6f7..69e82f438f58 100644
--- a/Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml
@@ -105,6 +105,8 @@ properties:
             Vendor-specific CSR names. Consider using the generic names above
             for new bindings.
           oneOf:
+            - description: See native 'dbi' CSR region for details.
+              enum: [ ctrl ]
             - description: See native 'elbi/app' CSR region for details.
               enum: [ apb, mgmt, link, ulreg, appl ]
             - description: See native 'atu' CSR region for details.
@@ -117,7 +119,7 @@ properties:
               const: slcr
     allOf:
       - contains:
-          const: dbi
+          enum: [ dbi, ctrl ]
       - contains:
           const: config
 
diff --git a/Documentation/devicetree/bindings/pci/v3,v360epc-pci.yaml b/Documentation/devicetree/bindings/pci/v3,v360epc-pci.yaml
new file mode 100644
index 000000000000..38cac88f17bf
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/v3,v360epc-pci.yaml
@@ -0,0 +1,100 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/v3,v360epc-pci.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: V3 Semiconductor V360 EPC PCI bridge
+
+maintainers:
+  - Linus Walleij <linus.walleij@linaro.org>
+
+description:
+  This bridge is found in the ARM Integrator/AP (Application Platform)
+
+allOf:
+  - $ref: /schemas/pci/pci-host-bridge.yaml#
+
+properties:
+  compatible:
+    items:
+      - const: arm,integrator-ap-pci
+      - const: v3,v360epc-pci
+
+  reg:
+    items:
+      - description: V3 host bridge controller
+      - description: Configuration space
+
+  clocks:
+    maxItems: 1
+
+  dma-ranges:
+    maxItems: 2
+    description:
+      The inbound ranges must be aligned to a 1MB boundary, and may be 1MB, 2MB,
+      4MB, 8MB, 16MB, 32MB, 64MB, 128MB, 256MB, 512MB, 1GB or 2GB in size. The
+      memory should be marked as pre-fetchable.
+
+  interrupts:
+    description: Bus Error IRQ
+    maxItems: 1
+
+  ranges:
+    description:
+      The non-prefetchable and prefetchable memory windows must each be exactly
+      256MB (0x10000000) in size. The prefetchable memory window must be
+      immediately adjacent to the non-prefetchable memory window.
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - dma-ranges
+  - "#interrupt-cells"
+  - interrupt-map
+  - interrupt-map-mask
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    pci@62000000 {
+        compatible = "arm,integrator-ap-pci", "v3,v360epc-pci";
+        #interrupt-cells = <1>;
+        #size-cells = <2>;
+        #address-cells = <3>;
+        reg = <0x62000000 0x10000>, <0x61000000 0x01000000>;
+        device_type = "pci";
+        interrupt-parent = <&pic>;
+        interrupts = <17>; /* Bus error IRQ */
+        clocks = <&pciclk>;
+        ranges = <0x01000000 0 0x00000000 0x60000000 0 0x01000000>,     /* 16 MiB @ LB 60000000 */
+                 <0x02000000 0 0x40000000 0x40000000 0 0x10000000>,     /* 256 MiB @ LB 40000000 1:1 */
+                 <0x42000000 0 0x50000000 0x50000000 0 0x10000000>;     /* 256 MiB @ LB 50000000 1:1 */
+        dma-ranges = <0x02000000 0 0x20000000 0x20000000 0 0x20000000>, /* EBI: 512 MB @ LB 20000000 1:1 */
+                     <0x02000000 0 0x80000000 0x80000000 0 0x40000000>; /* CM alias: 1GB @ LB 80000000 */
+        interrupt-map-mask = <0xf800 0 0 0x7>;
+        interrupt-map =
+            /* IDSEL 9 */
+            <0x4800 0 0 1 &pic 13>, /* INT A on slot 9 is irq 13 */
+            <0x4800 0 0 2 &pic 14>, /* INT B on slot 9 is irq 14 */
+            <0x4800 0 0 3 &pic 15>, /* INT C on slot 9 is irq 15 */
+            <0x4800 0 0 4 &pic 16>, /* INT D on slot 9 is irq 16 */
+            /* IDSEL 10 */
+            <0x5000 0 0 1 &pic 14>, /* INT A on slot 10 is irq 14 */
+            <0x5000 0 0 2 &pic 15>, /* INT B on slot 10 is irq 15 */
+            <0x5000 0 0 3 &pic 16>, /* INT C on slot 10 is irq 16 */
+            <0x5000 0 0 4 &pic 13>, /* INT D on slot 10 is irq 13 */
+            /* IDSEL 11 */
+            <0x5800 0 0 1 &pic 15>, /* INT A on slot 11 is irq 15 */
+            <0x5800 0 0 2 &pic 16>, /* INT B on slot 11 is irq 16 */
+            <0x5800 0 0 3 &pic 13>, /* INT C on slot 11 is irq 13 */
+            <0x5800 0 0 4 &pic 14>, /* INT D on slot 11 is irq 14 */
+            /* IDSEL 12 */
+            <0x6000 0 0 1 &pic 16>, /* INT A on slot 12 is irq 16 */
+            <0x6000 0 0 2 &pic 13>, /* INT B on slot 12 is irq 13 */
+            <0x6000 0 0 3 &pic 14>, /* INT C on slot 12 is irq 14 */
+            <0x6000 0 0 4 &pic 15>; /* INT D on slot 12 is irq 15 */
+    };
+...
diff --git a/Documentation/devicetree/bindings/pci/v3-v360epc-pci.txt b/Documentation/devicetree/bindings/pci/v3-v360epc-pci.txt
deleted file mode 100644
index 11063293f761..000000000000
--- a/Documentation/devicetree/bindings/pci/v3-v360epc-pci.txt
+++ /dev/null
@@ -1,76 +0,0 @@
-V3 Semiconductor V360 EPC PCI bridge
-
-This bridge is found in the ARM Integrator/AP (Application Platform)
-
-Required properties:
-- compatible: should be one of:
-  "v3,v360epc-pci"
-  "arm,integrator-ap-pci", "v3,v360epc-pci"
-- reg: should contain two register areas:
-  first the base address of the V3 host bridge controller, 64KB
-  second the configuration area register space, 16MB
-- interrupts: should contain a reference to the V3 error interrupt
-  as routed on the system.
-- bus-range: see pci.txt
-- ranges: this follows the standard PCI bindings in the IEEE Std
-  1275-1994 (see pci.txt) with the following restriction:
-  - The non-prefetchable and prefetchable memory windows must
-    each be exactly 256MB (0x10000000) in size.
-  - The prefetchable memory window must be immediately adjacent
-    to the non-prefetcable memory window
-- dma-ranges: three ranges for the inbound memory region. The ranges must
-  be aligned to a 1MB boundary, and may be 1MB, 2MB, 4MB, 8MB, 16MB, 32MB,
-  64MB, 128MB, 256MB, 512MB, 1GB or 2GB in size. The memory should be marked
-  as pre-fetchable. Two ranges are supported by the hardware.
-
-Integrator-specific required properties:
-- syscon: should contain a link to the syscon device node, since
-  on the Integrator, some registers in the syscon are required to
-  operate the V3 host bridge.
-
-Example:
-
-pci: pciv3@62000000 {
-	compatible = "arm,integrator-ap-pci", "v3,v360epc-pci";
-	#interrupt-cells = <1>;
-	#size-cells = <2>;
-	#address-cells = <3>;
-	reg = <0x62000000 0x10000>, <0x61000000 0x01000000>;
-	interrupt-parent = <&pic>;
-	interrupts = <17>; /* Bus error IRQ */
-	clocks = <&pciclk>;
-	bus-range = <0x00 0xff>;
-	ranges = 0x01000000 0 0x00000000 /* I/O space @00000000 */
-		0x60000000 0 0x01000000 /* 16 MiB @ LB 60000000 */
-		0x02000000 0 0x40000000 /* non-prefectable memory @40000000 */
-		0x40000000 0 0x10000000 /* 256 MiB @ LB 40000000 1:1 */
-		0x42000000 0 0x50000000 /* prefetchable memory @50000000 */
-		0x50000000 0 0x10000000>; /* 256 MiB @ LB 50000000 1:1 */
-	dma-ranges = <0x02000000 0 0x20000000 /* EBI memory space */
-		0x20000000 0 0x20000000 /* 512 MB @ LB 20000000 1:1 */
-		0x02000000 0 0x80000000 /* Core module alias memory */
-		0x80000000 0 0x40000000>; /* 1GB @ LB 80000000 */
-	interrupt-map-mask = <0xf800 0 0 0x7>;
-	interrupt-map = <
-	/* IDSEL 9 */
-	0x4800 0 0 1 &pic 13 /* INT A on slot 9 is irq 13 */
-	0x4800 0 0 2 &pic 14 /* INT B on slot 9 is irq 14 */
-	0x4800 0 0 3 &pic 15 /* INT C on slot 9 is irq 15 */
-	0x4800 0 0 4 &pic 16 /* INT D on slot 9 is irq 16 */
-	/* IDSEL 10 */
-	0x5000 0 0 1 &pic 14 /* INT A on slot 10 is irq 14 */
-	0x5000 0 0 2 &pic 15 /* INT B on slot 10 is irq 15 */
-	0x5000 0 0 3 &pic 16 /* INT C on slot 10 is irq 16 */
-	0x5000 0 0 4 &pic 13 /* INT D on slot 10 is irq 13 */
-	/* IDSEL 11 */
-	0x5800 0 0 1 &pic 15 /* INT A on slot 11 is irq 15 */
-	0x5800 0 0 2 &pic 16 /* INT B on slot 11 is irq 16 */
-	0x5800 0 0 3 &pic 13 /* INT C on slot 11 is irq 13 */
-	0x5800 0 0 4 &pic 14 /* INT D on slot 11 is irq 14 */
-	/* IDSEL 12 */
-	0x6000 0 0 1 &pic 16 /* INT A on slot 12 is irq 16 */
-	0x6000 0 0 2 &pic 13 /* INT B on slot 12 is irq 13 */
-	0x6000 0 0 3 &pic 14 /* INT C on slot 12 is irq 14 */
-	0x6000 0 0 4 &pic 15 /* INT D on slot 12 is irq 15 */
-	>;
-};
diff --git a/Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml b/Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml
index d674a24c8ccc..9823456addea 100644
--- a/Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml
+++ b/Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml
@@ -76,64 +76,62 @@ unevaluatedProperties: false
 
 examples:
   - |
-
     versal {
-               #address-cells = <2>;
-               #size-cells = <2>;
-               cpm_pcie: pcie@fca10000 {
-                       compatible = "xlnx,versal-cpm-host-1.00";
-                       device_type = "pci";
-                       #address-cells = <3>;
-                       #interrupt-cells = <1>;
-                       #size-cells = <2>;
-                       interrupts = <0 72 4>;
-                       interrupt-parent = <&gic>;
-                       interrupt-map-mask = <0 0 0 7>;
-                       interrupt-map = <0 0 0 1 &pcie_intc_0 0>,
-                                       <0 0 0 2 &pcie_intc_0 1>,
-                                       <0 0 0 3 &pcie_intc_0 2>,
-                                       <0 0 0 4 &pcie_intc_0 3>;
-                       bus-range = <0x00 0xff>;
-                       ranges = <0x02000000 0x0 0xe0010000 0x0 0xe0010000 0x0 0x10000000>,
-                                <0x43000000 0x80 0x00000000 0x80 0x00000000 0x0 0x80000000>;
-                       msi-map = <0x0 &its_gic 0x0 0x10000>;
-                       reg = <0x0 0xfca10000 0x0 0x1000>,
-                             <0x6 0x00000000 0x0 0x10000000>;
-                       reg-names = "cpm_slcr", "cfg";
-                       pcie_intc_0: interrupt-controller {
-                               #address-cells = <0>;
-                               #interrupt-cells = <1>;
-                               interrupt-controller;
-                       };
-               };
-
-               cpm5_pcie: pcie@fcdd0000 {
-                       compatible = "xlnx,versal-cpm5-host";
-                       device_type = "pci";
-                       #address-cells = <3>;
-                       #interrupt-cells = <1>;
-                       #size-cells = <2>;
-                       interrupts = <0 72 4>;
-                       interrupt-parent = <&gic>;
-                       interrupt-map-mask = <0 0 0 7>;
-                       interrupt-map = <0 0 0 1 &pcie_intc_1 0>,
-                                       <0 0 0 2 &pcie_intc_1 1>,
-                                       <0 0 0 3 &pcie_intc_1 2>,
-                                       <0 0 0 4 &pcie_intc_1 3>;
-                       bus-range = <0x00 0xff>;
-                       ranges = <0x02000000 0x0 0xe0000000 0x0 0xe0000000 0x0 0x10000000>,
-                                <0x43000000 0x80 0x00000000 0x80 0x00000000 0x0 0x80000000>;
-                       msi-map = <0x0 &its_gic 0x0 0x10000>;
-                       reg = <0x00 0xfcdd0000 0x00 0x1000>,
-                             <0x06 0x00000000 0x00 0x1000000>,
-                             <0x00 0xfce20000 0x00 0x1000000>;
-                       reg-names = "cpm_slcr", "cfg", "cpm_csr";
-
-                       pcie_intc_1: interrupt-controller {
-                               #address-cells = <0>;
-                               #interrupt-cells = <1>;
-                               interrupt-controller;
-                       };
-               };
-
+        #address-cells = <2>;
+        #size-cells = <2>;
+        pcie@fca10000 {
+            compatible = "xlnx,versal-cpm-host-1.00";
+            device_type = "pci";
+            #address-cells = <3>;
+            #interrupt-cells = <1>;
+            #size-cells = <2>;
+            interrupts = <0 72 4>;
+            interrupt-parent = <&gic>;
+            interrupt-map-mask = <0 0 0 7>;
+            interrupt-map = <0 0 0 1 &pcie_intc_0 0>,
+                            <0 0 0 2 &pcie_intc_0 1>,
+                            <0 0 0 3 &pcie_intc_0 2>,
+                            <0 0 0 4 &pcie_intc_0 3>;
+            bus-range = <0x00 0xff>;
+            ranges = <0x02000000 0x0 0xe0010000 0x0 0xe0010000 0x0 0x10000000>,
+                     <0x43000000 0x80 0x00000000 0x80 0x00000000 0x0 0x80000000>;
+            msi-map = <0x0 &its_gic 0x0 0x10000>;
+            reg = <0x0 0xfca10000 0x0 0x1000>,
+                  <0x6 0x00000000 0x0 0x10000000>;
+            reg-names = "cpm_slcr", "cfg";
+            pcie_intc_0: interrupt-controller {
+                    #address-cells = <0>;
+                    #interrupt-cells = <1>;
+                    interrupt-controller;
+            };
+        };
+
+        pcie@fcdd0000 {
+            compatible = "xlnx,versal-cpm5-host";
+            device_type = "pci";
+            #address-cells = <3>;
+            #interrupt-cells = <1>;
+            #size-cells = <2>;
+            interrupts = <0 72 4>;
+            interrupt-parent = <&gic>;
+            interrupt-map-mask = <0 0 0 7>;
+            interrupt-map = <0 0 0 1 &pcie_intc_1 0>,
+                            <0 0 0 2 &pcie_intc_1 1>,
+                            <0 0 0 3 &pcie_intc_1 2>,
+                            <0 0 0 4 &pcie_intc_1 3>;
+            bus-range = <0x00 0xff>;
+            ranges = <0x02000000 0x0 0xe0000000 0x0 0xe0000000 0x0 0x10000000>,
+                     <0x43000000 0x80 0x00000000 0x80 0x00000000 0x0 0x80000000>;
+            msi-map = <0x0 &its_gic 0x0 0x10000>;
+            reg = <0x00 0xfcdd0000 0x00 0x1000>,
+                  <0x06 0x00000000 0x00 0x1000000>,
+                  <0x00 0xfce20000 0x00 0x1000000>;
+            reg-names = "cpm_slcr", "cfg", "cpm_csr";
+
+            pcie_intc_1: interrupt-controller {
+                #address-cells = <0>;
+                #interrupt-cells = <1>;
+                interrupt-controller;
+            };
+        };
     };
diff --git a/Documentation/devicetree/bindings/phy/brcm,brcmstb-usb-phy.yaml b/Documentation/devicetree/bindings/phy/brcm,brcmstb-usb-phy.yaml
index 580fbe37b37f..843d04027c30 100644
--- a/Documentation/devicetree/bindings/phy/brcm,brcmstb-usb-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/brcm,brcmstb-usb-phy.yaml
@@ -18,6 +18,7 @@ properties:
       - brcm,bcm4908-usb-phy
       - brcm,bcm7211-usb-phy
       - brcm,bcm7216-usb-phy
+      - brcm,bcm74110-usb-phy
       - brcm,brcmstb-usb-phy
 
   reg:
@@ -139,7 +140,9 @@ allOf:
       properties:
         compatible:
           contains:
-            const: brcm,bcm7216-usb-phy
+            enum:
+              - brcm,bcm7216-usb-phy
+              - brcm,bcm74110-usb-phy
     then:
       properties:
         reg:
diff --git a/Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml b/Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml
index daee0c0fc915..22dd91591a09 100644
--- a/Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml
@@ -43,15 +43,15 @@ properties:
   fsl,phy-tx-vref-tune-percent:
     description:
       Tunes the HS DC level relative to the nominal level
-    minimum: 94
+    minimum: 90
     maximum: 124
 
   fsl,phy-tx-rise-tune-percent:
     description:
       Adjusts the rise/fall time duration of the HS waveform relative to
       its nominal value
-    minimum: 97
-    maximum: 103
+    minimum: 90
+    maximum: 120
 
   fsl,phy-tx-preemp-amp-tune-microamp:
     description:
@@ -63,8 +63,7 @@ properties:
   fsl,phy-tx-vboost-level-microvolt:
     description:
       Adjust the boosted transmit launch pk-pk differential amplitude
-    minimum: 880
-    maximum: 1120
+    enum: [844, 1008, 1156]
 
   fsl,phy-comp-dis-tune-percent:
     description:
@@ -113,6 +112,34 @@ allOf:
           maxItems: 1
 
   - if:
+      properties:
+        compatible:
+          enum:
+            - fsl,imx8mq-usb-phy
+            - fsl,imx8mp-usb-phy
+    then:
+      properties:
+        fsl,phy-tx-vref-tune-percent:
+          minimum: 94
+        fsl,phy-tx-rise-tune-percent:
+          minimum: 97
+          maximum: 103
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - fsl,imx95-usb-phy
+    then:
+      properties:
+        fsl,phy-tx-vref-tune-percent:
+          maximum: 108
+        fsl,phy-comp-dis-tune-percent:
+          minimum: 94
+          maximum: 104
+
+  - if:
       required:
         - orientation-switch
     then:
diff --git a/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml b/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml
index f6e494d0d89b..acdbce937b0a 100644
--- a/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/mediatek,dsi-phy.yaml
@@ -30,6 +30,7 @@ properties:
           - const: mediatek,mt8173-mipi-tx
       - items:
           - enum:
+              - mediatek,mt6893-mipi-tx
               - mediatek,mt8188-mipi-tx
               - mediatek,mt8195-mipi-tx
               - mediatek,mt8365-mipi-tx
diff --git a/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml b/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml
index 6be3aa4557e5..b2218c151939 100644
--- a/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml
+++ b/Documentation/devicetree/bindings/phy/mediatek,tphy.yaml
@@ -78,6 +78,7 @@ properties:
       - items:
           - enum:
               - mediatek,mt2712-tphy
+              - mediatek,mt6893-tphy
               - mediatek,mt7629-tphy
               - mediatek,mt7986-tphy
               - mediatek,mt8183-tphy
diff --git a/Documentation/devicetree/bindings/phy/mediatek,xsphy.yaml b/Documentation/devicetree/bindings/phy/mediatek,xsphy.yaml
index a9e3139fd421..0bed847bb4ad 100644
--- a/Documentation/devicetree/bindings/phy/mediatek,xsphy.yaml
+++ b/Documentation/devicetree/bindings/phy/mediatek,xsphy.yaml
@@ -49,6 +49,7 @@ properties:
       - enum:
           - mediatek,mt3611-xsphy
           - mediatek,mt3612-xsphy
+          - mediatek,mt7988-xsphy
       - const: mediatek,xsphy
 
   reg:
@@ -150,6 +151,21 @@ patternProperties:
         minimum: 1
         maximum: 31
 
+      mediatek,syscon-type:
+        $ref: /schemas/types.yaml#/definitions/phandle-array
+        description:
+          A phandle to syscon used to access the register of type switch,
+          the field should always be 3 cells long.
+        items:
+          - items:
+              - description:
+                  Phandle to phy type configuration system controller
+              - description:
+                  Phy type configuration register offset
+              - description:
+                  Index of config segment
+                enum: [0, 1, 2, 3]
+
     required:
       - reg
       - clocks
diff --git a/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml b/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml
index 15dc8efe6ffe..9af39b33646a 100644
--- a/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml
+++ b/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml
@@ -99,8 +99,7 @@ patternProperties:
           Specifies the type of PHY for which the group of PHY lanes is used.
           Refer include/dt-bindings/phy/phy.h. Constants from the header should be used.
         $ref: /schemas/types.yaml#/definitions/uint32
-        minimum: 1
-        maximum: 9
+        enum: [1, 2, 3, 4, 5, 6, 7, 8, 9, 12]
 
       cdns,num-lanes:
         description:
diff --git a/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml b/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml
index 888e6b2aac5a..3e101c3c5ea9 100644
--- a/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml
+++ b/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml
@@ -42,6 +42,9 @@ properties:
       - const: phy
       - const: apb
 
+  phy-supply:
+    description: Single PHY regulator
+
   rockchip,enable-ssc:
     type: boolean
     description:
diff --git a/Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt b/Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt
deleted file mode 100644
index 960da7fcaa9e..000000000000
--- a/Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt
+++ /dev/null
@@ -1,84 +0,0 @@
-* ROCKCHIP type-c PHY
----------------------
-
-Required properties:
- - compatible : must be "rockchip,rk3399-typec-phy"
- - reg: Address and length of the usb phy control register set
- - rockchip,grf : phandle to the syscon managing the "general
-   register files"
- - clocks : phandle + clock specifier for the phy clocks
- - clock-names : string, clock name, must be "tcpdcore", "tcpdphy-ref";
- - assigned-clocks: main clock, should be <&cru SCLK_UPHY0_TCPDCORE> or
-		    <&cru SCLK_UPHY1_TCPDCORE>;
- - assigned-clock-rates : the phy core clk frequency, shall be: 50000000
- - resets : a list of phandle + reset specifier pairs
- - reset-names : string reset name, must be:
-		 "uphy", "uphy-pipe", "uphy-tcphy"
-
-Optional properties:
- - extcon : extcon specifier for the Power Delivery
-
-Required nodes : a sub-node is required for each port the phy provides.
-		 The sub-node name is used to identify dp or usb3 port,
-		 and shall be the following entries:
-	* "dp-port" : the name of DP port.
-	* "usb3-port" : the name of USB3 port.
-
-Required properties (port (child) node):
-- #phy-cells : must be 0, See ./phy-bindings.txt for details.
-
-Deprecated properties, do not use in new device tree sources, these
-properties are determined by the compatible value:
- - rockchip,typec-conn-dir
- - rockchip,usb3tousb2-en
- - rockchip,external-psm
- - rockchip,pipe-status
-
-Example:
-	tcphy0: phy@ff7c0000 {
-		compatible = "rockchip,rk3399-typec-phy";
-		reg = <0x0 0xff7c0000 0x0 0x40000>;
-		rockchip,grf = <&grf>;
-		extcon = <&fusb0>;
-		clocks = <&cru SCLK_UPHY0_TCPDCORE>,
-			 <&cru SCLK_UPHY0_TCPDPHY_REF>;
-		clock-names = "tcpdcore", "tcpdphy-ref";
-		assigned-clocks = <&cru SCLK_UPHY0_TCPDCORE>;
-		assigned-clock-rates = <50000000>;
-		resets = <&cru SRST_UPHY0>,
-			 <&cru SRST_UPHY0_PIPE_L00>,
-			 <&cru SRST_P_UPHY0_TCPHY>;
-		reset-names = "uphy", "uphy-pipe", "uphy-tcphy";
-
-		tcphy0_dp: dp-port {
-			#phy-cells = <0>;
-		};
-
-		tcphy0_usb3: usb3-port {
-			#phy-cells = <0>;
-		};
-	};
-
-	tcphy1: phy@ff800000 {
-		compatible = "rockchip,rk3399-typec-phy";
-		reg = <0x0 0xff800000 0x0 0x40000>;
-		rockchip,grf = <&grf>;
-		extcon = <&fusb1>;
-		clocks = <&cru SCLK_UPHY1_TCPDCORE>,
-			 <&cru SCLK_UPHY1_TCPDPHY_REF>;
-		clock-names = "tcpdcore", "tcpdphy-ref";
-		assigned-clocks = <&cru SCLK_UPHY1_TCPDCORE>;
-		assigned-clock-rates = <50000000>;
-		resets = <&cru SRST_UPHY1>,
-			 <&cru SRST_UPHY1_PIPE_L00>,
-			 <&cru SRST_P_UPHY1_TCPHY>;
-		reset-names = "uphy", "uphy-pipe", "uphy-tcphy";
-
-		tcphy1_dp: dp-port {
-			#phy-cells = <0>;
-		};
-
-		tcphy1_usb3: usb3-port {
-			#phy-cells = <0>;
-		};
-	};
diff --git a/Documentation/devicetree/bindings/phy/phy-rockchip-usbdp.yaml b/Documentation/devicetree/bindings/phy/phy-rockchip-usbdp.yaml
index b42f1272903d..8b7059d5b182 100644
--- a/Documentation/devicetree/bindings/phy/phy-rockchip-usbdp.yaml
+++ b/Documentation/devicetree/bindings/phy/phy-rockchip-usbdp.yaml
@@ -47,6 +47,9 @@ properties:
       - const: pcs_apb
       - const: pma_apb
 
+  phy-supply:
+    description: Single PHY regulator
+
   rockchip,dp-lane-mux:
     $ref: /schemas/types.yaml#/definitions/uint32-array
     minItems: 2
diff --git a/Documentation/devicetree/bindings/phy/qcom,ipq5332-uniphy-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,ipq5332-uniphy-pcie-phy.yaml
index e39168d55d23..6e9df81441e9 100644
--- a/Documentation/devicetree/bindings/phy/qcom,ipq5332-uniphy-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,ipq5332-uniphy-pcie-phy.yaml
@@ -11,26 +11,24 @@ maintainers:
   - Varadarajan Narayanan <quic_varada@quicinc.com>
 
 description:
-  PCIe and USB combo PHY found in Qualcomm IPQ5332 SoC
+  PCIe and USB combo PHY found in Qualcomm IPQ5018 & IPQ5332 SoCs
 
 properties:
   compatible:
     enum:
+      - qcom,ipq5018-uniphy-pcie-phy
       - qcom,ipq5332-uniphy-pcie-phy
 
   reg:
     maxItems: 1
 
   clocks:
-    items:
-      - description: pcie pipe clock
-      - description: pcie ahb clock
+    minItems: 1
+    maxItems: 2
 
   resets:
-    items:
-      - description: phy reset
-      - description: ahb reset
-      - description: cfg reset
+    minItems: 2
+    maxItems: 3
 
   "#phy-cells":
     const: 0
@@ -53,6 +51,41 @@ required:
 
 additionalProperties: false
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,ipq5018-uniphy-pcie-phy
+    then:
+      properties:
+        clocks:
+          items:
+            - description: pcie pipe clock
+        resets:
+          items:
+            - description: phy reset
+            - description: cfg reset
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,ipq5332-uniphy-pcie-phy
+    then:
+      properties:
+        clocks:
+          items:
+            - description: pcie pipe clock
+            - description: pcie ahb clock
+        resets:
+          items:
+            - description: phy reset
+            - description: ahb reset
+            - description: cfg reset
+
 examples:
   - |
     #include <dt-bindings/clock/qcom,ipq5332-gcc.h>
diff --git a/Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml b/Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml
index af275cea3456..2822dce8d9f4 100644
--- a/Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml
@@ -16,6 +16,7 @@ properties:
           - enum:
               - renesas,usb2-phy-r8a77470  # RZ/G1C
               - renesas,usb2-phy-r9a08g045 # RZ/G3S
+              - renesas,usb2-phy-r9a09g057 # RZ/V2H(P)
 
       - items:
           - enum:
@@ -105,8 +106,13 @@ allOf:
       properties:
         compatible:
           contains:
-            const: renesas,rzg2l-usb2-phy
+            enum:
+              - renesas,usb2-phy-r9a09g057
+              - renesas,rzg2l-usb2-phy
     then:
+      properties:
+        clocks:
+          minItems: 2
       required:
         - resets
 
diff --git a/Documentation/devicetree/bindings/phy/rockchip,inno-usb2phy.yaml b/Documentation/devicetree/bindings/phy/rockchip,inno-usb2phy.yaml
index 6a7ef556414c..58e735b5dd05 100644
--- a/Documentation/devicetree/bindings/phy/rockchip,inno-usb2phy.yaml
+++ b/Documentation/devicetree/bindings/phy/rockchip,inno-usb2phy.yaml
@@ -13,12 +13,14 @@ properties:
   compatible:
     enum:
       - rockchip,px30-usb2phy
+      - rockchip,rk3036-usb2phy
       - rockchip,rk3128-usb2phy
       - rockchip,rk3228-usb2phy
       - rockchip,rk3308-usb2phy
       - rockchip,rk3328-usb2phy
       - rockchip,rk3366-usb2phy
       - rockchip,rk3399-usb2phy
+      - rockchip,rk3562-usb2phy
       - rockchip,rk3568-usb2phy
       - rockchip,rk3576-usb2phy
       - rockchip,rk3588-usb2phy
@@ -184,12 +186,14 @@ allOf:
           contains:
             enum:
               - rockchip,px30-usb2phy
+              - rockchip,rk3036-usb2phy
               - rockchip,rk3128-usb2phy
               - rockchip,rk3228-usb2phy
               - rockchip,rk3308-usb2phy
               - rockchip,rk3328-usb2phy
               - rockchip,rk3366-usb2phy
               - rockchip,rk3399-usb2phy
+              - rockchip,rk3562-usb2phy
               - rockchip,rk3568-usb2phy
               - rockchip,rk3588-usb2phy
               - rockchip,rv1108-usb2phy
diff --git a/Documentation/devicetree/bindings/phy/rockchip,pcie3-phy.yaml b/Documentation/devicetree/bindings/phy/rockchip,pcie3-phy.yaml
index ba67dca5a446..d7de8b527c5c 100644
--- a/Documentation/devicetree/bindings/phy/rockchip,pcie3-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/rockchip,pcie3-phy.yaml
@@ -46,6 +46,9 @@ properties:
   reset-names:
     const: phy
 
+  phy-supply:
+    description: Single PHY regulator
+
   rockchip,phy-grf:
     $ref: /schemas/types.yaml#/definitions/phandle
     description: phandle to the syscon managing the phy "general register files"
diff --git a/Documentation/devicetree/bindings/phy/rockchip,rk3399-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/rockchip,rk3399-pcie-phy.yaml
new file mode 100644
index 000000000000..f46f065e5dbe
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/rockchip,rk3399-pcie-phy.yaml
@@ -0,0 +1,45 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/rockchip,rk3399-pcie-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Rockchip RK3399 PCIE PHY
+
+maintainers:
+  - Heiko Stuebner <heiko@sntech.de>
+
+properties:
+  compatible:
+    const: rockchip,rk3399-pcie-phy
+
+  '#phy-cells':
+    oneOf:
+      - const: 0
+        deprecated: true
+      - const: 1
+        description: One lane per phy mode
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    const: refclk
+
+  resets:
+    maxItems: 1
+
+  reset-names:
+    const: phy
+
+required:
+  - compatible
+  - '#phy-cells'
+  - clocks
+  - clock-names
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+...
diff --git a/Documentation/devicetree/bindings/phy/rockchip,rk3399-typec-phy.yaml b/Documentation/devicetree/bindings/phy/rockchip,rk3399-typec-phy.yaml
new file mode 100644
index 000000000000..91c011f68cd0
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/rockchip,rk3399-typec-phy.yaml
@@ -0,0 +1,116 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/rockchip,rk3399-typec-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Rockchip Type-C PHY
+
+maintainers:
+  - Heiko Stuebner <heiko@sntech.de>
+
+properties:
+  compatible:
+    const: rockchip,rk3399-typec-phy
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 2
+
+  clock-names:
+    items:
+      - const: tcpdcore
+      - const: tcpdphy-ref
+
+  extcon: true
+
+  power-domains:
+    maxItems: 1
+
+  resets:
+    maxItems: 3
+
+  reset-names:
+    items:
+      - const: uphy
+      - const: uphy-pipe
+      - const: uphy-tcphy
+
+  rockchip,grf:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      Phandle to the syscon managing the "general register files" (GRF).
+
+  dp-port:
+    type: object
+    additionalProperties: false
+
+    properties:
+      '#phy-cells':
+        const: 0
+
+      port:
+        $ref: /schemas/graph.yaml#/properties/port
+        description: Connection to USB Type-C connector
+
+    required:
+      - '#phy-cells'
+
+  usb3-port:
+    type: object
+    additionalProperties: false
+
+    properties:
+      '#phy-cells':
+        const: 0
+
+      orientation-switch: true
+
+      port:
+        $ref: /schemas/graph.yaml#/properties/port
+        description: Connection to USB Type-C connector SS port
+
+    required:
+      - '#phy-cells'
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - resets
+  - reset-names
+  - dp-port
+  - usb3-port
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/rk3399-cru.h>
+
+    phy@ff7c0000 {
+        compatible = "rockchip,rk3399-typec-phy";
+        reg = <0xff7c0000 0x40000>;
+        rockchip,grf = <&grf>;
+        extcon = <&fusb0>;
+        clocks = <&cru SCLK_UPHY0_TCPDCORE>,
+           <&cru SCLK_UPHY0_TCPDPHY_REF>;
+        clock-names = "tcpdcore", "tcpdphy-ref";
+        resets = <&cru SRST_UPHY0>,
+                 <&cru SRST_UPHY0_PIPE_L00>,
+                 <&cru SRST_P_UPHY0_TCPHY>;
+        reset-names = "uphy", "uphy-pipe", "uphy-tcphy";
+
+        dp-port {
+            #phy-cells = <0>;
+        };
+
+        usb3-port {
+            #phy-cells = <0>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/phy/rockchip-pcie-phy.txt b/Documentation/devicetree/bindings/phy/rockchip-pcie-phy.txt
deleted file mode 100644
index b496042f1f44..000000000000
--- a/Documentation/devicetree/bindings/phy/rockchip-pcie-phy.txt
+++ /dev/null
@@ -1,36 +0,0 @@
-Rockchip PCIE PHY
------------------------
-
-Required properties:
- - compatible: rockchip,rk3399-pcie-phy
- - clocks: Must contain an entry in clock-names.
-	See ../clocks/clock-bindings.txt for details.
- - clock-names: Must be "refclk"
- - resets: Must contain an entry in reset-names.
-	See ../reset/reset.txt for details.
- - reset-names: Must be "phy"
-
-Required properties for legacy PHY mode (deprecated):
- - #phy-cells: must be 0
-
-Required properties for per-lane PHY mode (preferred):
- - #phy-cells: must be 1
-
-Example:
-
-grf: syscon@ff770000 {
-	compatible = "rockchip,rk3399-grf", "syscon", "simple-mfd";
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	...
-
-	pcie_phy: pcie-phy {
-		compatible = "rockchip,rk3399-pcie-phy";
-		#phy-cells = <0>;
-		clocks = <&cru SCLK_PCIEPHY_REF>;
-		clock-names = "refclk";
-		resets = <&cru SRST_PCIEPHY>;
-		reset-names = "phy";
-	};
-};
diff --git a/Documentation/devicetree/bindings/phy/samsung,exynos2200-eusb2-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,exynos2200-eusb2-phy.yaml
new file mode 100644
index 000000000000..5e7e1bc2e39a
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/samsung,exynos2200-eusb2-phy.yaml
@@ -0,0 +1,80 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/samsung,exynos2200-eusb2-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Samsung Exynos2200 eUSB2 phy controller
+
+maintainers:
+  - Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
+
+description:
+  Samsung Exynos2200 eUSB2 phy, based on Synopsys eUSB2 IP block, supports
+  LS/FS/HS usb connectivity.
+
+properties:
+  compatible:
+    enum:
+      - samsung,exynos2200-eusb2-phy
+
+  reg:
+    maxItems: 1
+
+  "#phy-cells":
+    const: 0
+
+  clocks:
+    items:
+      - description: Reference clock
+      - description: Bus (APB) clock
+      - description: Control clock
+
+  clock-names:
+    items:
+      - const: ref
+      - const: bus
+      - const: ctrl
+
+  resets:
+    maxItems: 1
+
+  phys:
+    maxItems: 1
+    description:
+      Phandle to eUSB2 to USB 2.0 repeater
+
+  vdd-supply:
+    description:
+      Phandle to 0.88V regulator supply to PHY digital circuit.
+
+  vdda12-supply:
+    description:
+      Phandle to 1.2V regulator supply to PHY refclk pll block.
+
+required:
+  - compatible
+  - reg
+  - "#phy-cells"
+  - clocks
+  - clock-names
+  - vdd-supply
+  - vdda12-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    usb_hsphy: phy@10ab0000 {
+        compatible = "samsung,exynos2200-eusb2-phy";
+        reg = <0x10ab0000 0x10000>;
+        #phy-cells = <0>;
+
+        clocks = <&cmu_hsi0 7>,
+                 <&cmu_hsi0 5>,
+                 <&cmu_hsi0 8>;
+        clock-names = "ref", "bus", "ctrl";
+
+        vdd-supply = <&vreg_0p88>;
+        vdda12-supply = <&vreg_1p2>;
+    };
diff --git a/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml
index 27295acbba76..cc60d2f6f70e 100644
--- a/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml
@@ -26,31 +26,41 @@ properties:
   compatible:
     enum:
       - google,gs101-usb31drd-phy
+      - samsung,exynos2200-usb32drd-phy
       - samsung,exynos5250-usbdrd-phy
       - samsung,exynos5420-usbdrd-phy
       - samsung,exynos5433-usbdrd-phy
       - samsung,exynos7-usbdrd-phy
+      - samsung,exynos7870-usbdrd-phy
       - samsung,exynos850-usbdrd-phy
 
   clocks:
-    minItems: 2
+    minItems: 1
     maxItems: 5
 
   clock-names:
-    minItems: 2
+    minItems: 1
     maxItems: 5
     description: |
-      At least two clocks::
+      Typically two clocks:
         - Main PHY clock (same as USB DRD controller i.e. DWC3 IP clock), used
           for register access.
         - PHY reference clock (usually crystal clock), used for PHY operations,
           associated by phy name. It is used to determine bit values for clock
           settings register.  For Exynos5420 this is given as 'sclk_usbphy30'
-          in the CMU.
+          in the CMU. It's not needed for Exynos2200.
 
   "#phy-cells":
     const: 1
 
+  phys:
+    maxItems: 1
+    description:
+      USBDRD-underlying high-speed PHY
+
+  phy-names:
+    const: hs
+
   port:
     $ref: /schemas/graph.yaml#/properties/port
     description:
@@ -155,6 +165,27 @@ allOf:
         compatible:
           contains:
             enum:
+              - samsung,exynos2200-usb32drd-phy
+    then:
+      properties:
+        clocks:
+          maxItems: 1
+        clock-names:
+          items:
+            - const: phy
+        reg:
+          maxItems: 1
+        reg-names:
+          maxItems: 1
+      required:
+        - phys
+        - phy-names
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
               - samsung,exynos5433-usbdrd-phy
               - samsung,exynos7-usbdrd-phy
     then:
@@ -184,6 +215,7 @@ allOf:
             enum:
               - samsung,exynos5250-usbdrd-phy
               - samsung,exynos5420-usbdrd-phy
+              - samsung,exynos7870-usbdrd-phy
               - samsung,exynos850-usbdrd-phy
     then:
       properties:
diff --git a/Documentation/devicetree/bindings/regulator/brcm,bcm59054.yaml b/Documentation/devicetree/bindings/regulator/brcm,bcm59054.yaml
new file mode 100644
index 000000000000..5b46d7fca05e
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/brcm,bcm59054.yaml
@@ -0,0 +1,56 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/regulator/brcm,bcm59054.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Broadcom BCM59054 Power Management Unit regulators
+
+description: |
+  This is a part of device tree bindings for the BCM59054 power
+  management unit.
+
+  See Documentation/devicetree/bindings/mfd/brcm,bcm59056.yaml for
+  additional information and example.
+
+maintainers:
+  - Artur Weber <aweber.kernel@gmail.com>
+
+patternProperties:
+  "^(cam|sim|mmc)ldo[1-2]$":
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+  "^(rf|sd|sdx|aud|mic|usb|vib|tcx)ldo$":
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+  "^(c|mm|v)sr$":
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+  "^(io|sd)sr[1-2]$":
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+  "^gpldo[1-3]$":
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+  "^lvldo[1-2]$":
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+properties:
+  vbus:
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+additionalProperties: false
diff --git a/Documentation/devicetree/bindings/regulator/brcm,bcm59056.yaml b/Documentation/devicetree/bindings/regulator/brcm,bcm59056.yaml
new file mode 100644
index 000000000000..7a5e36394d21
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/brcm,bcm59056.yaml
@@ -0,0 +1,51 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/regulator/brcm,bcm59056.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Broadcom BCM59056 Power Management Unit regulators
+
+description: |
+  This is a part of device tree bindings for the BCM59056 power
+  management unit.
+
+  See Documentation/devicetree/bindings/mfd/brcm,bcm59056.yaml for
+  additional information and example.
+
+maintainers:
+  - Artur Weber <aweber.kernel@gmail.com>
+
+patternProperties:
+  "^(cam|sim|mmc)ldo[1-2]$":
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+  "^(rf|sd|sdx|aud|mic|usb|vib)ldo$":
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+  "^(c|m|v)sr$":
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+  "^(io|sd)sr[1-2]$":
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+  "^gpldo[1-6]$":
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+properties:
+  vbus:
+    type: object
+    $ref: /schemas/regulator/regulator.yaml#
+    unevaluatedProperties: false
+
+additionalProperties: false
diff --git a/Documentation/devicetree/bindings/regulator/rohm,bd96802-regulator.yaml b/Documentation/devicetree/bindings/regulator/rohm,bd96802-regulator.yaml
new file mode 100644
index 000000000000..671eaf1096d3
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/rohm,bd96802-regulator.yaml
@@ -0,0 +1,44 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/regulator/rohm,bd96802-regulator.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ROHM BD96802 Power Management Integrated Circuit regulators
+
+maintainers:
+  - Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
+
+description:
+  This module is part of the ROHM BD96802 MFD device. For more details
+  see Documentation/devicetree/bindings/mfd/rohm,bd96802-pmic.yaml.
+
+  The regulator controller is represented as a sub-node of the PMIC node
+  on the device tree.
+
+  Regulator nodes should be named to buck1 and buck2.
+
+patternProperties:
+  "^buck[1-2]$":
+    type: object
+    description:
+      Properties for single BUCK regulator.
+    $ref: regulator.yaml#
+
+    properties:
+      rohm,initial-voltage-microvolt:
+        description:
+          Initial voltage for regulator. Voltage can be tuned +/-150 mV from
+          this value. NOTE, This can be modified via I2C only when PMIC is in
+          STBY state.
+        minimum: 500000
+        maximum: 3300000
+
+      rohm,keep-on-stby:
+        description:
+          Keep the regulator powered when PMIC transitions to STBY state.
+        type: boolean
+
+    unevaluatedProperties: false
+
+additionalProperties: false
diff --git a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml
index c8bb2eef442d..7c5b13caa40b 100644
--- a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml
@@ -23,7 +23,9 @@ properties:
           - microchip,sam9x60-rtc
           - microchip,sama7g5-rtc
       - items:
-          - const: microchip,sam9x7-rtc
+          - enum:
+              - microchip,sam9x7-rtc
+              - microchip,sama7d65-rtc
           - const: microchip,sam9x60-rtc
 
   reg:
diff --git a/Documentation/devicetree/bindings/rtc/atmel,at91sam9260-rtt.yaml b/Documentation/devicetree/bindings/rtc/atmel,at91sam9260-rtt.yaml
index a7f6c1d1a08a..9c9b981fe38b 100644
--- a/Documentation/devicetree/bindings/rtc/atmel,at91sam9260-rtt.yaml
+++ b/Documentation/devicetree/bindings/rtc/atmel,at91sam9260-rtt.yaml
@@ -22,6 +22,7 @@ properties:
           - enum:
               - microchip,sam9x60-rtt
               - microchip,sam9x7-rtt
+              - microchip,sama7d65-rtt
           - const: atmel,at91sam9260-rtt
       - items:
           - const: microchip,sama7g5-rtt
diff --git a/Documentation/devicetree/bindings/rtc/nxp,s32g-rtc.yaml b/Documentation/devicetree/bindings/rtc/nxp,s32g-rtc.yaml
new file mode 100644
index 000000000000..40fd2fa298fe
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/nxp,s32g-rtc.yaml
@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/rtc/nxp,s32g-rtc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NXP S32G2/S32G3 Real Time Clock (RTC)
+
+maintainers:
+  - Bogdan Hamciuc <bogdan.hamciuc@nxp.com>
+  - Ciprian Marian Costea <ciprianmarian.costea@nxp.com>
+
+description:
+  RTC hardware module present on S32G2/S32G3 SoCs is used as a wakeup source.
+  It is not kept alive during system reset and it is not battery-powered.
+
+allOf:
+  - $ref: rtc.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - enum:
+          - nxp,s32g2-rtc
+      - items:
+          - const: nxp,s32g3-rtc
+          - const: nxp,s32g2-rtc
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: ipg clock drives the access to the RTC iomapped registers
+      - description: Clock source for the RTC module. Can be selected between
+          4 different clock sources using an integrated hardware mux.
+          On S32G2/S32G3 SoCs, 'source0' is the SIRC clock (~32KHz) and it is
+          available during standby and runtime. 'source1' is reserved and cannot
+          be used. 'source2' is the FIRC clock and it is only available during
+          runtime providing a better resolution (~48MHz). 'source3' is an external
+          RTC clock source which can be additionally added in hardware.
+
+  clock-names:
+    items:
+      - const: ipg
+      - enum: [ source0, source1, source2, source3 ]
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    rtc@40060000 {
+        compatible = "nxp,s32g3-rtc",
+                     "nxp,s32g2-rtc";
+        reg = <0x40060000 0x1000>;
+        interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&clks 54>, <&clks 55>;
+        clock-names = "ipg", "source0";
+    };
diff --git a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml
index 68ef3208c886..7497dc3ac5b2 100644
--- a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml
@@ -55,6 +55,12 @@ properties:
     description:
       RTC alarm is not owned by the OS
 
+  qcom,uefi-rtc-info:
+    type: boolean
+    description:
+      RTC offset is stored as a four-byte GPS time offset in a 12-byte UEFI
+      variable 882f8c2b-9646-435f-8de5-f208ff80c1bd-RTCInfo
+
   wakeup-source: true
 
 required:
diff --git a/Documentation/devicetree/bindings/rtc/renesas,rzn1-rtc.yaml b/Documentation/devicetree/bindings/rtc/renesas,rzn1-rtc.yaml
index f6e0c613af67..f6fdcc7090b6 100644
--- a/Documentation/devicetree/bindings/rtc/renesas,rzn1-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/renesas,rzn1-rtc.yaml
@@ -33,10 +33,14 @@ properties:
       - const: pps
 
   clocks:
-    maxItems: 1
+    minItems: 1
+    maxItems: 2
 
   clock-names:
-    const: hclk
+    minItems: 1
+    items:
+      - const: hclk
+      - const: xtal
 
   power-domains:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
index 8cbf5b6772dd..ccdcc889ba8e 100644
--- a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
+++ b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
@@ -208,8 +208,8 @@ allOf:
 
         pcie-phy:
           type: object
-          description:
-            Documentation/devicetree/bindings/phy/rockchip-pcie-phy.txt
+          $ref: /schemas/phy/rockchip,rk3399-pcie-phy.yaml#
+          unevaluatedProperties: false
 
       patternProperties:
         "^phy@[0-9a-f]+$":
@@ -333,6 +333,15 @@ examples:
         #phy-cells = <0>;
       };
 
+      pcie-phy {
+        compatible = "rockchip,rk3399-pcie-phy";
+        #phy-cells = <1>;
+        clocks = <&cru SCLK_PCIEPHY_REF>;
+        clock-names = "refclk";
+        resets = <&cru SRST_PCIEPHY>;
+        reset-names = "phy";
+      };
+
       phy@f780 {
         compatible = "rockchip,rk3399-emmc-phy";
         reg = <0xf780 0x20>;
diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml
index 6a49e8efc0f7..8dc81b1ca48e 100644
--- a/Documentation/devicetree/bindings/trivial-devices.yaml
+++ b/Documentation/devicetree/bindings/trivial-devices.yaml
@@ -295,8 +295,6 @@ properties:
           - mps,mp5990
             # Monolithic Power Systems Inc. digital step-down converter mp9941
           - mps,mp9941
-            # Monolithic Power Systems Inc. synchronous step-down converter mpq8785
-          - mps,mpq8785
             # Temperature sensor with integrated fan control
           - national,lm63
             # Serial Interface ACPI-Compatible Microprocessor System Hardware Monitor
diff --git a/Documentation/devicetree/bindings/usb/rockchip,dwc3.yaml b/Documentation/devicetree/bindings/usb/rockchip,dwc3.yaml
index fba2cb05ecba..fd1b13c0ed6b 100644
--- a/Documentation/devicetree/bindings/usb/rockchip,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/rockchip,dwc3.yaml
@@ -18,7 +18,7 @@ description:
   Documentation/devicetree/bindings/phy/rockchip,inno-usb2phy.yaml
 
   Type-C PHY
-  Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt
+  Documentation/devicetree/bindings/phy/rockchip,rk3399-typec-phy.yaml
 
 select:
   properties:
diff --git a/Documentation/driver-api/cxl/access-coordinates.rst b/Documentation/driver-api/cxl/access-coordinates.rst
deleted file mode 100644
index b07950ea30c9..000000000000
--- a/Documentation/driver-api/cxl/access-coordinates.rst
+++ /dev/null
@@ -1,91 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-.. include:: <isonum.txt>
-
-==================================
-CXL Access Coordinates Computation
-==================================
-
-Shared Upstream Link Calculation
-================================
-For certain CXL region construction with endpoints behind CXL switches (SW) or
-Root Ports (RP), there is the possibility of the total bandwidth for all
-the endpoints behind a switch being more than the switch upstream link.
-A similar situation can occur within the host, upstream of the root ports.
-The CXL driver performs an additional pass after all the targets have
-arrived for a region in order to recalculate the bandwidths with possible
-upstream link being a limiting factor in mind.
-
-The algorithm assumes the configuration is a symmetric topology as that
-maximizes performance. When asymmetric topology is detected, the calculation
-is aborted. An asymmetric topology is detected during topology walk where the
-number of RPs detected as a grandparent is not equal to the number of devices
-iterated in the same iteration loop. The assumption is made that subtle
-asymmetry in properties does not happen and all paths to EPs are equal.
-
-There can be multiple switches under an RP. There can be multiple RPs under
-a CXL Host Bridge (HB). There can be multiple HBs under a CXL Fixed Memory
-Window Structure (CFMWS).
-
-An example hierarchy:
-
->                CFMWS 0
->                  |
->         _________|_________
->        |                   |
->    ACPI0017-0          ACPI0017-1
-> GP0/HB0/ACPI0016-0   GP1/HB1/ACPI0016-1
->    |          |        |           |
->   RP0        RP1      RP2         RP3
->    |          |        |           |
->  SW 0       SW 1     SW 2        SW 3
->  |   |      |   |    |   |       |   |
-> EP0 EP1    EP2 EP3  EP4  EP5    EP6 EP7
-
-Computation for the example hierarchy:
-
-Min (GP0 to CPU BW,
-     Min(SW 0 Upstream Link to RP0 BW,
-         Min(SW0SSLBIS for SW0DSP0 (EP0), EP0 DSLBIS, EP0 Upstream Link) +
-         Min(SW0SSLBIS for SW0DSP1 (EP1), EP1 DSLBIS, EP1 Upstream link)) +
-     Min(SW 1 Upstream Link to RP1 BW,
-         Min(SW1SSLBIS for SW1DSP0 (EP2), EP2 DSLBIS, EP2 Upstream Link) +
-         Min(SW1SSLBIS for SW1DSP1 (EP3), EP3 DSLBIS, EP3 Upstream link))) +
-Min (GP1 to CPU BW,
-     Min(SW 2 Upstream Link to RP2 BW,
-         Min(SW2SSLBIS for SW2DSP0 (EP4), EP4 DSLBIS, EP4 Upstream Link) +
-         Min(SW2SSLBIS for SW2DSP1 (EP5), EP5 DSLBIS, EP5 Upstream link)) +
-     Min(SW 3 Upstream Link to RP3 BW,
-         Min(SW3SSLBIS for SW3DSP0 (EP6), EP6 DSLBIS, EP6 Upstream Link) +
-         Min(SW3SSLBIS for SW3DSP1 (EP7), EP7 DSLBIS, EP7 Upstream link))))
-
-The calculation starts at cxl_region_shared_upstream_perf_update(). A xarray
-is created to collect all the endpoint bandwidths via the
-cxl_endpoint_gather_bandwidth() function. The min() of bandwidth from the
-endpoint CDAT and the upstream link bandwidth is calculated. If the endpoint
-has a CXL switch as a parent, then min() of calculated bandwidth and the
-bandwidth from the SSLBIS for the switch downstream port that is associated
-with the endpoint is calculated. The final bandwidth is stored in a
-'struct cxl_perf_ctx' in the xarray indexed by a device pointer. If the
-endpoint is direct attached to a root port (RP), the device pointer would be an
-RP device. If the endpoint is behind a switch, the device pointer would be the
-upstream device of the parent switch.
-
-At the next stage, the code walks through one or more switches if they exist
-in the topology. For endpoints directly attached to RPs, this step is skipped.
-If there is another switch upstream, the code takes the min() of the current
-gathered bandwidth and the upstream link bandwidth. If there's a switch
-upstream, then the SSLBIS of the upstream switch.
-
-Once the topology walk reaches the RP, whether it's direct attached endpoints
-or walking through the switch(es), cxl_rp_gather_bandwidth() is called. At
-this point all the bandwidths are aggregated per each host bridge, which is
-also the index for the resulting xarray.
-
-The next step is to take the min() of the per host bridge bandwidth and the
-bandwidth from the Generic Port (GP). The bandwidths for the GP is retrieved
-via ACPI tables SRAT/HMAT. The min bandwidth are aggregated under the same
-ACPI0017 device to form a new xarray.
-
-Finally, the cxl_region_update_bandwidth() is called and the aggregated
-bandwidth from all the members of the last xarray is updated for the
-access coordinates residing in the cxl region (cxlr) context.
diff --git a/Documentation/driver-api/cxl/allocation/dax.rst b/Documentation/driver-api/cxl/allocation/dax.rst
new file mode 100644
index 000000000000..c6f7a5da832f
--- /dev/null
+++ b/Documentation/driver-api/cxl/allocation/dax.rst
@@ -0,0 +1,60 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========
+DAX Devices
+===========
+CXL capacity exposed as a DAX device can be accessed directly via mmap.
+Users may wish to use this interface mechanism to write their own userland
+CXL allocator, or to managed shared or persistent memory regions across multiple
+hosts.
+
+If the capacity is shared across hosts or persistent, appropriate flushing
+mechanisms must be employed unless the region supports Snoop Back-Invalidate.
+
+Note that mappings must be aligned (size and base) to the dax device's base
+alignment, which is typically 2MB - but maybe be configured larger.
+
+::
+
+  #include <stdio.h>
+  #include <stdlib.h>
+  #include <stdint.h>
+  #include <sys/mman.h>
+  #include <fcntl.h>
+  #include <unistd.h>
+
+  #define DEVICE_PATH "/dev/dax0.0" // Replace DAX device path
+  #define DEVICE_SIZE (4ULL * 1024 * 1024 * 1024) // 4GB
+
+  int main() {
+      int fd;
+      void* mapped_addr;
+
+      /* Open the DAX device */
+      fd = open(DEVICE_PATH, O_RDWR);
+      if (fd < 0) {
+          perror("open");
+          return -1;
+      }
+
+      /* Map the device into memory */
+      mapped_addr = mmap(NULL, DEVICE_SIZE, PROT_READ | PROT_WRITE,
+                         MAP_SHARED, fd, 0);
+      if (mapped_addr == MAP_FAILED) {
+          perror("mmap");
+          close(fd);
+          return -1;
+      }
+
+      printf("Mapped address: %p\n", mapped_addr);
+
+      /* You can now access the device through the mapped address */
+      uint64_t* ptr = (uint64_t*)mapped_addr;
+      *ptr = 0x1234567890abcdef; // Write a value to the device
+      printf("Value at address %p: 0x%016llx\n", ptr, *ptr);
+
+      /* Clean up */
+      munmap(mapped_addr, DEVICE_SIZE);
+      close(fd);
+      return 0;
+  }
diff --git a/Documentation/driver-api/cxl/allocation/hugepages.rst b/Documentation/driver-api/cxl/allocation/hugepages.rst
new file mode 100644
index 000000000000..1023c6922829
--- /dev/null
+++ b/Documentation/driver-api/cxl/allocation/hugepages.rst
@@ -0,0 +1,32 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==========
+Huge Pages
+==========
+
+Contiguous Memory Allocator
+===========================
+CXL Memory onlined as SystemRAM during early boot is eligible for use by CMA,
+as the NUMA node hosting that capacity will be `Online` at the time CMA
+carves out contiguous capacity.
+
+CXL Memory deferred to the CXL Driver for configuration cannot have its
+capacity allocated by CMA - as the NUMA node hosting the capacity is `Offline`
+at :code:`__init` time - when CMA carves out contiguous capacity.
+
+HugeTLB
+=======
+Different huge page sizes allow different memory configurations.
+
+2MB Huge Pages
+--------------
+All CXL capacity regardless of configuration time or memory zone is eligible
+for use as 2MB huge pages.
+
+1GB Huge Pages
+--------------
+CXL capacity onlined in :code:`ZONE_NORMAL` is eligible for 1GB Gigantic Page
+allocation.
+
+CXL capacity onlined in :code:`ZONE_MOVABLE` is not eligible for 1GB Gigantic
+Page allocation.
diff --git a/Documentation/driver-api/cxl/allocation/page-allocator.rst b/Documentation/driver-api/cxl/allocation/page-allocator.rst
new file mode 100644
index 000000000000..7b8fe1b8d5bb
--- /dev/null
+++ b/Documentation/driver-api/cxl/allocation/page-allocator.rst
@@ -0,0 +1,85 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================
+The Page Allocator
+==================
+
+The kernel page allocator services all general page allocation requests, such
+as :code:`kmalloc`.  CXL configuration steps affect the behavior of the page
+allocator based on the selected `Memory Zone` and `NUMA node` the capacity is
+placed in.
+
+This section mostly focuses on how these configurations affect the page
+allocator (as of Linux v6.15) rather than the overall page allocator behavior.
+
+NUMA nodes and mempolicy
+========================
+Unless a task explicitly registers a mempolicy, the default memory policy
+of the linux kernel is to allocate memory from the `local NUMA node` first,
+and fall back to other nodes only if the local node is pressured.
+
+Generally, we expect to see local DRAM and CXL memory on separate NUMA nodes,
+with the CXL memory being non-local.  Technically, however, it is possible
+for a compute node to have no local DRAM, and for CXL memory to be the
+`local` capacity for that compute node.
+
+
+Memory Zones
+============
+CXL capacity may be onlined in :code:`ZONE_NORMAL` or :code:`ZONE_MOVABLE`.
+
+As of v6.15, the page allocator attempts to allocate from the highest
+available and compatible ZONE for an allocation from the local node first.
+
+An example of a `zone incompatibility` is attempting to service an allocation
+marked :code:`GFP_KERNEL` from :code:`ZONE_MOVABLE`.  Kernel allocations are
+typically not migratable, and as a result can only be serviced from
+:code:`ZONE_NORMAL` or lower.
+
+To simplify this, the page allocator will prefer :code:`ZONE_MOVABLE` over
+:code:`ZONE_NORMAL` by default, but if :code:`ZONE_MOVABLE` is depleted, it
+will fallback to allocate from :code:`ZONE_NORMAL`.
+
+
+Zone and Node Quirks
+====================
+Let's consider a configuration where the local DRAM capacity is largely onlined
+into :code:`ZONE_NORMAL`, with no :code:`ZONE_MOVABLE` capacity present. The
+CXL capacity has the opposite configuration - all onlined in
+:code:`ZONE_MOVABLE`.
+
+Under the default allocation policy, the page allocator will completely skip
+:code:`ZONE_MOVABLE` as a valid allocation target.  This is because, as of
+Linux v6.15, the page allocator does (approximately) the following: ::
+
+  for (each zone in local_node):
+
+    for (each node in fallback_order):
+
+      attempt_allocation(gfp_flags);
+
+Because the local node does not have :code:`ZONE_MOVABLE`, the CXL node is
+functionally unreachable for direct allocation.  As a result, the only way
+for CXL capacity to be used is via `demotion` in the reclaim path.
+
+This configuration also means that if the DRAM ndoe has :code:`ZONE_MOVABLE`
+capacity - when that capacity is depleted, the page allocator will actually
+prefer CXL :code:`ZONE_MOVABLE` pages over DRAM :code:`ZONE_NORMAL` pages.
+
+We may wish to invert this priority in future Linux versions.
+
+If `demotion` and `swap` are disabled, Linux will begin to cause OOM crashes
+when the DRAM nodes are depleted. See the reclaim section for more details.
+
+
+CGroups and CPUSets
+===================
+Finally, assuming CXL memory is reachable via the page allocation (i.e. onlined
+in :code:`ZONE_NORMAL`), the :code:`cpusets.mems_allowed` may be used by
+containers to limit the accessibility of certain NUMA nodes for tasks in that
+container.  Users may wish to utilize this in multi-tenant systems where some
+tasks prefer not to use slower memory.
+
+In the reclaim section we'll discuss some limitations of this interface to
+prevent demotions of shared data to CXL memory (if demotions are enabled).
+
diff --git a/Documentation/driver-api/cxl/allocation/reclaim.rst b/Documentation/driver-api/cxl/allocation/reclaim.rst
new file mode 100644
index 000000000000..f40f1cae391a
--- /dev/null
+++ b/Documentation/driver-api/cxl/allocation/reclaim.rst
@@ -0,0 +1,51 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=======
+Reclaim
+=======
+Another way CXL memory can be utilized *indirectly* is via the reclaim system
+in :code:`mm/vmscan.c`.  Reclaim is engaged when memory capacity on the system
+becomes pressured based on global and cgroup-local `watermark` settings.
+
+In this section we won't discuss the `watermark` configurations, just how CXL
+memory can be consumed by various pieces of reclaim system.
+
+Demotion
+========
+By default, the reclaim system will prefer swap (or zswap) when reclaiming
+memory.  Enabling :code:`kernel/mm/numa/demotion_enabled` will cause vmscan
+to opportunistically prefer distant NUMA nodes to swap or zswap, if capacity
+is available.
+
+Demotion engages the :code:`mm/memory_tier.c` component to determine the
+next demotion node.  The next demotion node is based on the :code:`HMAT`
+or :code:`CDAT` performance data.
+
+cpusets.mems_allowed quirk
+--------------------------
+In Linux v6.15 and below, demotion does not respect :code:`cpusets.mems_allowed`
+when migrating pages.  As a result, if demotion is enabled, vmscan cannot
+guarantee isolation of a container's memory from nodes not set in mems_allowed.
+
+In Linux v6.XX and up, demotion does attempt to respect
+:code:`cpusets.mems_allowed`; however, certain classes of shared memory
+originally instantiated by another cgroup (such as common libraries - e.g.
+libc) may still be demoted.  As a result, the mems_allowed interface still
+cannot provide perfect isolation from the remote nodes.
+
+ZSwap and Node Preference
+=========================
+In Linux v6.15 and below, ZSwap allocates memory from the local node of the
+processor for the new pages being compressed.  Since pages being compressed
+are typically cold, the result is a cold page becomes promoted - only to
+be later demoted as it ages off the LRU.
+
+In Linux v6.XX, ZSwap tries to prefer the node of the page being compressed
+as the allocation target for the compression page.  This helps prevent
+thrashing.
+
+Demotion with ZSwap
+===================
+When enabling both Demotion and ZSwap, you create a situation where ZSwap
+will prefer the slowest form of CXL memory by default until that tier of
+memory is exhausted.
diff --git a/Documentation/driver-api/cxl/devices/device-types.rst b/Documentation/driver-api/cxl/devices/device-types.rst
new file mode 100644
index 000000000000..f5e4330c1cfe
--- /dev/null
+++ b/Documentation/driver-api/cxl/devices/device-types.rst
@@ -0,0 +1,165 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+Devices and Protocols
+=====================
+
+The type of CXL device (Memory, Accelerator, etc) dictates many configuration steps. This section
+covers some basic background on device types and on-device resources used by the platform and OS
+which impact configuration.
+
+Protocols
+=========
+
+There are three core protocols to CXL.  For the purpose of this documentation,
+we will only discuss very high level definitions as the specific hardware
+details are largely abstracted away from Linux.  See the CXL specification
+for more details.
+
+CXL.io
+------
+The basic interaction protocol, similar to PCIe configuration mechanisms.
+Typically used for initialization, configuration, and I/O access for anything
+other than memory (CXL.mem) or cache (CXL.cache) operations.
+
+The Linux CXL driver exposes access to .io functionalty via the various sysfs
+interfaces and /dev/cxl/ devices (which exposes direct access to device
+mailboxes).
+
+CXL.cache
+---------
+The mechanism by which a device may coherently access and cache host memory.
+
+Largely transparent to Linux once configured.
+
+CXL.mem
+---------
+The mechanism by which the CPU may coherently access and cache device memory.
+
+Largely transparent to Linux once configured.
+
+
+Device Types
+============
+
+Type-1
+------
+
+A Type-1 CXL device:
+
+* Supports cxl.io and cxl.cache protocols
+* Implements a fully coherent cache
+* Allows Device-to-Host coherence and Host-to-Device snoops.
+* Does NOT have host-managed device memory (HDM)
+
+Typical examples of type-1 devices is a Smart NIC - which may want to
+directly operate on host-memory (DMA) to store incoming packets. These
+devices largely rely on CPU-attached memory.
+
+Type-2
+------
+
+A Type-2 CXL Device:
+
+* Supports cxl.io, cxl.cache, and cxl.mem protocols
+* Optionally implements coherent cache and Host-Managed Device Memory
+* Is typically an accelerator device w/ high bandwidth memory.
+
+The primary difference between a type-1 and type-2 device is the presence
+of host-managed device memory, which allows the device to operate on a
+local memory bank - while the CPU sill has coherent DMA to the same memory.
+
+The allows things like GPUs to expose their memory via DAX devices or file
+descriptors, allows drivers and programs direct access to device memory
+rather than use block-transfer semantics.
+
+Type-3
+------
+
+A Type-3 CXL Device
+
+* Supports cxl.io and cxl.mem
+* Implements Host-Managed Device Memory
+* May provide either Volatile or Persistent memory capacity (or both).
+
+A basic example of a type-3 device is a simple memory expander, whose
+local memory capacity is exposed to the CPU for access directly via
+basic coherent DMA.
+
+Switch
+------
+
+A CXL switch is a device capacity of routing any CXL (and by extension, PCIe)
+protocol between an upstream, downstream, or peer devices.  Many devices, such
+as Multi-Logical Devices, imply the presence of switching in some manner.
+
+Logical Devices and Heads
+-------------------------
+
+A CXL device may present one or more "Logical Devices" to one or more hosts
+(via physical "Heads").
+
+A Single-Logical Device (SLD) is a device which presents a single device to
+one or more heads.
+
+A Multi-Logical Device (MLD) is a device which may present multiple devices
+to one or more devices.
+
+A Single-Headed Device exposes only a single physical connection.
+
+A Multi-Headed Device exposes multiple physical connections.
+
+MHSLD
+~~~~~
+A Multi-Headed Single-Logical Device (MHSLD) exposes a single logical
+device to multiple heads which may be connected to one or more discrete
+hosts.  An example of this would be a simple memory-pool which may be
+statically configured (prior to boot) to expose portions of its memory
+to Linux via :doc:`CEDT <../platform/acpi/cedt>`.
+
+MHMLD
+~~~~~
+A Multi-Headed Multi-Logical Device (MHMLD) exposes multiple logical
+devices to multiple heads which may be connected to one or more discrete
+hosts.  An example of this would be a Dynamic Capacity Device or which
+may be configured at runtime to expose portions of its memory to Linux.
+
+Example Devices
+===============
+
+Memory Expander
+---------------
+The simplest form of Type-3 device is a memory expander.  A memory expander
+exposes Host-Managed Device Memory (HDM) to Linux.  This memory may be
+Volatile or Non-Volatile (Persistent).
+
+Memory Expanders will typically be considered a form of Single-Headed,
+Single-Logical Device - as its form factor will typically be an add-in-card
+(AIC) or some other similar form-factor.
+
+The Linux CXL driver provides support for static or dynamic configuration of
+basic memory expanders.  The platform may program decoders prior to OS init
+(e.g. auto-decoders), or the user may program the fabric if the platform
+defers these operations to the OS.
+
+Multiple Memory Expanders may be added to an external chassis and exposed to
+a host via a head attached to a CXL switch.  This is a "memory pool", and
+would be considered an MHSLD or MHMLD depending on the management capabilities
+provided by the switch platform.
+
+As of v6.14, Linux does not provide a formalized interface to manage non-DCD
+MHSLD or MHMLD devices.
+
+Dynamic Capacity Device (DCD)
+-----------------------------
+
+A Dynamic Capacity Device is a Type-3 device which provides dynamic management
+of memory capacity. The basic premise of a DCD to provide an allocator-like
+interface for physical memory capacity to a "Fabric Manager" (an external,
+privileged host with privileges to change configurations for other hosts).
+
+A DCD manages "Memory Extents", which may be volatile or persistent. Extents
+may also be exclusive to a single host or shared across multiple hosts.
+
+As of v6.14, Linux does not provide a formalized interface to manage DCD
+devices, however there is active work on LKML targeting future release.
diff --git a/Documentation/driver-api/cxl/index.rst b/Documentation/driver-api/cxl/index.rst
index 965ba90e8fb7..9e1414ad3357 100644
--- a/Documentation/driver-api/cxl/index.rst
+++ b/Documentation/driver-api/cxl/index.rst
@@ -4,12 +4,50 @@
 Compute Express Link
 ====================
 
-.. toctree::
-   :maxdepth: 1
+CXL device configuration has a complex handoff between platform (Hardware,
+BIOS, EFI), OS (early boot, core kernel, driver), and user policy decisions
+that have impacts on each other.  The docs here break up configurations steps.
 
-   memory-devices
-   access-coordinates
+.. toctree::
+   :maxdepth: 2
+   :caption: Overview
 
+   theory-of-operation
    maturity-map
 
+.. toctree::
+   :maxdepth: 2
+   :caption: Device Reference
+
+   devices/device-types
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Platform Configuration
+
+   platform/bios-and-efi
+   platform/acpi
+   platform/cdat
+   platform/example-configs
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Linux Kernel Configuration
+
+   linux/overview
+   linux/early-boot
+   linux/cxl-driver
+   linux/dax-driver
+   linux/memory-hotplug
+   linux/access-coordinates
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Memory Allocation
+
+   allocation/dax
+   allocation/page-allocator
+   allocation/reclaim
+   allocation/hugepages.rst
+
 .. only::  subproject and html
diff --git a/Documentation/driver-api/cxl/linux/access-coordinates.rst b/Documentation/driver-api/cxl/linux/access-coordinates.rst
new file mode 100644
index 000000000000..341a7c682043
--- /dev/null
+++ b/Documentation/driver-api/cxl/linux/access-coordinates.rst
@@ -0,0 +1,178 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+==================================
+CXL Access Coordinates Computation
+==================================
+
+Latency and Bandwidth Calculation
+=================================
+A memory region performance coordinates (latency and bandwidth) are typically
+provided via ACPI tables :doc:`SRAT <../platform/acpi/srat>` and
+:doc:`HMAT <../platform/acpi/hmat>`. However, the platform firmware (BIOS) is
+not able to annotate those for CXL devices that are hot-plugged since they do
+not exist during platform firmware initialization. The CXL driver can compute
+the performance coordinates by retrieving data from several components.
+
+The :doc:`SRAT <../platform/acpi/srat>` provides a Generic Port Affinity
+subtable that ties a proximity domain to a device handle, which in this case
+would be the CXL hostbridge. Using this association, the performance
+coordinates for the Generic Port can be retrieved from the
+:doc:`HMAT <../platform/acpi/hmat>` subtable. This piece represents the
+performance coordinates between a CPU and a Generic Port (CXL hostbridge).
+
+The :doc:`CDAT <../platform/cdat>` provides the performance coordinates for
+the CXL device itself. That is the bandwidth and latency to access that device's
+memory region. The DSMAS subtable provides a DSMADHandle that is tied to a
+Device Physical Address (DPA) range. The DSLBIS subtable provides the
+performance coordinates that's tied to a DSMADhandle and this ties the two
+table entries together to provide the performance coordinates for each DPA
+region. For example, if a device exports a DRAM region and a PMEM region,
+then there would be different performance characteristsics for each of those
+regions.
+
+If there's a CXL switch in the topology, then the performance coordinates for the
+switch is provided by SSLBIS subtable. This provides the bandwidth and latency
+for traversing the switch between the switch upstream port and the switch
+downstream port that points to the endpoint device.
+
+Simple topology example::
+
+ GP0/HB0/ACPI0016-0
+        RP0
+         |
+         | L0
+         |
+     SW 0 / USP0
+     SW 0 / DSP0
+         |
+         | L1
+         |
+        EP0
+
+In this example, there is a CXL switch between an endpoint and a root port.
+Latency in this example is calculated as such:
+L(EP0) - Latency from EP0 CDAT DSMAS+DSLBIS
+L(L1) - Link latency between EP0 and SW0DSP0
+L(SW0) - Latency for the switch from SW0 CDAT SSLBIS.
+L(L0) - Link latency between SW0 and RP0
+L(RP0) - Latency from root port to CPU via SRAT and HMAT (Generic Port).
+Total read and write latencies are the sum of all these parts.
+
+Bandwidth in this example is calculated as such:
+B(EP0) - Bandwidth from EP0 CDAT DSMAS+DSLBIS
+B(L1) - Link bandwidth between EP0 and SW0DSP0
+B(SW0) - Bandwidth for the switch from SW0 CDAT SSLBIS.
+B(L0) - Link bandwidth between SW0 and RP0
+B(RP0) - Bandwidth from root port to CPU via SRAT and HMAT (Generic Port).
+The total read and write bandwidth is the min() of all these parts.
+
+To calculate the link bandwidth:
+LinkOperatingFrequency (GT/s) is the current negotiated link speed.
+DataRatePerLink (MB/s) = LinkOperatingFrequency / 8
+Bandwidth (MB/s) = PCIeCurrentLinkWidth * DataRatePerLink
+Where PCIeCurrentLinkWidth is the number of lanes in the link.
+
+To calculate the link latency:
+LinkLatency (picoseconds) = FlitSize / LinkBandwidth (MB/s)
+
+See `CXL Memory Device SW Guide r1.0 <https://www.intel.com/content/www/us/en/content-details/643805/cxl-memory-device-software-guide.html>`_,
+section 2.11.3 and 2.11.4 for details.
+
+In the end, the access coordinates for a constructed memory region is calculated from one
+or more memory partitions from each of the CXL device(s).
+
+Shared Upstream Link Calculation
+================================
+For certain CXL region construction with endpoints behind CXL switches (SW) or
+Root Ports (RP), there is the possibility of the total bandwidth for all
+the endpoints behind a switch being more than the switch upstream link.
+A similar situation can occur within the host, upstream of the root ports.
+The CXL driver performs an additional pass after all the targets have
+arrived for a region in order to recalculate the bandwidths with possible
+upstream link being a limiting factor in mind.
+
+The algorithm assumes the configuration is a symmetric topology as that
+maximizes performance. When asymmetric topology is detected, the calculation
+is aborted. An asymmetric topology is detected during topology walk where the
+number of RPs detected as a grandparent is not equal to the number of devices
+iterated in the same iteration loop. The assumption is made that subtle
+asymmetry in properties does not happen and all paths to EPs are equal.
+
+There can be multiple switches under an RP. There can be multiple RPs under
+a CXL Host Bridge (HB). There can be multiple HBs under a CXL Fixed Memory
+Window Structure (CFMWS) in the :doc:`CEDT <../platform/acpi/cedt>`.
+
+An example hierarchy::
+
+                CFMWS 0
+                  |
+         _________|_________
+        |                   |
+    ACPI0017-0          ACPI0017-1
+ GP0/HB0/ACPI0016-0   GP1/HB1/ACPI0016-1
+    |          |        |           |
+   RP0        RP1      RP2         RP3
+    |          |        |           |
+  SW 0       SW 1     SW 2        SW 3
+  |   |      |   |    |   |       |   |
+ EP0 EP1    EP2 EP3  EP4  EP5    EP6 EP7
+
+Computation for the example hierarchy:
+
+Min (GP0 to CPU BW,
+     Min(SW 0 Upstream Link to RP0 BW,
+         Min(SW0SSLBIS for SW0DSP0 (EP0), EP0 DSLBIS, EP0 Upstream Link) +
+         Min(SW0SSLBIS for SW0DSP1 (EP1), EP1 DSLBIS, EP1 Upstream link)) +
+     Min(SW 1 Upstream Link to RP1 BW,
+         Min(SW1SSLBIS for SW1DSP0 (EP2), EP2 DSLBIS, EP2 Upstream Link) +
+         Min(SW1SSLBIS for SW1DSP1 (EP3), EP3 DSLBIS, EP3 Upstream link))) +
+Min (GP1 to CPU BW,
+     Min(SW 2 Upstream Link to RP2 BW,
+         Min(SW2SSLBIS for SW2DSP0 (EP4), EP4 DSLBIS, EP4 Upstream Link) +
+         Min(SW2SSLBIS for SW2DSP1 (EP5), EP5 DSLBIS, EP5 Upstream link)) +
+     Min(SW 3 Upstream Link to RP3 BW,
+         Min(SW3SSLBIS for SW3DSP0 (EP6), EP6 DSLBIS, EP6 Upstream Link) +
+         Min(SW3SSLBIS for SW3DSP1 (EP7), EP7 DSLBIS, EP7 Upstream link))))
+
+The calculation starts at cxl_region_shared_upstream_perf_update(). A xarray
+is created to collect all the endpoint bandwidths via the
+cxl_endpoint_gather_bandwidth() function. The min() of bandwidth from the
+endpoint CDAT and the upstream link bandwidth is calculated. If the endpoint
+has a CXL switch as a parent, then min() of calculated bandwidth and the
+bandwidth from the SSLBIS for the switch downstream port that is associated
+with the endpoint is calculated. The final bandwidth is stored in a
+'struct cxl_perf_ctx' in the xarray indexed by a device pointer. If the
+endpoint is direct attached to a root port (RP), the device pointer would be an
+RP device. If the endpoint is behind a switch, the device pointer would be the
+upstream device of the parent switch.
+
+At the next stage, the code walks through one or more switches if they exist
+in the topology. For endpoints directly attached to RPs, this step is skipped.
+If there is another switch upstream, the code takes the min() of the current
+gathered bandwidth and the upstream link bandwidth. If there's a switch
+upstream, then the SSLBIS of the upstream switch.
+
+Once the topology walk reaches the RP, whether it's direct attached endpoints
+or walking through the switch(es), cxl_rp_gather_bandwidth() is called. At
+this point all the bandwidths are aggregated per each host bridge, which is
+also the index for the resulting xarray.
+
+The next step is to take the min() of the per host bridge bandwidth and the
+bandwidth from the Generic Port (GP). The bandwidths for the GP are retrieved
+via ACPI tables (:doc:`SRAT <../platform/acpi/srat>` and
+:doc:`HMAT <../platform/acpi/hmat>`). The minimum bandwidth are aggregated
+under the same ACPI0017 device to form a new xarray.
+
+Finally, the cxl_region_update_bandwidth() is called and the aggregated
+bandwidth from all the members of the last xarray is updated for the
+access coordinates residing in the cxl region (cxlr) context.
+
+QTG ID
+======
+Each :doc:`CEDT <../platform/acpi/cedt>` has a QTG ID field. This field provides
+the ID that associates with a QoS Throttling Group (QTG) for the CFMWS window.
+Once the access coordinates are calculated, an ACPI Device Specific Method can
+be issued to the ACPI0016 device to retrieve the QTG ID depends on the access
+coordinates provided. The QTG ID for the device can be used as guidance to match
+to the CFMWS to setup the best Linux root decoder for the device performance.
diff --git a/Documentation/driver-api/cxl/linux/cxl-driver.rst b/Documentation/driver-api/cxl/linux/cxl-driver.rst
new file mode 100644
index 000000000000..9759e90c3cf1
--- /dev/null
+++ b/Documentation/driver-api/cxl/linux/cxl-driver.rst
@@ -0,0 +1,630 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================
+CXL Driver Operation
+====================
+
+The devices described in this section are present in ::
+
+  /sys/bus/cxl/devices/
+  /dev/cxl/
+
+The :code:`cxl-cli` library, maintained as part of the NDTCL project, may
+be used to script interactions with these devices.
+
+Drivers
+=======
+The CXL driver is split into a number of drivers.
+
+* cxl_core  - fundamental init interface and core object creation
+* cxl_port  - initializes root and provides port enumeration interface.
+* cxl_acpi  - initializes root decoders and interacts with ACPI data.
+* cxl_p/mem - initializes memory devices
+* cxl_pci   - uses cxl_port to enumates the actual fabric hierarchy.
+
+Driver Devices
+==============
+Here is an example from a single-socket system with 4 host bridges. Two host
+bridges have a single memory device attached, and the devices are interleaved
+into a single memory region. The memory region has been converted to dax. ::
+
+  # ls /sys/bus/cxl/devices/
+    dax_region0  decoder3.0  decoder6.0  mem0   port3
+    decoder0.0   decoder4.0  decoder6.1  mem1   port4
+    decoder1.0   decoder5.0  endpoint5   port1  region0
+    decoder2.0   decoder5.1  endpoint6   port2  root0
+
+
+.. kernel-render:: DOT
+   :alt: Digraph of CXL fabric describing host-bridge interleaving
+   :caption: Diagraph of CXL fabric with a host-bridge interleave memory region
+
+   digraph foo {
+     "root0" -> "port1";
+     "root0" -> "port3";
+     "root0" -> "decoder0.0";
+     "port1" -> "endpoint5";
+     "port3" -> "endpoint6";
+     "port1" -> "decoder1.0";
+     "port3" -> "decoder3.0";
+     "endpoint5" -> "decoder5.0";
+     "endpoint6" -> "decoder6.0";
+     "decoder0.0" -> "region0";
+     "decoder0.0" -> "decoder1.0";
+     "decoder0.0" -> "decoder3.0";
+     "decoder1.0" -> "decoder5.0";
+     "decoder3.0" -> "decoder6.0";
+     "decoder5.0" -> "region0";
+     "decoder6.0" -> "region0";
+     "region0" -> "dax_region0";
+     "dax_region0" -> "dax0.0";
+   }
+
+For this section we'll explore the devices present in this configuration, but
+we'll explore more configurations in-depth in example configurations below.
+
+Base Devices
+------------
+Most devices in a CXL fabric are a `port` of some kind (because each
+device mostly routes request from one device to the next, rather than
+provide a direct service).
+
+Root
+~~~~
+The `CXL Root` is logical object created by the `cxl_acpi` driver during
+:code:`cxl_acpi_probe` - if the :code:`ACPI0017` `Compute Express Link
+Root Object` Device Class is found.
+
+The Root contains links to:
+
+* `Host Bridge Ports` defined by CHBS in the :doc:`CEDT<../platform/acpi/cedt>`
+
+* `Downstream Ports` typically connected to `Host Bridge Ports`.
+
+* `Root Decoders` defined by CFMWS the :doc:`CEDT<../platform/acpi/cedt>`
+
+::
+
+  # ls /sys/bus/cxl/devices/root0
+    decoder0.0          dport0  dport5    port2  subsystem
+    decoders_committed  dport1  modalias  port3  uevent
+    devtype             dport4  port1     port4  uport
+
+  # cat /sys/bus/cxl/devices/root0/devtype
+    cxl_port
+
+  # cat port1/devtype
+    cxl_port
+
+  # cat decoder0.0/devtype
+    cxl_decoder_root
+
+The root is first `logical port` in the CXL fabric, as presented by the Linux
+CXL driver.  The `CXL root` is a special type of `switch port`, in that it
+only has downstream port connections.
+
+Port
+~~~~
+A `port` object is better described as a `switch port`.  It may represent a
+host bridge to the root or an actual switch port on a switch. A `switch port`
+contains one or more decoders used to route memory requests downstream ports,
+which may be connected to another `switch port` or an `endpoint port`.
+
+::
+
+  # ls /sys/bus/cxl/devices/port1
+    decoder1.0          dport0    driver     parent_dport  uport
+    decoders_committed  dport113  endpoint5  subsystem
+    devtype             dport2    modalias   uevent
+
+  # cat devtype
+    cxl_port
+
+  # cat decoder1.0/devtype
+    cxl_decoder_switch
+
+  # cat endpoint5/devtype
+    cxl_port
+
+CXL `Host Bridges` in the fabric are probed during :code:`cxl_acpi_probe` at
+the time the `CXL Root` is probed.  The allows for the immediate logical
+connection to between the root and host bridge.
+
+* The root has a downstream port connection to a host bridge
+
+* The host bridge has an upstream port connection to the root.
+
+* The host bridge has one or more downstream port connections to switch
+  or endpoint ports.
+
+A `Host Bridge` is a special type of CXL `switch port`. It is explicitly
+defined in the ACPI specification via `ACPI0016` ID.  `Host Bridge` ports
+will be probed at `acpi_probe` time, while similar ports on an actual switch
+will be probed later.  Otherwise, switch and host bridge ports look very
+similar - the both contain switch decoders which route accesses between
+upstream and downstream ports.
+
+Endpoint
+~~~~~~~~
+An `endpoint` is a terminal port in the fabric.  This is a `logical device`,
+and may be one of many `logical devices` presented by a memory device. It
+is still considered a type of `port` in the fabric.
+
+An `endpoint` contains `endpoint decoders` and the device's Coherent Device
+Attribute Table (which describes the device's capabilities). ::
+
+  # ls /sys/bus/cxl/devices/endpoint5
+    CDAT        decoders_committed  modalias      uevent
+    decoder5.0  devtype             parent_dport  uport
+    decoder5.1  driver              subsystem
+
+  # cat /sys/bus/cxl/devices/endpoint5/devtype
+    cxl_port
+
+  # cat /sys/bus/cxl/devices/endpoint5/decoder5.0/devtype
+    cxl_decoder_endpoint
+
+
+Memory Device (memdev)
+~~~~~~~~~~~~~~~~~~~~~~
+A `memdev` is probed and added by the `cxl_pci` driver in :code:`cxl_pci_probe`
+and is managed by the `cxl_mem` driver. It primarily provides the `IOCTL`
+interface to a memory device, via :code:`/dev/cxl/memN`, and exposes various
+device configuration data. ::
+
+  # ls /sys/bus/cxl/devices/mem0
+    dev       firmware_version    payload_max  security   uevent
+    driver    label_storage_size  pmem         serial
+    firmware  numa_node           ram          subsystem
+
+A Memory Device is a discrete base object that is not a port.  While the
+physical device it belongs to may also host an `endpoint`, the relationship
+between an `endpoint` and a `memdev` is not captured in sysfs.
+
+Port Relationships
+~~~~~~~~~~~~~~~~~~
+In our example described above, there are four host bridges attached to the
+root, and two of the host bridges have one endpoint attached.
+
+.. kernel-render:: DOT
+   :alt: Digraph of CXL fabric describing host-bridge interleaving
+   :caption: Diagraph of CXL fabric with a host-bridge interleave memory region
+
+   digraph foo {
+     "root0"    -> "port1";
+     "root0"    -> "port2";
+     "root0"    -> "port3";
+     "root0"    -> "port4";
+     "port1" -> "endpoint5";
+     "port3" -> "endpoint6";
+   }
+
+Decoders
+--------
+A `Decoder` is short for a CXL Host-Managed Device Memory (HDM) Decoder. It is
+a device that routes accesses through the CXL fabric to an endpoint, and at
+the endpoint translates a `Host Physical` to `Device Physical` Addressing.
+
+The CXL 3.1 specification heavily implies that only endpoint decoders should
+engage in translation of `Host Physical Address` to `Device Physical Address`.
+::
+
+  8.2.4.20 CXL HDM Decoder Capability Structure
+
+  IMPLEMENTATION NOTE
+  CXL Host Bridge and Upstream Switch Port Decode Flow
+
+  IMPLEMENTATION NOTE
+  Device Decode Logic
+
+These notes imply that there are two logical groups of decoders.
+
+* Routing Decoder - a decoder which routes accesses but does not translate
+  addresses from HPA to DPA.
+
+* Translating Decoder - a decoder which translates accesses from HPA to DPA
+  for an endpoint to service.
+
+The CXL drivers distinguish 3 decoder types: root, switch, and endpoint. Only
+endpoint decoders are Translating Decoders, all others are Routing Decoders.
+
+.. note:: PLATFORM VENDORS BE AWARE
+
+   Linux makes a strong assumption that endpoint decoders are the only decoder
+   in the fabric that actively translates HPA to DPA.  Linux assumes routing
+   decoders pass the HPA unchanged to the next decoder in the fabric.
+
+   It is therefore assumed that any given decoder in the fabric will have an
+   address range that is a subset of its upstream port decoder. Any deviation
+   from this scheme undefined per the specification.  Linux prioritizes
+   spec-defined / architectural behavior.
+
+Decoders may have one or more `Downstream Targets` if configured to interleave
+memory accesses.  This will be presented in sysfs via the :code:`target_list`
+parameter.
+
+Root Decoder
+~~~~~~~~~~~~
+A `Root Decoder` is logical construct of the physical address and interleave
+configurations present in the CFMWS field of the :doc:`CEDT
+<../platform/acpi/cedt>`.
+Linux presents this information as a decoder present in the `CXL Root`.  We
+consider this a `Root Decoder`, though technically it exists on the boundary
+of the CXL specification and platform-specific CXL root implementations.
+
+Linux considers these logical decoders a type of `Routing Decoder`, and is the
+first decoder in the CXL fabric to receive a memory access from the platform's
+memory controllers.
+
+`Root Decoders` are created during :code:`cxl_acpi_probe`.  One root decoder
+is created per CFMWS entry in the :doc:`CEDT <../platform/acpi/cedt>`.
+
+The :code:`target_list` parameter is filled by the CFMWS target fields. Targets
+of a root decoder are `Host Bridges`, which means interleave done at the root
+decoder level is an `Inter-Host-Bridge Interleave`.
+
+Only root decoders are capable of `Inter-Host-Bridge Interleave`.
+
+Such interleaves must be configured by the platform and described in the ACPI
+CEDT CFMWS, as the target CXL host bridge UIDs in the CFMWS must match the CXL
+host bridge UIDs in the CHBS field of the :doc:`CEDT
+<../platform/acpi/cedt>` and the UID field of CXL Host Bridges defined in
+the :doc:`DSDT <../platform/acpi/dsdt>`.
+
+Interleave settings in a root decoder describe how to interleave accesses among
+the *immediate downstream targets*, not the entire interleave set.
+
+The memory range described in the root decoder is used to
+
+1) Create a memory region (:code:`region0` in this example), and
+
+2) Associate the region with an IO Memory Resource (:code:`kernel/resource.c`)
+
+::
+
+  # ls /sys/bus/cxl/devices/decoder0.0/
+    cap_pmem           devtype                 region0
+    cap_ram            interleave_granularity  size
+    cap_type2          interleave_ways         start
+    cap_type3          locked                  subsystem
+    create_ram_region  modalias                target_list
+    delete_region      qos_class               uevent
+
+  # cat /sys/bus/cxl/devices/decoder0.0/region0/resource
+    0xc050000000
+
+The IO Memory Resource is created during early boot when the CFMWS region is
+identified in the EFI Memory Map or E820 table (on x86).
+
+Root decoders are defined as a separate devtype, but are also a type
+of `Switch Decoder` due to having downstream targets. ::
+
+  # cat /sys/bus/cxl/devices/decoder0.0/devtype
+    cxl_decoder_root
+
+Switch Decoder
+~~~~~~~~~~~~~~
+Any non-root, translating decoder is considered a `Switch Decoder`, and will
+present with the type :code:`cxl_decoder_switch`. Both `Host Bridge` and `CXL
+Switch` (device) decoders are of type :code:`cxl_decoder_switch`. ::
+
+  # ls /sys/bus/cxl/devices/decoder1.0/
+    devtype                 locked    size       target_list
+    interleave_granularity  modalias  start      target_type
+    interleave_ways         region    subsystem  uevent
+
+  # cat /sys/bus/cxl/devices/decoder1.0/devtype
+    cxl_decoder_switch
+
+  # cat /sys/bus/cxl/devices/decoder1.0/region
+    region0
+
+A `Switch Decoder` has associations between a region defined by a root
+decoder and downstream target ports.  Interleaving done within a switch decoder
+is a multi-downstream-port interleave (or `Intra-Host-Bridge Interleave` for
+host bridges).
+
+Interleave settings in a switch decoder describe how to interleave accesses
+among the *immediate downstream targets*, not the entire interleave set.
+
+Switch decoders are created during :code:`cxl_switch_port_probe` in the
+:code:`cxl_port` driver, and is created based on a PCI device's DVSEC
+registers.
+
+Switch decoder programming is validated during probe if the platform programs
+them during boot (See `Auto Decoders` below), or on commit if programmed at
+runtime (See `Runtime Programming` below).
+
+
+Endpoint Decoder
+~~~~~~~~~~~~~~~~
+Any decoder attached to a *terminal* point in the CXL fabric (`An Endpoint`) is
+considered an `Endpoint Decoder`. Endpoint decoders are of type
+:code:`cxl_decoder_endpoint`. ::
+
+  # ls /sys/bus/cxl/devices/decoder5.0
+    devtype                 locked    start
+    dpa_resource            modalias  subsystem
+    dpa_size                mode      target_type
+    interleave_granularity  region    uevent
+    interleave_ways         size
+
+  # cat /sys/bus/cxl/devices/decoder5.0/devtype
+    cxl_decoder_endpoint
+
+  # cat /sys/bus/cxl/devices/decoder5.0/region
+    region0
+
+An `Endpoint Decoder` has an association with a region defined by a root
+decoder and describes the device-local resource associated with this region.
+
+Unlike root and switch decoders, endpoint decoders translate `Host Physical` to
+`Device Physical` address ranges.  The interleave settings on an endpoint
+therefore describe the entire *interleave set*.
+
+`Device Physical Address` regions must be committed in-order. For example, the
+DPA region starting at 0x80000000 cannot be committed before the DPA region
+starting at 0x0.
+
+As of Linux v6.15, Linux does not support *imbalanced* interleave setups, all
+endpoints in an interleave set are expected to have the same interleave
+settings (granularity and ways must be the same).
+
+Endpoint decoders are created during :code:`cxl_endpoint_port_probe` in the
+:code:`cxl_port` driver, and is created based on a PCI device's DVSEC registers.
+
+Decoder Relationships
+~~~~~~~~~~~~~~~~~~~~~
+In our example described above, there is one root decoder which routes memory
+accesses over two host bridges.  Each host bridge has a decoder which routes
+access to their singular endpoint targets.  Each endpoint has a decoder which
+translates HPA to DPA and services the memory request.
+
+The driver validates relationships between ports by decoder programming, so
+we can think of decoders being related in a similarly hierarchical fashion to
+ports.
+
+.. kernel-render:: DOT
+   :alt: Digraph of hierarchical relationship between root, switch, and endpoint decoders.
+   :caption: Diagraph of CXL root, switch, and endpoint decoders.
+
+   digraph foo {
+     "root0"    -> "decoder0.0";
+     "decoder0.0" -> "decoder1.0";
+     "decoder0.0" -> "decoder3.0";
+     "decoder1.0" -> "decoder5.0";
+     "decoder3.0" -> "decoder6.0";
+   }
+
+Regions
+-------
+
+Memory Region
+~~~~~~~~~~~~~
+A `Memory Region` is a logical construct that connects a set of CXL ports in
+the fabric to an IO Memory Resource.  It is ultimately used to expose the memory
+on these devices to the DAX subsystem via a `DAX Region`.
+
+An example RAM region: ::
+
+  # ls /sys/bus/cxl/devices/region0/
+    access0      devtype                 modalias  subsystem  uuid
+    access1      driver                  mode      target0
+    commit       interleave_granularity  resource  target1
+    dax_region0  interleave_ways         size      uevent
+
+A memory region can be constructed during endpoint probe, if decoders were
+programmed by BIOS/EFI (see `Auto Decoders`), or by creating a region manually
+via a `Root Decoder`'s :code:`create_ram_region` or :code:`create_pmem_region`
+interfaces.
+
+The interleave settings in a `Memory Region` describe the configuration of the
+`Interleave Set` - and are what can be expected to be seen in the endpoint
+interleave settings.
+
+.. kernel-render:: DOT
+   :alt: Digraph of CXL memory region relationships between root and endpoint decoders.
+   :caption: Regions are created based on root decoder configurations. Endpoint decoders
+             must be programmed with the same interleave settings as the region.
+
+   digraph foo {
+     "root0"    -> "decoder0.0";
+     "decoder0.0" -> "region0";
+     "region0" -> "decoder5.0";
+     "region0" -> "decoder6.0";
+   }
+
+DAX Region
+~~~~~~~~~~
+A `DAX Region` is used to convert a CXL `Memory Region` to a DAX device. A
+DAX device may then be accessed directly via a file descriptor interface, or
+converted to System RAM via the DAX kmem driver.  See the DAX driver section
+for more details. ::
+
+  # ls /sys/bus/cxl/devices/dax_region0/
+    dax0.0      devtype  modalias   uevent
+    dax_region  driver   subsystem
+
+Mailbox Interfaces
+------------------
+A mailbox command interface for each device is exposed in ::
+
+  /dev/cxl/mem0
+  /dev/cxl/mem1
+
+These mailboxes may receive any specification-defined command. Raw commands
+(custom commands) can only be sent to these interfaces if the build config
+:code:`CXL_MEM_RAW_COMMANDS` is set.  This is considered a debug and/or
+development interface, not an officially supported mechanism for creation
+of vendor-specific commands (see the `fwctl` subsystem for that).
+
+Decoder Programming
+===================
+
+Runtime Programming
+-------------------
+During probe, the only decoders *required* to be programmed are `Root Decoders`.
+In reality, `Root Decoders` are a logical construct to describe the memory
+region and interleave configuration at the host bridge level - as described
+in the ACPI CEDT CFMWS.
+
+All other `Switch` and `Endpoint` decoders may be programmed by the user
+at runtime - if the platform supports such configurations.
+
+This interaction is what creates a `Software Defined Memory` environment.
+
+See the :code:`cxl-cli` documentation for more information about how to
+configure CXL decoders at runtime.
+
+Auto Decoders
+-------------
+Auto Decoders are decoders programmed by BIOS/EFI at boot time, and are
+almost always locked (cannot be changed).  This is done by a platform
+which may have a static configuration - or certain quirks which may prevent
+dynamic runtime changes to the decoders (such as requiring additional
+controller programming within the CPU complex outside the scope of CXL).
+
+Auto Decoders are probed automatically as long as the devices and memory
+regions they are associated with probe without issue.  When probing Auto
+Decoders, the driver's primary responsibility is to ensure the fabric is
+sane - as-if validating runtime programmed regions and decoders.
+
+If Linux cannot validate auto-decoder configuration, the memory will not
+be surfaced as a DAX device - and therefore not be exposed to the page
+allocator - effectively stranding it.
+
+Interleave
+----------
+
+The Linux CXL driver supports `Cross-Link First` interleave. This dictates
+how interleave is programmed at each decoder step, as the driver validates
+the relationships between a decoder and it's parent.
+
+For example, in a `Cross-Link First` interleave setup with 16 endpoints
+attached to 4 host bridges, linux expects the following ways/granularity
+across the root, host bridge, and endpoints respectively.
+
+.. flat-table:: 4x4 cross-link first interleave settings
+
+  * - decoder
+    - ways
+    - granularity
+
+  * - root
+    - 4
+    - 256
+
+  * - host bridge
+    - 4
+    - 1024
+
+  * - endpoint
+    - 16
+    - 256
+
+At the root, every a given access will be routed to the
+:code:`((HPA / 256) % 4)th` target host bridge. Within a host bridge, every
+:code:`((HPA / 1024) % 4)th` target endpoint.  Each endpoint translates based
+on the entire 16 device interleave set.
+
+Unbalanced interleave sets are not supported - decoders at a similar point
+in the hierarchy (e.g. all host bridge decoders) must have the same ways and
+granularity configuration.
+
+At Root
+~~~~~~~
+Root decoder interleave is defined by CFMWS field of the :doc:`CEDT
+<../platform/acpi/cedt>`.  The CEDT may actually define multiple CFMWS
+configurations to describe the same physical capacity, with the intent to allow
+users to decide at runtime whether to online memory as interleaved or
+non-interleaved. ::
+
+             Subtable Type : 01 [CXL Fixed Memory Window Structure]
+       Window base address : 0000000100000000
+               Window size : 0000000100000000
+  Interleave Members (2^n) : 00
+     Interleave Arithmetic : 00
+              First Target : 00000007
+
+             Subtable Type : 01 [CXL Fixed Memory Window Structure]
+       Window base address : 0000000200000000
+               Window size : 0000000100000000
+  Interleave Members (2^n) : 00
+     Interleave Arithmetic : 00
+              First Target : 00000006
+
+             Subtable Type : 01 [CXL Fixed Memory Window Structure]
+       Window base address : 0000000300000000
+               Window size : 0000000200000000
+  Interleave Members (2^n) : 01
+     Interleave Arithmetic : 00
+              First Target : 00000007
+               Next Target : 00000006
+
+In this example, the CFMWS defines two discrete non-interleaved 4GB regions
+for each host bridge, and one interleaved 8GB region that targets both. This
+would result in 3 root decoders presenting in the root. ::
+
+  # ls /sys/bus/cxl/devices/root0/decoder*
+    decoder0.0  decoder0.1  decoder0.2
+
+  # cat /sys/bus/cxl/devices/decoder0.0/target_list start size
+    7
+    0x100000000
+    0x100000000
+
+  # cat /sys/bus/cxl/devices/decoder0.1/target_list start size
+    6
+    0x200000000
+    0x100000000
+
+  # cat /sys/bus/cxl/devices/decoder0.2/target_list start size
+    7,6
+    0x300000000
+    0x200000000
+
+These decoders are not runtime programmable.  They are used to generate a
+`Memory Region` to bring this memory online with runtime programmed settings
+at the `Switch` and `Endpoint` decoders.
+
+At Host Bridge or Switch
+~~~~~~~~~~~~~~~~~~~~~~~~
+`Host Bridge` and `Switch` decoders are programmable via the following fields:
+
+- :code:`start` - the HPA region associated with the memory region
+- :code:`size` - the size of the region
+- :code:`target_list` - the list of downstream ports
+- :code:`interleave_ways` - the number downstream ports to interleave across
+- :code:`interleave_granularity` - the granularity to interleave at.
+
+Linux expects the :code:`interleave_granularity` of switch decoders to be
+derived from their upstream port connections. In `Cross-Link First` interleave
+configurations, the :code:`interleave_granularity` of a decoder is equal to
+:code:`parent_interleave_granularity * parent_interleave_ways`.
+
+At Endpoint
+~~~~~~~~~~~
+`Endpoint Decoders` are programmed similar to Host Bridge and Switch decoders,
+with the exception that the ways and granularity are defined by the interleave
+set (e.g. the interleave settings defined by the associated `Memory Region`).
+
+- :code:`start` - the HPA region associated with the memory region
+- :code:`size` - the size of the region
+- :code:`interleave_ways` - the number endpoints in the interleave set
+- :code:`interleave_granularity` - the granularity to interleave at.
+
+These settings are used by endpoint decoders to *Translate* memory requests
+from HPA to DPA.  This is why they must be aware of the entire interleave set.
+
+Linux does not support unbalanced interleave configurations.  As a result, all
+endpoints in an interleave set must have the same ways and granularity.
+
+Example Configurations
+======================
+.. toctree::
+   :maxdepth: 1
+
+   example-configurations/single-device.rst
+   example-configurations/hb-interleave.rst
+   example-configurations/intra-hb-interleave.rst
+   example-configurations/multi-interleave.rst
diff --git a/Documentation/driver-api/cxl/linux/dax-driver.rst b/Documentation/driver-api/cxl/linux/dax-driver.rst
new file mode 100644
index 000000000000..10d953a2167b
--- /dev/null
+++ b/Documentation/driver-api/cxl/linux/dax-driver.rst
@@ -0,0 +1,43 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================
+DAX Driver Operation
+====================
+The `Direct Access Device` driver was originally designed to provide a
+memory-like access mechanism to memory-like block-devices.  It was
+extended to support CXL Memory Devices, which provide user-configured
+memory devices.
+
+The CXL subsystem depends on the DAX subsystem to either:
+
+- Generate a file-like interface to userland via :code:`/dev/daxN.Y`, or
+- Engage the memory-hotplug interface to add CXL memory to page allocator.
+
+The DAX subsystem exposes this ability through the `cxl_dax_region` driver.
+A `dax_region` provides the translation between a CXL `memory_region` and
+a `DAX Device`.
+
+DAX Device
+==========
+A `DAX Device` is a file-like interface exposed in :code:`/dev/daxN.Y`. A
+memory region exposed via dax device can be accessed via userland software
+via the :code:`mmap()` system-call.  The result is direct mappings to the
+CXL capacity in the task's page tables.
+
+Users wishing to manually handle allocation of CXL memory should use this
+interface.
+
+kmem conversion
+===============
+The :code:`dax_kmem` driver converts a `DAX Device` into a series of `hotplug
+memory blocks` managed by :code:`kernel/memory-hotplug.c`.  This capacity
+will be exposed to the kernel page allocator in the user-selected memory
+zone.
+
+The :code:`memmap_on_memory` setting (both global and DAX device local)
+dictates where the kernell will allocate the :code:`struct folio` descriptors
+for this memory will come from.  If :code:`memmap_on_memory` is set, memory
+hotplug will set aside a portion of the memory block capacity to allocate
+folios. If unset, the memory is allocated via a normal :code:`GFP_KERNEL`
+allocation - and as a result will most likely land on the local NUM node of the
+CPU executing the hotplug operation.
diff --git a/Documentation/driver-api/cxl/linux/early-boot.rst b/Documentation/driver-api/cxl/linux/early-boot.rst
new file mode 100644
index 000000000000..a7fc6fc85fbe
--- /dev/null
+++ b/Documentation/driver-api/cxl/linux/early-boot.rst
@@ -0,0 +1,137 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================
+Linux Init (Early Boot)
+=======================
+
+Linux configuration is split into two major steps: Early-Boot and everything else.
+
+During early boot, Linux sets up immutable resources (such as numa nodes), while
+later operations include things like driver probe and memory hotplug.  Linux may
+read EFI and ACPI information throughout this process to configure logical
+representations of the devices.
+
+During Linux Early Boot stage (functions in the kernel that have the __init
+decorator), the system takes the resources created by EFI/BIOS
+(:doc:`ACPI tables <../platform/acpi>`) and turns them into resources that the
+kernel can consume.
+
+
+BIOS, Build and Boot Options
+============================
+
+There are 4 pre-boot options that need to be considered during kernel build
+which dictate how memory will be managed by Linux during early boot.
+
+* EFI_MEMORY_SP
+
+  * BIOS/EFI Option that dictates whether memory is SystemRAM or
+    Specific Purpose.  Specific Purpose memory will be deferred to
+    drivers to manage - and not immediately exposed as system RAM.
+
+* CONFIG_EFI_SOFT_RESERVE
+
+  * Linux Build config option that dictates whether the kernel supports
+    Specific Purpose memory.
+
+* CONFIG_MHP_DEFAULT_ONLINE_TYPE
+
+  * Linux Build config that dictates whether and how Specific Purpose memory
+    converted to a dax device should be managed (left as DAX or onlined as
+    SystemRAM in ZONE_NORMAL or ZONE_MOVABLE).
+
+* nosoftreserve
+
+  * Linux kernel boot option that dictates whether Soft Reserve should be
+    supported.  Similar to CONFIG_EFI_SOFT_RESERVE.
+
+Memory Map Creation
+===================
+
+While the kernel parses the EFI memory map, if :code:`Specific Purpose` memory
+is supported and detected, it will set this region aside as
+:code:`SOFT_RESERVED`.
+
+If :code:`EFI_MEMORY_SP=0`, :code:`CONFIG_EFI_SOFT_RESERVE=n`, or
+:code:`nosoftreserve=y` - Linux will default a CXL device memory region to
+SystemRAM.  This will expose the memory to the kernel page allocator in
+:code:`ZONE_NORMAL`, making it available for use for most allocations (including
+:code:`struct page` and page tables).
+
+If `Specific Purpose` is set and supported, :code:`CONFIG_MHP_DEFAULT_ONLINE_TYPE_*`
+dictates whether the memory is onlined by default (:code:`_OFFLINE` or
+:code:`_ONLINE_*`), and if online which zone to online this memory to by default
+(:code:`_NORMAL` or :code:`_MOVABLE`).
+
+If placed in :code:`ZONE_MOVABLE`, the memory will not be available for most
+kernel allocations (such as :code:`struct page` or page tables).  This may
+significant impact performance depending on the memory capacity of the system.
+
+
+NUMA Node Reservation
+=====================
+
+Linux refers to the proximity domains (:code:`PXM`) defined in the :doc:`SRAT
+<../platform/acpi/srat>` to create NUMA nodes in :code:`acpi_numa_init`.
+Typically, there is a 1:1 relation between :code:`PXM` and NUMA node IDs.
+
+The SRAT is the only ACPI defined way of defining Proximity Domains. Linux
+chooses to, at most, map those 1:1 with NUMA nodes.
+:doc:`CEDT <../platform/acpi/cedt>` adds a description of SPA ranges which
+Linux may map to one or more NUMA nodes.
+
+If there are CXL ranges in the CFMWS but not in SRAT, then a fake :code:`PXM`
+is created (as of v6.15). In the future, Linux may reject CFMWS not described
+by SRAT due to the ambiguity of proximity domain association.
+
+It is important to note that NUMA node creation cannot be done at runtime. All
+possible NUMA nodes are identified at :code:`__init` time, more specifically
+during :code:`mm_init`. The CEDT and SRAT must contain sufficient :code:`PXM`
+data for Linux to identify NUMA nodes their associated memory regions.
+
+The relevant code exists in: :code:`linux/drivers/acpi/numa/srat.c`.
+
+See :doc:`Example Platform Configurations <../platform/example-configs>`
+for more info.
+
+Memory Tiers Creation
+=====================
+Memory tiers are a collection of NUMA nodes grouped by performance characteristics.
+During :code:`__init`, Linux initializes the system with a default memory tier that
+contains all nodes marked :code:`N_MEMORY`.
+
+:code:`memory_tier_init` is called at boot for all nodes with memory online by
+default. :code:`memory_tier_late_init` is called during late-init for nodes setup
+during driver configuration.
+
+Nodes are only marked :code:`N_MEMORY` if they have *online* memory.
+
+Tier membership can be inspected in ::
+
+  /sys/devices/virtual/memory_tiering/memory_tierN/nodelist
+  0-1
+
+If nodes are grouped which have clear difference in performance, check the
+:doc:`HMAT <../platform/acpi/hmat>` and CDAT information for the CXL nodes. All
+nodes default to the DRAM tier, unless HMAT/CDAT information is reported to the
+memory_tier component via `access_coordinates`.
+
+For more, see :doc:`CXL access coordinates documentation
+<../linux/access-coordinates>`.
+
+Contiguous Memory Allocation
+============================
+The contiguous memory allocator (CMA) enables reservation of contiguous memory
+regions on NUMA nodes during early boot.  However, CMA cannot reserve memory
+on NUMA nodes that are not online during early boot. ::
+
+  void __init hugetlb_cma_reserve(int order) {
+    if (!node_online(nid))
+      /* do not allow reservations */
+  }
+
+This means if users intend to defer management of CXL memory to the driver, CMA
+cannot be used to guarantee huge page allocations.  If enabling CXL memory as
+SystemRAM in `ZONE_NORMAL` during early boot, CMA reservations per-node can be
+made with the :code:`cma_pernuma` or :code:`numa_cma` kernel command line
+parameters.
diff --git a/Documentation/driver-api/cxl/linux/example-configurations/hb-interleave.rst b/Documentation/driver-api/cxl/linux/example-configurations/hb-interleave.rst
new file mode 100644
index 000000000000..f071490763a2
--- /dev/null
+++ b/Documentation/driver-api/cxl/linux/example-configurations/hb-interleave.rst
@@ -0,0 +1,314 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+Inter-Host-Bridge Interleave
+============================
+This cxl-cli configuration dump shows the following host configuration:
+
+* A single socket system with one CXL root
+* CXL Root has Four (4) CXL Host Bridges
+* Two CXL Host Bridges have a single CXL Memory Expander Attached
+* The CXL root is configured to interleave across the two host bridges.
+
+This output is generated by :code:`cxl list -v` and describes the relationships
+between objects exposed in :code:`/sys/bus/cxl/devices/`.
+
+::
+
+  [
+    {
+        "bus":"root0",
+        "provider":"ACPI.CXL",
+        "nr_dports":4,
+        "dports":[
+            {
+                "dport":"pci0000:00",
+                "alias":"ACPI0016:01",
+                "id":0
+            },
+            {
+                "dport":"pci0000:a8",
+                "alias":"ACPI0016:02",
+                "id":4
+            },
+            {
+                "dport":"pci0000:2a",
+                "alias":"ACPI0016:03",
+                "id":1
+            },
+            {
+                "dport":"pci0000:d2",
+                "alias":"ACPI0016:00",
+                "id":5
+            }
+        ],
+
+This chunk shows the CXL "bus" (root0) has 4 downstream ports attached to CXL
+Host Bridges.  The `Root` can be considered the singular upstream port attached
+to the platform's memory controller - which routes memory requests to it.
+
+The `ports:root0` section lays out how each of these downstream ports are
+configured.  If a port is not configured (id's 0 and 1), they are omitted.
+
+::
+
+        "ports:root0":[
+            {
+                "port":"port1",
+                "host":"pci0000:d2",
+                "depth":1,
+                "nr_dports":3,
+                "dports":[
+                    {
+                        "dport":"0000:d2:01.1",
+                        "alias":"device:02",
+                        "id":0
+                    },
+                    {
+                        "dport":"0000:d2:01.3",
+                        "alias":"device:05",
+                        "id":2
+                    },
+                    {
+                        "dport":"0000:d2:07.1",
+                        "alias":"device:0d",
+                        "id":113
+                    }
+                ],
+
+This chunk shows the available downstream ports associated with the CXL Host
+Bridge :code:`port1`.  In this case, :code:`port1` has 3 available downstream
+ports: :code:`dport1`, :code:`dport2`, and :code:`dport113`..
+
+::
+
+                "endpoints:port1":[
+                    {
+                        "endpoint":"endpoint5",
+                        "host":"mem0",
+                        "parent_dport":"0000:d2:01.1",
+                        "depth":2,
+                        "memdev":{
+                            "memdev":"mem0",
+                            "ram_size":137438953472,
+                            "serial":0,
+                            "numa_node":0,
+                            "host":"0000:d3:00.0"
+                        },
+                        "decoders:endpoint5":[
+                            {
+                                "decoder":"decoder5.0",
+                                "resource":825975898112,
+                                "size":274877906944,
+                                "interleave_ways":2,
+                                "interleave_granularity":256,
+                                "region":"region0",
+                                "dpa_resource":0,
+                                "dpa_size":137438953472,
+                                "mode":"ram"
+                            }
+                        ]
+                    }
+                ],
+
+This chunk shows the endpoints attached to the host bridge :code:`port1`.
+
+:code:`endpoint5` contains a single configured decoder :code:`decoder5.0`
+which has the same interleave configuration as :code:`region0` (shown later).
+
+Next we have the decodesr belonging to the host bridge:
+
+::
+
+                "decoders:port1":[
+                    {
+                        "decoder":"decoder1.0",
+                        "resource":825975898112,
+                        "size":274877906944,
+                        "interleave_ways":1,
+                        "region":"region0",
+                        "nr_targets":1,
+                        "targets":[
+                            {
+                                "target":"0000:d2:01.1",
+                                "alias":"device:02",
+                                "position":0,
+                                "id":0
+                            }
+                        ]
+                    }
+                ]
+            },
+
+Host Bridge :code:`port1` has a single decoder (:code:`decoder1.0`), whose only
+target is :code:`dport1` - which is attached to :code:`endpoint5`.
+
+The following chunk shows a similar configuration for Host Bridge :code:`port3`,
+the second host bridge with a memory device attached.
+
+::
+
+            {
+                "port":"port3",
+                "host":"pci0000:a8",
+                "depth":1,
+                "nr_dports":1,
+                "dports":[
+                    {
+                        "dport":"0000:a8:01.1",
+                        "alias":"device:c3",
+                        "id":0
+                    }
+                ],
+                "endpoints:port3":[
+                    {
+                        "endpoint":"endpoint6",
+                        "host":"mem1",
+                        "parent_dport":"0000:a8:01.1",
+                        "depth":2,
+                        "memdev":{
+                            "memdev":"mem1",
+                            "ram_size":137438953472,
+                            "serial":0,
+                            "numa_node":0,
+                            "host":"0000:a9:00.0"
+                        },
+                        "decoders:endpoint6":[
+                            {
+                                "decoder":"decoder6.0",
+                                "resource":825975898112,
+                                "size":274877906944,
+                                "interleave_ways":2,
+                                "interleave_granularity":256,
+                                "region":"region0",
+                                "dpa_resource":0,
+                                "dpa_size":137438953472,
+                                "mode":"ram"
+                            }
+                        ]
+                    }
+                ],
+                "decoders:port3":[
+                    {
+                        "decoder":"decoder3.0",
+                        "resource":825975898112,
+                        "size":274877906944,
+                        "interleave_ways":1,
+                        "region":"region0",
+                        "nr_targets":1,
+                        "targets":[
+                            {
+                                "target":"0000:a8:01.1",
+                                "alias":"device:c3",
+                                "position":0,
+                                "id":0
+                            }
+                        ]
+                    }
+                ]
+            },
+
+
+The next chunk shows the two CXL host bridges without attached endpoints.
+
+::
+
+            {
+                "port":"port2",
+                "host":"pci0000:00",
+                "depth":1,
+                "nr_dports":2,
+                "dports":[
+                    {
+                        "dport":"0000:00:01.3",
+                        "alias":"device:55",
+                        "id":2
+                    },
+                    {
+                        "dport":"0000:00:07.1",
+                        "alias":"device:5d",
+                        "id":113
+                    }
+                ]
+            },
+            {
+                "port":"port4",
+                "host":"pci0000:2a",
+                "depth":1,
+                "nr_dports":1,
+                "dports":[
+                    {
+                        "dport":"0000:2a:01.1",
+                        "alias":"device:d0",
+                        "id":0
+                    }
+                ]
+            }
+        ],
+
+Next we have the `Root Decoders` belonging to :code:`root0`.  This root decoder
+applies the interleave across the downstream ports :code:`port1` and
+:code:`port3` - with a granularity of 256 bytes.
+
+This information is generated by the CXL driver reading the ACPI CEDT CMFWS.
+
+::
+
+        "decoders:root0":[
+            {
+                "decoder":"decoder0.0",
+                "resource":825975898112,
+                "size":274877906944,
+                "interleave_ways":2,
+                "interleave_granularity":256,
+                "max_available_extent":0,
+                "volatile_capable":true,
+                "nr_targets":2,
+                "targets":[
+                    {
+                        "target":"pci0000:a8",
+                        "alias":"ACPI0016:02",
+                        "position":1,
+                        "id":4
+                    },
+                    {
+                        "target":"pci0000:d2",
+                        "alias":"ACPI0016:00",
+                        "position":0,
+                        "id":5
+                    }
+                ],
+
+Finally we have the `Memory Region` associated with the `Root Decoder`
+:code:`decoder0.0`.  This region describes the overall interleave configuration
+of the interleave set.
+
+::
+
+                "regions:decoder0.0":[
+                    {
+                        "region":"region0",
+                        "resource":825975898112,
+                        "size":274877906944,
+                        "type":"ram",
+                        "interleave_ways":2,
+                        "interleave_granularity":256,
+                        "decode_state":"commit",
+                        "mappings":[
+                            {
+                                "position":1,
+                                "memdev":"mem1",
+                                "decoder":"decoder6.0"
+                            },
+                            {
+                                "position":0,
+                                "memdev":"mem0",
+                                "decoder":"decoder5.0"
+                            }
+                        ]
+                    }
+                ]
+            }
+        ]
+    }
+  ]
diff --git a/Documentation/driver-api/cxl/linux/example-configurations/intra-hb-interleave.rst b/Documentation/driver-api/cxl/linux/example-configurations/intra-hb-interleave.rst
new file mode 100644
index 000000000000..077dfaf8458d
--- /dev/null
+++ b/Documentation/driver-api/cxl/linux/example-configurations/intra-hb-interleave.rst
@@ -0,0 +1,291 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+Intra-Host-Bridge Interleave
+============================
+This cxl-cli configuration dump shows the following host configuration:
+
+* A single socket system with one CXL root
+* CXL Root has Four (4) CXL Host Bridges
+* One (1) CXL Host Bridges has two CXL Memory Expanders Attached
+* The Host bridge decoder is programmed to interleave across the expanders.
+
+This output is generated by :code:`cxl list -v` and describes the relationships
+between objects exposed in :code:`/sys/bus/cxl/devices/`.
+
+::
+
+  [
+    {
+        "bus":"root0",
+        "provider":"ACPI.CXL",
+        "nr_dports":4,
+        "dports":[
+            {
+                "dport":"pci0000:00",
+                "alias":"ACPI0016:01",
+                "id":0
+            },
+            {
+                "dport":"pci0000:a8",
+                "alias":"ACPI0016:02",
+                "id":4
+            },
+            {
+                "dport":"pci0000:2a",
+                "alias":"ACPI0016:03",
+                "id":1
+            },
+            {
+                "dport":"pci0000:d2",
+                "alias":"ACPI0016:00",
+                "id":5
+            }
+        ],
+
+This chunk shows the CXL "bus" (root0) has 4 downstream ports attached to CXL
+Host Bridges.  The `Root` can be considered the singular upstream port attached
+to the platform's memory controller - which routes memory requests to it.
+
+The `ports:root0` section lays out how each of these downstream ports are
+configured.  If a port is not configured (id's 0 and 1), they are omitted.
+
+::
+
+        "ports:root0":[
+            {
+                "port":"port1",
+                "host":"pci0000:d2",
+                "depth":1,
+                "nr_dports":3,
+                "dports":[
+                    {
+                        "dport":"0000:d2:01.1",
+                        "alias":"device:02",
+                        "id":0
+                    },
+                    {
+                        "dport":"0000:d2:01.3",
+                        "alias":"device:05",
+                        "id":2
+                    },
+                    {
+                        "dport":"0000:d2:07.1",
+                        "alias":"device:0d",
+                        "id":113
+                    }
+                ],
+
+This chunk shows the available downstream ports associated with the CXL Host
+Bridge :code:`port1`.  In this case, :code:`port1` has 3 available downstream
+ports: :code:`dport1`, :code:`dport2`, and :code:`dport113`..
+
+::
+
+                "endpoints:port1":[
+                    {
+                        "endpoint":"endpoint5",
+                        "host":"mem0",
+                        "parent_dport":"0000:d2:01.1",
+                        "depth":2,
+                        "memdev":{
+                            "memdev":"mem0",
+                            "ram_size":137438953472,
+                            "serial":0,
+                            "numa_node":0,
+                            "host":"0000:d3:00.0"
+                        },
+                        "decoders:endpoint5":[
+                            {
+                                "decoder":"decoder5.0",
+                                "resource":825975898112,
+                                "size":274877906944,
+                                "interleave_ways":2,
+                                "interleave_granularity":256,
+                                "region":"region0",
+                                "dpa_resource":0,
+                                "dpa_size":137438953472,
+                                "mode":"ram"
+                            }
+                        ]
+                    },
+                    {
+                        "endpoint":"endpoint6",
+                        "host":"mem1",
+                        "parent_dport":"0000:d2:01.3,
+                        "depth":2,
+                        "memdev":{
+                            "memdev":"mem1",
+                            "ram_size":137438953472,
+                            "serial":0,
+                            "numa_node":0,
+                            "host":"0000:a9:00.0"
+                        },
+                        "decoders:endpoint6":[
+                            {
+                                "decoder":"decoder6.0",
+                                "resource":825975898112,
+                                "size":274877906944,
+                                "interleave_ways":2,
+                                "interleave_granularity":256,
+                                "region":"region0",
+                                "dpa_resource":0,
+                                "dpa_size":137438953472,
+                                "mode":"ram"
+                            }
+                        ]
+                    }
+                ],
+
+This chunk shows the endpoints attached to the host bridge :code:`port1`.
+
+:code:`endpoint5` contains a single configured decoder :code:`decoder5.0`
+which has the same interleave configuration memory region they belong to
+(show later).
+
+Next we have the decoders belonging to the host bridge:
+
+::
+
+                "decoders:port1":[
+                    {
+                        "decoder":"decoder1.0",
+                        "resource":825975898112,
+                        "size":274877906944,
+                        "interleave_ways":2,
+                        "interleave_granularity":256,
+                        "region":"region0",
+                        "nr_targets":2,
+                        "targets":[
+                            {
+                                "target":"0000:d2:01.1",
+                                "alias":"device:02",
+                                "position":0,
+                                "id":0
+                            },
+                            {
+                                "target":"0000:d2:01.3",
+                                "alias":"device:05",
+                                "position":1,
+                                "id":0
+                            }
+                        ]
+                    }
+                ]
+            },
+
+Host Bridge :code:`port1` has a single decoder (:code:`decoder1.0`) with two
+targets: :code:`dport1` and :code:`dport3` - which are attached to
+:code:`endpoint5` and :code:`endpoint6` respectively.
+
+The host bridge decoder interleaves these devices at a 256 byte granularity.
+
+The next chunk shows the three CXL host bridges without attached endpoints.
+
+::
+
+            {
+                "port":"port2",
+                "host":"pci0000:00",
+                "depth":1,
+                "nr_dports":2,
+                "dports":[
+                    {
+                        "dport":"0000:00:01.3",
+                        "alias":"device:55",
+                        "id":2
+                    },
+                    {
+                        "dport":"0000:00:07.1",
+                        "alias":"device:5d",
+                        "id":113
+                    }
+                ]
+            },
+            {
+                "port":"port3",
+                "host":"pci0000:a8",
+                "depth":1,
+                "nr_dports":1,
+                "dports":[
+                    {
+                        "dport":"0000:a8:01.1",
+                        "alias":"device:c3",
+                        "id":0
+                    }
+                ],
+            },
+            {
+                "port":"port4",
+                "host":"pci0000:2a",
+                "depth":1,
+                "nr_dports":1,
+                "dports":[
+                    {
+                        "dport":"0000:2a:01.1",
+                        "alias":"device:d0",
+                        "id":0
+                    }
+                ]
+            }
+        ],
+
+Next we have the `Root Decoders` belonging to :code:`root0`.  This root decoder
+applies the interleave across the downstream ports :code:`port1` and
+:code:`port3` - with a granularity of 256 bytes.
+
+This information is generated by the CXL driver reading the ACPI CEDT CMFWS.
+
+::
+
+        "decoders:root0":[
+            {
+                "decoder":"decoder0.0",
+                "resource":825975898112,
+                "size":274877906944,
+                "interleave_ways":1,
+                "max_available_extent":0,
+                "volatile_capable":true,
+                "nr_targets":2,
+                "targets":[
+                    {
+                        "target":"pci0000:a8",
+                        "alias":"ACPI0016:02",
+                        "position":1,
+                        "id":4
+                    },
+                ],
+
+Finally we have the `Memory Region` associated with the `Root Decoder`
+:code:`decoder0.0`.  This region describes the overall interleave configuration
+of the interleave set.
+
+::
+
+                "regions:decoder0.0":[
+                    {
+                        "region":"region0",
+                        "resource":825975898112,
+                        "size":274877906944,
+                        "type":"ram",
+                        "interleave_ways":2,
+                        "interleave_granularity":256,
+                        "decode_state":"commit",
+                        "mappings":[
+                            {
+                                "position":1,
+                                "memdev":"mem1",
+                                "decoder":"decoder6.0"
+                            },
+                            {
+                                "position":0,
+                                "memdev":"mem0",
+                                "decoder":"decoder5.0"
+                            }
+                        ]
+                    }
+                ]
+            }
+        ]
+    }
+  ]
diff --git a/Documentation/driver-api/cxl/linux/example-configurations/multi-interleave.rst b/Documentation/driver-api/cxl/linux/example-configurations/multi-interleave.rst
new file mode 100644
index 000000000000..008f9053c630
--- /dev/null
+++ b/Documentation/driver-api/cxl/linux/example-configurations/multi-interleave.rst
@@ -0,0 +1,401 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======================
+Multi-Level Interleave
+======================
+This cxl-cli configuration dump shows the following host configuration:
+
+* A single socket system with one CXL root
+* CXL Root has Four (4) CXL Host Bridges
+* Two CXL Host Bridges have a two CXL Memory Expanders Attached each.
+* The CXL root is configured to interleave across the two host bridges.
+* Each host bridge with expanders interleaves across two endpoints.
+
+This output is generated by :code:`cxl list -v` and describes the relationships
+between objects exposed in :code:`/sys/bus/cxl/devices/`.
+
+::
+
+  [
+    {
+        "bus":"root0",
+        "provider":"ACPI.CXL",
+        "nr_dports":4,
+        "dports":[
+            {
+                "dport":"pci0000:00",
+                "alias":"ACPI0016:01",
+                "id":0
+            },
+            {
+                "dport":"pci0000:a8",
+                "alias":"ACPI0016:02",
+                "id":4
+            },
+            {
+                "dport":"pci0000:2a",
+                "alias":"ACPI0016:03",
+                "id":1
+            },
+            {
+                "dport":"pci0000:d2",
+                "alias":"ACPI0016:00",
+                "id":5
+            }
+        ],
+
+This chunk shows the CXL "bus" (root0) has 4 downstream ports attached to CXL
+Host Bridges.  The `Root` can be considered the singular upstream port attached
+to the platform's memory controller - which routes memory requests to it.
+
+The `ports:root0` section lays out how each of these downstream ports are
+configured.  If a port is not configured (id's 0 and 1), they are omitted.
+
+::
+
+        "ports:root0":[
+            {
+                "port":"port1",
+                "host":"pci0000:d2",
+                "depth":1,
+                "nr_dports":3,
+                "dports":[
+                    {
+                        "dport":"0000:d2:01.1",
+                        "alias":"device:02",
+                        "id":0
+                    },
+                    {
+                        "dport":"0000:d2:01.3",
+                        "alias":"device:05",
+                        "id":2
+                    },
+                    {
+                        "dport":"0000:d2:07.1",
+                        "alias":"device:0d",
+                        "id":113
+                    }
+                ],
+
+This chunk shows the available downstream ports associated with the CXL Host
+Bridge :code:`port1`.  In this case, :code:`port1` has 3 available downstream
+ports: :code:`dport0`, :code:`dport2`, and :code:`dport113`.
+
+::
+
+                "endpoints:port1":[
+                    {
+                        "endpoint":"endpoint5",
+                        "host":"mem0",
+                        "parent_dport":"0000:d2:01.1",
+                        "depth":2,
+                        "memdev":{
+                            "memdev":"mem0",
+                            "ram_size":137438953472,
+                            "serial":0,
+                            "numa_node":0,
+                            "host":"0000:d3:00.0"
+                        },
+                        "decoders:endpoint5":[
+                            {
+                                "decoder":"decoder5.0",
+                                "resource":825975898112,
+                                "size":549755813888,
+                                "interleave_ways":4,
+                                "interleave_granularity":256,
+                                "region":"region0",
+                                "dpa_resource":0,
+                                "dpa_size":137438953472,
+                                "mode":"ram"
+                            }
+                        ]
+                    },
+                    {
+                        "endpoint":"endpoint6",
+                        "host":"mem1",
+                        "parent_dport":"0000:d2:01.3",
+                        "depth":2,
+                        "memdev":{
+                            "memdev":"mem1",
+                            "ram_size":137438953472,
+                            "serial":0,
+                            "numa_node":0,
+                            "host":"0000:d3:00.0"
+                        },
+                        "decoders:endpoint6":[
+                            {
+                                "decoder":"decoder6.0",
+                                "resource":825975898112,
+                                "size":549755813888,
+                                "interleave_ways":4,
+                                "interleave_granularity":256,
+                                "region":"region0",
+                                "dpa_resource":0,
+                                "dpa_size":137438953472,
+                                "mode":"ram"
+                            }
+                        ]
+                    }
+                ],
+
+This chunk shows the endpoints attached to the host bridge :code:`port1`.
+
+:code:`endpoint5` contains a single configured decoder :code:`decoder5.0`
+which has the same interleave configuration as :code:`region0` (shown later).
+
+:code:`endpoint6` contains a single configured decoder :code:`decoder5.0`
+which has the same interleave configuration as :code:`region0` (shown later).
+
+Next we have the decoders belonging to the host bridge:
+
+::
+
+                "decoders:port1":[
+                    {
+                        "decoder":"decoder1.0",
+                        "resource":825975898112,
+                        "size":549755813888,
+                        "interleave_ways":2,
+                        "interleave_granularity":512,
+                        "region":"region0",
+                        "nr_targets":2,
+                        "targets":[
+                            {
+                                "target":"0000:d2:01.1",
+                                "alias":"device:02",
+                                "position":0,
+                                "id":0
+                            },
+                            {
+                                "target":"0000:d2:01.3",
+                                "alias":"device:05",
+                                "position":2,
+                                "id":0
+                            }
+                        ]
+                    }
+                ]
+            },
+
+Host Bridge :code:`port1` has a single decoder (:code:`decoder1.0`), whose
+targets are :code:`dport0` and :code:`dport2` - which are attached to
+:code:`endpoint5` and :code:`endpoint6` respectively.
+
+The following chunk shows a similar configuration for Host Bridge :code:`port3`,
+the second host bridge with a memory device attached.
+
+::
+
+            {
+                "port":"port3",
+                "host":"pci0000:a8",
+                "depth":1,
+                "nr_dports":1,
+                "dports":[
+                    {
+                        "dport":"0000:a8:01.1",
+                        "alias":"device:c3",
+                        "id":0
+                    },
+                    {
+                        "dport":"0000:a8:01.3",
+                        "alias":"device:c5",
+                        "id":0
+                    }
+                ],
+                "endpoints:port3":[
+                    {
+                        "endpoint":"endpoint7",
+                        "host":"mem2",
+                        "parent_dport":"0000:a8:01.1",
+                        "depth":2,
+                        "memdev":{
+                            "memdev":"mem2",
+                            "ram_size":137438953472,
+                            "serial":0,
+                            "numa_node":0,
+                            "host":"0000:a9:00.0"
+                        },
+                        "decoders:endpoint7":[
+                            {
+                                "decoder":"decoder7.0",
+                                "resource":825975898112,
+                                "size":549755813888,
+                                "interleave_ways":4,
+                                "interleave_granularity":256,
+                                "region":"region0",
+                                "dpa_resource":0,
+                                "dpa_size":137438953472,
+                                "mode":"ram"
+                            }
+                        ]
+                    },
+                    {
+                        "endpoint":"endpoint8",
+                        "host":"mem3",
+                        "parent_dport":"0000:a8:01.3",
+                        "depth":2,
+                        "memdev":{
+                            "memdev":"mem3",
+                            "ram_size":137438953472,
+                            "serial":0,
+                            "numa_node":0,
+                            "host":"0000:a9:00.0"
+                        },
+                        "decoders:endpoint8":[
+                            {
+                                "decoder":"decoder8.0",
+                                "resource":825975898112,
+                                "size":549755813888,
+                                "interleave_ways":4,
+                                "interleave_granularity":256,
+                                "region":"region0",
+                                "dpa_resource":0,
+                                "dpa_size":137438953472,
+                                "mode":"ram"
+                            }
+                        ]
+                    }
+                ],
+                "decoders:port3":[
+                    {
+                        "decoder":"decoder3.0",
+                        "resource":825975898112,
+                        "size":549755813888,
+                        "interleave_ways":2,
+                        "interleave_granularity":512,
+                        "region":"region0",
+                        "nr_targets":1,
+                        "targets":[
+                            {
+                                "target":"0000:a8:01.1",
+                                "alias":"device:c3",
+                                "position":1,
+                                "id":0
+                            },
+                            {
+                                "target":"0000:a8:01.3",
+                                "alias":"device:c5",
+                                "position":3,
+                                "id":0
+                            }
+                        ]
+                    }
+                ]
+            },
+
+
+The next chunk shows the two CXL host bridges without attached endpoints.
+
+::
+
+            {
+                "port":"port2",
+                "host":"pci0000:00",
+                "depth":1,
+                "nr_dports":2,
+                "dports":[
+                    {
+                        "dport":"0000:00:01.3",
+                        "alias":"device:55",
+                        "id":2
+                    },
+                    {
+                        "dport":"0000:00:07.1",
+                        "alias":"device:5d",
+                        "id":113
+                    }
+                ]
+            },
+            {
+                "port":"port4",
+                "host":"pci0000:2a",
+                "depth":1,
+                "nr_dports":1,
+                "dports":[
+                    {
+                        "dport":"0000:2a:01.1",
+                        "alias":"device:d0",
+                        "id":0
+                    }
+                ]
+            }
+        ],
+
+Next we have the `Root Decoders` belonging to :code:`root0`.  This root decoder
+applies the interleave across the downstream ports :code:`port1` and
+:code:`port3` - with a granularity of 256 bytes.
+
+This information is generated by the CXL driver reading the ACPI CEDT CMFWS.
+
+::
+
+        "decoders:root0":[
+            {
+                "decoder":"decoder0.0",
+                "resource":825975898112,
+                "size":549755813888,
+                "interleave_ways":2,
+                "interleave_granularity":256,
+                "max_available_extent":0,
+                "volatile_capable":true,
+                "nr_targets":2,
+                "targets":[
+                    {
+                        "target":"pci0000:a8",
+                        "alias":"ACPI0016:02",
+                        "position":1,
+                        "id":4
+                    },
+                    {
+                        "target":"pci0000:d2",
+                        "alias":"ACPI0016:00",
+                        "position":0,
+                        "id":5
+                    }
+                ],
+
+Finally we have the `Memory Region` associated with the `Root Decoder`
+:code:`decoder0.0`.  This region describes the overall interleave configuration
+of the interleave set.  So we see there are a total of :code:`4` interleave
+targets across 4 endpoint decoders.
+
+::
+
+                "regions:decoder0.0":[
+                    {
+                        "region":"region0",
+                        "resource":825975898112,
+                        "size":549755813888,
+                        "type":"ram",
+                        "interleave_ways":4,
+                        "interleave_granularity":256,
+                        "decode_state":"commit",
+                        "mappings":[
+                            {
+                                "position":3,
+                                "memdev":"mem3",
+                                "decoder":"decoder8.0"
+                            },
+                            {
+                                "position":2,
+                                "memdev":"mem1",
+                                "decoder":"decoder6.0"
+                            }
+                            {
+                                "position":1,
+                                "memdev":"mem2",
+                                "decoder":"decoder7.0"
+                            },
+                            {
+                                "position":0,
+                                "memdev":"mem0",
+                                "decoder":"decoder5.0"
+                            }
+                        ]
+                    }
+                ]
+            }
+        ]
+    }
+  ]
diff --git a/Documentation/driver-api/cxl/linux/example-configurations/single-device.rst b/Documentation/driver-api/cxl/linux/example-configurations/single-device.rst
new file mode 100644
index 000000000000..5fd38eb0aaf4
--- /dev/null
+++ b/Documentation/driver-api/cxl/linux/example-configurations/single-device.rst
@@ -0,0 +1,246 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=============
+Single Device
+=============
+This cxl-cli configuration dump shows the following host configuration:
+
+* A single socket system with one CXL root
+* CXL Root has Four (4) CXL Host Bridges
+* One CXL Host Bridges has a single CXL Memory Expander Attached
+* No interleave is present.
+
+This output is generated by :code:`cxl list -v` and describes the relationships
+between objects exposed in :code:`/sys/bus/cxl/devices/`.
+
+::
+
+  [
+    {
+        "bus":"root0",
+        "provider":"ACPI.CXL",
+        "nr_dports":4,
+        "dports":[
+            {
+                "dport":"pci0000:00",
+                "alias":"ACPI0016:01",
+                "id":0
+            },
+            {
+                "dport":"pci0000:a8",
+                "alias":"ACPI0016:02",
+                "id":4
+            },
+            {
+                "dport":"pci0000:2a",
+                "alias":"ACPI0016:03",
+                "id":1
+            },
+            {
+                "dport":"pci0000:d2",
+                "alias":"ACPI0016:00",
+                "id":5
+            }
+        ],
+
+This chunk shows the CXL "bus" (root0) has 4 downstream ports attached to CXL
+Host Bridges.  The `Root` can be considered the singular upstream port attached
+to the platform's memory controller - which routes memory requests to it.
+
+The `ports:root0` section lays out how each of these downstream ports are
+configured.  If a port is not configured (id's 0, 1, and 4), they are omitted.
+
+::
+
+        "ports:root0":[
+            {
+                "port":"port1",
+                "host":"pci0000:d2",
+                "depth":1,
+                "nr_dports":3,
+                "dports":[
+                    {
+                        "dport":"0000:d2:01.1",
+                        "alias":"device:02",
+                        "id":0
+                    },
+                    {
+                        "dport":"0000:d2:01.3",
+                        "alias":"device:05",
+                        "id":2
+                    },
+                    {
+                        "dport":"0000:d2:07.1",
+                        "alias":"device:0d",
+                        "id":113
+                    }
+                ],
+
+This chunk shows the available downstream ports associated with the CXL Host
+Bridge :code:`port1`.  In this case, :code:`port1` has 3 available downstream
+ports: :code:`dport1`, :code:`dport2`, and :code:`dport113`..
+
+::
+
+                "endpoints:port1":[
+                    {
+                        "endpoint":"endpoint5",
+                        "host":"mem0",
+                        "parent_dport":"0000:d2:01.1",
+                        "depth":2,
+                        "memdev":{
+                            "memdev":"mem0",
+                            "ram_size":137438953472,
+                            "serial":0,
+                            "numa_node":0,
+                            "host":"0000:d3:00.0"
+                        },
+                        "decoders:endpoint5":[
+                            {
+                                "decoder":"decoder5.0",
+                                "resource":825975898112,
+                                "size":137438953472,
+                                "interleave_ways":1,
+                                "region":"region0",
+                                "dpa_resource":0,
+                                "dpa_size":137438953472,
+                                "mode":"ram"
+                            }
+                        ]
+                    }
+                ],
+
+This chunk shows the endpoints attached to the host bridge :code:`port1`.
+
+:code:`endpoint5` contains a single configured decoder :code:`decoder5.0`
+which has the same interleave configuration as :code:`region0` (shown later).
+
+Next we have the decoders belonging to the host bridge:
+
+::
+
+                "decoders:port1":[
+                    {
+                        "decoder":"decoder1.0",
+                        "resource":825975898112,
+                        "size":137438953472,
+                        "interleave_ways":1,
+                        "region":"region0",
+                        "nr_targets":1,
+                        "targets":[
+                            {
+                                "target":"0000:d2:01.1",
+                                "alias":"device:02",
+                                "position":0,
+                                "id":0
+                            }
+                        ]
+                    }
+                ]
+            },
+
+Host Bridge :code:`port1` has a single decoder (:code:`decoder1.0`), whose only
+target is :code:`dport1` - which is attached to :code:`endpoint5`.
+
+The next chunk shows the three CXL host bridges without attached endpoints.
+
+::
+
+            {
+                "port":"port2",
+                "host":"pci0000:00",
+                "depth":1,
+                "nr_dports":2,
+                "dports":[
+                    {
+                        "dport":"0000:00:01.3",
+                        "alias":"device:55",
+                        "id":2
+                    },
+                    {
+                        "dport":"0000:00:07.1",
+                        "alias":"device:5d",
+                        "id":113
+                    }
+                ]
+            },
+            {
+                "port":"port3",
+                "host":"pci0000:a8",
+                "depth":1,
+                "nr_dports":1,
+                "dports":[
+                    {
+                        "dport":"0000:a8:01.1",
+                        "alias":"device:c3",
+                        "id":0
+                    }
+                ]
+            },
+            {
+                "port":"port4",
+                "host":"pci0000:2a",
+                "depth":1,
+                "nr_dports":1,
+                "dports":[
+                    {
+                        "dport":"0000:2a:01.1",
+                        "alias":"device:d0",
+                        "id":0
+                    }
+                ]
+            }
+        ],
+
+Next we have the `Root Decoders` belonging to :code:`root0`.  This root decoder
+is a pass-through decoder because :code:`interleave_ways` is set to :code:`1`.
+
+This information is generated by the CXL driver reading the ACPI CEDT CMFWS.
+
+::
+
+        "decoders:root0":[
+            {
+                "decoder":"decoder0.0",
+                "resource":825975898112,
+                "size":137438953472,
+                "interleave_ways":1,
+                "max_available_extent":0,
+                "volatile_capable":true,
+                "nr_targets":1,
+                "targets":[
+                    {
+                        "target":"pci0000:d2",
+                        "alias":"ACPI0016:00",
+                        "position":0,
+                        "id":5
+                    }
+                ],
+
+Finally we have the `Memory Region` associated with the `Root Decoder`
+:code:`decoder0.0`.  This region describes the discrete region associated
+with the lone device.
+
+::
+
+                "regions:decoder0.0":[
+                    {
+                        "region":"region0",
+                        "resource":825975898112,
+                        "size":137438953472,
+                        "type":"ram",
+                        "interleave_ways":1,
+                        "decode_state":"commit",
+                        "mappings":[
+                            {
+                                "position":0,
+                                "memdev":"mem0",
+                                "decoder":"decoder5.0"
+                            }
+                        ]
+                    }
+                ]
+            }
+        ]
+    }
+  ]
diff --git a/Documentation/driver-api/cxl/linux/memory-hotplug.rst b/Documentation/driver-api/cxl/linux/memory-hotplug.rst
new file mode 100644
index 000000000000..af368c2bc9cf
--- /dev/null
+++ b/Documentation/driver-api/cxl/linux/memory-hotplug.rst
@@ -0,0 +1,78 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============
+Memory Hotplug
+==============
+The final phase of surfacing CXL memory to the kernel page allocator is for
+the `DAX` driver to surface a `Driver Managed` memory region via the
+memory-hotplug component.
+
+There are four major configurations to consider:
+
+1) Default Online Behavior (on/off and zone)
+2) Hotplug Memory Block size
+3) Memory Map Resource location
+4) Driver-Managed Memory Designation
+
+Default Online Behavior
+=======================
+The default-online behavior of hotplug memory is dictated by the following,
+in order of precedence:
+
+- :code:`CONFIG_MHP_DEFAULT_ONLINE_TYPE` Build Configuration
+- :code:`memhp_default_state` Boot parameter
+- :code:`/sys/devices/system/memory/auto_online_blocks` value
+
+These dictate whether hotplugged memory blocks arrive in one of three states:
+
+1) Offline
+2) Online in :code:`ZONE_NORMAL`
+3) Online in :code:`ZONE_MOVABLE`
+
+:code:`ZONE_NORMAL` implies this capacity may be used for almost any allocation,
+while :code:`ZONE_MOVABLE` implies this capacity should only be used for
+migratable allocations.
+
+:code:`ZONE_MOVABLE` attempts to retain the hotplug-ability of a memory block
+so that it the entire region may be hot-unplugged at a later time.  Any capacity
+onlined into :code:`ZONE_NORMAL` should be considered permanently attached to
+the page allocator.
+
+Hotplug Memory Block Size
+=========================
+By default, on most architectures, the Hotplug Memory Block Size is either
+128MB or 256MB.  On x86, the block size increases up to 2GB as total memory
+capacity exceeds 64GB.  As of v6.15, Linux does not take into account the
+size and alignment of the ACPI CEDT CFMWS regions (see Early Boot docs) when
+deciding the Hotplug Memory Block Size.
+
+Memory Map
+==========
+The location of :code:`struct folio` allocations to represent the hotplugged
+memory capacity are dictated by the following system settings:
+
+- :code:`/sys_module/memory_hotplug/parameters/memmap_on_memory`
+- :code:`/sys/bus/dax/devices/daxN.Y/memmap_on_memory`
+
+If both of these parameters are set to true, :code:`struct folio` for this
+capacity will be carved out of the memory block being onlined.  This has
+performance implications if the memory is particularly high-latency and
+its :code:`struct folio` becomes hotly contended.
+
+If either parameter is set to false, :code:`struct folio` for this capacity
+will be allocated from the local node of the processor running the hotplug
+procedure.  This capacity will be allocated from :code:`ZONE_NORMAL` on
+that node, as it is a :code:`GFP_KERNEL` allocation.
+
+Systems with extremely large amounts of :code:`ZONE_MOVABLE` memory (e.g.
+CXL memory pools) must ensure that there is sufficient local
+:code:`ZONE_NORMAL` capacity to host the memory map for the hotplugged capacity.
+
+Driver Managed Memory
+=====================
+The DAX driver surfaces this memory to memory-hotplug as "Driver Managed". This
+is not a configurable setting, but it's important to note that driver managed
+memory is explicitly excluded from use during kexec.  This is required to ensure
+any reset or out-of-band operations that the CXL device may be subject to during
+a functional system-reboot (such as a reset-on-probe) will not cause portions of
+the kexec kernel to be overwritten.
diff --git a/Documentation/driver-api/cxl/linux/overview.rst b/Documentation/driver-api/cxl/linux/overview.rst
new file mode 100644
index 000000000000..648beb2c8c83
--- /dev/null
+++ b/Documentation/driver-api/cxl/linux/overview.rst
@@ -0,0 +1,103 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+========
+Overview
+========
+
+This section presents the configuration process of a CXL Type-3 memory device,
+and how it is ultimately exposed to users as either a :code:`DAX` device or
+normal memory pages via the kernel's page allocator.
+
+Portions marked with a bullet are points at which certain kernel objects
+are generated.
+
+1) Early Boot
+
+  a) BIOS, Build, and Boot Parameters
+
+    i) EFI_MEMORY_SP
+    ii) CONFIG_EFI_SOFT_RESERVE
+    iii) CONFIG_MHP_DEFAULT_ONLINE_TYPE
+    iv) nosoftreserve
+
+  b) Memory Map Creation
+
+    i) EFI Memory Map / E820 Consulted for Soft-Reserved
+
+      * CXL Memory is set aside to be handled by the CXL driver
+
+      * Soft-Reserved IO Resource created for CFMWS entry
+
+  c) NUMA Node Creation
+
+    * Nodes created from ACPI CEDT CFMWS and SRAT Proximity domains (PXM)
+
+  d) Memory Tier Creation
+
+    * A default memory_tier is created with all nodes.
+
+  e) Contiguous Memory Allocation
+
+    * Any requested CMA is allocated from Online nodes
+
+  f) Init Finishes, Drivers start probing
+
+2) ACPI and PCI Drivers
+
+  a) Detects PCI device is CXL, marking it for probe by CXL driver
+
+3) CXL Driver Operation
+
+  a) Base device creation
+
+    * root, port, and memdev devices created
+    * CEDT CFMWS IO Resource creation
+
+  b) Decoder creation
+
+    * root, switch, and endpoint decoders created
+
+  c) Logical device creation
+
+    * memory_region and endpoint devices created
+
+  d) Devices are associated with each other
+
+    * If auto-decoder (BIOS-programmed decoders), driver validates
+      configurations, builds associations, and locks configs at probe time.
+
+    * If user-configured, validation and associations are built at
+      decoder-commit time.
+
+  e) Regions surfaced as DAX region
+
+    * dax_region created
+
+    * DAX device created via DAX driver
+
+4) DAX Driver Operation
+
+  a) DAX driver surfaces DAX region as one of two dax device modes
+
+    * kmem - dax device is converted to hotplug memory blocks
+
+      * DAX kmem IO Resource creation
+
+    * hmem - dax device is left as daxdev to be accessed as a file.
+
+      * If hmem, journey ends here.
+
+  b) DAX kmem surfaces memory region to Memory Hotplug to add to page
+     allocator as "driver managed memory"
+
+5) Memory Hotplug
+
+  a) mhp component surfaces a dax device memory region as multiple memory
+     blocks to the page allocator
+
+    * blocks appear in :code:`/sys/bus/memory/devices` and linked to a NUMA node
+
+  b) blocks are onlined into the requested zone (NORMAL or MOVABLE)
+
+    * Memory is marked "Driver Managed" to avoid kexec from using it as region
+      for kernel updates
diff --git a/Documentation/driver-api/cxl/maturity-map.rst b/Documentation/driver-api/cxl/maturity-map.rst
index a2288f9df658..1330f3f52129 100644
--- a/Documentation/driver-api/cxl/maturity-map.rst
+++ b/Documentation/driver-api/cxl/maturity-map.rst
@@ -51,9 +51,9 @@ in place, but there are several corner cases that are pending closure.
 
 * [2] CXL Window Enumeration
 
-  * [0] :ref:`Extended-linear memory-side cache <extended-linear>`
+  * [2] :ref:`Extended-linear memory-side cache <extended-linear>`
   * [0] Low Memory-hole
-  * [0] Hetero-interleave
+  * [X] Hetero-interleave
 
 * [2] Switch Enumeration
 
@@ -173,7 +173,7 @@ Accelerator
 User Flow Support
 -----------------
 
-* [0] HPA->DPA Address translation (need xormaps export solution)
+* [0] Inject & clear poison by HPA
 
 Details
 =======
diff --git a/Documentation/driver-api/cxl/platform/acpi.rst b/Documentation/driver-api/cxl/platform/acpi.rst
new file mode 100644
index 000000000000..ee7e6bd4c43d
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/acpi.rst
@@ -0,0 +1,76 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========
+ACPI Tables
+===========
+
+ACPI is the "Advanced Configuration and Power Interface", which is a standard
+that defines how platforms and OS manage power and configure computer hardware.
+For the purpose of this theory of operation, when referring to "ACPI" we will
+usually refer to "ACPI Tables" - which are the way a platform (BIOS/EFI)
+communicates static configuration information to the operation system.
+
+The Following ACPI tables contain *static* configuration and performance data
+about CXL devices.
+
+.. toctree::
+   :maxdepth: 1
+
+   acpi/cedt.rst
+   acpi/srat.rst
+   acpi/hmat.rst
+   acpi/slit.rst
+   acpi/dsdt.rst
+
+The SRAT table may also contain generic port/initiator content that is intended
+to describe the generic port, but not information about the rest of the path to
+the endpoint.
+
+Linux uses these tables to configure kernel resources for statically configured
+(by BIOS/EFI) CXL devices, such as:
+
+- NUMA nodes
+- Memory Tiers
+- NUMA Abstract Distances
+- SystemRAM Memory Regions
+- Weighted Interleave Node Weights
+
+ACPI Debugging
+==============
+
+The :code:`acpidump -b` command dumps the ACPI tables into binary format.
+
+The :code:`iasl -d` command disassembles the files into human readable format.
+
+Example :code:`acpidump -b && iasl -d cedt.dat` ::
+
+   [000h 0000   4]   Signature : "CEDT"    [CXL Early Discovery Table]
+
+Common Issues
+-------------
+Most failures described here result in a failure of the driver to surface
+memory as a DAX device and/or kmem.
+
+* CEDT CFMWS targets list UIDs do not match CEDT CHBS UIDs.
+* CEDT CFMWS targets list UIDs do not match DSDT CXL Host Bridge UIDs.
+* CEDT CFMWS Restriction Bits are not correct.
+* CEDT CFMWS Memory regions are poorly aligned.
+* CEDT CFMWS Memory regions spans a platform memory hole.
+* CEDT CHBS UIDs do not match DSDT CXL Host Bridge UIDs.
+* CEDT CHBS Specification version is incorrect.
+* SRAT is missing regions described in CEDT CFMWS.
+
+  * Result: failure to create a NUMA node for the region, or
+    region is placed in wrong node.
+
+* HMAT is missing data for regions described in CEDT CFMWS.
+
+  * Result: NUMA node being placed in the wrong memory tier.
+
+* SLIT has bad data.
+
+  * Result: Lots of performance mechanisms in the kernel will be very unhappy.
+
+All of these issues will appear to users as if the driver is failing to
+support CXL - when in reality they are all the failure of a platform to
+configure the ACPI tables correctly.
diff --git a/Documentation/driver-api/cxl/platform/acpi/cedt.rst b/Documentation/driver-api/cxl/platform/acpi/cedt.rst
new file mode 100644
index 000000000000..1d9c9d3592dc
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/acpi/cedt.rst
@@ -0,0 +1,62 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+================================
+CEDT - CXL Early Discovery Table
+================================
+
+The CXL Early Discovery Table is generated by BIOS to describe the CXL memory
+regions configured at boot by the BIOS.
+
+CHBS
+====
+The CXL Host Bridge Structure describes CXL host bridges.  Other than describing
+device register information, it reports the specific host bridge UID for this
+host bridge.  These host bridge ID's will be referenced in other tables.
+
+Example ::
+
+          Subtable Type : 00 [CXL Host Bridge Structure]
+               Reserved : 00
+                 Length : 0020
+ Associated host bridge : 00000007    <- Host bridge _UID
+  Specification version : 00000001
+               Reserved : 00000000
+          Register base : 0000010370400000
+        Register length : 0000000000010000
+
+CFMWS
+=====
+The CXL Fixed Memory Window structure describes a memory region associated
+with one or more CXL host bridges (as described by the CHBS).  It additionally
+describes any inter-host-bridge interleave configuration that may have been
+programmed by BIOS.
+
+Example ::
+
+            Subtable Type : 01 [CXL Fixed Memory Window Structure]
+                 Reserved : 00
+                   Length : 002C
+                 Reserved : 00000000
+      Window base address : 000000C050000000   <- Memory Region
+              Window size : 0000003CA0000000
+ Interleave Members (2^n) : 01                 <- Interleave configuration
+    Interleave Arithmetic : 00
+                 Reserved : 0000
+              Granularity : 00000000
+             Restrictions : 0006
+                    QtgId : 0001
+             First Target : 00000007           <- Host Bridge _UID
+              Next Target : 00000006           <- Host Bridge _UID
+
+The restriction field dictates what this SPA range may be used for (memory type,
+voltile vs persistent, etc). One or more bits may be set. ::
+
+  Bit[0]: CXL Type 2 Memory
+  Bit[1]: CXL Type 3 Memory
+  Bit[2]: Volatile Memory
+  Bit[3]: Persistent Memory
+  Bit[4]: Fixed Config (HPA cannot be re-used)
+
+INTRA-host-bridge interleave (multiple devices on one host bridge) is NOT
+reported in this structure, and is solely defined via CXL device decoder
+programming (host bridge and endpoint decoders).
diff --git a/Documentation/driver-api/cxl/platform/acpi/dsdt.rst b/Documentation/driver-api/cxl/platform/acpi/dsdt.rst
new file mode 100644
index 000000000000..b4583b01d67d
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/acpi/dsdt.rst
@@ -0,0 +1,28 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================================
+DSDT - Differentiated system Description Table
+==============================================
+
+This table describes what peripherals a machine has.
+
+This table's UIDs for CXL devices - specifically host bridges, must be
+consistent with the contents of the CEDT, otherwise the CXL driver will
+fail to probe correctly.
+
+Example Compute Express Link Host Bridge ::
+
+    Scope (_SB)
+    {
+        Device (S0D0)
+        {
+            Name (_HID, "ACPI0016" /* Compute Express Link Host Bridge */)  // _HID: Hardware ID
+            Name (_CID, Package (0x02)  // _CID: Compatible ID
+            {
+                EisaId ("PNP0A08") /* PCI Express Bus */,
+                EisaId ("PNP0A03") /* PCI Bus */
+            })
+            ...
+            Name (_UID, 0x05)  // _UID: Unique ID
+            ...
+      }
diff --git a/Documentation/driver-api/cxl/platform/acpi/hmat.rst b/Documentation/driver-api/cxl/platform/acpi/hmat.rst
new file mode 100644
index 000000000000..095a26f02a37
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/acpi/hmat.rst
@@ -0,0 +1,32 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================================
+HMAT - Heterogeneous Memory Attribute Table
+===========================================
+
+The Heterogeneous Memory Attributes Table contains information such as cache
+attributes and bandwidth and latency details for memory proximity domains.
+For the purpose of this document, we will only discuss the SSLIB entry.
+
+SLLBI
+=====
+The System Locality Latency and Bandwidth Information records latency and
+bandwidth information for proximity domains.
+
+This table is used by Linux to configure interleave weights and memory tiers.
+
+Example (Heavily truncated for brevity) ::
+
+               Structure Type : 0001 [SLLBI]
+                    Data Type : 00         <- Latency
+ Target Proximity Domain List : 00000000
+ Target Proximity Domain List : 00000001
+                        Entry : 0080       <- DRAM LTC
+                        Entry : 0100       <- CXL LTC
+
+               Structure Type : 0001 [SLLBI]
+                    Data Type : 03         <- Bandwidth
+ Target Proximity Domain List : 00000000
+ Target Proximity Domain List : 00000001
+                        Entry : 1200       <- DRAM BW
+                        Entry : 0200       <- CXL BW
diff --git a/Documentation/driver-api/cxl/platform/acpi/slit.rst b/Documentation/driver-api/cxl/platform/acpi/slit.rst
new file mode 100644
index 000000000000..a56768e8fe41
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/acpi/slit.rst
@@ -0,0 +1,21 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+========================================
+SLIT - System Locality Information Table
+========================================
+
+The system locality information table provides "abstract distances" between
+accessor and memory nodes.  Node without initiators (cpus) are infinitely (FF)
+distance away from all other nodes.
+
+The abstract distance described in this table does not describe any real
+latency of bandwidth information.
+
+Example ::
+
+    Signature : "SLIT"    [System Locality Information Table]
+   Localities : 0000000000000004
+ Locality   0 : 10 20 20 30
+ Locality   1 : 20 10 30 20
+ Locality   2 : FF FF 0A FF
+ Locality   3 : FF FF FF 0A
diff --git a/Documentation/driver-api/cxl/platform/acpi/srat.rst b/Documentation/driver-api/cxl/platform/acpi/srat.rst
new file mode 100644
index 000000000000..cc98ca0e508e
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/acpi/srat.rst
@@ -0,0 +1,71 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================================
+SRAT - Static Resource Affinity Table
+=====================================
+
+The System/Static Resource Affinity Table describes resource (CPU, Memory)
+affinity to "Proximity Domains". This table is technically optional, but for
+performance information (see "HMAT") to be enumerated by linux it must be
+present.
+
+There is a careful dance between the CEDT and SRAT tables and how NUMA nodes are
+created.  If things don't look quite the way you expect - check the SRAT Memory
+Affinity entries and CEDT CFMWS to determine what your platform actually
+supports in terms of flexible topologies.
+
+The SRAT may statically assign portions of a CFMWS SPA range to a specific
+proximity domains.  See linux numa creation for more information about how
+this presents in the NUMA topology.
+
+Proximity Domain
+================
+A proximity domain is ROUGHLY equivalent to "NUMA Node" - though a 1-to-1
+mapping is not guaranteed.  There are scenarios where "Proximity Domain 4" may
+map to "NUMA Node 3", for example.  (See "NUMA Node Creation")
+
+Memory Affinity
+===============
+Generally speaking, if a host does any amount of CXL fabric (decoder)
+programming in BIOS - an SRAT entry for that memory needs to be present.
+
+Example ::
+
+         Subtable Type : 01 [Memory Affinity]
+                Length : 28
+      Proximity Domain : 00000001          <- NUMA Node 1
+             Reserved1 : 0000
+          Base Address : 000000C050000000  <- Physical Memory Region
+        Address Length : 0000003CA0000000
+             Reserved2 : 00000000
+ Flags (decoded below) : 0000000B
+              Enabled : 1
+        Hot Pluggable : 1
+         Non-Volatile : 0
+
+
+Generic Port Affinity
+=====================
+The Generic Port Affinity subtable provides an association between a proximity
+domain and a device handle representing a Generic Port such as a CXL host
+bridge. With the association, latency and bandwidth numbers can be retrieved
+from the SRAT for the path between CPU(s) (initiator) and the Generic Port.
+This is used to construct performance coordinates for hotplugged CXL DEVICES,
+which cannot be enumerated at boot by platform firmware.
+
+Example ::
+
+         Subtable Type : 06 [Generic Port Affinity]
+                Length : 20               <- 32d, length of table
+              Reserved : 00
+    Device Handle Type : 00               <- 0 - ACPI, 1 - PCI
+      Proximity Domain : 00000001
+         Device Handle : ACPI0016:01
+                 Flags : 00000001         <- Bit 0 (Enabled)
+              Reserved : 00000000
+
+The Proximity Domain is matched up to the :doc:`HMAT <hmat>` SSLBI Target
+Proximity Domain List for the related latency or bandwidth numbers. Those
+performance numbers are tied to a CXL host bridge via the Device Handle.
+The driver uses the association to retrieve the Generic Port performance
+numbers for the whole CXL path access coordinates calculation.
diff --git a/Documentation/driver-api/cxl/platform/bios-and-efi.rst b/Documentation/driver-api/cxl/platform/bios-and-efi.rst
new file mode 100644
index 000000000000..645322632cc9
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/bios-and-efi.rst
@@ -0,0 +1,262 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======================
+BIOS/EFI Configuration
+======================
+
+BIOS and EFI are largely responsible for configuring static information about
+devices (or potential future devices) such that Linux can build the appropriate
+logical representations of these devices.
+
+At a high level, this is what occurs during this phase of configuration.
+
+* The bootloader starts the BIOS/EFI.
+
+* BIOS/EFI do early device probe to determine static configuration
+
+* BIOS/EFI creates ACPI Tables that describe static config for the OS
+
+* BIOS/EFI create the system memory map (EFI Memory Map, E820, etc)
+
+* BIOS/EFI calls :code:`start_kernel` and begins the Linux Early Boot process.
+
+Much of what this section is concerned with is ACPI Table production and
+static memory map configuration. More detail on these tables can be found
+at :doc:`ACPI Tables <acpi>`.
+
+.. note::
+   Platform Vendors should read carefully, as this sections has recommendations
+   on physical memory region size and alignment, memory holes, HDM interleave,
+   and what linux expects of HDM decoders trying to work with these features.
+
+UEFI Settings
+=============
+If your platform supports it, the :code:`uefisettings` command can be used to
+read/write EFI settings. Changes will be reflected on the next reboot. Kexec
+is not a sufficient reboot.
+
+One notable configuration here is the EFI_MEMORY_SP (Specific Purpose) bit.
+When this is enabled, this bit tells linux to defer management of a memory
+region to a driver (in this case, the CXL driver). Otherwise, the memory is
+treated as "normal memory", and is exposed to the page allocator during
+:code:`__init`.
+
+uefisettings examples
+---------------------
+
+:code:`uefisettings identify` ::
+
+        uefisettings identify
+
+        bios_vendor: xxx
+        bios_version: xxx
+        bios_release: xxx
+        bios_date: xxx
+        product_name: xxx
+        product_family: xxx
+        product_version: xxx
+
+On some AMD platforms, the :code:`EFI_MEMORY_SP` bit is set via the :code:`CXL
+Memory Attribute` field.  This may be called something else on your platform.
+
+:code:`uefisettings get "CXL Memory Attribute"` ::
+
+        selector: xxx
+        ...
+        question: Question {
+            name: "CXL Memory Attribute",
+            answer: "Enabled",
+            ...
+        }
+
+Physical Memory Map
+===================
+
+Physical Address Region Alignment
+---------------------------------
+
+As of Linux v6.14, the hotplug memory system requires memory regions to be
+uniform in size and alignment.  While the CXL specification allows for memory
+regions as small as 256MB, the supported memory block size and alignment for
+hotplugged memory is architecture-defined.
+
+A Linux memory blocks may be as small as 128MB and increase in powers of two.
+
+* On ARM, the default block size and alignment is either 128MB or 256MB.
+
+* On x86, the default block size is 256MB, and increases to 2GB as the
+  capacity of the system increases up to 64GB.
+
+For best support across versions, platform vendors should place CXL memory at
+a 2GB aligned base address, and regions should be 2GB aligned.  This also helps
+prevent the creating thousands of memory devices (one per block).
+
+Memory Holes
+------------
+
+Holes in the memory map are tricky.  Consider a 4GB device located at base
+address 0x100000000, but with the following memory map ::
+
+  ---------------------
+  |    0x100000000    |
+  |        CXL        |
+  |    0x1BFFFFFFF    |
+  ---------------------
+  |    0x1C0000000    |
+  |    MEMORY HOLE    |
+  |    0x1FFFFFFFF    |
+  ---------------------
+  |    0x200000000    |
+  |     CXL CONT.     |
+  |    0x23FFFFFFF    |
+  ---------------------
+
+There are two issues to consider:
+
+* decoder programming, and
+* memory block alignment.
+
+If your architecture requires 2GB uniform size and aligned memory blocks, the
+only capacity Linux is capable of mapping (as of v6.14) would be the capacity
+from `0x100000000-0x180000000`.  The remaining capacity will be stranded, as
+they are not of 2GB aligned length.
+
+Assuming your architecture and memory configuration allows 1GB memory blocks,
+this memory map is supported and this should be presented as multiple CFMWS
+in the CEDT that describe each side of the memory hole separately - along with
+matching decoders.
+
+Multiple decoders can (and should) be used to manage such a memory hole (see
+below), but each chunk of a memory hole should be aligned to a reasonable block
+size (larger alignment is always better).  If you intend to have memory holes
+in the memory map, expect to use one decoder per contiguous chunk of host
+physical memory.
+
+As of v6.14, Linux does provide support for memory hotplug of multiple
+physical memory regions separated by a memory hole described by a single
+HDM decoder.
+
+
+Decoder Programming
+===================
+If BIOS/EFI intends to program the decoders to be statically configured,
+there are a few things to consider to avoid major pitfalls that will
+prevent Linux compatibility.  Some of these recommendations are not
+required "per the specification", but Linux makes no guarantees of support
+otherwise.
+
+
+Translation Point
+-----------------
+Per the specification, the only decoders which **TRANSLATE** Host Physical
+Address (HPA) to Device Physical Address (DPA) are the **Endpoint Decoders**.
+All other decoders in the fabric are intended to route accesses without
+translating the addresses.
+
+This is heavily implied by the specification, see: ::
+
+  CXL Specification 3.1
+  8.2.4.20: CXL HDM Decoder Capability Structure
+  - Implementation Note: CXL Host Bridge and Upstream Switch Port Decoder Flow
+  - Implementation Note: Device Decoder Logic
+
+Given this, Linux makes a strong assumption that decoders between CPU and
+endpoint will all be programmed with addresses ranges that are subsets of
+their parent decoder.
+
+Due to some ambiguity in how Architecture, ACPI, PCI, and CXL specifications
+"hand off" responsibility between domains, some early adopting platforms
+attempted to do translation at the originating memory controller or host
+bridge.  This configuration requires a platform specific extension to the
+driver and is not officially endorsed - despite being supported.
+
+It is *highly recommended* **NOT** to do this; otherwise, you are on your own
+to implement driver support for your platform.
+
+Interleave and Configuration Flexibility
+----------------------------------------
+If providing cross-host-bridge interleave, a CFMWS entry in the :doc:`CEDT
+<acpi/cedt>` must be presented with target host-bridges for the interleaved
+device sets (there may be multiple behind each host bridge).
+
+If providing intra-host-bridge interleaving, only 1 CFMWS entry in the CEDT is
+required for that host bridge - if it covers the entire capacity of the devices
+behind the host bridge.
+
+If intending to provide users flexibility in programming decoders beyond the
+root, you may want to provide multiple CFMWS entries in the CEDT intended for
+different purposes.  For example, you may want to consider adding:
+
+1) A CFMWS entry to cover all interleavable host bridges.
+2) A CFMWS entry to cover all devices on a single host bridge.
+3) A CFMWS entry to cover each device.
+
+A platform may choose to add all of these, or change the mode based on a BIOS
+setting.  For each CFMWS entry, Linux expects descriptions of the described
+memory regions in the :doc:`SRAT <acpi/srat>` to determine the number of
+NUMA nodes it should reserve during early boot / init.
+
+As of v6.14, Linux will create a NUMA node for each CEDT CFMWS entry, even if
+a matching SRAT entry does not exist; however, this is not guaranteed in the
+future and such a configuration should be avoided.
+
+Memory Holes
+------------
+If your platform includes memory holes intersparsed between your CXL memory, it
+is recommended to utilize multiple decoders to cover these regions of memory,
+rather than try to program the decoders to accept the entire range and expect
+Linux to manage the overlap.
+
+For example, consider the Memory Hole described above ::
+
+  ---------------------
+  |    0x100000000    |
+  |        CXL        |
+  |    0x1BFFFFFFF    |
+  ---------------------
+  |    0x1C0000000    |
+  |    MEMORY HOLE    |
+  |    0x1FFFFFFFF    |
+  ---------------------
+  |    0x200000000    |
+  |     CXL CONT.     |
+  |    0x23FFFFFFF    |
+  ---------------------
+
+Assuming this is provided by a single device attached directly to a host bridge,
+Linux would expect the following decoder programming ::
+
+     -----------------------   -----------------------
+     | root-decoder-0      |   | root-decoder-1      |
+     |   base: 0x100000000 |   |   base: 0x200000000 |
+     |   size:  0xC0000000 |   |   size:  0x40000000 |
+     -----------------------   -----------------------
+                |                         |
+     -----------------------   -----------------------
+     | HB-decoder-0        |   | HB-decoder-1        |
+     |   base: 0x100000000 |   |   base: 0x200000000 |
+     |   size:  0xC0000000 |   |   size:  0x40000000 |
+     -----------------------   -----------------------
+                |                         |
+     -----------------------   -----------------------
+     | ep-decoder-0        |   | ep-decoder-1        |
+     |   base: 0x100000000 |   |   base: 0x200000000 |
+     |   size:  0xC0000000 |   |   size:  0x40000000 |
+     -----------------------   -----------------------
+
+With a CEDT configuration with two CFMWS describing the above root decoders.
+
+Linux makes no guarantee of support for strange memory hole situations.
+
+Multi-Media Devices
+-------------------
+The CFMWS field of the CEDT has special restriction bits which describe whether
+the described memory region allows volatile or persistent memory (or both). If
+the platform intends to support either:
+
+1) A device with multiple medias, or
+2) Using a persistent memory device as normal memory
+
+A platform may wish to create multiple CEDT CFMWS entries to describe the same
+memory, with the intent of allowing the end user flexibility in how that memory
+is configured. Linux does not presently have strong requirements in this area.
diff --git a/Documentation/driver-api/cxl/platform/cdat.rst b/Documentation/driver-api/cxl/platform/cdat.rst
new file mode 100644
index 000000000000..34bbe7264d71
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/cdat.rst
@@ -0,0 +1,118 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======================================
+Coherent Device Attribute Table (CDAT)
+======================================
+
+The CDAT provides functional and performance attributes of devices such
+as CXL accelerators, switches, or endpoints.  The table formatting is
+similar to ACPI tables. CDAT data may be parsed by BIOS at boot or may
+be enumerated at runtime (after device hotplug, for example).
+
+Terminology:
+DPA - Device Physical Address, used by the CXL device to denote the address
+it supports for that device.
+
+DSMADHandle - A device unique handle that is associated with a DPA range
+defined by the DSMAS table.
+
+
+===============================================
+Device Scoped Memory Affinity Structure (DSMAS)
+===============================================
+
+The DSMAS contains information such as DSMADHandle, the DPA Base, and DPA
+Length.
+
+This table is used by Linux in conjunction with the Device Scoped Latency and
+Bandwidth Information Structure (DSLBIS) to determine the performance
+attributes of the CXL device itself.
+
+Example ::
+
+ Structure Type : 00 [DSMAS]
+       Reserved : 00
+         Length : 0018              <- 24d, size of structure
+    DSMADHandle : 01
+          Flags : 00
+       Reserved : 0000
+       DPA Base : 0000000040000000  <- 1GiB base
+     DPA Length : 0000000080000000  <- 2GiB size
+
+
+==================================================================
+Device Scoped Latency and Bandwidth Information Structure (DSLBIS)
+==================================================================
+
+This table is used by Linux in conjunction with DSMAS to determine the
+performance attributes of a CXL device.  The DSLBIS contains latency
+and bandwidth information based on DSMADHandle matching.
+
+Example ::
+
+   Structure Type : 01 [DSLBIS]
+         Reserved : 00
+           Length : 18                     <- 24d, size of structure
+           Handle : 0001                   <- DSMAS handle
+            Flags : 00                     <- Matches flag field for HMAT SLLBIS
+        Data Type : 00                     <- Latency
+ Entry Basee Unit : 0000000000001000       <- Entry Base Unit field in HMAT SSLBIS
+            Entry : 010000000000           <- First byte used here, CXL LTC
+         Reserved : 0000
+
+   Structure Type : 01 [DSLBIS]
+         Reserved : 00
+           Length : 18                     <- 24d, size of structure
+           Handle : 0001                   <- DSMAS handle
+            Flags : 00                     <- Matches flag field for HMAT SLLBIS
+        Data Type : 03                     <- Bandwidth
+ Entry Basee Unit : 0000000000001000       <- Entry Base Unit field in HMAT SSLBIS
+            Entry : 020000000000           <- First byte used here, CXL BW
+         Reserved : 0000
+
+
+==================================================================
+Switch Scoped Latency and Bandwidth Information Structure (SSLBIS)
+==================================================================
+
+The SSLBIS contains information about the latency and bandwidth of a switch.
+
+The table is used by Linux to compute the performance coordinates of a CXL path
+from the device to the root port where a switch is part of the path.
+
+Example ::
+
+  Structure Type : 05 [SSLBIS]
+        Reserved : 00
+          Length : 20                           <- 32d, length of record, including SSLB entries
+       Data Type : 00                           <- Latency
+        Reserved : 000000
+ Entry Base Unit : 00000000000000001000         <- Matches Entry Base Unit in HMAT SSLBIS
+
+                                                <- SSLB Entry 0
+       Port X ID : 0100                         <- First port, 0100h represents an upstream port
+       Port Y ID : 0000                         <- Second port, downstream port 0
+         Latency : 0100                         <- Port latency
+        Reserved : 0000
+                                                <- SSLB Entry 1
+       Port X ID : 0100
+       Port Y ID : 0001
+         Latency : 0100
+        Reserved : 0000
+
+
+  Structure Type : 05 [SSLBIS]
+        Reserved : 00
+          Length : 18                           <- 24d, length of record, including SSLB entry
+       Data Type : 03                           <- Bandwidth
+        Reserved : 000000
+ Entry Base Unit : 00000000000000001000         <- Matches Entry Base Unit in HMAT SSLBIS
+
+                                                <- SSLB Entry 0
+       Port X ID : 0100                         <- First port, 0100h represents an upstream port
+       Port Y ID : FFFF                         <- Second port, FFFFh indicates any port
+       Bandwidth : 1200                         <- Port bandwidth
+        Reserved : 0000
+
+The CXL driver uses a combination of CDAT, HMAT, SRAT, and other data to
+generate "whole path performance" data for a CXL device.
diff --git a/Documentation/driver-api/cxl/platform/example-configs.rst b/Documentation/driver-api/cxl/platform/example-configs.rst
new file mode 100644
index 000000000000..90a10d7473c6
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/example-configs.rst
@@ -0,0 +1,13 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Example Platform Configurations
+###############################
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Contents
+
+   example-configurations/one-dev-per-hb.rst
+   example-configurations/multi-dev-per-hb.rst
+   example-configurations/hb-interleave.rst
+   example-configurations/flexible.rst
diff --git a/Documentation/driver-api/cxl/platform/example-configurations/flexible.rst b/Documentation/driver-api/cxl/platform/example-configurations/flexible.rst
new file mode 100644
index 000000000000..dab704b6fcc2
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/example-configurations/flexible.rst
@@ -0,0 +1,296 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+Flexible Presentation
+=====================
+This system has a single socket with two CXL host bridges. Each host bridge
+has two CXL memory expanders with a 4GB of memory (32GB total).
+
+On this system, the platform designer wanted to provide the user flexibility
+to configure the memory devices in various interleave or NUMA node
+configurations.  So they provided every combination.
+
+Things to note:
+
+* Cross-Bridge interleave is described in one CFMWS that covers all capacity.
+* One CFMWS is also described per-host bridge.
+* One CFMWS is also described per-device.
+* This SRAT describes one node for each of the above CFMWS.
+* The HMAT describes performance for each node in the SRAT.
+
+:doc:`CEDT <../acpi/cedt>`::
+
+            Subtable Type : 00 [CXL Host Bridge Structure]
+                 Reserved : 00
+                   Length : 0020
+   Associated host bridge : 00000007
+    Specification version : 00000001
+                 Reserved : 00000000
+            Register base : 0000010370400000
+          Register length : 0000000000010000
+
+            Subtable Type : 00 [CXL Host Bridge Structure]
+                 Reserved : 00
+                   Length : 0020
+   Associated host bridge : 00000006
+    Specification version : 00000001
+                 Reserved : 00000000
+            Register base : 0000010380800000
+          Register length : 0000000000010000
+
+            Subtable Type : 01 [CXL Fixed Memory Window Structure]
+                 Reserved : 00
+                   Length : 002C
+                 Reserved : 00000000
+      Window base address : 0000001000000000
+              Window size : 0000000400000000
+ Interleave Members (2^n) : 01
+    Interleave Arithmetic : 00
+                 Reserved : 0000
+              Granularity : 00000000
+             Restrictions : 0006
+                    QtgId : 0001
+             First Target : 00000007
+            Second Target : 00000006
+
+            Subtable Type : 01 [CXL Fixed Memory Window Structure]
+                 Reserved : 00
+                   Length : 002C
+                 Reserved : 00000000
+      Window base address : 0000002000000000
+              Window size : 0000000200000000
+ Interleave Members (2^n) : 00
+    Interleave Arithmetic : 00
+                 Reserved : 0000
+              Granularity : 00000000
+             Restrictions : 0006
+                    QtgId : 0001
+             First Target : 00000007
+
+            Subtable Type : 01 [CXL Fixed Memory Window Structure]
+                 Reserved : 00
+                   Length : 002C
+                 Reserved : 00000000
+      Window base address : 0000002200000000
+              Window size : 0000000200000000
+ Interleave Members (2^n) : 00
+    Interleave Arithmetic : 00
+                 Reserved : 0000
+              Granularity : 00000000
+             Restrictions : 0006
+                    QtgId : 0001
+             First Target : 00000006
+
+            Subtable Type : 01 [CXL Fixed Memory Window Structure]
+                 Reserved : 00
+                   Length : 002C
+                 Reserved : 00000000
+      Window base address : 0000003000000000
+              Window size : 0000000100000000
+ Interleave Members (2^n) : 00
+    Interleave Arithmetic : 00
+                 Reserved : 0000
+              Granularity : 00000000
+             Restrictions : 0006
+                    QtgId : 0001
+             First Target : 00000007
+
+            Subtable Type : 01 [CXL Fixed Memory Window Structure]
+                 Reserved : 00
+                   Length : 002C
+                 Reserved : 00000000
+      Window base address : 0000003100000000
+              Window size : 0000000100000000
+ Interleave Members (2^n) : 00
+    Interleave Arithmetic : 00
+                 Reserved : 0000
+              Granularity : 00000000
+             Restrictions : 0006
+                    QtgId : 0001
+             First Target : 00000007
+
+            Subtable Type : 01 [CXL Fixed Memory Window Structure]
+                 Reserved : 00
+                   Length : 002C
+                 Reserved : 00000000
+      Window base address : 0000003200000000
+              Window size : 0000000100000000
+ Interleave Members (2^n) : 00
+    Interleave Arithmetic : 00
+                 Reserved : 0000
+              Granularity : 00000000
+             Restrictions : 0006
+                    QtgId : 0001
+             First Target : 00000006
+
+            Subtable Type : 01 [CXL Fixed Memory Window Structure]
+                 Reserved : 00
+                   Length : 002C
+                 Reserved : 00000000
+      Window base address : 0000003300000000
+              Window size : 0000000100000000
+ Interleave Members (2^n) : 00
+    Interleave Arithmetic : 00
+                 Reserved : 0000
+              Granularity : 00000000
+             Restrictions : 0006
+                    QtgId : 0001
+             First Target : 00000006
+
+:doc:`SRAT <../acpi/srat>`::
+
+         Subtable Type : 01 [Memory Affinity]
+                Length : 28
+      Proximity Domain : 00000001
+             Reserved1 : 0000
+          Base Address : 0000001000000000
+        Address Length : 0000000400000000
+             Reserved2 : 00000000
+ Flags (decoded below) : 0000000B
+             Enabled : 1
+       Hot Pluggable : 1
+        Non-Volatile : 0
+
+         Subtable Type : 01 [Memory Affinity]
+                Length : 28
+      Proximity Domain : 00000002
+             Reserved1 : 0000
+          Base Address : 0000002000000000
+        Address Length : 0000000200000000
+             Reserved2 : 00000000
+ Flags (decoded below) : 0000000B
+             Enabled : 1
+       Hot Pluggable : 1
+        Non-Volatile : 0
+
+         Subtable Type : 01 [Memory Affinity]
+                Length : 28
+      Proximity Domain : 00000003
+             Reserved1 : 0000
+          Base Address : 0000002200000000
+        Address Length : 0000000200000000
+             Reserved2 : 00000000
+ Flags (decoded below) : 0000000B
+             Enabled : 1
+       Hot Pluggable : 1
+        Non-Volatile : 0
+
+         Subtable Type : 01 [Memory Affinity]
+                Length : 28
+      Proximity Domain : 00000004
+             Reserved1 : 0000
+          Base Address : 0000003000000000
+        Address Length : 0000000100000000
+             Reserved2 : 00000000
+ Flags (decoded below) : 0000000B
+             Enabled : 1
+       Hot Pluggable : 1
+        Non-Volatile : 0
+
+         Subtable Type : 01 [Memory Affinity]
+                Length : 28
+      Proximity Domain : 00000005
+             Reserved1 : 0000
+          Base Address : 0000003100000000
+        Address Length : 0000000100000000
+             Reserved2 : 00000000
+ Flags (decoded below) : 0000000B
+             Enabled : 1
+       Hot Pluggable : 1
+        Non-Volatile : 0
+
+         Subtable Type : 01 [Memory Affinity]
+                Length : 28
+      Proximity Domain : 00000006
+             Reserved1 : 0000
+          Base Address : 0000003200000000
+        Address Length : 0000000100000000
+             Reserved2 : 00000000
+ Flags (decoded below) : 0000000B
+             Enabled : 1
+       Hot Pluggable : 1
+        Non-Volatile : 0
+
+         Subtable Type : 01 [Memory Affinity]
+                Length : 28
+      Proximity Domain : 00000007
+             Reserved1 : 0000
+          Base Address : 0000003300000000
+        Address Length : 0000000100000000
+             Reserved2 : 00000000
+ Flags (decoded below) : 0000000B
+             Enabled : 1
+       Hot Pluggable : 1
+        Non-Volatile : 0
+
+:doc:`HMAT <../acpi/hmat>`::
+
+               Structure Type : 0001 [SLLBI]
+                    Data Type : 00   [Latency]
+ Target Proximity Domain List : 00000000
+ Target Proximity Domain List : 00000001
+ Target Proximity Domain List : 00000002
+ Target Proximity Domain List : 00000003
+ Target Proximity Domain List : 00000004
+ Target Proximity Domain List : 00000005
+ Target Proximity Domain List : 00000006
+ Target Proximity Domain List : 00000007
+                        Entry : 0080
+                        Entry : 0100
+                        Entry : 0100
+                        Entry : 0100
+                        Entry : 0100
+                        Entry : 0100
+                        Entry : 0100
+                        Entry : 0100
+
+               Structure Type : 0001 [SLLBI]
+                    Data Type : 03   [Bandwidth]
+ Target Proximity Domain List : 00000000
+ Target Proximity Domain List : 00000001
+ Target Proximity Domain List : 00000002
+ Target Proximity Domain List : 00000003
+ Target Proximity Domain List : 00000004
+ Target Proximity Domain List : 00000005
+ Target Proximity Domain List : 00000006
+ Target Proximity Domain List : 00000007
+                        Entry : 1200
+                        Entry : 0400
+                        Entry : 0200
+                        Entry : 0200
+                        Entry : 0100
+                        Entry : 0100
+                        Entry : 0100
+                        Entry : 0100
+
+:doc:`SLIT <../acpi/slit>`::
+
+     Signature : "SLIT"    [System Locality Information Table]
+    Localities : 0000000000000003
+  Locality   0 : 10 20 20 20 20 20 20 20
+  Locality   1 : FF 0A FF FF FF FF FF FF
+  Locality   2 : FF FF 0A FF FF FF FF FF
+  Locality   3 : FF FF FF 0A FF FF FF FF
+  Locality   4 : FF FF FF FF 0A FF FF FF
+  Locality   5 : FF FF FF FF FF 0A FF FF
+  Locality   6 : FF FF FF FF FF FF 0A FF
+  Locality   7 : FF FF FF FF FF FF FF 0A
+
+:doc:`DSDT <../acpi/dsdt>`::
+
+  Scope (_SB)
+  {
+    Device (S0D0)
+    {
+        Name (_HID, "ACPI0016" /* Compute Express Link Host Bridge */)  // _HID: Hardware ID
+        ...
+        Name (_UID, 0x07)  // _UID: Unique ID
+    }
+    ...
+    Device (S0D5)
+    {
+        Name (_HID, "ACPI0016" /* Compute Express Link Host Bridge */)  // _HID: Hardware ID
+        ...
+        Name (_UID, 0x06)  // _UID: Unique ID
+    }
+  }
diff --git a/Documentation/driver-api/cxl/platform/example-configurations/hb-interleave.rst b/Documentation/driver-api/cxl/platform/example-configurations/hb-interleave.rst
new file mode 100644
index 000000000000..c474dcf09fb0
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/example-configurations/hb-interleave.rst
@@ -0,0 +1,107 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+Cross-Host-Bridge Interleave
+============================
+This system has a single socket with two CXL host bridges. Each host bridge
+has a single CXL memory expander with a 4GB of memory.
+
+Things to note:
+
+* Cross-Bridge interleave is described.
+* The expanders are described by a single CFMWS.
+* This SRAT describes one node for both host bridges.
+* The HMAT describes a single node's performance.
+
+:doc:`CEDT <../acpi/cedt>`::
+
+            Subtable Type : 00 [CXL Host Bridge Structure]
+                 Reserved : 00
+                   Length : 0020
+   Associated host bridge : 00000007
+    Specification version : 00000001
+                 Reserved : 00000000
+            Register base : 0000010370400000
+          Register length : 0000000000010000
+
+            Subtable Type : 00 [CXL Host Bridge Structure]
+                 Reserved : 00
+                   Length : 0020
+   Associated host bridge : 00000006
+    Specification version : 00000001
+                 Reserved : 00000000
+            Register base : 0000010380800000
+          Register length : 0000000000010000
+
+            Subtable Type : 01 [CXL Fixed Memory Window Structure]
+                 Reserved : 00
+                   Length : 002C
+                 Reserved : 00000000
+      Window base address : 0000001000000000
+              Window size : 0000000200000000
+ Interleave Members (2^n) : 01
+    Interleave Arithmetic : 00
+                 Reserved : 0000
+              Granularity : 00000000
+             Restrictions : 0006
+                    QtgId : 0001
+             First Target : 00000007
+            Second Target : 00000006
+
+:doc:`SRAT <../acpi/srat>`::
+
+         Subtable Type : 01 [Memory Affinity]
+                Length : 28
+      Proximity Domain : 00000001
+             Reserved1 : 0000
+          Base Address : 0000001000000000
+        Address Length : 0000000200000000
+             Reserved2 : 00000000
+ Flags (decoded below) : 0000000B
+             Enabled : 1
+       Hot Pluggable : 1
+        Non-Volatile : 0
+
+:doc:`HMAT <../acpi/hmat>`::
+
+               Structure Type : 0001 [SLLBI]
+                    Data Type : 00   [Latency]
+ Target Proximity Domain List : 00000000
+ Target Proximity Domain List : 00000001
+ Target Proximity Domain List : 00000002
+                        Entry : 0080
+                        Entry : 0100
+
+               Structure Type : 0001 [SLLBI]
+                    Data Type : 03   [Bandwidth]
+ Target Proximity Domain List : 00000000
+ Target Proximity Domain List : 00000001
+ Target Proximity Domain List : 00000002
+                        Entry : 1200
+                        Entry : 0400
+
+:doc:`SLIT <../acpi/slit>`::
+
+     Signature : "SLIT"    [System Locality Information Table]
+    Localities : 0000000000000003
+  Locality   0 : 10 20
+  Locality   1 : FF 0A
+
+:doc:`DSDT <../acpi/dsdt>`::
+
+  Scope (_SB)
+  {
+    Device (S0D0)
+    {
+        Name (_HID, "ACPI0016" /* Compute Express Link Host Bridge */)  // _HID: Hardware ID
+        ...
+        Name (_UID, 0x07)  // _UID: Unique ID
+    }
+    ...
+    Device (S0D5)
+    {
+        Name (_HID, "ACPI0016" /* Compute Express Link Host Bridge */)  // _HID: Hardware ID
+        ...
+        Name (_UID, 0x06)  // _UID: Unique ID
+    }
+  }
diff --git a/Documentation/driver-api/cxl/platform/example-configurations/multi-dev-per-hb.rst b/Documentation/driver-api/cxl/platform/example-configurations/multi-dev-per-hb.rst
new file mode 100644
index 000000000000..a7854a79dbbd
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/example-configurations/multi-dev-per-hb.rst
@@ -0,0 +1,90 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+================================
+Multiple Devices per Host Bridge
+================================
+
+In this example system we will have a single socket and one CXL host bridge.
+There are two CXL memory expanders with 4GB attached to the host bridge.
+
+Things to note:
+
+* Intra-Bridge interleave is not described here.
+* The expanders are described by a single CEDT/CFMWS.
+* This CEDT/SRAT describes one node for both devices.
+* There is only one proximity domain the HMAT for both devices.
+
+:doc:`CEDT <../acpi/cedt>`::
+
+            Subtable Type : 00 [CXL Host Bridge Structure]
+                 Reserved : 00
+                   Length : 0020
+   Associated host bridge : 00000007
+    Specification version : 00000001
+                 Reserved : 00000000
+            Register base : 0000010370400000
+          Register length : 0000000000010000
+
+            Subtable Type : 01 [CXL Fixed Memory Window Structure]
+                 Reserved : 00
+                   Length : 002C
+                 Reserved : 00000000
+      Window base address : 0000001000000000
+              Window size : 0000000200000000
+ Interleave Members (2^n) : 00
+    Interleave Arithmetic : 00
+                 Reserved : 0000
+              Granularity : 00000000
+             Restrictions : 0006
+                    QtgId : 0001
+             First Target : 00000007
+
+:doc:`SRAT <../acpi/srat>`::
+
+         Subtable Type : 01 [Memory Affinity]
+                Length : 28
+      Proximity Domain : 00000001
+             Reserved1 : 0000
+          Base Address : 0000001000000000
+        Address Length : 0000000200000000
+             Reserved2 : 00000000
+ Flags (decoded below) : 0000000B
+             Enabled : 1
+       Hot Pluggable : 1
+        Non-Volatile : 0
+
+:doc:`HMAT <../acpi/hmat>`::
+
+               Structure Type : 0001 [SLLBI]
+                    Data Type : 00   [Latency]
+ Target Proximity Domain List : 00000000
+ Target Proximity Domain List : 00000001
+                        Entry : 0080
+                        Entry : 0100
+
+               Structure Type : 0001 [SLLBI]
+                    Data Type : 03   [Bandwidth]
+ Target Proximity Domain List : 00000000
+ Target Proximity Domain List : 00000001
+                        Entry : 1200
+                        Entry : 0200
+
+:doc:`SLIT <../acpi/slit>`::
+
+     Signature : "SLIT"    [System Locality Information Table]
+    Localities : 0000000000000003
+  Locality   0 : 10 20
+  Locality   1 : FF 0A
+
+:doc:`DSDT <../acpi/dsdt>`::
+
+  Scope (_SB)
+  {
+    Device (S0D0)
+    {
+        Name (_HID, "ACPI0016" /* Compute Express Link Host Bridge */)  // _HID: Hardware ID
+        ...
+        Name (_UID, 0x07)  // _UID: Unique ID
+    }
+    ...
+  }
diff --git a/Documentation/driver-api/cxl/platform/example-configurations/one-dev-per-hb.rst b/Documentation/driver-api/cxl/platform/example-configurations/one-dev-per-hb.rst
new file mode 100644
index 000000000000..aebda0eb3e17
--- /dev/null
+++ b/Documentation/driver-api/cxl/platform/example-configurations/one-dev-per-hb.rst
@@ -0,0 +1,136 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==========================
+One Device per Host Bridge
+==========================
+
+This system has a single socket with two CXL host bridges. Each host bridge
+has a single CXL memory expander with a 4GB of memory.
+
+Things to note:
+
+* Cross-Bridge interleave is not being used.
+* The expanders are in two separate but adjascent memory regions.
+* This CEDT/SRAT describes one node per device
+* The expanders have the same performance and will be in the same memory tier.
+
+:doc:`CEDT <../acpi/cedt>`::
+
+            Subtable Type : 00 [CXL Host Bridge Structure]
+                 Reserved : 00
+                   Length : 0020
+   Associated host bridge : 00000007
+    Specification version : 00000001
+                 Reserved : 00000000
+            Register base : 0000010370400000
+          Register length : 0000000000010000
+
+            Subtable Type : 00 [CXL Host Bridge Structure]
+                 Reserved : 00
+                   Length : 0020
+   Associated host bridge : 00000006
+    Specification version : 00000001
+                 Reserved : 00000000
+            Register base : 0000010380800000
+          Register length : 0000000000010000
+
+            Subtable Type : 01 [CXL Fixed Memory Window Structure]
+                 Reserved : 00
+                   Length : 002C
+                 Reserved : 00000000
+      Window base address : 0000001000000000
+              Window size : 0000000100000000
+ Interleave Members (2^n) : 00
+    Interleave Arithmetic : 00
+                 Reserved : 0000
+              Granularity : 00000000
+             Restrictions : 0006
+                    QtgId : 0001
+             First Target : 00000007
+
+            Subtable Type : 01 [CXL Fixed Memory Window Structure]
+                 Reserved : 00
+                   Length : 002C
+                 Reserved : 00000000
+      Window base address : 0000001100000000
+              Window size : 0000000100000000
+ Interleave Members (2^n) : 00
+    Interleave Arithmetic : 00
+                 Reserved : 0000
+              Granularity : 00000000
+             Restrictions : 0006
+                    QtgId : 0001
+             First Target : 00000006
+
+:doc:`SRAT <../acpi/srat>`::
+
+         Subtable Type : 01 [Memory Affinity]
+                Length : 28
+      Proximity Domain : 00000001
+             Reserved1 : 0000
+          Base Address : 0000001000000000
+        Address Length : 0000000100000000
+             Reserved2 : 00000000
+ Flags (decoded below) : 0000000B
+             Enabled : 1
+       Hot Pluggable : 1
+        Non-Volatile : 0
+
+         Subtable Type : 01 [Memory Affinity]
+                Length : 28
+      Proximity Domain : 00000002
+             Reserved1 : 0000
+          Base Address : 0000001100000000
+        Address Length : 0000000100000000
+             Reserved2 : 00000000
+ Flags (decoded below) : 0000000B
+             Enabled : 1
+       Hot Pluggable : 1
+        Non-Volatile : 0
+
+:doc:`HMAT <../acpi/hmat>`::
+
+               Structure Type : 0001 [SLLBI]
+                    Data Type : 00   [Latency]
+ Target Proximity Domain List : 00000000
+ Target Proximity Domain List : 00000001
+ Target Proximity Domain List : 00000002
+                        Entry : 0080
+                        Entry : 0100
+                        Entry : 0100
+
+               Structure Type : 0001 [SLLBI]
+                    Data Type : 03   [Bandwidth]
+ Target Proximity Domain List : 00000000
+ Target Proximity Domain List : 00000001
+ Target Proximity Domain List : 00000002
+                        Entry : 1200
+                        Entry : 0200
+                        Entry : 0200
+
+:doc:`SLIT <../acpi/slit>`::
+
+     Signature : "SLIT"    [System Locality Information Table]
+    Localities : 0000000000000003
+  Locality   0 : 10 20 20
+  Locality   1 : FF 0A FF
+  Locality   2 : FF FF 0A
+
+:doc:`DSDT <../acpi/dsdt>`::
+
+  Scope (_SB)
+  {
+    Device (S0D0)
+    {
+        Name (_HID, "ACPI0016" /* Compute Express Link Host Bridge */)  // _HID: Hardware ID
+        ...
+        Name (_UID, 0x07)  // _UID: Unique ID
+    }
+    ...
+    Device (S0D5)
+    {
+        Name (_HID, "ACPI0016" /* Compute Express Link Host Bridge */)  // _HID: Hardware ID
+        ...
+        Name (_UID, 0x06)  // _UID: Unique ID
+    }
+  }
diff --git a/Documentation/driver-api/cxl/memory-devices.rst b/Documentation/driver-api/cxl/theory-of-operation.rst
index d732c42526df..40793dad3630 100644
--- a/Documentation/driver-api/cxl/memory-devices.rst
+++ b/Documentation/driver-api/cxl/theory-of-operation.rst
@@ -1,9 +1,9 @@
 .. SPDX-License-Identifier: GPL-2.0
 .. include:: <isonum.txt>
 
-===================================
-Compute Express Link Memory Devices
-===================================
+===============================================
+Compute Express Link Driver Theory of Operation
+===============================================
 
 A Compute Express Link Memory Device is a CXL component that implements the
 CXL.mem protocol. It contains some amount of volatile memory, persistent memory,
@@ -14,8 +14,8 @@ that optionally define a device's contribution to an interleaved address
 range across multiple devices underneath a host-bridge or interleaved
 across host-bridges.
 
-CXL Bus: Theory of Operation
-============================
+The CXL Bus
+===========
 Similar to how a RAID driver takes disk objects and assembles them into a new
 logical device, the CXL subsystem is tasked to take PCIe and ACPI objects and
 assemble them into a CXL.mem decode topology. The need for runtime configuration
@@ -347,6 +347,9 @@ CXL Core
 .. kernel-doc:: drivers/cxl/cxl.h
    :internal:
 
+.. kernel-doc:: drivers/cxl/acpi.c
+   :identifiers: add_cxl_resources
+
 .. kernel-doc:: drivers/cxl/core/hdm.c
    :doc: cxl core hdm
 
@@ -371,12 +374,26 @@ CXL Core
 .. kernel-doc:: drivers/cxl/core/pmem.c
    :doc: cxl pmem
 
+.. kernel-doc:: drivers/cxl/core/pmem.c
+   :identifiers:
+
 .. kernel-doc:: drivers/cxl/core/regs.c
    :doc: cxl registers
 
+.. kernel-doc:: drivers/cxl/core/regs.c
+   :identifiers:
+
 .. kernel-doc:: drivers/cxl/core/mbox.c
    :doc: cxl mbox
 
+.. kernel-doc:: drivers/cxl/core/mbox.c
+   :identifiers:
+
+.. kernel-doc:: drivers/cxl/core/features.c
+   :doc: cxl features
+
+See :c:func:`devm_cxl_setup_features` for API details.
+
 CXL Regions
 -----------
 .. kernel-doc:: drivers/cxl/core/region.c
diff --git a/Documentation/driver-api/dmaengine/provider.rst b/Documentation/driver-api/dmaengine/provider.rst
index 8f0910668ca3..1594598b3317 100644
--- a/Documentation/driver-api/dmaengine/provider.rst
+++ b/Documentation/driver-api/dmaengine/provider.rst
@@ -172,8 +172,8 @@ Currently, the types available are:
   - It's usually used for copying pixel data between host memory and
     memory-mapped GPU device memory, such as found on modern PCI video graphics
     cards. The most immediate example is the OpenGL API function
-    ``glReadPielx()``, which might require a verbatim copy of a huge framebuffer
-    from local device memory onto host memory.
+    ``glReadPixels()``, which might require a verbatim copy of a huge
+    framebuffer from local device memory onto host memory.
 
 - DMA_XOR
 
diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index d75728eb05f8..3d56f94ac2ee 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -391,12 +391,11 @@ PCI
   devm_pci_remap_cfgspace()	: ioremap PCI configuration space
   devm_pci_remap_cfg_resource()	: ioremap PCI configuration space resource
 
-  pcim_enable_device()		: after success, some PCI ops become managed
+  pcim_enable_device()		: after success, the PCI device gets disabled automatically on driver detach
   pcim_iomap()			: do iomap() on a single BAR
   pcim_iomap_regions()		: do request_region() and iomap() on multiple BARs
   pcim_iomap_table()		: array of mapped addresses indexed by BAR
   pcim_iounmap()		: do iounmap() on a single BAR
-  pcim_iounmap_regions()	: do iounmap() and release_region() on multiple BARs
   pcim_pin_device()		: keep PCI device enabled after release
   pcim_set_mwi()		: enable Memory-Write-Invalidate PCI transaction
 
diff --git a/Documentation/edac/memory_repair.rst b/Documentation/edac/memory_repair.rst
index 52162a422864..5f8da7c9b186 100644
--- a/Documentation/edac/memory_repair.rst
+++ b/Documentation/edac/memory_repair.rst
@@ -119,3 +119,34 @@ sysfs
 
 Sysfs files are documented in
 `Documentation/ABI/testing/sysfs-edac-memory-repair`.
+
+Examples
+--------
+
+The memory repair usage takes the form shown in this example:
+
+1. CXL memory sparing
+
+Memory sparing is defined as a repair function that replaces a portion of
+memory with a portion of functional memory at that same DPA. The subclass
+for this operation, cacheline/row/bank/rank sparing, vary in terms of the
+scope of the sparing being performed.
+
+Memory sparing maintenance operations may be supported by CXL devices that
+implement CXL.mem protocol. A sparing maintenance operation requests the
+CXL device to perform a repair operation on its media. For example, a CXL
+device with DRAM components that support memory sparing features may
+implement sparing maintenance operations.
+
+2. CXL memory Soft Post Package Repair (sPPR)
+
+Post Package Repair (PPR) maintenance operations may be supported by CXL
+devices that implement CXL.mem protocol. A PPR maintenance operation
+requests the CXL device to perform a repair operation on its media.
+For example, a CXL device with DRAM components that support PPR features
+may implement PPR Maintenance operations. Soft PPR (sPPR) is a temporary
+row repair. Soft PPR may be faster, but the repair is lost with a power
+cycle.
+
+Sysfs files for memory repair are documented in
+`Documentation/ABI/testing/sysfs-edac-memory-repair`
diff --git a/Documentation/edac/scrub.rst b/Documentation/edac/scrub.rst
index daab929cdba1..2cfa74fa1ffd 100644
--- a/Documentation/edac/scrub.rst
+++ b/Documentation/edac/scrub.rst
@@ -264,3 +264,79 @@ Sysfs files are documented in
 `Documentation/ABI/testing/sysfs-edac-scrub`
 
 `Documentation/ABI/testing/sysfs-edac-ecs`
+
+Examples
+--------
+
+The usage takes the form shown in these examples:
+
+1. CXL memory Patrol Scrub
+
+The following are the use cases identified why we might increase the scrub rate.
+
+- Scrubbing is needed at device granularity because a device is showing
+  unexpectedly high errors.
+
+- Scrubbing may apply to memory that isn't online at all yet. Likely this
+  is a system wide default setting on boot.
+
+- Scrubbing at a higher rate because the monitor software has determined that
+  more reliability is necessary for a particular data set. This is called
+  Differentiated Reliability.
+
+1.1. Device based scrubbing
+
+CXL memory is exposed to memory management subsystem and ultimately userspace
+via CXL devices. Device-based scrubbing is used for the first use case
+described in "Section 1 CXL Memory Patrol Scrub".
+
+When combining control via the device interfaces and region interfaces,
+"see Section 1.2 Region based scrubbing".
+
+Sysfs files for scrubbing are documented in
+`Documentation/ABI/testing/sysfs-edac-scrub`
+
+1.2. Region based scrubbing
+
+CXL memory is exposed to memory management subsystem and ultimately userspace
+via CXL regions. CXL Regions represent mapped memory capacity in system
+physical address space. These can incorporate one or more parts of multiple CXL
+memory devices with traffic interleaved across them. The user may want to control
+the scrub rate via this more abstract region instead of having to figure out the
+constituent devices and program them separately. The scrub rate for each device
+covers the whole device. Thus if multiple regions use parts of that device then
+requests for scrubbing of other regions may result in a higher scrub rate than
+requested for this specific region.
+
+Region-based scrubbing is used for the third use case described in
+"Section 1 CXL Memory Patrol Scrub".
+
+Userspace must follow below set of rules on how to set the scrub rates for any
+mixture of requirements.
+
+1. Taking each region in turn from lowest desired scrub rate to highest and set
+   their scrub rates. Later regions may override the scrub rate on individual
+   devices (and hence potentially whole regions).
+
+2. Take each device for which enhanced scrubbing is required (higher rate) and
+   set those scrub rates. This will override the scrub rates of individual devices,
+   setting them to the maximum rate required for any of the regions they help back,
+   unless a specific rate is already defined.
+
+Sysfs files for scrubbing are documented in
+`Documentation/ABI/testing/sysfs-edac-scrub`
+
+2. CXL memory Error Check Scrub (ECS)
+
+The Error Check Scrub (ECS) feature enables a memory device to perform error
+checking and correction (ECC) and count single-bit errors. The associated
+memory controller sets the ECS mode with a trigger sent to the memory
+device. CXL ECS control allows the host, thus the userspace, to change the
+attributes for error count mode, threshold number of errors per segment
+(indicating how many segments have at least that number of errors) for
+reporting errors, and reset the ECS counter. Thus the responsibility for
+initiating Error Check Scrub on a memory device may lie with the memory
+controller or platform when unexpectedly high error rates are detected.
+
+Sysfs files for scrubbing are documented in
+`Documentation/ABI/testing/sysfs-edac-ecs`
diff --git a/Documentation/hwmon/acpi_power_meter.rst b/Documentation/hwmon/acpi_power_meter.rst
index 8628c1161015..a91403a2a26f 100644
--- a/Documentation/hwmon/acpi_power_meter.rst
+++ b/Documentation/hwmon/acpi_power_meter.rst
@@ -37,9 +37,16 @@ arbitrary strings that ACPI provides with the meter.  The measures/ directory
 contains symlinks to the devices that this meter measures.
 
 Some computers have the ability to enforce a power cap in hardware.  If this is
-the case, the `power[1-*]_cap` and related sysfs files will appear.  When the
-average power consumption exceeds the cap, an ACPI event will be broadcast on
-the netlink event socket and a poll notification will be sent to the
+the case, the `power[1-*]_cap` and related sysfs files will appear.
+For information on enabling the power cap feature, refer to the description
+of the "force_on_cap" option in the "Module Parameters" chapter.
+To use the power cap feature properly, you need to set appropriate value
+(in microWatts) to the `power[1-*]_cap` sysfs files.
+The value must be within the range between the minimum value at `power[1-]_cap_min`
+and the maximum value at `power[1-]_cap_max (both in microWatts)`.
+
+When the average power consumption exceeds the cap, an ACPI event will be
+broadcast on the netlink event socket and a poll notification will be sent to the
 appropriate `power[1-*]_alarm` file to indicate that capping has begun, and the
 hardware has taken action to reduce power consumption.  Most likely this will
 result in reduced performance.
@@ -52,3 +59,19 @@ follows:
 `power[1-*]_cap` will be notified if the firmware changes the power cap.
 `power[1-*]_interval` will be notified if the firmware changes the averaging
 interval.
+
+Module Parameters
+-----------------
+
+* force_cap_on: bool
+                        Forcefully enable the power capping feature to specify
+                        the upper limit of the system's power consumption.
+
+                        By default, the driver's power capping feature is only
+                        enabled on IBM products.
+                        Therefore, on other systems that support power capping,
+                        you will need to use the option to enable it.
+
+                        Note: power capping is potentially unsafe feature.
+                        Please check the platform specifications to make sure
+                        that capping is supported before using this option.
diff --git a/Documentation/hwmon/asus_ec_sensors.rst b/Documentation/hwmon/asus_ec_sensors.rst
index d2be9db29614..816d1f9947ea 100644
--- a/Documentation/hwmon/asus_ec_sensors.rst
+++ b/Documentation/hwmon/asus_ec_sensors.rst
@@ -4,6 +4,7 @@ Kernel driver asus_ec_sensors
 =================================
 
 Supported boards:
+ * MAXIMUS VI HERO
  * PRIME X470-PRO
  * PRIME X570-PRO
  * PRIME X670E-PRO WIFI
@@ -20,6 +21,7 @@ Supported boards:
  * ROG CROSSHAIR X670E GENE
  * ROG MAXIMUS XI HERO
  * ROG MAXIMUS XI HERO (WI-FI)
+ * ROG MAXIMUS Z690 FORMULA
  * ROG STRIX B550-E GAMING
  * ROG STRIX B550-I GAMING
  * ROG STRIX X570-E GAMING
diff --git a/Documentation/hwmon/ina238.rst b/Documentation/hwmon/ina238.rst
index d9f479984420..d1b93cf8627f 100644
--- a/Documentation/hwmon/ina238.rst
+++ b/Documentation/hwmon/ina238.rst
@@ -14,6 +14,12 @@ Supported chips:
     Datasheet:
 	https://www.ti.com/lit/gpn/ina238
 
+  * Silergy SQ52206
+
+    Prefix: 'SQ52206'
+
+    Addresses: I2C 0x40 - 0x4f
+
 Author: Nathan Rossi <nathan.rossi@digi.com>
 
 Description
@@ -54,3 +60,12 @@ temp1_input		Die temperature measurement (mC)
 temp1_max		Maximum die temperature threshold (mC)
 temp1_max_alarm		Maximum die temperature alarm
 ======================= =======================================================
+
+Additional sysfs entries for sq52206
+------------------------------------
+
+======================= =======================================================
+energy1_input		Energy measurement (mJ)
+
+power1_input_highest	Peak Power (uW)
+======================= =======================================================
diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst
index ffe1a756a4f9..b45bfb4ebf30 100644
--- a/Documentation/hwmon/index.rst
+++ b/Documentation/hwmon/index.rst
@@ -106,6 +106,8 @@ Hardware Monitoring Kernel Drivers
    jc42
    k10temp
    k8temp
+   kbatt
+   kfan
    lan966x
    lineage-pem
    lm25066
@@ -125,6 +127,7 @@ Hardware Monitoring Kernel Drivers
    lm95234
    lm95245
    lochnagar
+   lt3074
    lt7182s
    ltc2992
    ltc2945
@@ -161,6 +164,7 @@ Hardware Monitoring Kernel Drivers
    max6639
    max6650
    max6697
+   max77705
    max8688
    mc13783-adc
    mc34vr500
diff --git a/Documentation/hwmon/kbatt.rst b/Documentation/hwmon/kbatt.rst
new file mode 100644
index 000000000000..b72718c5ede3
--- /dev/null
+++ b/Documentation/hwmon/kbatt.rst
@@ -0,0 +1,60 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Kernel driver kbatt
+===================
+
+Supported chips:
+
+  * KEBA battery monitoring controller (IP core in FPGA)
+
+    Prefix: 'kbatt'
+
+Authors:
+
+	Gerhard Engleder <eg@keba.com>
+	Petar Bojanic <boja@keba.com>
+
+Description
+-----------
+
+The KEBA battery monitoring controller is an IP core for FPGAs, which
+monitors the health of a coin cell battery. The coin cell battery is
+typically used to supply the RTC during power off to keep the current
+time. E.g., the CP500 FPGA includes this IP core to monitor the coin cell
+battery of PLCs and the corresponding cp500 driver creates an auxiliary
+device for the kbatt driver.
+
+This driver provides information about the coin cell battery health to
+user space. Actually the user space shall be informed that the coin cell
+battery is nearly empty and needs to be replaced.
+
+The coin cell battery must be tested actively to get to know if its nearly
+empty or not. Therefore, a load is put on the coin cell battery and the
+resulting voltage is evaluated. This evaluation is done by some hard wired
+analog logic, which compares the voltage to a defined limit. If the
+voltage is above the limit, then the coin cell battery is assumed to be
+ok. If the voltage is below the limit, then the coin cell battery is
+nearly empty (or broken, removed, ...) and shall be replaced by a new one.
+The KEBA battery monitoring controller allows to start the test of the
+coin cell battery and to get the result if the voltage is above or below
+the limit. The actual voltage is not available. Only the information if
+the voltage is below a limit is available.
+
+The test load, which is put on the coin cell battery for the health check,
+is similar to the load during power off. Therefore, the lifetime of the
+coin cell battery is reduced directly by the duration of each test. To
+limit the negative impact to the lifetime the test is limited to at most
+once every 10 seconds. The test load is put on the coin cell battery for
+100ms. Thus, in worst case the coin cell battery lifetime is reduced by
+1% of the uptime or 3.65 days per year. As the coin cell battery lasts
+multiple years, this lifetime reduction negligible.
+
+This driver only provides a single alarm attribute, which is raised when
+the coin cell battery is nearly empty.
+
+====================== ==== ===================================================
+Attribute              R/W  Contents
+====================== ==== ===================================================
+in0_min_alarm          R    voltage of coin cell battery under load is below
+                            limit
+====================== ==== ===================================================
diff --git a/Documentation/hwmon/kfan.rst b/Documentation/hwmon/kfan.rst
new file mode 100644
index 000000000000..ce02dddfb4b8
--- /dev/null
+++ b/Documentation/hwmon/kfan.rst
@@ -0,0 +1,39 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Kernel driver kfan
+==================
+
+Supported chips:
+
+  * KEBA fan controller (IP core in FPGA)
+
+    Prefix: 'kfan'
+
+Authors:
+
+	Gerhard Engleder <eg@keba.com>
+	Petar Bojanic <boja@keba.com>
+
+Description
+-----------
+
+The KEBA fan controller is an IP core for FPGAs, which monitors the health
+and controls the speed of a fan. The fan is typically used to cool the CPU
+and the whole device. E.g., the CP500 FPGA includes this IP core to monitor
+and control the fan of PLCs and the corresponding cp500 driver creates an
+auxiliary device for the kfan driver.
+
+This driver provides information about the fan health to user space.
+The user space shall be informed if the fan is removed or blocked.
+Additionally, the speed in RPM is reported for fans with tacho signal.
+
+For fan control PWM is supported. For PWM 255 equals 100%. None-regulable
+fans can be turned on with PWM 255 and turned off with PWM 0.
+
+====================== ==== ===================================================
+Attribute              R/W  Contents
+====================== ==== ===================================================
+fan1_fault             R    Fan fault
+fan1_input             R    Fan tachometer input (in RPM)
+pwm1                   RW   Fan target duty cycle (0..255)
+====================== ==== ===================================================
diff --git a/Documentation/hwmon/lt3074.rst b/Documentation/hwmon/lt3074.rst
new file mode 100644
index 000000000000..234f369153cf
--- /dev/null
+++ b/Documentation/hwmon/lt3074.rst
@@ -0,0 +1,72 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Kernel driver lt3074
+====================
+
+Supported chips:
+
+  * Analog Devices LT3074
+
+    Prefix: 'lt3074'
+
+    Addresses scanned: -
+
+    Datasheet: https://www.analog.com/en/products/lt3074.html
+
+Authors: Cedric Encarnacion <cedricjustine.encarnacion@analog.com>
+
+
+Description
+-----------
+
+This driver supports hardware monitoring for Analog Devices LT3074 Linear
+Regulator with PMBus interface.
+
+The LT3074 is a low voltage, ultra-low noise and ultra-fast transient
+response linear regulator with PMBus serial interface. PMBus telemetry
+feature provides information regarding the output voltage and current,
+input voltage, bias voltage and die temperature.
+
+The driver is a client driver to the core PMBus driver. Please see
+Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
+
+Usage Notes
+-----------
+
+This driver does not auto-detect devices. You will have to instantiate
+the devices explicitly. Please see Documentation/i2c/instantiating-devices.rst
+for details.
+
+Platform data support
+---------------------
+
+The driver supports standard PMBus driver platform data.
+
+Sysfs entries
+-------------
+
+======================= =======================================================
+in1_label		"vin"
+in1_input		Measured input voltage
+in1_max			Input overvoltage warning limit
+in1_max_alarm		Input overvoltage warning status
+in1_min			Input undervoltage warning limit
+in1_min_alarm		Input undervoltage warning status
+in2_label		"vmon"
+in2_input		Measured bias voltage
+in2_max			Bias overvoltage warning limit
+in2_min			Bias undervoltage warning limit
+in3_label		"vout1"
+in3_input		Measured output voltage
+in3_max			Output overvoltage warning limit
+in3_max_alarm		Output overvoltage warning status
+in3_min			Output undervoltage warning limit
+in3_min_alarm		Output undervoltage warning status
+curr1_label		"iout1"
+curr1_input		Measured output current.
+curr1_crit		Output overcurrent fault limit
+curr1_crit_alarm	Output overcurrent fault status
+temp1_input		Measured temperature
+temp1_max		Maximum temperature limit
+temp1_max_alarm		Overtemperature warning status
+======================= =======================================================
diff --git a/Documentation/hwmon/max34440.rst b/Documentation/hwmon/max34440.rst
index 162d289f0814..8591a7152ce5 100644
--- a/Documentation/hwmon/max34440.rst
+++ b/Documentation/hwmon/max34440.rst
@@ -3,6 +3,14 @@ Kernel driver max34440
 
 Supported chips:
 
+  * ADI ADPM12160
+
+    Prefixes: 'adpm12160'
+
+    Addresses scanned: -
+
+    Datasheet: -
+
   * Maxim MAX34440
 
     Prefixes: 'max34440'
@@ -67,13 +75,14 @@ Author: Guenter Roeck <linux@roeck-us.net>
 Description
 -----------
 
-This driver supports hardware monitoring for Maxim MAX34440 PMBus 6-Channel
-Power-Supply Manager, MAX34441 PMBus 5-Channel Power-Supply Manager
-and Intelligent Fan Controller, and MAX34446 PMBus Power-Supply Data Logger.
-It also supports the MAX34451, MAX34460, and MAX34461 PMBus Voltage Monitor &
-Sequencers. The MAX34451 supports monitoring voltage or current of 12 channels
-based on GIN pins. The MAX34460 supports 12 voltage channels, and the MAX34461
-supports 16 voltage channels.
+This driver supports multiple devices: hardware monitoring for Maxim MAX34440
+PMBus 6-Channel Power-Supply Manager, MAX34441 PMBus 5-Channel Power-Supply
+Manager and Intelligent Fan Controller, and MAX34446 PMBus Power-Supply Data
+Logger; PMBus Voltage Monitor and Sequencers for MAX34451, MAX34460, and
+MAX34461; PMBus DC/DC Power Module ADPM12160. The MAX34451 supports monitoring
+voltage or current of 12 channels based on GIN pins. The MAX34460 supports 12
+voltage channels, and the MAX34461 supports 16 voltage channels. The ADPM1260
+also monitors both input and output of voltage and current.
 
 The driver is a client driver to the core PMBus driver. Please see
 Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
@@ -128,7 +137,10 @@ in[1-6]_highest		Historical maximum voltage.
 in[1-6]_reset_history	Write any value to reset history.
 ======================= =======================================================
 
-.. note:: MAX34446 only supports in[1-4].
+.. note::
+
+    - MAX34446 only supports in[1-4].
+    - ADPM12160 only supports in[1-2]. Label is "vin1" and "vout1" respectively.
 
 Curr
 ~~~~
@@ -150,6 +162,7 @@ curr[1-6]_reset_history	Write any value to reset history.
 
     - in6 and curr6 attributes only exist for MAX34440.
     - MAX34446 only supports curr[1-4].
+    - For ADPM12160, curr[1] is "iin1" and curr[2-6] are "iout[1-5].
 
 Power
 ~~~~~
@@ -185,6 +198,7 @@ temp[1-8]_reset_history	Write any value to reset history.
 .. note::
    - temp7 and temp8 attributes only exist for MAX34440.
    - MAX34446 only supports temp[1-3].
+   - ADPM12160 only supports temp[1].
 
 
 .. note::
diff --git a/Documentation/hwmon/max77705.rst b/Documentation/hwmon/max77705.rst
new file mode 100644
index 000000000000..4a7680a340e1
--- /dev/null
+++ b/Documentation/hwmon/max77705.rst
@@ -0,0 +1,39 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Kernel driver max77705
+======================
+
+Supported chips:
+
+  * Maxim Integrated MAX77705
+
+    Prefix: 'max77705'
+
+    Addresses scanned: none
+
+    Datasheet: Not available
+
+Authors:
+      - Dzmitry Sankouski <dsankouski@gmail.com>
+
+Description
+-----------
+
+The MAX77705 PMIC provides current and voltage measurements besides fuelgauge:
+- chip input current
+- system bus current and voltage
+- VBYP voltage
+
+Sysfs Attributes
+----------------
+
+================= ========================================
+in1_label         "vbyp"
+in1_input         Measured chip vbyp voltage
+in2_label         "vsys"
+in2_input         Measured chip system bus voltage
+curr1_label       "iin"
+curr1_input       Measured chip input current.
+curr2_label       "isys"
+curr2_input       Measured chip system bus current.
+================= ========================================
diff --git a/Documentation/hwmon/mpq8785.rst b/Documentation/hwmon/mpq8785.rst
index bf8176b87086..198d5dfd7c30 100644
--- a/Documentation/hwmon/mpq8785.rst
+++ b/Documentation/hwmon/mpq8785.rst
@@ -5,6 +5,8 @@ Kernel driver mpq8785
 
 Supported chips:
 
+  * MPS MPM3695 family
+  * MPS MPM82504
   * MPS MPQ8785
 
     Prefix: 'mpq8785'
@@ -14,6 +16,22 @@ Author: Charles Hsu <ythsu0511@gmail.com>
 Description
 -----------
 
+The MPM3695 family is a scalable, ultra-thin, fully integrated power module with
+a PMBus interface. It offers a complete power solution that achieves up to
+10A (-10 variant), 20A (-25 variant), 25A (-20 variant), 100A (-100 variant)
+of output current with excellent load and line regulation across a wide input
+voltage range. It operates at high efficiency over a wide load range, and can
+be parallled to deliver higher current. Variants -10,-20 and -100 have different
+voltage scale configuration register range (10 bits) than -25 version (11 bits).
+
+The MPM82504 is a quad 25A, scalable, fully integrated power module with a PMBus
+interface. The device offers a complete power solution that achieves up to 25A
+per output channel. The MPM82504 has four output channels that can be paralleled
+to provide 50A, 75A, or 100A of output current for flexible configurations.
+The device can also operate in parallel with the MPM3695-100 and additional
+MPM82504 devices to provide a higher output current. The MPM82504 operates
+at high efficiency across a wide load range.
+
 The MPQ8785 is a fully integrated, PMBus-compatible, high-frequency, synchronous
 buck converter. The MPQ8785 offers a very compact solution that achieves up to
 40A output current per phase, with excellent load and line regulation over a
@@ -23,19 +41,16 @@ output current load range.
 The PMBus interface provides converter configurations and key parameters
 monitoring.
 
-The MPQ8785 adopts MPS's proprietary multi-phase digital constant-on-time (MCOT)
+The devices adopts MPS's proprietary multi-phase digital constant-on-time (MCOT)
 control, which provides fast transient response and eases loop stabilization.
-The MCOT scheme also allows multiple MPQ8785 devices to be connected in parallel
-with excellent current sharing and phase interleaving for high-current
+The MCOT scheme also allows multiple devices or channels to be connected in
+parallel with excellent current sharing and phase interleaving for high-current
 applications.
 
 Fully integrated protection features include over-current protection (OCP),
 over-voltage protection (OVP), under-voltage protection (UVP), and
 over-temperature protection (OTP).
 
-The MPQ8785 requires a minimal number of readily available, standard external
-components, and is available in a TLGA (5mmx6mm) package.
-
 Device compliant with:
 
 - PMBus rev 1.3 interface.
diff --git a/Documentation/leds/index.rst b/Documentation/leds/index.rst
index 0ab0a2128a11..76fae171039c 100644
--- a/Documentation/leds/index.rst
+++ b/Documentation/leds/index.rst
@@ -28,5 +28,5 @@ LEDs
    leds-mlxcpld
    leds-mt6370-rgb
    leds-sc27xx
-   leds-st1202.rst
+   leds-st1202
    leds-qcom-lpg
diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml
index 5ec3d35b7a38..b41b31eebcae 100644
--- a/Documentation/netlink/specs/rt-link.yaml
+++ b/Documentation/netlink/specs/rt-link.yaml
@@ -1685,15 +1685,19 @@ attribute-sets:
       -
         name: iflags
         type: u16
+        byte-order: big-endian
       -
         name: oflags
         type: u16
+        byte-order: big-endian
       -
         name: ikey
         type: u32
+        byte-order: big-endian
       -
         name: okey
         type: u32
+        byte-order: big-endian
       -
         name: local
         type: binary
@@ -1713,10 +1717,11 @@ attribute-sets:
         type: u8
       -
         name: encap-limit
-        type: u32
+        type: u8
       -
         name: flowinfo
         type: u32
+        byte-order: big-endian
       -
         name: flags
         type: u32
@@ -1729,9 +1734,11 @@ attribute-sets:
       -
         name: encap-sport
         type: u16
+        byte-order: big-endian
       -
         name: encap-dport
         type: u16
+        byte-order: big-endian
       -
         name: collect-metadata
         type: flag
@@ -1754,6 +1761,54 @@ attribute-sets:
         name: erspan-hwid
         type: u16
   -
+    name: linkinfo-gre6-attrs
+    subset-of: linkinfo-gre-attrs
+    attributes:
+      -
+        name: link
+      -
+        name: iflags
+      -
+        name: oflags
+      -
+        name: ikey
+      -
+        name: okey
+      -
+        name: local
+        display-hint: ipv6
+      -
+        name: remote
+        display-hint: ipv6
+      -
+        name: ttl
+      -
+        name: encap-limit
+      -
+        name: flowinfo
+      -
+        name: flags
+      -
+        name: encap-type
+      -
+        name: encap-flags
+      -
+        name: encap-sport
+      -
+        name: encap-dport
+      -
+        name: collect-metadata
+      -
+        name: fwmark
+      -
+        name: erspan-index
+      -
+        name: erspan-ver
+      -
+        name: erspan-dir
+      -
+        name: erspan-hwid
+  -
     name: linkinfo-vti-attrs
     name-prefix: ifla-vti-
     header: linux/if_tunnel.h
@@ -1764,9 +1819,11 @@ attribute-sets:
       -
         name: ikey
         type: u32
+        byte-order: big-endian
       -
         name: okey
         type: u32
+        byte-order: big-endian
       -
         name: local
         type: binary
@@ -1816,6 +1873,7 @@ attribute-sets:
       -
         name: port
         type: u16
+        byte-order: big-endian
       -
         name: collect-metadata
         type: flag
@@ -1835,6 +1893,7 @@ attribute-sets:
       -
         name: label
         type: u32
+        byte-order: big-endian
       -
         name: ttl-inherit
         type: u8
@@ -1875,9 +1934,11 @@ attribute-sets:
       -
         name: flowinfo
         type: u32
+        byte-order: big-endian
       -
         name: flags
         type: u16
+        byte-order: big-endian
       -
         name: proto
         type: u8
@@ -1907,9 +1968,11 @@ attribute-sets:
       -
         name: encap-sport
         type: u16
+        byte-order: big-endian
       -
         name: encap-dport
         type: u16
+        byte-order: big-endian
       -
         name: collect-metadata
         type: flag
@@ -2225,6 +2288,9 @@ sub-messages:
         value: gretap
         attribute-set: linkinfo-gre-attrs
       -
+        value: ip6gre
+        attribute-set: linkinfo-gre6-attrs
+      -
         value: geneve
         attribute-set: linkinfo-geneve-attrs
       -
diff --git a/Documentation/rust/coding-guidelines.rst b/Documentation/rust/coding-guidelines.rst
index 27f2a7bb5a4a..6ff9e754755d 100644
--- a/Documentation/rust/coding-guidelines.rst
+++ b/Documentation/rust/coding-guidelines.rst
@@ -85,6 +85,18 @@ written after the documentation, e.g.:
 	    // ...
 	}
 
+This applies to both public and private items. This increases consistency with
+public items, allows changes to visibility with less changes involved and will
+allow us to potentially generate the documentation for private items as well.
+In other words, if documentation is written for a private item, then ``///``
+should still be used. For instance:
+
+.. code-block:: rust
+
+	/// My private function.
+	// TODO: ...
+	fn f() {}
+
 One special kind of comments are the ``// SAFETY:`` comments. These must appear
 before every ``unsafe`` block, and they explain why the code inside the block is
 correct/sound, i.e. why it cannot trigger undefined behavior in any case, e.g.:
@@ -191,6 +203,23 @@ or:
 	/// [`struct mutex`]: srctree/include/linux/mutex.h
 
 
+C FFI types
+-----------
+
+Rust kernel code refers to C types, such as ``int``, using type aliases such as
+``c_int``, which are readily available from the ``kernel`` prelude. Please do
+not use the aliases from ``core::ffi`` -- they may not map to the correct types.
+
+These aliases should generally be referred directly by their identifier, i.e.
+as a single segment path. For instance:
+
+.. code-block:: rust
+
+	fn f(p: *const c_char) -> c_int {
+	    // ...
+	}
+
+
 Naming
 ------
 
diff --git a/Documentation/rust/quick-start.rst b/Documentation/rust/quick-start.rst
index 6d2607870ba4..155f7107329a 100644
--- a/Documentation/rust/quick-start.rst
+++ b/Documentation/rust/quick-start.rst
@@ -90,15 +90,53 @@ they should generally work out of the box, e.g.::
 Ubuntu
 ******
 
-Ubuntu LTS and non-LTS (interim) releases provide recent Rust releases and thus
-they should generally work out of the box, e.g.::
+25.04
+~~~~~
+
+The latest Ubuntu releases provide recent Rust releases and thus they should
+generally work out of the box, e.g.::
+
+	apt install rustc rust-src bindgen rustfmt rust-clippy
+
+In addition, ``RUST_LIB_SRC`` needs to be set, e.g.::
+
+	RUST_LIB_SRC=/usr/src/rustc-$(rustc --version | cut -d' ' -f2)/library
+
+For convenience, ``RUST_LIB_SRC`` can be exported to the global environment.
 
-	apt install rustc-1.80 rust-1.80-src bindgen-0.65 rustfmt-1.80 rust-1.80-clippy
+
+24.04 LTS and older
+~~~~~~~~~~~~~~~~~~~
+
+Though Ubuntu 24.04 LTS and older versions still provide recent Rust
+releases, they require some additional configuration to be set, using
+the versioned packages, e.g.::
+
+	apt install rustc-1.80 rust-1.80-src bindgen-0.65 rustfmt-1.80 \
+		rust-1.80-clippy
+	ln -s /usr/lib/rust-1.80/bin/rustfmt /usr/bin/rustfmt-1.80
+	ln -s /usr/lib/rust-1.80/bin/clippy-driver /usr/bin/clippy-driver-1.80
+
+None of these packages set their tools as defaults; therefore they should be
+specified explicitly, e.g.::
+
+	make LLVM=1 RUSTC=rustc-1.80 RUSTDOC=rustdoc-1.80 RUSTFMT=rustfmt-1.80 \
+		CLIPPY_DRIVER=clippy-driver-1.80 BINDGEN=bindgen-0.65
+
+Alternatively, modify the ``PATH`` variable to place the Rust 1.80 binaries
+first and set ``bindgen`` as the default, e.g.::
+
+	PATH=/usr/lib/rust-1.80/bin:$PATH
+	update-alternatives --install /usr/bin/bindgen bindgen \
+		/usr/bin/bindgen-0.65 100
+	update-alternatives --set bindgen /usr/bin/bindgen-0.65
 
 ``RUST_LIB_SRC`` needs to be set when using the versioned packages, e.g.::
 
 	RUST_LIB_SRC=/usr/src/rustc-$(rustc-1.80 --version | cut -d' ' -f2)/library
 
+For convenience, ``RUST_LIB_SRC`` can be exported to the global environment.
+
 In addition, ``bindgen-0.65`` is available in newer releases (24.04 LTS and
 24.10), but it may not be available in older ones (20.04 LTS and 22.04 LTS),
 thus ``bindgen`` may need to be built manually (please see below).
diff --git a/Documentation/rust/testing.rst b/Documentation/rust/testing.rst
index f692494f7b74..f43cb77bcc69 100644
--- a/Documentation/rust/testing.rst
+++ b/Documentation/rust/testing.rst
@@ -133,13 +133,85 @@ please see:
 The ``#[test]`` tests
 ---------------------
 
-Additionally, there are the ``#[test]`` tests. These can be run using the
-``rusttest`` Make target::
+Additionally, there are the ``#[test]`` tests. Like for documentation tests,
+these are also fairly similar to what you would expect from userspace, and they
+are also mapped to KUnit.
+
+These tests are introduced by the ``kunit_tests`` procedural macro, which takes
+the name of the test suite as an argument.
+
+For instance, assume we want to test the function ``f`` from the documentation
+tests section. We could write, in the same file where we have our function:
+
+.. code-block:: rust
+
+	#[kunit_tests(rust_kernel_mymod)]
+	mod tests {
+	    use super::*;
+
+	    #[test]
+	    fn test_f() {
+	        assert_eq!(f(10, 20), 30);
+	    }
+	}
+
+And if we run it, the kernel log would look like::
+
+	    KTAP version 1
+	    # Subtest: rust_kernel_mymod
+	    # speed: normal
+	    1..1
+	    # test_f.speed: normal
+	    ok 1 test_f
+	ok 1 rust_kernel_mymod
+
+Like documentation tests, the ``assert!`` and ``assert_eq!`` macros are mapped
+back to KUnit and do not panic. Similarly, the
+`? <https://doc.rust-lang.org/reference/expressions/operator-expr.html#the-question-mark-operator>`_
+operator is supported, i.e. the test functions may return either nothing (i.e.
+the unit type ``()``) or ``Result`` (i.e. any ``Result<T, E>``). For instance:
+
+.. code-block:: rust
+
+	#[kunit_tests(rust_kernel_mymod)]
+	mod tests {
+	    use super::*;
+
+	    #[test]
+	    fn test_g() -> Result {
+	        let x = g()?;
+	        assert_eq!(x, 30);
+	        Ok(())
+	    }
+	}
+
+If we run the test and the call to ``g`` fails, then the kernel log would show::
+
+	    KTAP version 1
+	    # Subtest: rust_kernel_mymod
+	    # speed: normal
+	    1..1
+	    # test_g: ASSERTION FAILED at rust/kernel/lib.rs:335
+	    Expected is_test_result_ok(test_g()) to be true, but is false
+	    # test_g.speed: normal
+	    not ok 1 test_g
+	not ok 1 rust_kernel_mymod
+
+If a ``#[test]`` test could be useful as an example for the user, then please
+use a documentation test instead. Even edge cases of an API, e.g. error or
+boundary cases, can be interesting to show in examples.
+
+The ``rusttest`` host tests
+---------------------------
+
+These are userspace tests that can be built and run in the host (i.e. the one
+that performs the kernel build) using the ``rusttest`` Make target::
 
 	make LLVM=1 rusttest
 
-This requires the kernel ``.config``. It runs the ``#[test]`` tests on the host
-(currently) and thus is fairly limited in what these tests can test.
+This requires the kernel ``.config``.
+
+Currently, they are mostly used for testing the ``macros`` crate's examples.
 
 The Kselftests
 --------------
diff --git a/Documentation/virt/hyperv/vmbus.rst b/Documentation/virt/hyperv/vmbus.rst
index 1dcef6a7fda3..654bb4849972 100644
--- a/Documentation/virt/hyperv/vmbus.rst
+++ b/Documentation/virt/hyperv/vmbus.rst
@@ -250,10 +250,18 @@ interrupts are not Linux IRQs, there are no entries in /proc/interrupts
 or /proc/irq corresponding to individual VMBus channel interrupts.
 
 An online CPU in a Linux guest may not be taken offline if it has
-VMBus channel interrupts assigned to it.  Any such channel
-interrupts must first be manually reassigned to another CPU as
-described above.  When no channel interrupts are assigned to the
-CPU, it can be taken offline.
+VMBus channel interrupts assigned to it. Starting in kernel v6.15,
+any such interrupts are automatically reassigned to some other CPU
+at the time of offlining. The "other" CPU is chosen by the
+implementation and is not load balanced or otherwise intelligently
+determined. If the CPU is onlined again, channel interrupts previously
+assigned to it are not moved back. As a result, after multiple CPUs
+have been offlined, and perhaps onlined again, the interrupt-to-CPU
+mapping may be scrambled and non-optimal. In such a case, optimal
+assignments must be re-established manually. For kernels v6.14 and
+earlier, any conflicting channel interrupts must first be manually
+reassigned to another CPU as described above. Then when no channel
+interrupts are assigned to the CPU, it can be taken offline.
 
 The VMBus channel interrupt handling code is designed to work
 correctly even if an interrupt is received on a CPU other than the
@@ -324,3 +332,15 @@ rescinded, neither Hyper-V nor Linux retains any state about
 its previous existence. Such a device might be re-added later,
 in which case it is treated as an entirely new device. See
 vmbus_onoffer_rescind().
+
+For some devices, such as the KVP device, Hyper-V automatically
+sends a rescind message when the primary channel is closed,
+likely as a result of unbinding the device from its driver.
+The rescind causes Linux to remove the device. But then Hyper-V
+immediately reoffers the device to the guest, causing a new
+instance of the device to be created in Linux. For other
+devices, such as the synthetic SCSI and NIC devices, closing the
+primary channel does *not* result in Hyper-V sending a rescind
+message. The device continues to exist in Linux on the VMBus,
+but with no driver bound to it. The same driver or a new driver
+can subsequently be bound to the existing instance of the device.
diff --git a/Documentation/virt/uml/user_mode_linux_howto_v2.rst b/Documentation/virt/uml/user_mode_linux_howto_v2.rst
index 584000b743f3..c37e8e594d12 100644
--- a/Documentation/virt/uml/user_mode_linux_howto_v2.rst
+++ b/Documentation/virt/uml/user_mode_linux_howto_v2.rst
@@ -147,18 +147,12 @@ The image hostname will be set to the same as the host on which you
 are creating its image. It is a good idea to change that to avoid
 "Oh, bummer, I rebooted the wrong machine".
 
-UML supports two classes of network devices - the older uml_net ones
-which are scheduled for obsoletion. These are called ethX. It also
-supports the newer vector IO devices which are significantly faster
-and have support for some standard virtual network encapsulations like
-Ethernet over GRE and Ethernet over L2TPv3. These are called vec0.
+UML supports vector I/O high performance network devices which have
+support for some standard virtual network encapsulations like
+Ethernet over GRE and Ethernet over L2TPv3. These are called vecX.
 
-Depending on which one is in use, ``/etc/network/interfaces`` will
-need entries like::
-
-   # legacy UML network devices
-   auto eth0
-   iface eth0 inet dhcp
+When vector network devices are in use, ``/etc/network/interfaces``
+will need entries like::
 
    # vector UML network devices
    auto vec0
@@ -219,16 +213,6 @@ remote UML and other VM instances.
 +-----------+--------+------------------------------------+------------+
 | vde       | vector | dep. on VDE VPN: Virt.Net Locator  | varies     |
 +-----------+--------+------------------------------------+------------+
-| tuntap    | legacy | none                               | ~ 500Mbit  |
-+-----------+--------+------------------------------------+------------+
-| daemon    | legacy | none                               | ~ 450Mbit  |
-+-----------+--------+------------------------------------+------------+
-| socket    | legacy | none                               | ~ 450Mbit  |
-+-----------+--------+------------------------------------+------------+
-| ethertap  | legacy | obsolete                           | ~ 500Mbit  |
-+-----------+--------+------------------------------------+------------+
-| vde       | legacy | obsolete                           | ~ 500Mbit  |
-+-----------+--------+------------------------------------+------------+
 
 * All transports which have tso and checksum offloads can deliver speeds
   approaching 10G on TCP streams.
@@ -236,27 +220,16 @@ remote UML and other VM instances.
 * All transports which have multi-packet rx and/or tx can deliver pps
   rates of up to 1Mps or more.
 
-* All legacy transports are generally limited to ~600-700MBit and 0.05Mps.
-
 * GRE and L2TPv3 allow connections to all of: local machine, remote
   machines, remote network devices and remote UML instances.
 
-* Socket allows connections only between UML instances.
-
-* Daemon and bess require running a local switch. This switch may be
-  connected to the host as well.
-
 
 Network configuration privileges
 ================================
 
 The majority of the supported networking modes need ``root`` privileges.
-For example, in the legacy tuntap networking mode, users were required
-to be part of the group associated with the tunnel device.
-
-For newer network drivers like the vector transports, ``root`` privilege
-is required to fire an ioctl to setup the tun interface and/or use
-raw sockets where needed.
+For example, for vector transports, ``root`` privilege is required to fire
+an ioctl to setup the tun interface and/or use raw sockets where needed.
 
 This can be achieved by granting the user a particular capability instead
 of running UML as root.  In case of vector transport, a user can add the
@@ -610,12 +583,6 @@ connect to a local area cloud (all the UML nodes using the same
 multicast address running on hosts in the same multicast domain (LAN)
 will be automagically connected together to a virtual LAN.
 
-Configuring Legacy transports
-=============================
-
-Legacy transports are now considered obsolete. Please use the vector
-versions.
-
 ***********
 Running UML
 ***********
diff --git a/LICENSES/deprecated/CC0-1.0 b/LICENSES/deprecated/CC0-1.0
new file mode 100644
index 000000000000..d6054d574d50
--- /dev/null
+++ b/LICENSES/deprecated/CC0-1.0
@@ -0,0 +1,129 @@
+Valid-License-Identifier: CC0-1.0
+SPDX-URL: https://spdx.org/licenses/CC0-1.0.html
+Usage-Guide:
+  To use the Creative Commons Zero v1.0 Universal License put the
+  following SPDX tag/value pair into a comment according to the
+  placement guidelines in the licensing rules documentation:
+    SPDX-License-Identifier: CC0-1.0
+License-Text:
+Creative Commons Legal Code
+
+CC0 1.0 Universal
+
+    CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE
+    LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN
+    ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS
+    INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES
+    REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS
+    PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM
+    THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED
+    HEREUNDER.
+
+Statement of Purpose
+
+The laws of most jurisdictions throughout the world automatically confer
+exclusive Copyright and Related Rights (defined below) upon the creator
+and subsequent owner(s) (each and all, an "owner") of an original work of
+authorship and/or a database (each, a "Work").
+
+Certain owners wish to permanently relinquish those rights to a Work for
+the purpose of contributing to a commons of creative, cultural and
+scientific works ("Commons") that the public can reliably and without fear
+of later claims of infringement build upon, modify, incorporate in other
+works, reuse and redistribute as freely as possible in any form whatsoever
+and for any purposes, including without limitation commercial purposes.
+These owners may contribute to the Commons to promote the ideal of a free
+culture and the further production of creative, cultural and scientific
+works, or to gain reputation or greater distribution for their Work in
+part through the use and efforts of others.
+
+For these and/or other purposes and motivations, and without any
+expectation of additional consideration or compensation, the person
+associating CC0 with a Work (the "Affirmer"), to the extent that he or she
+is an owner of Copyright and Related Rights in the Work, voluntarily
+elects to apply CC0 to the Work and publicly distribute the Work under its
+terms, with knowledge of his or her Copyright and Related Rights in the
+Work and the meaning and intended legal effect of CC0 on those rights.
+
+1. Copyright and Related Rights. A Work made available under CC0 may be
+protected by copyright and related or neighboring rights ("Copyright and
+Related Rights"). Copyright and Related Rights include, but are not
+limited to, the following:
+
+  i. the right to reproduce, adapt, distribute, perform, display,
+     communicate, and translate a Work;
+ ii. moral rights retained by the original author(s) and/or performer(s);
+iii. publicity and privacy rights pertaining to a person's image or
+     likeness depicted in a Work;
+ iv. rights protecting against unfair competition in regards to a Work,
+     subject to the limitations in paragraph 4(a), below;
+  v. rights protecting the extraction, dissemination, use and reuse of data
+     in a Work;
+ vi. database rights (such as those arising under Directive 96/9/EC of the
+     European Parliament and of the Council of 11 March 1996 on the legal
+     protection of databases, and under any national implementation
+     thereof, including any amended or successor version of such
+     directive); and
+vii. other similar, equivalent or corresponding rights throughout the
+     world based on applicable law or treaty, and any national
+     implementations thereof.
+
+2. Waiver. To the greatest extent permitted by, but not in contravention
+of, applicable law, Affirmer hereby overtly, fully, permanently,
+irrevocably and unconditionally waives, abandons, and surrenders all of
+Affirmer's Copyright and Related Rights and associated claims and causes
+of action, whether now known or unknown (including existing as well as
+future claims and causes of action), in the Work (i) in all territories
+worldwide, (ii) for the maximum duration provided by applicable law or
+treaty (including future time extensions), (iii) in any current or future
+medium and for any number of copies, and (iv) for any purpose whatsoever,
+including without limitation commercial, advertising or promotional
+purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each
+member of the public at large and to the detriment of Affirmer's heirs and
+successors, fully intending that such Waiver shall not be subject to
+revocation, rescission, cancellation, termination, or any other legal or
+equitable action to disrupt the quiet enjoyment of the Work by the public
+as contemplated by Affirmer's express Statement of Purpose.
+
+3. Public License Fallback. Should any part of the Waiver for any reason
+be judged legally invalid or ineffective under applicable law, then the
+Waiver shall be preserved to the maximum extent permitted taking into
+account Affirmer's express Statement of Purpose. In addition, to the
+extent the Waiver is so judged Affirmer hereby grants to each affected
+person a royalty-free, non transferable, non sublicensable, non exclusive,
+irrevocable and unconditional license to exercise Affirmer's Copyright and
+Related Rights in the Work (i) in all territories worldwide, (ii) for the
+maximum duration provided by applicable law or treaty (including future
+time extensions), (iii) in any current or future medium and for any number
+of copies, and (iv) for any purpose whatsoever, including without
+limitation commercial, advertising or promotional purposes (the
+"License"). The License shall be deemed effective as of the date CC0 was
+applied by Affirmer to the Work. Should any part of the License for any
+reason be judged legally invalid or ineffective under applicable law, such
+partial invalidity or ineffectiveness shall not invalidate the remainder
+of the License, and in such case Affirmer hereby affirms that he or she
+will not (i) exercise any of his or her remaining Copyright and Related
+Rights in the Work or (ii) assert any associated claims and causes of
+action with respect to the Work, in either case contrary to Affirmer's
+express Statement of Purpose.
+
+4. Limitations and Disclaimers.
+
+ a. No trademark or patent rights held by Affirmer are waived, abandoned,
+    surrendered, licensed or otherwise affected by this document.
+ b. Affirmer offers the Work as-is and makes no representations or
+    warranties of any kind concerning the Work, express, implied,
+    statutory or otherwise, including without limitation warranties of
+    title, merchantability, fitness for a particular purpose, non
+    infringement, or the absence of latent or other defects, accuracy, or
+    the present or absence of errors, whether or not discoverable, all to
+    the greatest extent permissible under applicable law.
+ c. Affirmer disclaims responsibility for clearing rights of other persons
+    that may apply to the Work or any use thereof, including without
+    limitation any person's Copyright and Related Rights in the Work.
+    Further, Affirmer disclaims responsibility for obtaining any necessary
+    consents, permissions or other rights required for any use of the
+    Work.
+ d. Affirmer understands and acknowledges that Creative Commons is not a
+    party to this document and has no duty or obligation with respect to
+    this CC0 or use of the Work.
diff --git a/MAINTAINERS b/MAINTAINERS
index 98201e1f4ab5..f2668b81115c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2147,7 +2147,7 @@ F:	arch/arm/plat-*/
 
 ARM/ACTIONS SEMI ARCHITECTURE
 M:	Andreas Färber <afaerber@suse.de>
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-actions@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -2400,7 +2400,7 @@ F:	arch/arm/boot/dts/intel/axm/
 F:	arch/arm/mach-axxia/
 
 ARM/BITMAIN ARCHITECTURE
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	Documentation/devicetree/bindings/arm/bitmain.yaml
@@ -3069,7 +3069,7 @@ F:	include/linux/soc/qcom/
 F:	include/soc/qcom/
 
 ARM/RDA MICRO ARCHITECTURE
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-unisoc@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -3776,7 +3776,7 @@ F:	Documentation/admin-guide/aoe/
 F:	drivers/block/aoe/
 
 ATC260X PMIC MFD DRIVER
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 M:	Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
 L:	linux-actions@lists.infradead.org
 S:	Maintained
@@ -6374,11 +6374,20 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6.git
 F:	Documentation/crypto/
 F:	Documentation/devicetree/bindings/crypto/
 F:	arch/*/crypto/
-F:	arch/*/lib/crypto/
 F:	crypto/
 F:	drivers/crypto/
 F:	include/crypto/
 F:	include/linux/crypto*
+
+CRYPTO LIBRARY
+M:	Eric Biggers <ebiggers@kernel.org>
+M:	Jason A. Donenfeld <Jason@zx2c4.com>
+M:	Ard Biesheuvel <ardb@kernel.org>
+L:	linux-crypto@vger.kernel.org
+S:	Maintained
+T:	git https://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux.git libcrypto-next
+T:	git https://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux.git libcrypto-fixes
+F:	arch/*/lib/crypto/
 F:	lib/crypto/
 
 CRYPTO SPEED TEST COMPARE
@@ -6806,7 +6815,7 @@ S:	Orphan
 F:	drivers/mtd/nand/raw/denali*
 
 DESIGNWARE EDMA CORE IP DRIVER
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	dmaengine@vger.kernel.org
 S:	Maintained
 F:	drivers/dma/dw-edma/
@@ -8652,7 +8661,7 @@ S:	Maintained
 F:	drivers/edac/pnd2_edac.[ch]
 
 EDAC-QCOM
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-arm-msm@vger.kernel.org
 L:	linux-edac@vger.kernel.org
 S:	Maintained
@@ -10719,20 +10728,23 @@ F:	kernel/time/timer_list.c
 F:	kernel/time/timer_migration.*
 F:	tools/testing/selftests/timers/
 
-HIGH-RESOLUTION TIMERS [RUST]
+DELAY, SLEEP, TIMEKEEPING, TIMERS [RUST]
 M:	Andreas Hindborg <a.hindborg@kernel.org>
 R:	Boqun Feng <boqun.feng@gmail.com>
+R:	FUJITA Tomonori <fujita.tomonori@gmail.com>
 R:	Frederic Weisbecker <frederic@kernel.org>
 R:	Lyude Paul <lyude@redhat.com>
 R:	Thomas Gleixner <tglx@linutronix.de>
 R:	Anna-Maria Behnsen <anna-maria@linutronix.de>
+R:	John Stultz <jstultz@google.com>
+R:	Stephen Boyd <sboyd@kernel.org>
 L:	rust-for-linux@vger.kernel.org
 S:	Supported
 W:	https://rust-for-linux.com
 B:	https://github.com/Rust-for-Linux/linux/issues
-T:	git https://github.com/Rust-for-Linux/linux.git hrtimer-next
-F:	rust/kernel/time/hrtimer.rs
-F:	rust/kernel/time/hrtimer/
+T:	git https://github.com/Rust-for-Linux/linux.git timekeeping-next
+F:	rust/kernel/time.rs
+F:	rust/kernel/time/
 
 HIGH-SPEED SCC DRIVER FOR AX.25
 L:	linux-hams@vger.kernel.org
@@ -10778,7 +10790,7 @@ F:	net/dsa/tag_hellcreek.c
 
 HISILICON DMA DRIVER
 M:	Zhou Wang <wangzhou1@hisilicon.com>
-M:	Jie Hai <haijie1@huawei.com>
+M:	Longfang Liu <liulongfang@huawei.com>
 L:	dmaengine@vger.kernel.org
 S:	Maintained
 F:	drivers/dma/hisi_dma.c
@@ -10860,6 +10872,7 @@ W:	http://www.hisilicon.com
 F:	Documentation/admin-guide/perf/hisi-pcie-pmu.rst
 F:	Documentation/admin-guide/perf/hisi-pmu.rst
 F:	drivers/perf/hisilicon
+F:	tools/perf/pmu-events/arch/arm64/hisilicon/
 
 HISILICON PTT DRIVER
 M:	Yicong Yang <yangyicong@hisilicon.com>
@@ -12269,7 +12282,7 @@ M:	Andy Shevchenko <andy@kernel.org>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
 F:	arch/x86/include/asm/intel-mid.h
-F:	arch/x86/pci/intel_mid_pci.c
+F:	arch/x86/pci/intel_mid.c
 F:	arch/x86/platform/intel-mid/
 F:	drivers/dma/hsu/
 F:	drivers/extcon/extcon-intel-mrfld.c
@@ -14156,6 +14169,15 @@ L:	linux-scsi@vger.kernel.org
 S:	Maintained
 F:	drivers/scsi/sym53c8xx_2/
 
+LT3074 HARDWARE MONITOR DRIVER
+M:	Cedric Encarnacion <cedricjustine.encarnacion@analog.com>
+L:	linux-hwmon@vger.kernel.org
+S:	Supported
+W:	https://ez.analog.com/linux-software-drivers
+F:	Documentation/devicetree/bindings/hwmon/pmbus/adi,lt3074.yaml
+F:	Documentation/hwmon/lt3074.rst
+F:	drivers/hwmon/pmbus/lt3074.c
+
 LTC1660 DAC DRIVER
 M:	Marcus Folkesson <marcus.folkesson@gmail.com>
 L:	linux-iio@vger.kernel.org
@@ -14849,7 +14871,7 @@ F:	drivers/hid/hid-mcp2221.c
 
 MCP251XFD SPI-CAN NETWORK DRIVER
 M:	Marc Kleine-Budde <mkl@pengutronix.de>
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 R:	Thomas Kopp <thomas.kopp@microchip.com>
 L:	linux-can@vger.kernel.org
 S:	Maintained
@@ -16015,7 +16037,7 @@ F:	arch/arm64/boot/dts/marvell/armada-3720-eDPU.dts
 F:	arch/arm64/boot/dts/marvell/armada-3720-uDPU.*
 
 MHI BUS
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	mhi@lists.linux.dev
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
@@ -18777,6 +18799,13 @@ S:	Maintained
 F:	Documentation/hwmon/pc87427.rst
 F:	drivers/hwmon/pc87427.c
 
+MAX77705 HARDWARE MONITORING DRIVER
+M:	Dzmitry Sankouski <dsankouski@gmail.com>
+L:	linux-hwmon@vger.kernel.org
+S:	Maintained
+F:	Documentation/hwmon/max77705.rst
+F:	drivers/hwmon/max77705-hwmon.c
+
 PCA9532 LED DRIVER
 M:	Riku Voipio <riku.voipio@iki.fi>
 S:	Maintained
@@ -18820,7 +18849,7 @@ M:	Thomas Petazzoni <thomas.petazzoni@bootlin.com>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-F:	Documentation/devicetree/bindings/pci/pci-armada8k.txt
+F:	Documentation/devicetree/bindings/pci/marvell,armada8k-pcie.yaml
 F:	drivers/pci/controller/dwc/pcie-armada8k.c
 
 PCI DRIVER FOR CADENCE PCIE IP
@@ -18940,6 +18969,7 @@ M:	Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
 L:	linux-pci@vger.kernel.org
 L:	linux-renesas-soc@vger.kernel.org
 S:	Maintained
+F:	Documentation/PCI/controller/rcar-pcie-firmware.rst
 F:	Documentation/devicetree/bindings/pci/*rcar*
 F:	drivers/pci/controller/*rcar*
 F:	drivers/pci/controller/dwc/*rcar*
@@ -18954,7 +18984,7 @@ F:	drivers/pci/controller/dwc/pci-exynos.c
 
 PCI DRIVER FOR SYNOPSYS DESIGNWARE
 M:	Jingoo Han <jingoohan1@gmail.com>
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-pci@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/pci/snps,dw-pcie-ep.yaml
@@ -18977,7 +19007,7 @@ PCI DRIVER FOR V3 SEMICONDUCTOR V360EPC
 M:	Linus Walleij <linus.walleij@linaro.org>
 L:	linux-pci@vger.kernel.org
 S:	Maintained
-F:	Documentation/devicetree/bindings/pci/v3-v360epc-pci.txt
+F:	Documentation/devicetree/bindings/pci/v3,v360epc-pci.yaml
 F:	drivers/pci/controller/pci-v3-semi.c
 
 PCI DRIVER FOR XILINX VERSAL CPM
@@ -18989,8 +19019,8 @@ F:	Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml
 F:	drivers/pci/controller/pcie-xilinx-cpm.c
 
 PCI ENDPOINT SUBSYSTEM
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
-M:	Krzysztof Wilczyński <kw@linux.com>
+M:	Manivannan Sadhasivam <mani@kernel.org>
+M:	Krzysztof Wilczyński <kwilczynski@kernel.org>
 R:	Kishon Vijay Abraham I <kishon@kernel.org>
 L:	linux-pci@vger.kernel.org
 S:	Supported
@@ -19041,8 +19071,8 @@ F:	drivers/pci/controller/pci-xgene-msi.c
 
 PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS
 M:	Lorenzo Pieralisi <lpieralisi@kernel.org>
-M:	Krzysztof Wilczyński <kw@linux.com>
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Krzysztof Wilczyński <kwilczynski@kernel.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 R:	Rob Herring <robh@kernel.org>
 L:	linux-pci@vger.kernel.org
 S:	Supported
@@ -19050,6 +19080,7 @@ Q:	https://patchwork.kernel.org/project/linux-pci/list/
 B:	https://bugzilla.kernel.org
 C:	irc://irc.oftc.net/linux-pci
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git
+F:	Documentation/ABI/testing/debugfs-pcie-ptm
 F:	Documentation/devicetree/bindings/pci/
 F:	drivers/pci/controller/
 F:	drivers/pci/pci-bridge-emul.c
@@ -19198,7 +19229,7 @@ F:	Documentation/devicetree/bindings/pci/microchip*
 F:	drivers/pci/controller/plda/*microchip*
 
 PCIE DRIVER FOR QUALCOMM MSM
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
@@ -19234,7 +19265,7 @@ F:	Documentation/devicetree/bindings/pci/starfive,jh7110-pcie.yaml
 F:	drivers/pci/controller/plda/pcie-starfive.c
 
 PCIE ENDPOINT DRIVER FOR QUALCOMM
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
@@ -20362,7 +20393,7 @@ F:	drivers/iommu/arm/arm-smmu/arm-smmu-qcom*
 F:	drivers/iommu/msm_iommu*
 
 QUALCOMM IPC ROUTER (QRTR) DRIVER
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
 F:	include/trace/events/qrtr.h
@@ -20370,7 +20401,7 @@ F:	include/uapi/linux/qrtr.h
 F:	net/qrtr/
 
 QUALCOMM IPCC MAILBOX DRIVER
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-arm-msm@vger.kernel.org
 S:	Supported
 F:	Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
@@ -20405,7 +20436,7 @@ F:	Documentation/devicetree/bindings/media/qcom,*-iris.yaml
 F:	drivers/media/platform/qcom/iris/
 
 QUALCOMM NAND CONTROLLER DRIVER
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-mtd@lists.infradead.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
@@ -21459,6 +21490,7 @@ F:	include/linux/mfd/rohm-bd71828.h
 F:	include/linux/mfd/rohm-bd718x7.h
 F:	include/linux/mfd/rohm-bd957x.h
 F:	include/linux/mfd/rohm-bd96801.h
+F:	include/linux/mfd/rohm-bd96802.h
 F:	include/linux/mfd/rohm-generic.h
 F:	include/linux/mfd/rohm-shared.h
 
@@ -21568,7 +21600,7 @@ M:	Alex Gaynor <alex.gaynor@gmail.com>
 R:	Boqun Feng <boqun.feng@gmail.com>
 R:	Gary Guo <gary@garyguo.net>
 R:	Björn Roy Baron <bjorn3_gh@protonmail.com>
-R:	Benno Lossin <benno.lossin@proton.me>
+R:	Benno Lossin <lossin@kernel.org>
 R:	Andreas Hindborg <a.hindborg@kernel.org>
 R:	Alice Ryhl <aliceryhl@google.com>
 R:	Trevor Gross <tmgross@umich.edu>
@@ -21598,7 +21630,7 @@ F:	rust/kernel/alloc.rs
 F:	rust/kernel/alloc/
 
 RUST [PIN-INIT]
-M:	Benno Lossin <benno.lossin@proton.me>
+M:	Benno Lossin <lossin@kernel.org>
 L:	rust-for-linux@vger.kernel.org
 S:	Maintained
 W:	https://rust-for-linux.com/pin-init
@@ -21896,6 +21928,7 @@ F:	drivers/platform/x86/samsung-laptop.c
 
 SAMSUNG MULTIFUNCTION PMIC DEVICE DRIVERS
 M:	Krzysztof Kozlowski <krzk@kernel.org>
+R:	André Draszik <andre.draszik@linaro.org>
 L:	linux-kernel@vger.kernel.org
 L:	linux-samsung-soc@vger.kernel.org
 S:	Maintained
@@ -21906,7 +21939,7 @@ F:	Documentation/devicetree/bindings/mfd/samsung,s5m*.yaml
 F:	Documentation/devicetree/bindings/regulator/samsung,s2m*.yaml
 F:	Documentation/devicetree/bindings/regulator/samsung,s5m*.yaml
 F:	drivers/clk/clk-s2mps11.c
-F:	drivers/mfd/sec*.c
+F:	drivers/mfd/sec*.[ch]
 F:	drivers/regulator/s2m*.c
 F:	drivers/regulator/s5m*.c
 F:	drivers/rtc/rtc-s5m.c
@@ -22559,7 +22592,7 @@ M:	Benedikt Niedermayr <benedikt.niedermayr@siemens.com>
 M:	Tobias Schaffner <tobias.schaffner@siemens.com>
 L:	linux-leds@vger.kernel.org
 S:	Maintained
-F:	drivers/leds/simple/
+F:	drivers/leds/simatic/
 
 SIEMENS IPC PLATFORM DRIVERS
 M:	Bao Cheng Su <baocheng.su@siemens.com>
@@ -22971,7 +23004,7 @@ F:	Documentation/devicetree/bindings/media/i2c/sony,imx283.yaml
 F:	drivers/media/i2c/imx283.c
 
 SONY IMX290 SENSOR DRIVER
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-media@vger.kernel.org
 S:	Maintained
 T:	git git://linuxtv.org/media.git
@@ -22980,7 +23013,7 @@ F:	drivers/media/i2c/imx290.c
 
 SONY IMX296 SENSOR DRIVER
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-media@vger.kernel.org
 S:	Maintained
 T:	git git://linuxtv.org/media.git
@@ -24429,6 +24462,13 @@ F:	Documentation/devicetree/bindings/hwmon/ti,tps23861.yaml
 F:	Documentation/hwmon/tps23861.rst
 F:	drivers/hwmon/tps23861.c
 
+TEXAS INSTRUMENTS TPS6131X FLASH LED DRIVER
+M:	Matthias Fend <matthias.fend@emfend.at>
+L:	linux-leds@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/leds/ti,tps6131x.yaml
+F:	drivers/leds/flash/leds-tps6131x.c
+
 TEXAS INSTRUMENTS' DAC7612 DAC DRIVER
 M:	Ricardo Ribalda <ribalda@kernel.org>
 L:	linux-iio@vger.kernel.org
@@ -25125,13 +25165,12 @@ L:	linux-parisc@vger.kernel.org
 S:	Orphan
 F:	drivers/net/ethernet/dec/tulip/
 
-TUN/TAP driver
+TUN/TAP DRIVER
 M:	Willem de Bruijn <willemdebruijn.kernel@gmail.com>
 M:	Jason Wang <jasowang@redhat.com>
 S:	Maintained
 W:	http://vtun.sourceforge.net/tun
 F:	Documentation/networking/tuntap.rst
-F:	arch/um/os-Linux/drivers/
 F:	drivers/net/tap.c
 F:	drivers/net/tun*
 
@@ -25348,7 +25387,7 @@ S:	Maintained
 F:	drivers/ufs/host/ufs-mediatek*
 
 UNIVERSAL FLASH STORAGE HOST CONTROLLER DRIVER QUALCOMM HOOKS
-M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+M:	Manivannan Sadhasivam <mani@kernel.org>
 L:	linux-arm-msm@vger.kernel.org
 L:	linux-scsi@vger.kernel.org
 S:	Maintained
@@ -26801,6 +26840,17 @@ F:	lib/test_xarray.c
 F:	lib/xarray.c
 F:	tools/testing/radix-tree
 
+XARRAY API [RUST]
+M:	Tamir Duberstein <tamird@gmail.com>
+M:	Andreas Hindborg <a.hindborg@kernel.org>
+L:	rust-for-linux@vger.kernel.org
+S:	Supported
+W:	https://rust-for-linux.com
+B:	https://github.com/Rust-for-Linux/linux/issues
+C:	https://rust-for-linux.zulipchat.com
+T:	git https://github.com/Rust-for-Linux/linux.git xarray-next
+F:	rust/kernel/xarray.rs
+
 XBOX DVD IR REMOTE
 M:	Benjamin Valentin <benpicco@googlemail.com>
 S:	Maintained
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index e81964cce516..f71af368674c 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -167,7 +167,7 @@ CONFIG_MFD_MAX77686=y
 CONFIG_MFD_MAX77693=y
 CONFIG_MFD_MAX8997=y
 CONFIG_MFD_MAX8998=y
-CONFIG_MFD_SEC_CORE=y
+CONFIG_MFD_SEC_I2C=y
 CONFIG_MFD_STMPE=y
 CONFIG_STMPE_I2C=y
 CONFIG_MFD_TPS65090=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index aca01ad6aafc..50c170b4619f 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -612,7 +612,7 @@ CONFIG_MFD_QCOM_RPM=y
 CONFIG_MFD_SPMI_PMIC=y
 CONFIG_MFD_RK8XX_I2C=y
 CONFIG_MFD_RN5T618=y
-CONFIG_MFD_SEC_CORE=y
+CONFIG_MFD_SEC_I2C=y
 CONFIG_MFD_STMPE=y
 CONFIG_MFD_PALMAS=y
 CONFIG_MFD_TPS65090=y
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index ded4b9a5accf..ff29c5b0e9c9 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -335,7 +335,7 @@ CONFIG_MFD_MAX77693=y
 CONFIG_MFD_MAX8907=m
 CONFIG_EZX_PCAP=y
 CONFIG_UCB1400_CORE=m
-CONFIG_MFD_SEC_CORE=y
+CONFIG_MFD_SEC_I2C=y
 CONFIG_MFD_PALMAS=y
 CONFIG_MFD_TPS65090=y
 CONFIG_MFD_TPS6586X=y
diff --git a/arch/arm/include/asm/simd.h b/arch/arm/include/asm/simd.h
index d37559762180..be08a8da046f 100644
--- a/arch/arm/include/asm/simd.h
+++ b/arch/arm/include/asm/simd.h
@@ -8,7 +8,8 @@
 
 static __must_check inline bool may_use_simd(void)
 {
-	return IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && !in_hardirq();
+	return IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && !in_hardirq()
+	       && !irqs_disabled();
 }
 
 #endif	/* _ASM_SIMD_H */
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 0749cf8a6637..5219158d54cf 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -227,9 +227,9 @@ void __flush_dcache_folio(struct address_space *mapping, struct folio *folio)
 	}
 
 	/*
-	 * If this is a page cache page, and we have an aliasing VIPT cache,
+	 * If this is a page cache folio, and we have an aliasing VIPT cache,
 	 * we only need to do one flush - which would be at the relevant
-	 * userspace colour, which is congruent with page->index.
+	 * userspace colour, which is congruent with folio->index.
 	 */
 	if (mapping && cache_is_vipt_aliasing())
 		flush_pfn_alias(folio_pfn(folio), folio_pos(folio));
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 748698e91a4b..27e64f782cb3 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -515,7 +515,5 @@ void __init early_ioremap_init(void)
 bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size,
 				 unsigned long flags)
 {
-	unsigned long pfn = PHYS_PFN(offset);
-
-	return memblock_is_map_memory(pfn);
+	return memblock_is_map_memory(offset);
 }
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 7803d50b90f8..e559ad3cd148 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -877,6 +877,7 @@ void kernel_neon_begin(void)
 	 * the kernel mode NEON register contents never need to be preserved.
 	 */
 	BUG_ON(in_hardirq());
+	BUG_ON(irqs_disabled());
 	cpu = __smp_processor_id();
 
 	fpexc = fmrx(FPEXC) | FPEXC_EN;
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index 8b76821f190f..a541bb029aa4 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -269,7 +269,7 @@ config ARCH_QCOM
 	bool "Qualcomm Platforms"
 	select GPIOLIB
 	select PINCTRL
-	select HAVE_PWRCTL if PCI
+	select HAVE_PWRCTRL if PCI
 	help
 	  This enables support for the ARMv8 based Qualcomm chipsets.
 
diff --git a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi
index 18ab5639b301..0f3501951409 100644
--- a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi
@@ -280,6 +280,171 @@
 			resets = <&cpg 0x30>;
 		};
 
+		dmac0: dma-controller@11400000 {
+			compatible = "renesas,r9a09g057-dmac";
+			reg = <0 0x11400000 0 0x10000>;
+			interrupts = <GIC_SPI 499 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 89  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 90  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 91  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 92  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 93  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 94  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 95  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 96  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 97  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 98  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 99  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 100 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 101 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 102 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 103 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 104 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15";
+			clocks = <&cpg CPG_MOD 0x0>;
+			power-domains = <&cpg>;
+			resets = <&cpg 0x31>;
+			#dma-cells = <1>;
+			dma-channels = <16>;
+			renesas,icu = <&icu 4>;
+		};
+
+		dmac1: dma-controller@14830000 {
+			compatible = "renesas,r9a09g057-dmac";
+			reg = <0 0x14830000 0 0x10000>;
+			interrupts = <GIC_SPI 495 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 25  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 26  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 27  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 28  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 29  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 30  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 31  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 32  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 33  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 34  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 35  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 36  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 37  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 38  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 39  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 40  IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15";
+			clocks = <&cpg CPG_MOD 0x1>;
+			power-domains = <&cpg>;
+			resets = <&cpg 0x32>;
+			#dma-cells = <1>;
+			dma-channels = <16>;
+			renesas,icu = <&icu 0>;
+		};
+
+		dmac2: dma-controller@14840000 {
+			compatible = "renesas,r9a09g057-dmac";
+			reg = <0 0x14840000 0 0x10000>;
+			interrupts = <GIC_SPI 496 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 41  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 42  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 43  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 44  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 45  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 46  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 47  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 48  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 49  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 50  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 51  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 52  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 53  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 54  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 55  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 56  IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15";
+			clocks = <&cpg CPG_MOD 0x2>;
+			power-domains = <&cpg>;
+			resets = <&cpg 0x33>;
+			#dma-cells = <1>;
+			dma-channels = <16>;
+			renesas,icu = <&icu 1>;
+		};
+
+		dmac3: dma-controller@12000000 {
+			compatible = "renesas,r9a09g057-dmac";
+			reg = <0 0x12000000 0 0x10000>;
+			interrupts = <GIC_SPI 497 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 57  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 58  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 59  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 60  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 61  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 62  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 63  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 64  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 65  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 66  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 67  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 68  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 69  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 70  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 71  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 72  IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15";
+			clocks = <&cpg CPG_MOD 0x3>;
+			power-domains = <&cpg>;
+			resets = <&cpg 0x34>;
+			#dma-cells = <1>;
+			dma-channels = <16>;
+			renesas,icu = <&icu 2>;
+		};
+
+		dmac4: dma-controller@12010000 {
+			compatible = "renesas,r9a09g057-dmac";
+			reg = <0 0x12010000 0 0x10000>;
+			interrupts = <GIC_SPI 498 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 73  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 74  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 75  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 76  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 77  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 78  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 79  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 80  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 81  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 82  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 83  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 84  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 85  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 86  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 87  IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 88  IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15";
+			clocks = <&cpg CPG_MOD 0x4>;
+			power-domains = <&cpg>;
+			resets = <&cpg 0x35>;
+			#dma-cells = <1>;
+			dma-channels = <16>;
+			renesas,icu = <&icu 3>;
+		};
+
 		ostm0: timer@11800000 {
 			compatible = "renesas,r9a09g057-ostm", "renesas,ostm";
 			reg = <0x0 0x11800000 0x0 0x1000>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 1e99db100607..897fc686e6a9 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -774,7 +774,7 @@ CONFIG_MFD_MT6397=y
 CONFIG_MFD_SPMI_PMIC=y
 CONFIG_MFD_RK8XX_I2C=y
 CONFIG_MFD_RK8XX_SPI=y
-CONFIG_MFD_SEC_CORE=y
+CONFIG_MFD_SEC_I2C=y
 CONFIG_MFD_SL28CPLD=y
 CONFIG_RZ_MTU3=y
 CONFIG_MFD_TI_AM335X_TSCADC=m
diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c
index 4e27cc29c79e..4fdc26ade1d7 100644
--- a/arch/arm64/hyperv/mshyperv.c
+++ b/arch/arm64/hyperv/mshyperv.c
@@ -28,6 +28,48 @@ int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
 }
 EXPORT_SYMBOL_GPL(hv_get_hypervisor_version);
 
+#ifdef CONFIG_ACPI
+
+static bool __init hyperv_detect_via_acpi(void)
+{
+	if (acpi_disabled)
+		return false;
+	/*
+	 * Hypervisor ID is only available in ACPI v6+, and the
+	 * structure layout was extended in v6 to accommodate that
+	 * new field.
+	 *
+	 * At the very minimum, this check makes sure not to read
+	 * past the FADT structure.
+	 *
+	 * It is also needed to catch running in some unknown
+	 * non-Hyper-V environment that has ACPI 5.x or less.
+	 * In such a case, it can't be Hyper-V.
+	 */
+	if (acpi_gbl_FADT.header.revision < 6)
+		return false;
+	return strncmp((char *)&acpi_gbl_FADT.hypervisor_id, "MsHyperV", 8) == 0;
+}
+
+#else
+
+static bool __init hyperv_detect_via_acpi(void)
+{
+	return false;
+}
+
+#endif
+
+static bool __init hyperv_detect_via_smccc(void)
+{
+	uuid_t hyperv_uuid = UUID_INIT(
+		0x58ba324d, 0x6447, 0x24cd,
+		0x75, 0x6c, 0xef, 0x8e,
+		0x24, 0x70, 0x59, 0x16);
+
+	return arm_smccc_hypervisor_has_uuid(&hyperv_uuid);
+}
+
 static int __init hyperv_init(void)
 {
 	struct hv_get_vp_registers_output	result;
@@ -36,13 +78,11 @@ static int __init hyperv_init(void)
 
 	/*
 	 * Allow for a kernel built with CONFIG_HYPERV to be running in
-	 * a non-Hyper-V environment, including on DT instead of ACPI.
+	 * a non-Hyper-V environment.
+	 *
 	 * In such cases, do nothing and return success.
 	 */
-	if (acpi_disabled)
-		return 0;
-
-	if (strncmp((char *)&acpi_gbl_FADT.hypervisor_id, "MsHyperV", 8))
+	if (!hyperv_detect_via_acpi() && !hyperv_detect_via_smccc())
 		return 0;
 
 	/* Setup the guest ID */
@@ -77,6 +117,9 @@ static int __init hyperv_init(void)
 
 	if (ms_hyperv.priv_high & HV_ACCESS_PARTITION_ID)
 		hv_get_partition_id();
+	ms_hyperv.vtl = get_vtl();
+	if (ms_hyperv.vtl > 0) /* non default VTL */
+		pr_info("Linux runs in Hyper-V Virtual Trust Level %d\n", ms_hyperv.vtl);
 
 	ms_hyperv_late_init();
 
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 1e7c7475e43f..ba5df0df02a4 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -298,19 +298,6 @@
 .Lskip_gcs_\@:
 .endm
 
-.macro __init_el2_mpam
-	/* Memory Partitioning And Monitoring: disable EL2 traps */
-	mrs	x1, id_aa64pfr0_el1
-	ubfx	x0, x1, #ID_AA64PFR0_EL1_MPAM_SHIFT, #4
-	cbz	x0, .Lskip_mpam_\@		// skip if no MPAM
-	msr_s	SYS_MPAM2_EL2, xzr		// use the default partition
-						// and disable lower traps
-	mrs_s	x0, SYS_MPAMIDR_EL1
-	tbz	x0, #MPAMIDR_EL1_HAS_HCR_SHIFT, .Lskip_mpam_\@	// skip if no MPAMHCR reg
-	msr_s	SYS_MPAMHCR_EL2, xzr		// clear TRAP_MPAMIDR_EL1 -> EL2
-.Lskip_mpam_\@:
-.endm
-
 /**
  * Initialize EL2 registers to sane values. This should be called early on all
  * cores that were booted in EL2. Note that everything gets initialised as
@@ -328,7 +315,6 @@
 	__init_el2_stage2
 	__init_el2_gicv3
 	__init_el2_hstr
-	__init_el2_mpam
 	__init_el2_nvhe_idregs
 	__init_el2_cptr
 	__init_el2_fgt
@@ -375,6 +361,16 @@
 #endif
 
 .macro finalise_el2_state
+	check_override id_aa64pfr0, ID_AA64PFR0_EL1_MPAM_SHIFT, .Linit_mpam_\@, .Lskip_mpam_\@, x1, x2
+
+.Linit_mpam_\@:
+	msr_s	SYS_MPAM2_EL2, xzr		// use the default partition
+						// and disable lower traps
+	mrs_s	x0, SYS_MPAMIDR_EL1
+	tbz	x0, #MPAMIDR_EL1_HAS_HCR_SHIFT, .Lskip_mpam_\@  // skip if no MPAMHCR reg
+	msr_s   SYS_MPAMHCR_EL2, xzr		// clear TRAP_MPAMIDR_EL1 -> EL2
+
+.Lskip_mpam_\@:
 	check_override id_aa64pfr0, ID_AA64PFR0_EL1_SVE_SHIFT, .Linit_sve_\@, .Lskip_sve_\@, x1, x2
 
 .Linit_sve_\@:	/* SVE register access */
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 9e93733523f6..74a4f738c5f5 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -58,7 +58,7 @@
 #define INIT_DIR_SIZE (PAGE_SIZE * (EARLY_PAGES(SWAPPER_PGTABLE_LEVELS, KIMAGE_VADDR, _end, EXTRA_PAGE) \
 				    + EARLY_SEGMENT_EXTRA_PAGES))
 
-#define INIT_IDMAP_DIR_PAGES	(EARLY_PAGES(INIT_IDMAP_PGTABLE_LEVELS, KIMAGE_VADDR, _end, 1))
+#define INIT_IDMAP_DIR_PAGES	(EARLY_PAGES(INIT_IDMAP_PGTABLE_LEVELS, KIMAGE_VADDR, kimage_limit, 1))
 #define INIT_IDMAP_DIR_SIZE	((INIT_IDMAP_DIR_PAGES + EARLY_IDMAP_EXTRA_PAGES) * PAGE_SIZE)
 
 #define INIT_IDMAP_FDT_PAGES	(EARLY_PAGES(INIT_IDMAP_PGTABLE_LEVELS, 0UL, UL(MAX_FDT_SIZE), 1) - 1)
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index eba1a98657f1..aa9efee17277 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -323,13 +323,14 @@ static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
 }
 
 /*
- * If mprotect/munmap/etc occurs during TLB batched flushing, we need to
- * synchronise all the TLBI issued with a DSB to avoid the race mentioned in
- * flush_tlb_batched_pending().
+ * If mprotect/munmap/etc occurs during TLB batched flushing, we need to ensure
+ * all the previously issued TLBIs targeting mm have completed. But since we
+ * can be executing on a remote CPU, a DSB cannot guarantee this like it can
+ * for arch_tlbbatch_flush(). Our only option is to flush the entire mm.
  */
 static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm)
 {
-	dsb(ish);
+	flush_tlb_mm(mm);
 }
 
 /*
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 45ea79cacf46..b34044e20128 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1199,8 +1199,10 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 		cpacr_restore(cpacr);
 	}
 
-	if (id_aa64pfr0_mpam(info->reg_id_aa64pfr0))
+	if (id_aa64pfr0_mpam(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1))) {
+		info->reg_mpamidr = read_cpuid(MPAMIDR_EL1);
 		init_cpu_ftr_reg(SYS_MPAMIDR_EL1, info->reg_mpamidr);
+	}
 
 	if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
 		init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid);
@@ -1453,7 +1455,8 @@ void update_cpu_features(int cpu,
 		cpacr_restore(cpacr);
 	}
 
-	if (id_aa64pfr0_mpam(info->reg_id_aa64pfr0)) {
+	if (id_aa64pfr0_mpam(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1))) {
+		info->reg_mpamidr = read_cpuid(MPAMIDR_EL1);
 		taint |= check_update_ftr_reg(SYS_MPAMIDR_EL1, cpu,
 					info->reg_mpamidr, boot->reg_mpamidr);
 	}
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 94525abd1c22..c1f2b6b04b41 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -496,8 +496,11 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0))
 		__cpuinfo_store_cpu_32bit(&info->aarch32);
 
-	if (id_aa64pfr0_mpam(info->reg_id_aa64pfr0))
-		info->reg_mpamidr = read_cpuid(MPAMIDR_EL1);
+	/*
+	 * info->reg_mpamidr deferred to {init,update}_cpu_features because we
+	 * don't want to read it (and trigger a trap on buggy firmware) if
+	 * using an aa64pfr0_el1 override to unconditionally disable MPAM.
+	 */
 
 	if (IS_ENABLED(CONFIG_ARM64_SME) &&
 	    id_aa64pfr1_sme(info->reg_id_aa64pfr1)) {
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 5a69b6eb4090..714b0b5ec5ac 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -10,6 +10,10 @@
 #error This file should only be included in vmlinux.lds.S
 #endif
 
+#if defined(CONFIG_LD_IS_LLD) && CONFIG_LLD_VERSION < 210000
+#define ASSERT(...)
+#endif
+
 #define PI_EXPORT_SYM(sym)		\
 	__PI_EXPORT_SYM(sym, __pi_ ## sym, Cannot export BSS symbol sym to startup code)
 #define __PI_EXPORT_SYM(sym, pisym, msg)\
@@ -140,4 +144,17 @@ KVM_NVHE_ALIAS(kvm_protected_mode_initialized);
 _kernel_codesize = ABSOLUTE(__inittext_end - _text);
 #endif
 
+/*
+ * LLD will occasionally error out with a '__init_end does not converge' error
+ * if INIT_IDMAP_DIR_SIZE is defined in terms of _end, as this results in a
+ * circular dependency. Counter this by dimensioning the initial IDMAP page
+ * tables based on kimage_limit, which is defined such that its value should
+ * not change as a result of the initdata segment being pushed over a 64k
+ * segment boundary due to changes in INIT_IDMAP_DIR_SIZE, provided that its
+ * value doesn't change by more than 2M between linker passes.
+ */
+kimage_limit = ALIGN(ABSOLUTE(_end + SZ_64K), SZ_2M);
+
+#undef ASSERT
+
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c
index c6b185b885f7..bc57b290e5e7 100644
--- a/arch/arm64/kernel/pi/idreg-override.c
+++ b/arch/arm64/kernel/pi/idreg-override.c
@@ -127,6 +127,7 @@ static const struct ftr_set_desc pfr0 __prel64_initconst = {
 	.fields		= {
 	        FIELD("sve", ID_AA64PFR0_EL1_SVE_SHIFT, pfr0_sve_filter),
 		FIELD("el0", ID_AA64PFR0_EL1_EL0_SHIFT, NULL),
+		FIELD("mpam", ID_AA64PFR0_EL1_MPAM_SHIFT, NULL),
 		{}
 	},
 };
@@ -154,6 +155,7 @@ static const struct ftr_set_desc pfr1 __prel64_initconst = {
 		FIELD("gcs", ID_AA64PFR1_EL1_GCS_SHIFT, NULL),
 		FIELD("mte", ID_AA64PFR1_EL1_MTE_SHIFT, NULL),
 		FIELD("sme", ID_AA64PFR1_EL1_SME_SHIFT, pfr1_sme_filter),
+		FIELD("mpam_frac", ID_AA64PFR1_EL1_MPAM_frac_SHIFT, NULL),
 		{}
 	},
 };
@@ -246,6 +248,7 @@ static const struct {
 	{ "rodata=off",			"arm64_sw.rodataoff=1" },
 	{ "arm64.nolva",		"id_aa64mmfr2.varange=0" },
 	{ "arm64.no32bit_el0",		"id_aa64pfr0.el0=1" },
+	{ "arm64.nompam",		"id_aa64pfr0.mpam=0 id_aa64pfr1.mpam_frac=0" },
 };
 
 static int __init parse_hexdigit(const char *p, u64 *v)
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index 569941eeb3fe..58c5fe7d7572 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -270,6 +270,7 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
 	u32 feature;
 	u8 action;
 	gpa_t gpa;
+	uuid_t uuid;
 
 	action = kvm_smccc_get_action(vcpu, func_id);
 	switch (action) {
@@ -355,10 +356,11 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
 			val[0] = gpa;
 		break;
 	case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID:
-		val[0] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0;
-		val[1] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1;
-		val[2] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2;
-		val[3] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3;
+		uuid = ARM_SMCCC_VENDOR_HYP_UID_KVM;
+		val[0] = smccc_uuid_to_reg(&uuid, 0);
+		val[1] = smccc_uuid_to_reg(&uuid, 1);
+		val[2] = smccc_uuid_to_reg(&uuid, 2);
+		val[3] = smccc_uuid_to_reg(&uuid, 3);
 		break;
 	case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID:
 		val[0] = smccc_feat->vendor_hyp_bmap;
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index 6ab3ef39ba7a..745bd575dcfa 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -105,7 +105,8 @@ static struct list_head ptable_list[3] = {
 
 #define PD_PTABLE(page) ((ptable_desc *)&(virt_to_page((void *)(page))->lru))
 #define PD_PAGE(ptable) (list_entry(ptable, struct page, lru))
-#define PD_MARKBITS(dp) (*(unsigned int *)&PD_PAGE(dp)->index)
+#define PD_PTDESC(ptable) (list_entry(ptable, struct ptdesc, pt_list))
+#define PD_MARKBITS(dp) (*(unsigned int *)&PD_PTDESC(dp)->pt_index)
 
 static const int ptable_shift[3] = {
 	7+2, /* PGD */
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index b81672729887..b8e96dfff19d 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -172,7 +172,7 @@ static void set_icache_stale_mask(void)
 	stale_cpu = cpumask_test_cpu(cpu, mask);
 
 	cpumask_setall(mask);
-	cpumask_assign_cpu(cpu, mask, stale_cpu);
+	__assign_cpu(cpu, mask, stale_cpu);
 	put_cpu();
 }
 #endif
diff --git a/arch/s390/lib/crypto/Makefile b/arch/s390/lib/crypto/Makefile
index 920197967f46..5df30f1e7930 100644
--- a/arch/s390/lib/crypto/Makefile
+++ b/arch/s390/lib/crypto/Makefile
@@ -3,4 +3,5 @@
 obj-$(CONFIG_CRYPTO_CHACHA_S390) += chacha_s390.o
 chacha_s390-y := chacha-glue.o chacha-s390.o
 
-obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256.o
+obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256-s390.o
+sha256-s390-y := sha256.o
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 79509c7f39de..f08e8a7fac93 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -52,13 +52,7 @@ config NO_IOMEM
 config UML_IOMEM_EMULATION
 	bool
 	select INDIRECT_IOMEM
-	select HAS_IOPORT
 	select GENERIC_PCI_IOMAP
-	select GENERIC_IOMAP
-	select NO_GENERIC_PCI_IOPORT_MAP
-
-config NO_IOPORT_MAP
-	def_bool !UML_IOMEM_EMULATION
 
 config ISA
 	bool
diff --git a/arch/um/configs/i386_defconfig b/arch/um/configs/i386_defconfig
index 1ffa088739f4..29d9666eceae 100644
--- a/arch/um/configs/i386_defconfig
+++ b/arch/um/configs/i386_defconfig
@@ -52,13 +52,6 @@ CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
-CONFIG_UML_NET=y
-CONFIG_UML_NET_ETHERTAP=y
-CONFIG_UML_NET_TUNTAP=y
-CONFIG_UML_NET_SLIP=y
-CONFIG_UML_NET_DAEMON=y
-CONFIG_UML_NET_MCAST=y
-CONFIG_UML_NET_SLIRP=y
 CONFIG_EXT4_FS=y
 CONFIG_QUOTA=y
 CONFIG_AUTOFS_FS=m
diff --git a/arch/um/configs/x86_64_defconfig b/arch/um/configs/x86_64_defconfig
index 03b10d3f6816..cf309c5406a2 100644
--- a/arch/um/configs/x86_64_defconfig
+++ b/arch/um/configs/x86_64_defconfig
@@ -51,13 +51,6 @@ CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
-CONFIG_UML_NET=y
-CONFIG_UML_NET_ETHERTAP=y
-CONFIG_UML_NET_TUNTAP=y
-CONFIG_UML_NET_SLIP=y
-CONFIG_UML_NET_DAEMON=y
-CONFIG_UML_NET_MCAST=y
-CONFIG_UML_NET_SLIRP=y
 CONFIG_EXT4_FS=y
 CONFIG_QUOTA=y
 CONFIG_AUTOFS_FS=m
diff --git a/arch/um/drivers/Kconfig b/arch/um/drivers/Kconfig
index 9cb196070614..34085bfc6d41 100644
--- a/arch/um/drivers/Kconfig
+++ b/arch/um/drivers/Kconfig
@@ -124,206 +124,18 @@ endmenu
 menu "UML Network Devices"
 	depends on NET
 
-# UML virtual driver
-config UML_NET
-	bool "Virtual network device"
-	help
-	  While the User-Mode port cannot directly talk to any physical
-	  hardware devices, this choice and the following transport options
-	  provide one or more virtual network devices through which the UML
-	  kernels can talk to each other, the host, and with the host's help,
-	  machines on the outside world.
-
-	  For more information, including explanations of the networking and
-	  sample configurations, see
-	  <http://user-mode-linux.sourceforge.net/old/networking.html>.
-
-	  If you'd like to be able to enable networking in the User-Mode
-	  linux environment, say Y; otherwise say N.  Note that you must
-	  enable at least one of the following transport options to actually
-	  make use of UML networking.
-
-config UML_NET_ETHERTAP
-	bool "Ethertap transport (obsolete)"
-	depends on UML_NET
-	help
-	  The Ethertap User-Mode Linux network transport allows a single
-	  running UML to exchange packets with its host over one of the
-	  host's Ethertap devices, such as /dev/tap0.  Additional running
-	  UMLs can use additional Ethertap devices, one per running UML.
-	  While the UML believes it's on a (multi-device, broadcast) virtual
-	  Ethernet network, it's in fact communicating over a point-to-point
-	  link with the host.
-
-	  To use this, your host kernel must have support for Ethertap
-	  devices.  Also, if your host kernel is 2.4.x, it must have
-	  CONFIG_NETLINK_DEV configured as Y or M.
-
-	  For more information, see
-	  <http://user-mode-linux.sourceforge.net/old/networking.html>  That site
-	  has examples of the UML command line to use to enable Ethertap
-	  networking.
-
-	  NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
-	  migrate to UML_NET_VECTOR.
-
-	  If unsure, say N.
-
-config UML_NET_TUNTAP
-	bool "TUN/TAP transport (obsolete)"
-	depends on UML_NET
-	help
-	  The UML TUN/TAP network transport allows a UML instance to exchange
-	  packets with the host over a TUN/TAP device.  This option will only
-	  work with a 2.4 host, unless you've applied the TUN/TAP patch to
-	  your 2.2 host kernel.
-
-	  To use this transport, your host kernel must have support for TUN/TAP
-	  devices, either built-in or as a module.
-
-	  NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
-	  migrate to UML_NET_VECTOR.
-
-	  If unsure, say N.
-
-config UML_NET_SLIP
-	bool "SLIP transport (obsolete)"
-	depends on UML_NET
-	help
-	  The slip User-Mode Linux network transport allows a running UML to
-	  network with its host over a point-to-point link.  Unlike Ethertap,
-	  which can carry any Ethernet frame (and hence even non-IP packets),
-	  the slip transport can only carry IP packets.
-
-	  To use this, your host must support slip devices.
-
-	  For more information, see
-	  <http://user-mode-linux.sourceforge.net/old/networking.html>.
-	  has examples of the UML command line to use to enable slip
-	  networking, and details of a few quirks with it.
-
-	  NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
-	  migrate to UML_NET_VECTOR.
-
-	  If unsure, say N.
-
-config UML_NET_DAEMON
-	bool "Daemon transport (obsolete)"
-	depends on UML_NET
-	help
-	  This User-Mode Linux network transport allows one or more running
-	  UMLs on a single host to communicate with each other, but not to
-	  the host.
-
-	  To use this form of networking, you'll need to run the UML
-	  networking daemon on the host.
-
-	  For more information, see
-	  <http://user-mode-linux.sourceforge.net/old/networking.html>  That site
-	  has examples of the UML command line to use to enable Daemon
-	  networking.
-
-	  NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
-	  migrate to UML_NET_VECTOR.
-
-	  If unsure, say N.
-
-config UML_NET_DAEMON_DEFAULT_SOCK
-	string "Default socket for daemon transport"
-	default "/tmp/uml.ctl"
-	depends on UML_NET_DAEMON
-	help
-	  This option allows setting the default socket for the daemon
-	  transport, normally it defaults to /tmp/uml.ctl.
-
 config UML_NET_VECTOR
 	bool "Vector I/O high performance network devices"
-	depends on UML_NET
 	select MAY_HAVE_RUNTIME_DEPS
 	help
 	  This User-Mode Linux network driver uses multi-message send
 	  and receive functions. The host running the UML guest must have
 	  a linux kernel version above 3.0 and a libc version > 2.13.
-	  This driver provides tap, raw, gre and l2tpv3 network transports
-	  with up to 4 times higher network throughput than the UML network
-	  drivers.
-
-config UML_NET_VDE
-	bool "VDE transport (obsolete)"
-	depends on UML_NET
-	depends on !MODVERSIONS
-	select MAY_HAVE_RUNTIME_DEPS
-	help
-	  This User-Mode Linux network transport allows one or more running
-	  UMLs on a single host to communicate with each other and also
-	  with the rest of the world using Virtual Distributed Ethernet,
-	  an improved fork of uml_switch.
+	  This driver provides tap, raw, gre and l2tpv3 network transports.
 
-	  You must have libvdeplug installed in order to build the vde
-	  transport into UML.
-
-	  To use this form of networking, you will need to run vde_switch
-	  on the host.
-
-	  For more information, see <http://wiki.virtualsquare.org/>
-	  That site has a good overview of what VDE is and also examples
-	  of the UML command line to use to enable VDE networking.
-
-	  NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
-	  migrate to UML_NET_VECTOR.
-
-	  If unsure, say N.
-
-config UML_NET_MCAST
-	bool "Multicast transport (obsolete)"
-	depends on UML_NET
-	help
-	  This Multicast User-Mode Linux network transport allows multiple
-	  UMLs (even ones running on different host machines!) to talk to
-	  each other over a virtual ethernet network.  However, it requires
-	  at least one UML with one of the other transports to act as a
-	  bridge if any of them need to be able to talk to their hosts or any
-	  other IP machines.
-
-	  To use this, your host kernel(s) must support IP Multicasting.
-
-	  For more information, see
-	  <http://user-mode-linux.sourceforge.net/old/networking.html>  That site
-	  has examples of the UML command line to use to enable Multicast
-	  networking, and notes about the security of this approach.
-
-	  NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
-	  migrate to UML_NET_VECTOR.
-
-	  If unsure, say N.
-
-config UML_NET_SLIRP
-	bool "SLiRP transport (obsolete)"
-	depends on UML_NET
-	help
-	  The SLiRP User-Mode Linux network transport allows a running UML
-	  to network by invoking a program that can handle SLIP encapsulated
-	  packets.  This is commonly (but not limited to) the application
-	  known as SLiRP, a program that can re-socket IP packets back onto
-	  he host on which it is run.  Only IP packets are supported,
-	  unlike other network transports that can handle all Ethernet
-	  frames.  In general, slirp allows the UML the same IP connectivity
-	  to the outside world that the host user is permitted, and unlike
-	  other transports, SLiRP works without the need of root level
-	  privileges, setuid binaries, or SLIP devices on the host.  This
-	  also means not every type of connection is possible, but most
-	  situations can be accommodated with carefully crafted slirp
-	  commands that can be passed along as part of the network device's
-	  setup string.  The effect of this transport on the UML is similar
-	  that of a host behind a firewall that masquerades all network
-	  connections passing through it (but is less secure).
-
-	  NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please
-	  migrate to UML_NET_VECTOR.
-
-	  If unsure, say N.
-
-	  Startup example: "eth0=slirp,FE:FD:01:02:03:04,/usr/local/bin/slirp"
+	  For more information, including explanations of the networking
+	  and sample configurations, see
+	  <file:Documentation/virt/uml/user_mode_linux_howto_v2.rst>.
 
 endmenu
 
@@ -367,3 +179,11 @@ config UML_PCI_OVER_VIRTIO_DEVICE_ID
 	  There's no official device ID assigned (yet), set the one you
 	  wish to use for experimentation here. The default of -1 is
 	  not valid and will cause the driver to fail at probe.
+
+config UML_PCI_OVER_VFIO
+	bool "Enable VFIO-based PCI passthrough"
+	select UML_PCI
+	help
+	  This driver provides support for VFIO-based PCI passthrough.
+	  Currently, only MSI-X capable devices are supported, and it
+	  is assumed that drivers will use MSI-X.
diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile
index 0a5820343ad3..6bf8cbf71d3c 100644
--- a/arch/um/drivers/Makefile
+++ b/arch/um/drivers/Makefile
@@ -6,12 +6,7 @@
 # pcap is broken in 2.5 because kbuild doesn't allow pcap.a to be linked
 # in to pcap.o
 
-slip-objs := slip_kern.o slip_user.o
-slirp-objs := slirp_kern.o slirp_user.o
-daemon-objs := daemon_kern.o daemon_user.o
 vector-objs := vector_kern.o vector_user.o vector_transports.o
-umcast-objs := umcast_kern.o umcast_user.o
-net-objs := net_kern.o net_user.o
 mconsole-objs := mconsole_kern.o mconsole_user.o
 hostaudio-objs := hostaudio_kern.o
 ubd-objs := ubd_kern.o ubd_user.o
@@ -19,13 +14,7 @@ port-objs := port_kern.o port_user.o
 harddog-objs := harddog_kern.o
 harddog-builtin-$(CONFIG_UML_WATCHDOG) := harddog_user.o harddog_user_exp.o
 rtc-objs := rtc_kern.o rtc_user.o
-
-LDFLAGS_vde.o = $(shell $(CC) $(CFLAGS) -print-file-name=libvdeplug.a)
-
-targets := vde_kern.o vde_user.o
-
-$(obj)/vde.o: $(obj)/vde_kern.o $(obj)/vde_user.o
-	$(LD) -r -dp -o $@ $^ $(ld_flags)
+vfio_uml-objs := vfio_kern.o vfio_user.o
 
 #XXX: The call below does not work because the flags are added before the
 # object name, so nothing from the library gets linked.
@@ -38,13 +27,7 @@ obj-y := stdio_console.o fd.o chan_kern.o chan_user.o line.o
 obj-$(CONFIG_SSL) += ssl.o
 obj-$(CONFIG_STDERR_CONSOLE) += stderr_console.o
 
-obj-$(CONFIG_UML_NET_SLIP) += slip.o slip_common.o
-obj-$(CONFIG_UML_NET_SLIRP) += slirp.o slip_common.o
-obj-$(CONFIG_UML_NET_DAEMON) += daemon.o 
 obj-$(CONFIG_UML_NET_VECTOR) += vector.o
-obj-$(CONFIG_UML_NET_VDE) += vde.o
-obj-$(CONFIG_UML_NET_MCAST) += umcast.o
-obj-$(CONFIG_UML_NET) += net.o 
 obj-$(CONFIG_MCONSOLE) += mconsole.o
 obj-$(CONFIG_MMAPPER) += mmapper_kern.o 
 obj-$(CONFIG_BLK_DEV_UBD) += ubd.o 
@@ -62,9 +45,10 @@ obj-$(CONFIG_VIRTIO_UML) += virtio_uml.o
 obj-$(CONFIG_UML_RTC) += rtc.o
 obj-$(CONFIG_UML_PCI) += virt-pci.o
 obj-$(CONFIG_UML_PCI_OVER_VIRTIO) += virtio_pcidev.o
+obj-$(CONFIG_UML_PCI_OVER_VFIO) += vfio_uml.o
 
 # pcap_user.o must be added explicitly.
-USER_OBJS := fd.o null.o pty.o tty.o xterm.o slip_common.o vde_user.o vector_user.o
+USER_OBJS := fd.o null.o pty.o tty.o xterm.o vector_user.o
 CFLAGS_null.o = -DDEV_NULL=$(DEV_NULL_PATH)
 
 CFLAGS_xterm.o += '-DCONFIG_XTERM_CHAN_DEFAULT_EMULATOR="$(CONFIG_XTERM_CHAN_DEFAULT_EMULATOR)"'
diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c
index e78a99816c86..26442db7d608 100644
--- a/arch/um/drivers/chan_kern.c
+++ b/arch/um/drivers/chan_kern.c
@@ -212,7 +212,7 @@ int enable_chan(struct line *line)
  * be permanently disabled.  This is discovered in IRQ context, but
  * the freeing of the IRQ must be done later.
  */
-static DEFINE_SPINLOCK(irqs_to_free_lock);
+static DEFINE_RAW_SPINLOCK(irqs_to_free_lock);
 static LIST_HEAD(irqs_to_free);
 
 void free_irqs(void)
@@ -222,9 +222,9 @@ void free_irqs(void)
 	struct list_head *ele;
 	unsigned long flags;
 
-	spin_lock_irqsave(&irqs_to_free_lock, flags);
+	raw_spin_lock_irqsave(&irqs_to_free_lock, flags);
 	list_splice_init(&irqs_to_free, &list);
-	spin_unlock_irqrestore(&irqs_to_free_lock, flags);
+	raw_spin_unlock_irqrestore(&irqs_to_free_lock, flags);
 
 	list_for_each(ele, &list) {
 		chan = list_entry(ele, struct chan, free_list);
@@ -246,9 +246,9 @@ static void close_one_chan(struct chan *chan, int delay_free_irq)
 		return;
 
 	if (delay_free_irq) {
-		spin_lock_irqsave(&irqs_to_free_lock, flags);
+		raw_spin_lock_irqsave(&irqs_to_free_lock, flags);
 		list_add(&chan->free_list, &irqs_to_free);
-		spin_unlock_irqrestore(&irqs_to_free_lock, flags);
+		raw_spin_unlock_irqrestore(&irqs_to_free_lock, flags);
 	} else {
 		if (chan->input && chan->enabled)
 			um_free_irq(chan->line->read_irq, chan);
diff --git a/arch/um/drivers/daemon.h b/arch/um/drivers/daemon.h
deleted file mode 100644
index 1509cc7eb907..000000000000
--- a/arch/um/drivers/daemon.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#ifndef __DAEMON_H__
-#define __DAEMON_H__
-
-#include <net_user.h>
-
-#define SWITCH_VERSION 3
-
-struct daemon_data {
-	char *sock_type;
-	char *ctl_sock;
-	void *ctl_addr;
-	void *data_addr;
-	void *local_addr;
-	int fd;
-	int control;
-	void *dev;
-};
-
-extern const struct net_user_info daemon_user_info;
-
-extern int daemon_user_write(int fd, void *buf, int len,
-			     struct daemon_data *pri);
-
-#endif
diff --git a/arch/um/drivers/daemon_kern.c b/arch/um/drivers/daemon_kern.c
deleted file mode 100644
index afde1e82c056..000000000000
--- a/arch/um/drivers/daemon_kern.c
+++ /dev/null
@@ -1,95 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and
- * James Leu (jleu@mindspring.net).
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Copyright (C) 2001 by various other people who didn't put their name here.
- */
-
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <net_kern.h>
-#include "daemon.h"
-
-struct daemon_init {
-	char *sock_type;
-	char *ctl_sock;
-};
-
-static void daemon_init(struct net_device *dev, void *data)
-{
-	struct uml_net_private *pri;
-	struct daemon_data *dpri;
-	struct daemon_init *init = data;
-
-	pri = netdev_priv(dev);
-	dpri = (struct daemon_data *) pri->user;
-	dpri->sock_type = init->sock_type;
-	dpri->ctl_sock = init->ctl_sock;
-	dpri->fd = -1;
-	dpri->control = -1;
-	dpri->dev = dev;
-	/* We will free this pointer. If it contains crap we're burned. */
-	dpri->ctl_addr = NULL;
-	dpri->data_addr = NULL;
-	dpri->local_addr = NULL;
-
-	printk("daemon backend (uml_switch version %d) - %s:%s",
-	       SWITCH_VERSION, dpri->sock_type, dpri->ctl_sock);
-	printk("\n");
-}
-
-static int daemon_read(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	return net_recvfrom(fd, skb_mac_header(skb),
-			    skb->dev->mtu + ETH_HEADER_OTHER);
-}
-
-static int daemon_write(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	return daemon_user_write(fd, skb->data, skb->len,
-				 (struct daemon_data *) &lp->user);
-}
-
-static const struct net_kern_info daemon_kern_info = {
-	.init			= daemon_init,
-	.protocol		= eth_protocol,
-	.read			= daemon_read,
-	.write			= daemon_write,
-};
-
-static int daemon_setup(char *str, char **mac_out, void *data)
-{
-	struct daemon_init *init = data;
-	char *remain;
-
-	*init = ((struct daemon_init)
-		{ .sock_type 		= "unix",
-		  .ctl_sock 		= CONFIG_UML_NET_DAEMON_DEFAULT_SOCK });
-
-	remain = split_if_spec(str, mac_out, &init->sock_type, &init->ctl_sock,
-			       NULL);
-	if (remain != NULL)
-		printk(KERN_WARNING "daemon_setup : Ignoring data socket "
-		       "specification\n");
-
-	return 1;
-}
-
-static struct transport daemon_transport = {
-	.list 		= LIST_HEAD_INIT(daemon_transport.list),
-	.name 		= "daemon",
-	.setup  	= daemon_setup,
-	.user 		= &daemon_user_info,
-	.kern 		= &daemon_kern_info,
-	.private_size 	= sizeof(struct daemon_data),
-	.setup_size 	= sizeof(struct daemon_init),
-};
-
-static int register_daemon(void)
-{
-	register_transport(&daemon_transport);
-	return 0;
-}
-
-late_initcall(register_daemon);
diff --git a/arch/um/drivers/daemon_user.c b/arch/um/drivers/daemon_user.c
deleted file mode 100644
index 785baedc3555..000000000000
--- a/arch/um/drivers/daemon_user.c
+++ /dev/null
@@ -1,194 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and
- * James Leu (jleu@mindspring.net).
- * Copyright (C) 2001 by various other people who didn't put their name here.
- */
-
-#include <stdint.h>
-#include <string.h>
-#include <unistd.h>
-#include <errno.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-#include <sys/time.h>
-#include <sys/un.h>
-#include "daemon.h"
-#include <net_user.h>
-#include <os.h>
-#include <um_malloc.h>
-
-enum request_type { REQ_NEW_CONTROL };
-
-#define SWITCH_MAGIC 0xfeedface
-
-struct request_v3 {
-	uint32_t magic;
-	uint32_t version;
-	enum request_type type;
-	struct sockaddr_un sock;
-};
-
-static struct sockaddr_un *new_addr(void *name, int len)
-{
-	struct sockaddr_un *sun;
-
-	sun = uml_kmalloc(sizeof(struct sockaddr_un), UM_GFP_KERNEL);
-	if (sun == NULL) {
-		printk(UM_KERN_ERR "new_addr: allocation of sockaddr_un "
-		       "failed\n");
-		return NULL;
-	}
-	sun->sun_family = AF_UNIX;
-	memcpy(sun->sun_path, name, len);
-	return sun;
-}
-
-static int connect_to_switch(struct daemon_data *pri)
-{
-	struct sockaddr_un *ctl_addr = pri->ctl_addr;
-	struct sockaddr_un *local_addr = pri->local_addr;
-	struct sockaddr_un *sun;
-	struct request_v3 req;
-	int fd, n, err;
-
-	pri->control = socket(AF_UNIX, SOCK_STREAM, 0);
-	if (pri->control < 0) {
-		err = -errno;
-		printk(UM_KERN_ERR "daemon_open : control socket failed, "
-		       "errno = %d\n", -err);
-		return err;
-	}
-
-	if (connect(pri->control, (struct sockaddr *) ctl_addr,
-		   sizeof(*ctl_addr)) < 0) {
-		err = -errno;
-		printk(UM_KERN_ERR "daemon_open : control connect failed, "
-		       "errno = %d\n", -err);
-		goto out;
-	}
-
-	fd = socket(AF_UNIX, SOCK_DGRAM, 0);
-	if (fd < 0) {
-		err = -errno;
-		printk(UM_KERN_ERR "daemon_open : data socket failed, "
-		       "errno = %d\n", -err);
-		goto out;
-	}
-	if (bind(fd, (struct sockaddr *) local_addr, sizeof(*local_addr)) < 0) {
-		err = -errno;
-		printk(UM_KERN_ERR "daemon_open : data bind failed, "
-		       "errno = %d\n", -err);
-		goto out_close;
-	}
-
-	sun = uml_kmalloc(sizeof(struct sockaddr_un), UM_GFP_KERNEL);
-	if (sun == NULL) {
-		printk(UM_KERN_ERR "new_addr: allocation of sockaddr_un "
-		       "failed\n");
-		err = -ENOMEM;
-		goto out_close;
-	}
-
-	req.magic = SWITCH_MAGIC;
-	req.version = SWITCH_VERSION;
-	req.type = REQ_NEW_CONTROL;
-	req.sock = *local_addr;
-	n = write(pri->control, &req, sizeof(req));
-	if (n != sizeof(req)) {
-		printk(UM_KERN_ERR "daemon_open : control setup request "
-		       "failed, err = %d\n", -errno);
-		err = -ENOTCONN;
-		goto out_free;
-	}
-
-	n = read(pri->control, sun, sizeof(*sun));
-	if (n != sizeof(*sun)) {
-		printk(UM_KERN_ERR "daemon_open : read of data socket failed, "
-		       "err = %d\n", -errno);
-		err = -ENOTCONN;
-		goto out_free;
-	}
-
-	pri->data_addr = sun;
-	return fd;
-
- out_free:
-	kfree(sun);
- out_close:
-	close(fd);
- out:
-	close(pri->control);
-	return err;
-}
-
-static int daemon_user_init(void *data, void *dev)
-{
-	struct daemon_data *pri = data;
-	struct timeval tv;
-	struct {
-		char zero;
-		int pid;
-		int usecs;
-	} name;
-
-	if (!strcmp(pri->sock_type, "unix"))
-		pri->ctl_addr = new_addr(pri->ctl_sock,
-					 strlen(pri->ctl_sock) + 1);
-	name.zero = 0;
-	name.pid = os_getpid();
-	gettimeofday(&tv, NULL);
-	name.usecs = tv.tv_usec;
-	pri->local_addr = new_addr(&name, sizeof(name));
-	pri->dev = dev;
-	pri->fd = connect_to_switch(pri);
-	if (pri->fd < 0) {
-		kfree(pri->local_addr);
-		pri->local_addr = NULL;
-		return pri->fd;
-	}
-
-	return 0;
-}
-
-static int daemon_open(void *data)
-{
-	struct daemon_data *pri = data;
-	return pri->fd;
-}
-
-static void daemon_remove(void *data)
-{
-	struct daemon_data *pri = data;
-
-	close(pri->fd);
-	pri->fd = -1;
-	close(pri->control);
-	pri->control = -1;
-
-	kfree(pri->data_addr);
-	pri->data_addr = NULL;
-	kfree(pri->ctl_addr);
-	pri->ctl_addr = NULL;
-	kfree(pri->local_addr);
-	pri->local_addr = NULL;
-}
-
-int daemon_user_write(int fd, void *buf, int len, struct daemon_data *pri)
-{
-	struct sockaddr_un *data_addr = pri->data_addr;
-
-	return net_sendto(fd, buf, len, data_addr, sizeof(*data_addr));
-}
-
-const struct net_user_info daemon_user_info = {
-	.init		= daemon_user_init,
-	.open		= daemon_open,
-	.close	 	= NULL,
-	.remove	 	= daemon_remove,
-	.add_address	= NULL,
-	.delete_address = NULL,
-	.mtu		= ETH_MAX_PACKET,
-	.max_packet	= ETH_MAX_PACKET + ETH_HEADER_OTHER,
-};
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
deleted file mode 100644
index d5a9c5aabaec..000000000000
--- a/arch/um/drivers/net_kern.c
+++ /dev/null
@@ -1,889 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and
- * James Leu (jleu@mindspring.net).
- * Copyright (C) 2001 by various other people who didn't put their name here.
- */
-
-#include <linux/memblock.h>
-#include <linux/etherdevice.h>
-#include <linux/ethtool.h>
-#include <linux/inetdevice.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/netdevice.h>
-#include <linux/platform_device.h>
-#include <linux/rtnetlink.h>
-#include <linux/skbuff.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <init.h>
-#include <irq_kern.h>
-#include <irq_user.h>
-#include "mconsole_kern.h"
-#include <net_kern.h>
-#include <net_user.h>
-
-#define DRIVER_NAME "uml-netdev"
-
-static DEFINE_SPINLOCK(opened_lock);
-static LIST_HEAD(opened);
-
-/*
- * The drop_skb is used when we can't allocate an skb.  The
- * packet is read into drop_skb in order to get the data off the
- * connection to the host.
- * It is reallocated whenever a maximum packet size is seen which is
- * larger than any seen before.  update_drop_skb is called from
- * eth_configure when a new interface is added.
- */
-static DEFINE_SPINLOCK(drop_lock);
-static struct sk_buff *drop_skb;
-static int drop_max;
-
-static int update_drop_skb(int max)
-{
-	struct sk_buff *new;
-	unsigned long flags;
-	int err = 0;
-
-	spin_lock_irqsave(&drop_lock, flags);
-
-	if (max <= drop_max)
-		goto out;
-
-	err = -ENOMEM;
-	new = dev_alloc_skb(max);
-	if (new == NULL)
-		goto out;
-
-	skb_put(new, max);
-
-	kfree_skb(drop_skb);
-	drop_skb = new;
-	drop_max = max;
-	err = 0;
-out:
-	spin_unlock_irqrestore(&drop_lock, flags);
-
-	return err;
-}
-
-static int uml_net_rx(struct net_device *dev)
-{
-	struct uml_net_private *lp = netdev_priv(dev);
-	int pkt_len;
-	struct sk_buff *skb;
-
-	/* If we can't allocate memory, try again next round. */
-	skb = dev_alloc_skb(lp->max_packet);
-	if (skb == NULL) {
-		drop_skb->dev = dev;
-		/* Read a packet into drop_skb and don't do anything with it. */
-		(*lp->read)(lp->fd, drop_skb, lp);
-		dev->stats.rx_dropped++;
-		return 0;
-	}
-
-	skb->dev = dev;
-	skb_put(skb, lp->max_packet);
-	skb_reset_mac_header(skb);
-	pkt_len = (*lp->read)(lp->fd, skb, lp);
-
-	if (pkt_len > 0) {
-		skb_trim(skb, pkt_len);
-		skb->protocol = (*lp->protocol)(skb);
-
-		dev->stats.rx_bytes += skb->len;
-		dev->stats.rx_packets++;
-		netif_rx(skb);
-		return pkt_len;
-	}
-
-	kfree_skb(skb);
-	return pkt_len;
-}
-
-static void uml_dev_close(struct work_struct *work)
-{
-	struct uml_net_private *lp =
-		container_of(work, struct uml_net_private, work);
-	dev_close(lp->dev);
-}
-
-static irqreturn_t uml_net_interrupt(int irq, void *dev_id)
-{
-	struct net_device *dev = dev_id;
-	struct uml_net_private *lp = netdev_priv(dev);
-	int err;
-
-	if (!netif_running(dev))
-		return IRQ_NONE;
-
-	spin_lock(&lp->lock);
-	while ((err = uml_net_rx(dev)) > 0) ;
-	if (err < 0) {
-		printk(KERN_ERR
-		       "Device '%s' read returned %d, shutting it down\n",
-		       dev->name, err);
-		/* dev_close can't be called in interrupt context, and takes
-		 * again lp->lock.
-		 * And dev_close() can be safely called multiple times on the
-		 * same device, since it tests for (dev->flags & IFF_UP). So
-		 * there's no harm in delaying the device shutdown.
-		 * Furthermore, the workqueue will not re-enqueue an already
-		 * enqueued work item. */
-		schedule_work(&lp->work);
-		goto out;
-	}
-out:
-	spin_unlock(&lp->lock);
-	return IRQ_HANDLED;
-}
-
-static int uml_net_open(struct net_device *dev)
-{
-	struct uml_net_private *lp = netdev_priv(dev);
-	int err;
-
-	if (lp->fd >= 0) {
-		err = -ENXIO;
-		goto out;
-	}
-
-	lp->fd = (*lp->open)(&lp->user);
-	if (lp->fd < 0) {
-		err = lp->fd;
-		goto out;
-	}
-
-	err = um_request_irq(dev->irq, lp->fd, IRQ_READ, uml_net_interrupt,
-			     IRQF_SHARED, dev->name, dev);
-	if (err < 0) {
-		printk(KERN_ERR "uml_net_open: failed to get irq(%d)\n", err);
-		err = -ENETUNREACH;
-		goto out_close;
-	}
-
-	netif_start_queue(dev);
-
-	/* clear buffer - it can happen that the host side of the interface
-	 * is full when we get here.  In this case, new data is never queued,
-	 * SIGIOs never arrive, and the net never works.
-	 */
-	while ((err = uml_net_rx(dev)) > 0) ;
-
-	spin_lock(&opened_lock);
-	list_add(&lp->list, &opened);
-	spin_unlock(&opened_lock);
-
-	return 0;
-out_close:
-	if (lp->close != NULL) (*lp->close)(lp->fd, &lp->user);
-	lp->fd = -1;
-out:
-	return err;
-}
-
-static int uml_net_close(struct net_device *dev)
-{
-	struct uml_net_private *lp = netdev_priv(dev);
-
-	netif_stop_queue(dev);
-
-	um_free_irq(dev->irq, dev);
-	if (lp->close != NULL)
-		(*lp->close)(lp->fd, &lp->user);
-	lp->fd = -1;
-
-	spin_lock(&opened_lock);
-	list_del(&lp->list);
-	spin_unlock(&opened_lock);
-
-	return 0;
-}
-
-static netdev_tx_t uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct uml_net_private *lp = netdev_priv(dev);
-	unsigned long flags;
-	int len;
-
-	netif_stop_queue(dev);
-
-	spin_lock_irqsave(&lp->lock, flags);
-
-	len = (*lp->write)(lp->fd, skb, lp);
-	skb_tx_timestamp(skb);
-
-	if (len == skb->len) {
-		dev->stats.tx_packets++;
-		dev->stats.tx_bytes += skb->len;
-		netif_trans_update(dev);
-		netif_start_queue(dev);
-
-		/* this is normally done in the interrupt when tx finishes */
-		netif_wake_queue(dev);
-	}
-	else if (len == 0) {
-		netif_start_queue(dev);
-		dev->stats.tx_dropped++;
-	}
-	else {
-		netif_start_queue(dev);
-		printk(KERN_ERR "uml_net_start_xmit: failed(%d)\n", len);
-	}
-
-	spin_unlock_irqrestore(&lp->lock, flags);
-
-	dev_consume_skb_any(skb);
-
-	return NETDEV_TX_OK;
-}
-
-static void uml_net_set_multicast_list(struct net_device *dev)
-{
-	return;
-}
-
-static void uml_net_tx_timeout(struct net_device *dev, unsigned int txqueue)
-{
-	netif_trans_update(dev);
-	netif_wake_queue(dev);
-}
-
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void uml_net_poll_controller(struct net_device *dev)
-{
-	disable_irq(dev->irq);
-	uml_net_interrupt(dev->irq, dev);
-	enable_irq(dev->irq);
-}
-#endif
-
-static void uml_net_get_drvinfo(struct net_device *dev,
-				struct ethtool_drvinfo *info)
-{
-	strscpy(info->driver, DRIVER_NAME);
-}
-
-static const struct ethtool_ops uml_net_ethtool_ops = {
-	.get_drvinfo	= uml_net_get_drvinfo,
-	.get_link	= ethtool_op_get_link,
-	.get_ts_info	= ethtool_op_get_ts_info,
-};
-
-void uml_net_setup_etheraddr(struct net_device *dev, char *str)
-{
-	u8 addr[ETH_ALEN];
-	char *end;
-	int i;
-
-	if (str == NULL)
-		goto random;
-
-	for (i = 0; i < 6; i++) {
-		addr[i] = simple_strtoul(str, &end, 16);
-		if ((end == str) ||
-		   ((*end != ':') && (*end != ',') && (*end != '\0'))) {
-			printk(KERN_ERR
-			       "setup_etheraddr: failed to parse '%s' "
-			       "as an ethernet address\n", str);
-			goto random;
-		}
-		str = end + 1;
-	}
-	if (is_multicast_ether_addr(addr)) {
-		printk(KERN_ERR
-		       "Attempt to assign a multicast ethernet address to a "
-		       "device disallowed\n");
-		goto random;
-	}
-	if (!is_valid_ether_addr(addr)) {
-		printk(KERN_ERR
-		       "Attempt to assign an invalid ethernet address to a "
-		       "device disallowed\n");
-		goto random;
-	}
-	if (!is_local_ether_addr(addr)) {
-		printk(KERN_WARNING
-		       "Warning: Assigning a globally valid ethernet "
-		       "address to a device\n");
-		printk(KERN_WARNING "You should set the 2nd rightmost bit in "
-		       "the first byte of the MAC,\n");
-		printk(KERN_WARNING "i.e. %02x:%02x:%02x:%02x:%02x:%02x\n",
-		       addr[0] | 0x02, addr[1], addr[2], addr[3], addr[4],
-		       addr[5]);
-	}
-	eth_hw_addr_set(dev, addr);
-	return;
-
-random:
-	printk(KERN_INFO
-	       "Choosing a random ethernet address for device %s\n", dev->name);
-	eth_hw_addr_random(dev);
-}
-
-static DEFINE_SPINLOCK(devices_lock);
-static LIST_HEAD(devices);
-
-static struct platform_driver uml_net_driver = {
-	.driver = {
-		.name  = DRIVER_NAME,
-	},
-};
-
-static void net_device_release(struct device *dev)
-{
-	struct uml_net *device = container_of(dev, struct uml_net, pdev.dev);
-	struct net_device *netdev = device->dev;
-	struct uml_net_private *lp = netdev_priv(netdev);
-
-	if (lp->remove != NULL)
-		(*lp->remove)(&lp->user);
-	list_del(&device->list);
-	kfree(device);
-	free_netdev(netdev);
-}
-
-static const struct net_device_ops uml_netdev_ops = {
-	.ndo_open 		= uml_net_open,
-	.ndo_stop 		= uml_net_close,
-	.ndo_start_xmit 	= uml_net_start_xmit,
-	.ndo_set_rx_mode	= uml_net_set_multicast_list,
-	.ndo_tx_timeout 	= uml_net_tx_timeout,
-	.ndo_set_mac_address	= eth_mac_addr,
-	.ndo_validate_addr	= eth_validate_addr,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller = uml_net_poll_controller,
-#endif
-};
-
-/*
- * Ensures that platform_driver_register is called only once by
- * eth_configure.  Will be set in an initcall.
- */
-static int driver_registered;
-
-static void eth_configure(int n, void *init, char *mac,
-			  struct transport *transport, gfp_t gfp_mask)
-{
-	struct uml_net *device;
-	struct net_device *dev;
-	struct uml_net_private *lp;
-	int err, size;
-
-	size = transport->private_size + sizeof(struct uml_net_private);
-
-	device = kzalloc(sizeof(*device), gfp_mask);
-	if (device == NULL) {
-		printk(KERN_ERR "eth_configure failed to allocate struct "
-		       "uml_net\n");
-		return;
-	}
-
-	dev = alloc_etherdev(size);
-	if (dev == NULL) {
-		printk(KERN_ERR "eth_configure: failed to allocate struct "
-		       "net_device for eth%d\n", n);
-		goto out_free_device;
-	}
-
-	INIT_LIST_HEAD(&device->list);
-	device->index = n;
-
-	/* If this name ends up conflicting with an existing registered
-	 * netdevice, that is OK, register_netdev{,ice}() will notice this
-	 * and fail.
-	 */
-	snprintf(dev->name, sizeof(dev->name), "eth%d", n);
-
-	uml_net_setup_etheraddr(dev, mac);
-
-	printk(KERN_INFO "Netdevice %d (%pM) : ", n, dev->dev_addr);
-
-	lp = netdev_priv(dev);
-	/* This points to the transport private data. It's still clear, but we
-	 * must memset it to 0 *now*. Let's help the drivers. */
-	memset(lp, 0, size);
-	INIT_WORK(&lp->work, uml_dev_close);
-
-	/* sysfs register */
-	if (!driver_registered) {
-		platform_driver_register(&uml_net_driver);
-		driver_registered = 1;
-	}
-	device->pdev.id = n;
-	device->pdev.name = DRIVER_NAME;
-	device->pdev.dev.release = net_device_release;
-	dev_set_drvdata(&device->pdev.dev, device);
-	if (platform_device_register(&device->pdev))
-		goto out_free_netdev;
-	SET_NETDEV_DEV(dev,&device->pdev.dev);
-
-	device->dev = dev;
-
-	/*
-	 * These just fill in a data structure, so there's no failure
-	 * to be worried about.
-	 */
-	(*transport->kern->init)(dev, init);
-
-	*lp = ((struct uml_net_private)
-		{ .list  		= LIST_HEAD_INIT(lp->list),
-		  .dev 			= dev,
-		  .fd 			= -1,
-		  .mac 			= { 0xfe, 0xfd, 0x0, 0x0, 0x0, 0x0},
-		  .max_packet		= transport->user->max_packet,
-		  .protocol 		= transport->kern->protocol,
-		  .open 		= transport->user->open,
-		  .close 		= transport->user->close,
-		  .remove 		= transport->user->remove,
-		  .read 		= transport->kern->read,
-		  .write 		= transport->kern->write,
-		  .add_address 		= transport->user->add_address,
-		  .delete_address  	= transport->user->delete_address });
-
-	spin_lock_init(&lp->lock);
-	memcpy(lp->mac, dev->dev_addr, sizeof(lp->mac));
-
-	if ((transport->user->init != NULL) &&
-	    ((*transport->user->init)(&lp->user, dev) != 0))
-		goto out_unregister;
-
-	dev->mtu = transport->user->mtu;
-	dev->netdev_ops = &uml_netdev_ops;
-	dev->ethtool_ops = &uml_net_ethtool_ops;
-	dev->watchdog_timeo = (HZ >> 1);
-	dev->irq = UM_ETH_IRQ;
-
-	err = update_drop_skb(lp->max_packet);
-	if (err)
-		goto out_undo_user_init;
-
-	rtnl_lock();
-	err = register_netdevice(dev);
-	rtnl_unlock();
-	if (err)
-		goto out_undo_user_init;
-
-	spin_lock(&devices_lock);
-	list_add(&device->list, &devices);
-	spin_unlock(&devices_lock);
-
-	return;
-
-out_undo_user_init:
-	if (transport->user->remove != NULL)
-		(*transport->user->remove)(&lp->user);
-out_unregister:
-	platform_device_unregister(&device->pdev);
-	return; /* platform_device_unregister frees dev and device */
-out_free_netdev:
-	free_netdev(dev);
-out_free_device:
-	kfree(device);
-}
-
-static struct uml_net *find_device(int n)
-{
-	struct uml_net *device;
-	struct list_head *ele;
-
-	spin_lock(&devices_lock);
-	list_for_each(ele, &devices) {
-		device = list_entry(ele, struct uml_net, list);
-		if (device->index == n)
-			goto out;
-	}
-	device = NULL;
- out:
-	spin_unlock(&devices_lock);
-	return device;
-}
-
-static int eth_parse(char *str, int *index_out, char **str_out,
-		     char **error_out)
-{
-	char *end;
-	int n, err = -EINVAL;
-
-	n = simple_strtoul(str, &end, 0);
-	if (end == str) {
-		*error_out = "Bad device number";
-		return err;
-	}
-
-	str = end;
-	if (*str != '=') {
-		*error_out = "Expected '=' after device number";
-		return err;
-	}
-
-	str++;
-	if (find_device(n)) {
-		*error_out = "Device already configured";
-		return err;
-	}
-
-	*index_out = n;
-	*str_out = str;
-	return 0;
-}
-
-struct eth_init {
-	struct list_head list;
-	char *init;
-	int index;
-};
-
-static DEFINE_SPINLOCK(transports_lock);
-static LIST_HEAD(transports);
-
-/* Filled in during early boot */
-static LIST_HEAD(eth_cmd_line);
-
-static int check_transport(struct transport *transport, char *eth, int n,
-			   void **init_out, char **mac_out, gfp_t gfp_mask)
-{
-	int len;
-
-	len = strlen(transport->name);
-	if (strncmp(eth, transport->name, len))
-		return 0;
-
-	eth += len;
-	if (*eth == ',')
-		eth++;
-	else if (*eth != '\0')
-		return 0;
-
-	*init_out = kmalloc(transport->setup_size, gfp_mask);
-	if (*init_out == NULL)
-		return 1;
-
-	if (!transport->setup(eth, mac_out, *init_out)) {
-		kfree(*init_out);
-		*init_out = NULL;
-	}
-	return 1;
-}
-
-void register_transport(struct transport *new)
-{
-	struct list_head *ele, *next;
-	struct eth_init *eth;
-	void *init;
-	char *mac = NULL;
-	int match;
-
-	spin_lock(&transports_lock);
-	BUG_ON(!list_empty(&new->list));
-	list_add(&new->list, &transports);
-	spin_unlock(&transports_lock);
-
-	list_for_each_safe(ele, next, &eth_cmd_line) {
-		eth = list_entry(ele, struct eth_init, list);
-		match = check_transport(new, eth->init, eth->index, &init,
-					&mac, GFP_KERNEL);
-		if (!match)
-			continue;
-		else if (init != NULL) {
-			eth_configure(eth->index, init, mac, new, GFP_KERNEL);
-			kfree(init);
-		}
-		list_del(&eth->list);
-	}
-}
-
-static int eth_setup_common(char *str, int index)
-{
-	struct list_head *ele;
-	struct transport *transport;
-	void *init;
-	char *mac = NULL;
-	int found = 0;
-
-	spin_lock(&transports_lock);
-	list_for_each(ele, &transports) {
-		transport = list_entry(ele, struct transport, list);
-	        if (!check_transport(transport, str, index, &init,
-					&mac, GFP_ATOMIC))
-			continue;
-		if (init != NULL) {
-			eth_configure(index, init, mac, transport, GFP_ATOMIC);
-			kfree(init);
-		}
-		found = 1;
-		break;
-	}
-
-	spin_unlock(&transports_lock);
-	return found;
-}
-
-static int __init eth_setup(char *str)
-{
-	struct eth_init *new;
-	char *error;
-	int n, err;
-
-	err = eth_parse(str, &n, &str, &error);
-	if (err) {
-		printk(KERN_ERR "eth_setup - Couldn't parse '%s' : %s\n",
-		       str, error);
-		return 1;
-	}
-
-	new = memblock_alloc_or_panic(sizeof(*new), SMP_CACHE_BYTES);
-
-	INIT_LIST_HEAD(&new->list);
-	new->index = n;
-	new->init = str;
-
-	list_add_tail(&new->list, &eth_cmd_line);
-	return 1;
-}
-
-__setup("eth", eth_setup);
-__uml_help(eth_setup,
-"eth[0-9]+=<transport>,<options>\n"
-"    Configure a network device.\n\n"
-);
-
-static int net_config(char *str, char **error_out)
-{
-	int n, err;
-
-	err = eth_parse(str, &n, &str, error_out);
-	if (err)
-		return err;
-
-	/* This string is broken up and the pieces used by the underlying
-	 * driver.  So, it is freed only if eth_setup_common fails.
-	 */
-	str = kstrdup(str, GFP_KERNEL);
-	if (str == NULL) {
-	        *error_out = "net_config failed to strdup string";
-		return -ENOMEM;
-	}
-	err = !eth_setup_common(str, n);
-	if (err)
-		kfree(str);
-	return err;
-}
-
-static int net_id(char **str, int *start_out, int *end_out)
-{
-	char *end;
-	int n;
-
-	n = simple_strtoul(*str, &end, 0);
-	if ((*end != '\0') || (end == *str))
-		return -1;
-
-	*start_out = n;
-	*end_out = n;
-	*str = end;
-	return n;
-}
-
-static int net_remove(int n, char **error_out)
-{
-	struct uml_net *device;
-	struct net_device *dev;
-	struct uml_net_private *lp;
-
-	device = find_device(n);
-	if (device == NULL)
-		return -ENODEV;
-
-	dev = device->dev;
-	lp = netdev_priv(dev);
-	if (lp->fd > 0)
-		return -EBUSY;
-	unregister_netdev(dev);
-	platform_device_unregister(&device->pdev);
-
-	return 0;
-}
-
-static struct mc_device net_mc = {
-	.list		= LIST_HEAD_INIT(net_mc.list),
-	.name		= "eth",
-	.config		= net_config,
-	.get_config	= NULL,
-	.id		= net_id,
-	.remove		= net_remove,
-};
-
-#ifdef CONFIG_INET
-static int uml_inetaddr_event(struct notifier_block *this, unsigned long event,
-			      void *ptr)
-{
-	struct in_ifaddr *ifa = ptr;
-	struct net_device *dev = ifa->ifa_dev->dev;
-	struct uml_net_private *lp;
-	void (*proc)(unsigned char *, unsigned char *, void *);
-	unsigned char addr_buf[4], netmask_buf[4];
-
-	if (dev->netdev_ops->ndo_open != uml_net_open)
-		return NOTIFY_DONE;
-
-	lp = netdev_priv(dev);
-
-	proc = NULL;
-	switch (event) {
-	case NETDEV_UP:
-		proc = lp->add_address;
-		break;
-	case NETDEV_DOWN:
-		proc = lp->delete_address;
-		break;
-	}
-	if (proc != NULL) {
-		memcpy(addr_buf, &ifa->ifa_address, sizeof(addr_buf));
-		memcpy(netmask_buf, &ifa->ifa_mask, sizeof(netmask_buf));
-		(*proc)(addr_buf, netmask_buf, &lp->user);
-	}
-	return NOTIFY_DONE;
-}
-
-/* uml_net_init shouldn't be called twice on two CPUs at the same time */
-static struct notifier_block uml_inetaddr_notifier = {
-	.notifier_call		= uml_inetaddr_event,
-};
-
-static void inet_register(void)
-{
-	struct list_head *ele;
-	struct uml_net_private *lp;
-	struct in_device *ip;
-	struct in_ifaddr *in;
-
-	register_inetaddr_notifier(&uml_inetaddr_notifier);
-
-	/* Devices may have been opened already, so the uml_inetaddr_notifier
-	 * didn't get a chance to run for them.  This fakes it so that
-	 * addresses which have already been set up get handled properly.
-	 */
-	spin_lock(&opened_lock);
-	list_for_each(ele, &opened) {
-		lp = list_entry(ele, struct uml_net_private, list);
-		ip = lp->dev->ip_ptr;
-		if (ip == NULL)
-			continue;
-		in = ip->ifa_list;
-		while (in != NULL) {
-			uml_inetaddr_event(NULL, NETDEV_UP, in);
-			in = in->ifa_next;
-		}
-	}
-	spin_unlock(&opened_lock);
-}
-#else
-static inline void inet_register(void)
-{
-}
-#endif
-
-static int uml_net_init(void)
-{
-	mconsole_register_dev(&net_mc);
-	inet_register();
-	return 0;
-}
-
-__initcall(uml_net_init);
-
-static void close_devices(void)
-{
-	struct list_head *ele;
-	struct uml_net_private *lp;
-
-	spin_lock(&opened_lock);
-	list_for_each(ele, &opened) {
-		lp = list_entry(ele, struct uml_net_private, list);
-		um_free_irq(lp->dev->irq, lp->dev);
-		if ((lp->close != NULL) && (lp->fd >= 0))
-			(*lp->close)(lp->fd, &lp->user);
-		if (lp->remove != NULL)
-			(*lp->remove)(&lp->user);
-	}
-	spin_unlock(&opened_lock);
-}
-
-__uml_exitcall(close_devices);
-
-void iter_addresses(void *d, void (*cb)(unsigned char *, unsigned char *,
-					void *),
-		    void *arg)
-{
-	struct net_device *dev = d;
-	struct in_device *ip = dev->ip_ptr;
-	struct in_ifaddr *in;
-	unsigned char address[4], netmask[4];
-
-	if (ip == NULL) return;
-	in = ip->ifa_list;
-	while (in != NULL) {
-		memcpy(address, &in->ifa_address, sizeof(address));
-		memcpy(netmask, &in->ifa_mask, sizeof(netmask));
-		(*cb)(address, netmask, arg);
-		in = in->ifa_next;
-	}
-}
-
-int dev_netmask(void *d, void *m)
-{
-	struct net_device *dev = d;
-	struct in_device *ip = dev->ip_ptr;
-	struct in_ifaddr *in;
-	__be32 *mask_out = m;
-
-	if (ip == NULL)
-		return 1;
-
-	in = ip->ifa_list;
-	if (in == NULL)
-		return 1;
-
-	*mask_out = in->ifa_mask;
-	return 0;
-}
-
-void *get_output_buffer(int *len_out)
-{
-	void *ret;
-
-	ret = (void *) __get_free_pages(GFP_KERNEL, 0);
-	if (ret) *len_out = PAGE_SIZE;
-	else *len_out = 0;
-	return ret;
-}
-
-void free_output_buffer(void *buffer)
-{
-	free_pages((unsigned long) buffer, 0);
-}
-
-int tap_setup_common(char *str, char *type, char **dev_name, char **mac_out,
-		     char **gate_addr)
-{
-	char *remain;
-
-	remain = split_if_spec(str, dev_name, mac_out, gate_addr, NULL);
-	if (remain != NULL) {
-		printk(KERN_ERR "tap_setup_common - Extra garbage on "
-		       "specification : '%s'\n", remain);
-		return 1;
-	}
-
-	return 0;
-}
-
-unsigned short eth_protocol(struct sk_buff *skb)
-{
-	return eth_type_trans(skb, skb->dev);
-}
diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c
deleted file mode 100644
index 4c9576452ab0..000000000000
--- a/arch/um/drivers/net_user.c
+++ /dev/null
@@ -1,271 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#include <stdio.h>
-#include <unistd.h>
-#include <stdarg.h>
-#include <errno.h>
-#include <stddef.h>
-#include <string.h>
-#include <sys/socket.h>
-#include <sys/wait.h>
-#include <net_user.h>
-#include <os.h>
-#include <um_malloc.h>
-
-int tap_open_common(void *dev, char *gate_addr)
-{
-	int tap_addr[4];
-
-	if (gate_addr == NULL)
-		return 0;
-	if (sscanf(gate_addr, "%d.%d.%d.%d", &tap_addr[0],
-		  &tap_addr[1], &tap_addr[2], &tap_addr[3]) != 4) {
-		printk(UM_KERN_ERR "Invalid tap IP address - '%s'\n",
-		       gate_addr);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-void tap_check_ips(char *gate_addr, unsigned char *eth_addr)
-{
-	int tap_addr[4];
-
-	if ((gate_addr != NULL) &&
-	    (sscanf(gate_addr, "%d.%d.%d.%d", &tap_addr[0],
-		    &tap_addr[1], &tap_addr[2], &tap_addr[3]) == 4) &&
-	    (eth_addr[0] == tap_addr[0]) &&
-	    (eth_addr[1] == tap_addr[1]) &&
-	    (eth_addr[2] == tap_addr[2]) &&
-	    (eth_addr[3] == tap_addr[3])) {
-		printk(UM_KERN_ERR "The tap IP address and the UML eth IP "
-		       "address must be different\n");
-	}
-}
-
-/* Do reliable error handling as this fails frequently enough. */
-void read_output(int fd, char *output, int len)
-{
-	int remain, ret, expected;
-	char c;
-	char *str;
-
-	if (output == NULL) {
-		output = &c;
-		len = sizeof(c);
-	}
-
-	*output = '\0';
-	ret = read(fd, &remain, sizeof(remain));
-
-	if (ret != sizeof(remain)) {
-		if (ret < 0)
-			ret = -errno;
-		expected = sizeof(remain);
-		str = "length";
-		goto err;
-	}
-
-	while (remain != 0) {
-		expected = (remain < len) ? remain : len;
-		ret = read(fd, output, expected);
-		if (ret != expected) {
-			if (ret < 0)
-				ret = -errno;
-			str = "data";
-			goto err;
-		}
-		remain -= ret;
-	}
-
-	return;
-
-err:
-	if (ret < 0)
-		printk(UM_KERN_ERR "read_output - read of %s failed, "
-		       "errno = %d\n", str, -ret);
-	else
-		printk(UM_KERN_ERR "read_output - read of %s failed, read only "
-		       "%d of %d bytes\n", str, ret, expected);
-}
-
-int net_read(int fd, void *buf, int len)
-{
-	int n;
-
-	n = read(fd,  buf,  len);
-
-	if ((n < 0) && (errno == EAGAIN))
-		return 0;
-	else if (n == 0)
-		return -ENOTCONN;
-	return n;
-}
-
-int net_recvfrom(int fd, void *buf, int len)
-{
-	int n;
-
-	CATCH_EINTR(n = recvfrom(fd,  buf,  len, 0, NULL, NULL));
-	if (n < 0) {
-		if (errno == EAGAIN)
-			return 0;
-		return -errno;
-	}
-	else if (n == 0)
-		return -ENOTCONN;
-	return n;
-}
-
-int net_write(int fd, void *buf, int len)
-{
-	int n;
-
-	n = write(fd, buf, len);
-
-	if ((n < 0) && (errno == EAGAIN))
-		return 0;
-	else if (n == 0)
-		return -ENOTCONN;
-	return n;
-}
-
-int net_send(int fd, void *buf, int len)
-{
-	int n;
-
-	CATCH_EINTR(n = send(fd, buf, len, 0));
-	if (n < 0) {
-		if (errno == EAGAIN)
-			return 0;
-		return -errno;
-	}
-	else if (n == 0)
-		return -ENOTCONN;
-	return n;
-}
-
-int net_sendto(int fd, void *buf, int len, void *to, int sock_len)
-{
-	int n;
-
-	CATCH_EINTR(n = sendto(fd, buf, len, 0, (struct sockaddr *) to,
-			       sock_len));
-	if (n < 0) {
-		if (errno == EAGAIN)
-			return 0;
-		return -errno;
-	}
-	else if (n == 0)
-		return -ENOTCONN;
-	return n;
-}
-
-struct change_pre_exec_data {
-	int close_me;
-	int stdout_fd;
-};
-
-static void change_pre_exec(void *arg)
-{
-	struct change_pre_exec_data *data = arg;
-
-	close(data->close_me);
-	dup2(data->stdout_fd, 1);
-}
-
-static int change_tramp(char **argv, char *output, int output_len)
-{
-	int pid, fds[2], err;
-	struct change_pre_exec_data pe_data;
-
-	err = os_pipe(fds, 1, 0);
-	if (err < 0) {
-		printk(UM_KERN_ERR "change_tramp - pipe failed, err = %d\n",
-		       -err);
-		return err;
-	}
-	pe_data.close_me = fds[0];
-	pe_data.stdout_fd = fds[1];
-	pid = run_helper(change_pre_exec, &pe_data, argv);
-
-	if (pid > 0)	/* Avoid hang as we won't get data in failure case. */
-		read_output(fds[0], output, output_len);
-
-	close(fds[0]);
-	close(fds[1]);
-
-	if (pid > 0)
-		helper_wait(pid);
-	return pid;
-}
-
-static void change(char *dev, char *what, unsigned char *addr,
-		   unsigned char *netmask)
-{
-	char addr_buf[sizeof("255.255.255.255\0")];
-	char netmask_buf[sizeof("255.255.255.255\0")];
-	char version[sizeof("nnnnn\0")];
-	char *argv[] = { "uml_net", version, what, dev, addr_buf,
-			 netmask_buf, NULL };
-	char *output;
-	int output_len, pid;
-
-	sprintf(version, "%d", UML_NET_VERSION);
-	sprintf(addr_buf, "%d.%d.%d.%d", addr[0], addr[1], addr[2], addr[3]);
-	sprintf(netmask_buf, "%d.%d.%d.%d", netmask[0], netmask[1],
-		netmask[2], netmask[3]);
-
-	output_len = UM_KERN_PAGE_SIZE;
-	output = uml_kmalloc(output_len, UM_GFP_KERNEL);
-	if (output == NULL)
-		printk(UM_KERN_ERR "change : failed to allocate output "
-		       "buffer\n");
-
-	pid = change_tramp(argv, output, output_len);
-	if (pid < 0) {
-		kfree(output);
-		return;
-	}
-
-	if (output != NULL) {
-		printk("%s", output);
-		kfree(output);
-	}
-}
-
-void open_addr(unsigned char *addr, unsigned char *netmask, void *arg)
-{
-	change(arg, "add", addr, netmask);
-}
-
-void close_addr(unsigned char *addr, unsigned char *netmask, void *arg)
-{
-	change(arg, "del", addr, netmask);
-}
-
-char *split_if_spec(char *str, ...)
-{
-	char **arg, *end, *ret = NULL;
-	va_list ap;
-
-	va_start(ap, str);
-	while ((arg = va_arg(ap, char **)) != NULL) {
-		if (*str == '\0')
-			goto out;
-		end = strchr(str, ',');
-		if (end != str)
-			*arg = str;
-		if (end == NULL)
-			goto out;
-		*end++ = '\0';
-		str = end;
-	}
-	ret = str;
-out:
-	va_end(ap);
-	return ret;
-}
diff --git a/arch/um/drivers/slip.h b/arch/um/drivers/slip.h
deleted file mode 100644
index 0f3b7ca99465..000000000000
--- a/arch/um/drivers/slip.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __UM_SLIP_H
-#define __UM_SLIP_H
-
-#include "slip_common.h"
-
-struct slip_data {
-	void *dev;
-	char name[sizeof("slnnnnn\0")];
-	char *addr;
-	char *gate_addr;
-	int slave;
-	struct slip_proto slip;
-};
-
-extern const struct net_user_info slip_user_info;
-
-extern int slip_user_read(int fd, void *buf, int len, struct slip_data *pri);
-extern int slip_user_write(int fd, void *buf, int len, struct slip_data *pri);
-
-#endif
diff --git a/arch/um/drivers/slip_common.c b/arch/um/drivers/slip_common.c
deleted file mode 100644
index 20fe4f42743d..000000000000
--- a/arch/um/drivers/slip_common.c
+++ /dev/null
@@ -1,55 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <string.h>
-#include "slip_common.h"
-#include <net_user.h>
-
-int slip_proto_read(int fd, void *buf, int len, struct slip_proto *slip)
-{
-	int i, n, size, start;
-
-	if(slip->more > 0){
-		i = 0;
-		while(i < slip->more){
-			size = slip_unesc(slip->ibuf[i++], slip->ibuf,
-					  &slip->pos, &slip->esc);
-			if(size){
-				memcpy(buf, slip->ibuf, size);
-				memmove(slip->ibuf, &slip->ibuf[i],
-					slip->more - i);
-				slip->more = slip->more - i;
-				return size;
-			}
-		}
-		slip->more = 0;
-	}
-
-	n = net_read(fd, &slip->ibuf[slip->pos],
-		     sizeof(slip->ibuf) - slip->pos);
-	if(n <= 0)
-		return n;
-
-	start = slip->pos;
-	for(i = 0; i < n; i++){
-		size = slip_unesc(slip->ibuf[start + i], slip->ibuf,&slip->pos,
-				  &slip->esc);
-		if(size){
-			memcpy(buf, slip->ibuf, size);
-			memmove(slip->ibuf, &slip->ibuf[start+i+1],
-				n - (i + 1));
-			slip->more = n - (i + 1);
-			return size;
-		}
-	}
-	return 0;
-}
-
-int slip_proto_write(int fd, void *buf, int len, struct slip_proto *slip)
-{
-	int actual, n;
-
-	actual = slip_esc(buf, slip->obuf, len);
-	n = net_write(fd, slip->obuf, actual);
-	if(n < 0)
-		return n;
-	else return len;
-}
diff --git a/arch/um/drivers/slip_common.h b/arch/um/drivers/slip_common.h
deleted file mode 100644
index d3798b5caf7f..000000000000
--- a/arch/um/drivers/slip_common.h
+++ /dev/null
@@ -1,106 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __UM_SLIP_COMMON_H
-#define __UM_SLIP_COMMON_H
-
-#define BUF_SIZE 1500
- /* two bytes each for a (pathological) max packet of escaped chars +  *
-  * terminating END char + initial END char                            */
-#define ENC_BUF_SIZE (2 * BUF_SIZE + 2)
-
-/* SLIP protocol characters. */
-#define SLIP_END             0300	/* indicates end of frame	*/
-#define SLIP_ESC             0333	/* indicates byte stuffing	*/
-#define SLIP_ESC_END         0334	/* ESC ESC_END means END 'data'	*/
-#define SLIP_ESC_ESC         0335	/* ESC ESC_ESC means ESC 'data'	*/
-
-static inline int slip_unesc(unsigned char c, unsigned char *buf, int *pos,
-                             int *esc)
-{
-	int ret;
-
-	switch(c){
-	case SLIP_END:
-		*esc = 0;
-		ret=*pos;
-		*pos=0;
-		return(ret);
-	case SLIP_ESC:
-		*esc = 1;
-		return(0);
-	case SLIP_ESC_ESC:
-		if(*esc){
-			*esc = 0;
-			c = SLIP_ESC;
-		}
-		break;
-	case SLIP_ESC_END:
-		if(*esc){
-			*esc = 0;
-			c = SLIP_END;
-		}
-		break;
-	}
-	buf[(*pos)++] = c;
-	return(0);
-}
-
-static inline int slip_esc(unsigned char *s, unsigned char *d, int len)
-{
-	unsigned char *ptr = d;
-	unsigned char c;
-
-	/*
-	 * Send an initial END character to flush out any
-	 * data that may have accumulated in the receiver
-	 * due to line noise.
-	 */
-
-	*ptr++ = SLIP_END;
-
-	/*
-	 * For each byte in the packet, send the appropriate
-	 * character sequence, according to the SLIP protocol.
-	 */
-
-	while (len-- > 0) {
-		switch(c = *s++) {
-		case SLIP_END:
-			*ptr++ = SLIP_ESC;
-			*ptr++ = SLIP_ESC_END;
-			break;
-		case SLIP_ESC:
-			*ptr++ = SLIP_ESC;
-			*ptr++ = SLIP_ESC_ESC;
-			break;
-		default:
-			*ptr++ = c;
-			break;
-		}
-	}
-	*ptr++ = SLIP_END;
-	return (ptr - d);
-}
-
-struct slip_proto {
-	unsigned char ibuf[ENC_BUF_SIZE];
-	unsigned char obuf[ENC_BUF_SIZE];
-	int more; /* more data: do not read fd until ibuf has been drained */
-	int pos;
-	int esc;
-};
-
-static inline void slip_proto_init(struct slip_proto * slip)
-{
-	memset(slip->ibuf, 0, sizeof(slip->ibuf));
-	memset(slip->obuf, 0, sizeof(slip->obuf));
-	slip->more = 0;
-	slip->pos = 0;
-	slip->esc = 0;
-}
-
-extern int slip_proto_read(int fd, void *buf, int len,
-			   struct slip_proto *slip);
-extern int slip_proto_write(int fd, void *buf, int len,
-			    struct slip_proto *slip);
-
-#endif
diff --git a/arch/um/drivers/slip_kern.c b/arch/um/drivers/slip_kern.c
deleted file mode 100644
index c58ccdcc16d6..000000000000
--- a/arch/um/drivers/slip_kern.c
+++ /dev/null
@@ -1,93 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#include <linux/if_arp.h>
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <net_kern.h>
-#include "slip.h"
-
-struct slip_init {
-	char *gate_addr;
-};
-
-static void slip_init(struct net_device *dev, void *data)
-{
-	struct uml_net_private *private;
-	struct slip_data *spri;
-	struct slip_init *init = data;
-
-	private = netdev_priv(dev);
-	spri = (struct slip_data *) private->user;
-
-	memset(spri->name, 0, sizeof(spri->name));
-	spri->addr = NULL;
-	spri->gate_addr = init->gate_addr;
-	spri->slave = -1;
-	spri->dev = dev;
-
-	slip_proto_init(&spri->slip);
-
-	dev->hard_header_len = 0;
-	dev->header_ops = NULL;
-	dev->addr_len = 0;
-	dev->type = ARPHRD_SLIP;
-	dev->tx_queue_len = 256;
-	dev->flags = IFF_NOARP;
-	printk("SLIP backend - SLIP IP = %s\n", spri->gate_addr);
-}
-
-static unsigned short slip_protocol(struct sk_buff *skbuff)
-{
-	return htons(ETH_P_IP);
-}
-
-static int slip_read(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	return slip_user_read(fd, skb_mac_header(skb), skb->dev->mtu,
-			      (struct slip_data *) &lp->user);
-}
-
-static int slip_write(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	return slip_user_write(fd, skb->data, skb->len,
-			       (struct slip_data *) &lp->user);
-}
-
-static const struct net_kern_info slip_kern_info = {
-	.init			= slip_init,
-	.protocol		= slip_protocol,
-	.read			= slip_read,
-	.write			= slip_write,
-};
-
-static int slip_setup(char *str, char **mac_out, void *data)
-{
-	struct slip_init *init = data;
-
-	*init = ((struct slip_init) { .gate_addr = NULL });
-
-	if (str[0] != '\0')
-		init->gate_addr = str;
-	return 1;
-}
-
-static struct transport slip_transport = {
-	.list 		= LIST_HEAD_INIT(slip_transport.list),
-	.name 		= "slip",
-	.setup  	= slip_setup,
-	.user 		= &slip_user_info,
-	.kern 		= &slip_kern_info,
-	.private_size 	= sizeof(struct slip_data),
-	.setup_size 	= sizeof(struct slip_init),
-};
-
-static int register_slip(void)
-{
-	register_transport(&slip_transport);
-	return 0;
-}
-
-late_initcall(register_slip);
diff --git a/arch/um/drivers/slip_user.c b/arch/um/drivers/slip_user.c
deleted file mode 100644
index 7334019c9e60..000000000000
--- a/arch/um/drivers/slip_user.c
+++ /dev/null
@@ -1,252 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <errno.h>
-#include <fcntl.h>
-#include <string.h>
-#include <termios.h>
-#include <sys/wait.h>
-#include <net_user.h>
-#include <os.h>
-#include "slip.h"
-#include <um_malloc.h>
-
-static int slip_user_init(void *data, void *dev)
-{
-	struct slip_data *pri = data;
-
-	pri->dev = dev;
-	return 0;
-}
-
-static int set_up_tty(int fd)
-{
-	int i;
-	struct termios tios;
-
-	if (tcgetattr(fd, &tios) < 0) {
-		printk(UM_KERN_ERR "could not get initial terminal "
-		       "attributes\n");
-		return -1;
-	}
-
-	tios.c_cflag = CS8 | CREAD | HUPCL | CLOCAL;
-	tios.c_iflag = IGNBRK | IGNPAR;
-	tios.c_oflag = 0;
-	tios.c_lflag = 0;
-	for (i = 0; i < NCCS; i++)
-		tios.c_cc[i] = 0;
-	tios.c_cc[VMIN] = 1;
-	tios.c_cc[VTIME] = 0;
-
-	cfsetospeed(&tios, B38400);
-	cfsetispeed(&tios, B38400);
-
-	if (tcsetattr(fd, TCSAFLUSH, &tios) < 0) {
-		printk(UM_KERN_ERR "failed to set terminal attributes\n");
-		return -1;
-	}
-	return 0;
-}
-
-struct slip_pre_exec_data {
-	int stdin_fd;
-	int stdout_fd;
-	int close_me;
-};
-
-static void slip_pre_exec(void *arg)
-{
-	struct slip_pre_exec_data *data = arg;
-
-	if (data->stdin_fd >= 0)
-		dup2(data->stdin_fd, 0);
-	dup2(data->stdout_fd, 1);
-	if (data->close_me >= 0)
-		close(data->close_me);
-}
-
-static int slip_tramp(char **argv, int fd)
-{
-	struct slip_pre_exec_data pe_data;
-	char *output;
-	int pid, fds[2], err, output_len;
-
-	err = os_pipe(fds, 1, 0);
-	if (err < 0) {
-		printk(UM_KERN_ERR "slip_tramp : pipe failed, err = %d\n",
-		       -err);
-		goto out;
-	}
-
-	err = 0;
-	pe_data.stdin_fd = fd;
-	pe_data.stdout_fd = fds[1];
-	pe_data.close_me = fds[0];
-	err = run_helper(slip_pre_exec, &pe_data, argv);
-	if (err < 0)
-		goto out_close;
-	pid = err;
-
-	output_len = UM_KERN_PAGE_SIZE;
-	output = uml_kmalloc(output_len, UM_GFP_KERNEL);
-	if (output == NULL) {
-		printk(UM_KERN_ERR "slip_tramp : failed to allocate output "
-		       "buffer\n");
-		os_kill_process(pid, 1);
-		err = -ENOMEM;
-		goto out_close;
-	}
-
-	close(fds[1]);
-	read_output(fds[0], output, output_len);
-	printk("%s", output);
-
-	err = helper_wait(pid);
-	close(fds[0]);
-
-	kfree(output);
-	return err;
-
-out_close:
-	close(fds[0]);
-	close(fds[1]);
-out:
-	return err;
-}
-
-static int slip_open(void *data)
-{
-	struct slip_data *pri = data;
-	char version_buf[sizeof("nnnnn\0")];
-	char gate_buf[sizeof("nnn.nnn.nnn.nnn\0")];
-	char *argv[] = { "uml_net", version_buf, "slip", "up", gate_buf,
-			 NULL };
-	int sfd, mfd, err;
-
-	err = get_pty();
-	if (err < 0) {
-		printk(UM_KERN_ERR "slip-open : Failed to open pty, err = %d\n",
-		       -err);
-		goto out;
-	}
-	mfd = err;
-
-	err = open(ptsname(mfd), O_RDWR, 0);
-	if (err < 0) {
-		printk(UM_KERN_ERR "Couldn't open tty for slip line, "
-		       "err = %d\n", -err);
-		goto out_close;
-	}
-	sfd = err;
-
-	err = set_up_tty(sfd);
-	if (err)
-		goto out_close2;
-
-	pri->slave = sfd;
-	pri->slip.pos = 0;
-	pri->slip.esc = 0;
-	if (pri->gate_addr != NULL) {
-		sprintf(version_buf, "%d", UML_NET_VERSION);
-		strcpy(gate_buf, pri->gate_addr);
-
-		err = slip_tramp(argv, sfd);
-
-		if (err < 0) {
-			printk(UM_KERN_ERR "slip_tramp failed - err = %d\n",
-			       -err);
-			goto out_close2;
-		}
-		err = os_get_ifname(pri->slave, pri->name);
-		if (err < 0) {
-			printk(UM_KERN_ERR "get_ifname failed, err = %d\n",
-			       -err);
-			goto out_close2;
-		}
-		iter_addresses(pri->dev, open_addr, pri->name);
-	}
-	else {
-		err = os_set_slip(sfd);
-		if (err < 0) {
-			printk(UM_KERN_ERR "Failed to set slip discipline "
-			       "encapsulation - err = %d\n", -err);
-			goto out_close2;
-		}
-	}
-	return mfd;
-out_close2:
-	close(sfd);
-out_close:
-	close(mfd);
-out:
-	return err;
-}
-
-static void slip_close(int fd, void *data)
-{
-	struct slip_data *pri = data;
-	char version_buf[sizeof("nnnnn\0")];
-	char *argv[] = { "uml_net", version_buf, "slip", "down", pri->name,
-			 NULL };
-	int err;
-
-	if (pri->gate_addr != NULL)
-		iter_addresses(pri->dev, close_addr, pri->name);
-
-	sprintf(version_buf, "%d", UML_NET_VERSION);
-
-	err = slip_tramp(argv, pri->slave);
-
-	if (err != 0)
-		printk(UM_KERN_ERR "slip_tramp failed - errno = %d\n", -err);
-	close(fd);
-	close(pri->slave);
-	pri->slave = -1;
-}
-
-int slip_user_read(int fd, void *buf, int len, struct slip_data *pri)
-{
-	return slip_proto_read(fd, buf, len, &pri->slip);
-}
-
-int slip_user_write(int fd, void *buf, int len, struct slip_data *pri)
-{
-	return slip_proto_write(fd, buf, len, &pri->slip);
-}
-
-static void slip_add_addr(unsigned char *addr, unsigned char *netmask,
-			  void *data)
-{
-	struct slip_data *pri = data;
-
-	if (pri->slave < 0)
-		return;
-	open_addr(addr, netmask, pri->name);
-}
-
-static void slip_del_addr(unsigned char *addr, unsigned char *netmask,
-			    void *data)
-{
-	struct slip_data *pri = data;
-
-	if (pri->slave < 0)
-		return;
-	close_addr(addr, netmask, pri->name);
-}
-
-const struct net_user_info slip_user_info = {
-	.init		= slip_user_init,
-	.open		= slip_open,
-	.close	 	= slip_close,
-	.remove	 	= NULL,
-	.add_address	= slip_add_addr,
-	.delete_address = slip_del_addr,
-	.mtu		= BUF_SIZE,
-	.max_packet	= BUF_SIZE,
-};
diff --git a/arch/um/drivers/slirp.h b/arch/um/drivers/slirp.h
deleted file mode 100644
index 4aef2b88249a..000000000000
--- a/arch/um/drivers/slirp.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __UM_SLIRP_H
-#define __UM_SLIRP_H
-
-#include "slip_common.h"
-
-#define SLIRP_MAX_ARGS 100
-/*
- * XXX this next definition is here because I don't understand why this
- * initializer doesn't work in slirp_kern.c:
- *
- *   argv :  { init->argv[ 0 ... SLIRP_MAX_ARGS-1 ] },
- *
- * or why I can't typecast like this:
- *
- *   argv :  (char* [SLIRP_MAX_ARGS])(init->argv), 
- */
-struct arg_list_dummy_wrapper { char *argv[SLIRP_MAX_ARGS]; };
-
-struct slirp_data {
-	void *dev;
-	struct arg_list_dummy_wrapper argw;
-	int pid;
-	int slave;
-	struct slip_proto slip;
-};
-
-extern const struct net_user_info slirp_user_info;
-
-extern int slirp_user_read(int fd, void *buf, int len, struct slirp_data *pri);
-extern int slirp_user_write(int fd, void *buf, int len,
-			    struct slirp_data *pri);
-
-#endif
diff --git a/arch/um/drivers/slirp_kern.c b/arch/um/drivers/slirp_kern.c
deleted file mode 100644
index 0a6151ee9572..000000000000
--- a/arch/um/drivers/slirp_kern.c
+++ /dev/null
@@ -1,120 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#include <linux/if_arp.h>
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <linux/string.h>
-#include <net_kern.h>
-#include <net_user.h>
-#include "slirp.h"
-
-struct slirp_init {
-	struct arg_list_dummy_wrapper argw;  /* XXX should be simpler... */
-};
-
-static void slirp_init(struct net_device *dev, void *data)
-{
-	struct uml_net_private *private;
-	struct slirp_data *spri;
-	struct slirp_init *init = data;
-	int i;
-
-	private = netdev_priv(dev);
-	spri = (struct slirp_data *) private->user;
-
-	spri->argw = init->argw;
-	spri->pid = -1;
-	spri->slave = -1;
-	spri->dev = dev;
-
-	slip_proto_init(&spri->slip);
-
-	dev->hard_header_len = 0;
-	dev->header_ops = NULL;
-	dev->addr_len = 0;
-	dev->type = ARPHRD_SLIP;
-	dev->tx_queue_len = 256;
-	dev->flags = IFF_NOARP;
-	printk("SLIRP backend - command line:");
-	for (i = 0; spri->argw.argv[i] != NULL; i++)
-		printk(" '%s'",spri->argw.argv[i]);
-	printk("\n");
-}
-
-static unsigned short slirp_protocol(struct sk_buff *skbuff)
-{
-	return htons(ETH_P_IP);
-}
-
-static int slirp_read(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	return slirp_user_read(fd, skb_mac_header(skb), skb->dev->mtu,
-			       (struct slirp_data *) &lp->user);
-}
-
-static int slirp_write(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	return slirp_user_write(fd, skb->data, skb->len,
-				(struct slirp_data *) &lp->user);
-}
-
-const struct net_kern_info slirp_kern_info = {
-	.init			= slirp_init,
-	.protocol		= slirp_protocol,
-	.read			= slirp_read,
-	.write			= slirp_write,
-};
-
-static int slirp_setup(char *str, char **mac_out, void *data)
-{
-	struct slirp_init *init = data;
-	int i=0;
-
-	*init = ((struct slirp_init) { .argw = { { "slirp", NULL  } } });
-
-	str = split_if_spec(str, mac_out, NULL);
-
-	if (str == NULL) /* no command line given after MAC addr */
-		return 1;
-
-	do {
-		if (i >= SLIRP_MAX_ARGS - 1) {
-			printk(KERN_WARNING "slirp_setup: truncating slirp "
-			       "arguments\n");
-			break;
-		}
-		init->argw.argv[i++] = str;
-		while(*str && *str!=',') {
-			if (*str == '_')
-				*str=' ';
-			str++;
-		}
-		if (*str != ',')
-			break;
-		*str++ = '\0';
-	} while (1);
-
-	init->argw.argv[i] = NULL;
-	return 1;
-}
-
-static struct transport slirp_transport = {
-	.list 		= LIST_HEAD_INIT(slirp_transport.list),
-	.name 		= "slirp",
-	.setup  	= slirp_setup,
-	.user 		= &slirp_user_info,
-	.kern 		= &slirp_kern_info,
-	.private_size 	= sizeof(struct slirp_data),
-	.setup_size 	= sizeof(struct slirp_init),
-};
-
-static int register_slirp(void)
-{
-	register_transport(&slirp_transport);
-	return 0;
-}
-
-late_initcall(register_slirp);
diff --git a/arch/um/drivers/slirp_user.c b/arch/um/drivers/slirp_user.c
deleted file mode 100644
index 97228aa080cb..000000000000
--- a/arch/um/drivers/slirp_user.c
+++ /dev/null
@@ -1,124 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#include <unistd.h>
-#include <errno.h>
-#include <string.h>
-#include <sys/wait.h>
-#include <net_user.h>
-#include <os.h>
-#include "slirp.h"
-
-static int slirp_user_init(void *data, void *dev)
-{
-	struct slirp_data *pri = data;
-
-	pri->dev = dev;
-	return 0;
-}
-
-struct slirp_pre_exec_data {
-	int stdin_fd;
-	int stdout_fd;
-};
-
-static void slirp_pre_exec(void *arg)
-{
-	struct slirp_pre_exec_data *data = arg;
-
-	if (data->stdin_fd != -1)
-		dup2(data->stdin_fd, 0);
-	if (data->stdout_fd != -1)
-		dup2(data->stdout_fd, 1);
-}
-
-static int slirp_tramp(char **argv, int fd)
-{
-	struct slirp_pre_exec_data pe_data;
-	int pid;
-
-	pe_data.stdin_fd = fd;
-	pe_data.stdout_fd = fd;
-	pid = run_helper(slirp_pre_exec, &pe_data, argv);
-
-	return pid;
-}
-
-static int slirp_open(void *data)
-{
-	struct slirp_data *pri = data;
-	int fds[2], err;
-
-	err = os_pipe(fds, 1, 1);
-	if (err)
-		return err;
-
-	err = slirp_tramp(pri->argw.argv, fds[1]);
-	if (err < 0) {
-		printk(UM_KERN_ERR "slirp_tramp failed - errno = %d\n", -err);
-		goto out;
-	}
-
-	pri->slave = fds[1];
-	pri->slip.pos = 0;
-	pri->slip.esc = 0;
-	pri->pid = err;
-
-	return fds[0];
-out:
-	close(fds[0]);
-	close(fds[1]);
-	return err;
-}
-
-static void slirp_close(int fd, void *data)
-{
-	struct slirp_data *pri = data;
-	int err;
-
-	close(fd);
-	close(pri->slave);
-
-	pri->slave = -1;
-
-	if (pri->pid<1) {
-		printk(UM_KERN_ERR "slirp_close: no child process to shut "
-		       "down\n");
-		return;
-	}
-
-#if 0
-	if (kill(pri->pid, SIGHUP)<0) {
-		printk(UM_KERN_ERR "slirp_close: sending hangup to %d failed "
-		       "(%d)\n", pri->pid, errno);
-	}
-#endif
-	err = helper_wait(pri->pid);
-	if (err < 0)
-		return;
-
-	pri->pid = -1;
-}
-
-int slirp_user_read(int fd, void *buf, int len, struct slirp_data *pri)
-{
-	return slip_proto_read(fd, buf, len, &pri->slip);
-}
-
-int slirp_user_write(int fd, void *buf, int len, struct slirp_data *pri)
-{
-	return slip_proto_write(fd, buf, len, &pri->slip);
-}
-
-const struct net_user_info slirp_user_info = {
-	.init		= slirp_user_init,
-	.open		= slirp_open,
-	.close	 	= slirp_close,
-	.remove	 	= NULL,
-	.add_address	= NULL,
-	.delete_address = NULL,
-	.mtu		= BUF_SIZE,
-	.max_packet	= BUF_SIZE,
-};
diff --git a/arch/um/drivers/umcast.h b/arch/um/drivers/umcast.h
deleted file mode 100644
index fe39bee1e3bd..000000000000
--- a/arch/um/drivers/umcast.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#ifndef __DRIVERS_UMCAST_H
-#define __DRIVERS_UMCAST_H
-
-#include <net_user.h>
-
-struct umcast_data {
-	char *addr;
-	unsigned short lport;
-	unsigned short rport;
-	void *listen_addr;
-	void *remote_addr;
-	int ttl;
-	int unicast;
-	void *dev;
-};
-
-extern const struct net_user_info umcast_user_info;
-
-extern int umcast_user_write(int fd, void *buf, int len,
-			     struct umcast_data *pri);
-
-#endif
diff --git a/arch/um/drivers/umcast_kern.c b/arch/um/drivers/umcast_kern.c
deleted file mode 100644
index 595a54f2b9c6..000000000000
--- a/arch/um/drivers/umcast_kern.c
+++ /dev/null
@@ -1,188 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * user-mode-linux networking multicast transport
- * Copyright (C) 2001 by Harald Welte <laforge@gnumonks.org>
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- *
- * based on the existing uml-networking code, which is
- * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and
- * James Leu (jleu@mindspring.net).
- * Copyright (C) 2001 by various other people who didn't put their name here.
- *
- */
-
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include "umcast.h"
-#include <net_kern.h>
-
-struct umcast_init {
-	char *addr;
-	int lport;
-	int rport;
-	int ttl;
-	bool unicast;
-};
-
-static void umcast_init(struct net_device *dev, void *data)
-{
-	struct uml_net_private *pri;
-	struct umcast_data *dpri;
-	struct umcast_init *init = data;
-
-	pri = netdev_priv(dev);
-	dpri = (struct umcast_data *) pri->user;
-	dpri->addr = init->addr;
-	dpri->lport = init->lport;
-	dpri->rport = init->rport;
-	dpri->unicast = init->unicast;
-	dpri->ttl = init->ttl;
-	dpri->dev = dev;
-
-	if (dpri->unicast) {
-		printk(KERN_INFO "ucast backend address: %s:%u listen port: "
-		       "%u\n", dpri->addr, dpri->rport, dpri->lport);
-	} else {
-		printk(KERN_INFO "mcast backend multicast address: %s:%u, "
-		       "TTL:%u\n", dpri->addr, dpri->lport, dpri->ttl);
-	}
-}
-
-static int umcast_read(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	return net_recvfrom(fd, skb_mac_header(skb),
-			    skb->dev->mtu + ETH_HEADER_OTHER);
-}
-
-static int umcast_write(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	return umcast_user_write(fd, skb->data, skb->len,
-				(struct umcast_data *) &lp->user);
-}
-
-static const struct net_kern_info umcast_kern_info = {
-	.init			= umcast_init,
-	.protocol		= eth_protocol,
-	.read			= umcast_read,
-	.write			= umcast_write,
-};
-
-static int mcast_setup(char *str, char **mac_out, void *data)
-{
-	struct umcast_init *init = data;
-	char *port_str = NULL, *ttl_str = NULL, *remain;
-	char *last;
-
-	*init = ((struct umcast_init)
-		{ .addr	= "239.192.168.1",
-		  .lport	= 1102,
-		  .ttl	= 1 });
-
-	remain = split_if_spec(str, mac_out, &init->addr, &port_str, &ttl_str,
-			       NULL);
-	if (remain != NULL) {
-		printk(KERN_ERR "mcast_setup - Extra garbage on "
-		       "specification : '%s'\n", remain);
-		return 0;
-	}
-
-	if (port_str != NULL) {
-		init->lport = simple_strtoul(port_str, &last, 10);
-		if ((*last != '\0') || (last == port_str)) {
-			printk(KERN_ERR "mcast_setup - Bad port : '%s'\n",
-			       port_str);
-			return 0;
-		}
-	}
-
-	if (ttl_str != NULL) {
-		init->ttl = simple_strtoul(ttl_str, &last, 10);
-		if ((*last != '\0') || (last == ttl_str)) {
-			printk(KERN_ERR "mcast_setup - Bad ttl : '%s'\n",
-			       ttl_str);
-			return 0;
-		}
-	}
-
-	init->unicast = false;
-	init->rport = init->lport;
-
-	printk(KERN_INFO "Configured mcast device: %s:%u-%u\n", init->addr,
-	       init->lport, init->ttl);
-
-	return 1;
-}
-
-static int ucast_setup(char *str, char **mac_out, void *data)
-{
-	struct umcast_init *init = data;
-	char *lport_str = NULL, *rport_str = NULL, *remain;
-	char *last;
-
-	*init = ((struct umcast_init)
-		{ .addr		= "",
-		  .lport	= 1102,
-		  .rport	= 1102 });
-
-	remain = split_if_spec(str, mac_out, &init->addr,
-			       &lport_str, &rport_str, NULL);
-	if (remain != NULL) {
-		printk(KERN_ERR "ucast_setup - Extra garbage on "
-		       "specification : '%s'\n", remain);
-		return 0;
-	}
-
-	if (lport_str != NULL) {
-		init->lport = simple_strtoul(lport_str, &last, 10);
-		if ((*last != '\0') || (last == lport_str)) {
-			printk(KERN_ERR "ucast_setup - Bad listen port : "
-			       "'%s'\n", lport_str);
-			return 0;
-		}
-	}
-
-	if (rport_str != NULL) {
-		init->rport = simple_strtoul(rport_str, &last, 10);
-		if ((*last != '\0') || (last == rport_str)) {
-			printk(KERN_ERR "ucast_setup - Bad remote port : "
-			       "'%s'\n", rport_str);
-			return 0;
-		}
-	}
-
-	init->unicast = true;
-
-	printk(KERN_INFO "Configured ucast device: :%u -> %s:%u\n",
-	       init->lport, init->addr, init->rport);
-
-	return 1;
-}
-
-static struct transport mcast_transport = {
-	.list	= LIST_HEAD_INIT(mcast_transport.list),
-	.name	= "mcast",
-	.setup	= mcast_setup,
-	.user	= &umcast_user_info,
-	.kern	= &umcast_kern_info,
-	.private_size	= sizeof(struct umcast_data),
-	.setup_size	= sizeof(struct umcast_init),
-};
-
-static struct transport ucast_transport = {
-	.list	= LIST_HEAD_INIT(ucast_transport.list),
-	.name	= "ucast",
-	.setup	= ucast_setup,
-	.user	= &umcast_user_info,
-	.kern	= &umcast_kern_info,
-	.private_size	= sizeof(struct umcast_data),
-	.setup_size	= sizeof(struct umcast_init),
-};
-
-static int register_umcast(void)
-{
-	register_transport(&mcast_transport);
-	register_transport(&ucast_transport);
-	return 0;
-}
-
-late_initcall(register_umcast);
diff --git a/arch/um/drivers/umcast_user.c b/arch/um/drivers/umcast_user.c
deleted file mode 100644
index b50b13cff04e..000000000000
--- a/arch/um/drivers/umcast_user.c
+++ /dev/null
@@ -1,184 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * user-mode-linux networking multicast transport
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Copyright (C) 2001 by Harald Welte <laforge@gnumonks.org>
- *
- * based on the existing uml-networking code, which is
- * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and
- * James Leu (jleu@mindspring.net).
- * Copyright (C) 2001 by various other people who didn't put their name here.
- *
- *
- */
-
-#include <unistd.h>
-#include <errno.h>
-#include <netinet/in.h>
-#include "umcast.h"
-#include <net_user.h>
-#include <um_malloc.h>
-
-static struct sockaddr_in *new_addr(char *addr, unsigned short port)
-{
-	struct sockaddr_in *sin;
-
-	sin = uml_kmalloc(sizeof(struct sockaddr_in), UM_GFP_KERNEL);
-	if (sin == NULL) {
-		printk(UM_KERN_ERR "new_addr: allocation of sockaddr_in "
-		       "failed\n");
-		return NULL;
-	}
-	sin->sin_family = AF_INET;
-	if (addr)
-		sin->sin_addr.s_addr = in_aton(addr);
-	else
-		sin->sin_addr.s_addr = INADDR_ANY;
-	sin->sin_port = htons(port);
-	return sin;
-}
-
-static int umcast_user_init(void *data, void *dev)
-{
-	struct umcast_data *pri = data;
-
-	pri->remote_addr = new_addr(pri->addr, pri->rport);
-	if (pri->unicast)
-		pri->listen_addr = new_addr(NULL, pri->lport);
-	else
-		pri->listen_addr = pri->remote_addr;
-	pri->dev = dev;
-	return 0;
-}
-
-static void umcast_remove(void *data)
-{
-	struct umcast_data *pri = data;
-
-	kfree(pri->listen_addr);
-	if (pri->unicast)
-		kfree(pri->remote_addr);
-	pri->listen_addr = pri->remote_addr = NULL;
-}
-
-static int umcast_open(void *data)
-{
-	struct umcast_data *pri = data;
-	struct sockaddr_in *lsin = pri->listen_addr;
-	struct sockaddr_in *rsin = pri->remote_addr;
-	struct ip_mreq mreq;
-	int fd, yes = 1, err = -EINVAL;
-
-
-	if ((!pri->unicast && lsin->sin_addr.s_addr == 0) ||
-	    (rsin->sin_addr.s_addr == 0) ||
-	    (lsin->sin_port == 0) || (rsin->sin_port == 0))
-		goto out;
-
-	fd = socket(AF_INET, SOCK_DGRAM, 0);
-
-	if (fd < 0) {
-		err = -errno;
-		printk(UM_KERN_ERR "umcast_open : data socket failed, "
-		       "errno = %d\n", errno);
-		goto out;
-	}
-
-	if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &yes, sizeof(yes)) < 0) {
-		err = -errno;
-		printk(UM_KERN_ERR "umcast_open: SO_REUSEADDR failed, "
-		       "errno = %d\n", errno);
-		goto out_close;
-	}
-
-	if (!pri->unicast) {
-		/* set ttl according to config */
-		if (setsockopt(fd, SOL_IP, IP_MULTICAST_TTL, &pri->ttl,
-			       sizeof(pri->ttl)) < 0) {
-			err = -errno;
-			printk(UM_KERN_ERR "umcast_open: IP_MULTICAST_TTL "
-			       "failed, error = %d\n", errno);
-			goto out_close;
-		}
-
-		/* set LOOP, so data does get fed back to local sockets */
-		if (setsockopt(fd, SOL_IP, IP_MULTICAST_LOOP,
-			       &yes, sizeof(yes)) < 0) {
-			err = -errno;
-			printk(UM_KERN_ERR "umcast_open: IP_MULTICAST_LOOP "
-			       "failed, error = %d\n", errno);
-			goto out_close;
-		}
-	}
-
-	/* bind socket to the address */
-	if (bind(fd, (struct sockaddr *) lsin, sizeof(*lsin)) < 0) {
-		err = -errno;
-		printk(UM_KERN_ERR "umcast_open : data bind failed, "
-		       "errno = %d\n", errno);
-		goto out_close;
-	}
-
-	if (!pri->unicast) {
-		/* subscribe to the multicast group */
-		mreq.imr_multiaddr.s_addr = lsin->sin_addr.s_addr;
-		mreq.imr_interface.s_addr = 0;
-		if (setsockopt(fd, SOL_IP, IP_ADD_MEMBERSHIP,
-			       &mreq, sizeof(mreq)) < 0) {
-			err = -errno;
-			printk(UM_KERN_ERR "umcast_open: IP_ADD_MEMBERSHIP "
-			       "failed, error = %d\n", errno);
-			printk(UM_KERN_ERR "There appears not to be a "
-			       "multicast-capable network interface on the "
-			       "host.\n");
-			printk(UM_KERN_ERR "eth0 should be configured in order "
-			       "to use the multicast transport.\n");
-			goto out_close;
-		}
-	}
-
-	return fd;
-
- out_close:
-	close(fd);
- out:
-	return err;
-}
-
-static void umcast_close(int fd, void *data)
-{
-	struct umcast_data *pri = data;
-
-	if (!pri->unicast) {
-		struct ip_mreq mreq;
-		struct sockaddr_in *lsin = pri->listen_addr;
-
-		mreq.imr_multiaddr.s_addr = lsin->sin_addr.s_addr;
-		mreq.imr_interface.s_addr = 0;
-		if (setsockopt(fd, SOL_IP, IP_DROP_MEMBERSHIP,
-			       &mreq, sizeof(mreq)) < 0) {
-			printk(UM_KERN_ERR "umcast_close: IP_DROP_MEMBERSHIP "
-			       "failed, error = %d\n", errno);
-		}
-	}
-
-	close(fd);
-}
-
-int umcast_user_write(int fd, void *buf, int len, struct umcast_data *pri)
-{
-	struct sockaddr_in *data_addr = pri->remote_addr;
-
-	return net_sendto(fd, buf, len, data_addr, sizeof(*data_addr));
-}
-
-const struct net_user_info umcast_user_info = {
-	.init	= umcast_user_init,
-	.open	= umcast_open,
-	.close	= umcast_close,
-	.remove	= umcast_remove,
-	.add_address	= NULL,
-	.delete_address = NULL,
-	.mtu	= ETH_MAX_PACKET,
-	.max_packet	= ETH_MAX_PACKET + ETH_HEADER_OTHER,
-};
diff --git a/arch/um/drivers/vde.h b/arch/um/drivers/vde.h
deleted file mode 100644
index cab0379e6142..000000000000
--- a/arch/um/drivers/vde.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2007 Luca Bigliardi (shammash@artha.org).
- */
-
-#ifndef __UM_VDE_H__
-#define __UM_VDE_H__
-
-struct vde_data {
-	char *vde_switch;
-	char *descr;
-	void *args;
-	void *conn;
-	void *dev;
-};
-
-struct vde_init {
-	char *vde_switch;
-	char *descr;
-	int port;
-	char *group;
-	int mode;
-};
-
-extern const struct net_user_info vde_user_info;
-
-extern void vde_init_libstuff(struct vde_data *vpri, struct vde_init *init);
-
-extern int vde_user_read(void *conn, void *buf, int len);
-extern int vde_user_write(void *conn, void *buf, int len);
-
-#endif
diff --git a/arch/um/drivers/vde_kern.c b/arch/um/drivers/vde_kern.c
deleted file mode 100644
index bc6f22cbfb35..000000000000
--- a/arch/um/drivers/vde_kern.c
+++ /dev/null
@@ -1,129 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2007 Luca Bigliardi (shammash@artha.org).
- *
- * Transport usage:
- *  ethN=vde,<vde_switch>,<mac addr>,<port>,<group>,<mode>,<description>
- *
- */
-
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <net_kern.h>
-#include <net_user.h>
-#include "vde.h"
-
-static void vde_init(struct net_device *dev, void *data)
-{
-	struct vde_init *init = data;
-	struct uml_net_private *pri;
-	struct vde_data *vpri;
-
-	pri = netdev_priv(dev);
-	vpri = (struct vde_data *) pri->user;
-
-	vpri->vde_switch = init->vde_switch;
-	vpri->descr = init->descr ? init->descr : "UML vde_transport";
-	vpri->args = NULL;
-	vpri->conn = NULL;
-	vpri->dev = dev;
-
-	printk("vde backend - %s, ", vpri->vde_switch ?
-	       vpri->vde_switch : "(default socket)");
-
-	vde_init_libstuff(vpri, init);
-
-	printk("\n");
-}
-
-static int vde_read(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	struct vde_data *pri = (struct vde_data *) &lp->user;
-
-	if (pri->conn != NULL)
-		return vde_user_read(pri->conn, skb_mac_header(skb),
-				     skb->dev->mtu + ETH_HEADER_OTHER);
-
-	printk(KERN_ERR "vde_read - we have no VDECONN to read from");
-	return -EBADF;
-}
-
-static int vde_write(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	struct vde_data *pri = (struct vde_data *) &lp->user;
-
-	if (pri->conn != NULL)
-		return vde_user_write((void *)pri->conn, skb->data,
-				      skb->len);
-
-	printk(KERN_ERR "vde_write - we have no VDECONN to write to");
-	return -EBADF;
-}
-
-static const struct net_kern_info vde_kern_info = {
-	.init			= vde_init,
-	.protocol		= eth_protocol,
-	.read			= vde_read,
-	.write			= vde_write,
-};
-
-static int vde_setup(char *str, char **mac_out, void *data)
-{
-	struct vde_init *init = data;
-	char *remain, *port_str = NULL, *mode_str = NULL, *last;
-
-	*init = ((struct vde_init)
-		{ .vde_switch		= NULL,
-		  .descr		= NULL,
-		  .port			= 0,
-		  .group		= NULL,
-		  .mode			= 0 });
-
-	remain = split_if_spec(str, &init->vde_switch, mac_out, &port_str,
-				&init->group, &mode_str, &init->descr, NULL);
-
-	if (remain != NULL)
-		printk(KERN_WARNING "vde_setup - Ignoring extra data :"
-		       "'%s'\n", remain);
-
-	if (port_str != NULL) {
-		init->port = simple_strtoul(port_str, &last, 10);
-		if ((*last != '\0') || (last == port_str)) {
-			printk(KERN_ERR "vde_setup - Bad port : '%s'\n",
-						port_str);
-			return 0;
-		}
-	}
-
-	if (mode_str != NULL) {
-		init->mode = simple_strtoul(mode_str, &last, 8);
-		if ((*last != '\0') || (last == mode_str)) {
-			printk(KERN_ERR "vde_setup - Bad mode : '%s'\n",
-						mode_str);
-			return 0;
-		}
-	}
-
-	printk(KERN_INFO "Configured vde device: %s\n", init->vde_switch ?
-	       init->vde_switch : "(default socket)");
-
-	return 1;
-}
-
-static struct transport vde_transport = {
-	.list 		= LIST_HEAD_INIT(vde_transport.list),
-	.name 		= "vde",
-	.setup  	= vde_setup,
-	.user 		= &vde_user_info,
-	.kern 		= &vde_kern_info,
-	.private_size 	= sizeof(struct vde_data),
-	.setup_size 	= sizeof(struct vde_init),
-};
-
-static int register_vde(void)
-{
-	register_transport(&vde_transport);
-	return 0;
-}
-
-late_initcall(register_vde);
diff --git a/arch/um/drivers/vde_user.c b/arch/um/drivers/vde_user.c
deleted file mode 100644
index bc7dc4e1e486..000000000000
--- a/arch/um/drivers/vde_user.c
+++ /dev/null
@@ -1,125 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2007 Luca Bigliardi (shammash@artha.org).
- */
-
-#include <stddef.h>
-#include <errno.h>
-#include <libvdeplug.h>
-#include <net_user.h>
-#include <um_malloc.h>
-#include "vde.h"
-
-static int vde_user_init(void *data, void *dev)
-{
-	struct vde_data *pri = data;
-	VDECONN *conn = NULL;
-	int err = -EINVAL;
-
-	pri->dev = dev;
-
-	conn = vde_open(pri->vde_switch, pri->descr, pri->args);
-
-	if (conn == NULL) {
-		err = -errno;
-		printk(UM_KERN_ERR "vde_user_init: vde_open failed, "
-		       "errno = %d\n", errno);
-		return err;
-	}
-
-	printk(UM_KERN_INFO "vde backend - connection opened\n");
-
-	pri->conn = conn;
-
-	return 0;
-}
-
-static int vde_user_open(void *data)
-{
-	struct vde_data *pri = data;
-
-	if (pri->conn != NULL)
-		return vde_datafd(pri->conn);
-
-	printk(UM_KERN_WARNING "vde_open - we have no VDECONN to open");
-	return -EINVAL;
-}
-
-static void vde_remove(void *data)
-{
-	struct vde_data *pri = data;
-
-	if (pri->conn != NULL) {
-		printk(UM_KERN_INFO "vde backend - closing connection\n");
-		vde_close(pri->conn);
-		pri->conn = NULL;
-		kfree(pri->args);
-		pri->args = NULL;
-		return;
-	}
-
-	printk(UM_KERN_WARNING "vde_remove - we have no VDECONN to remove");
-}
-
-const struct net_user_info vde_user_info = {
-	.init		= vde_user_init,
-	.open		= vde_user_open,
-	.close	 	= NULL,
-	.remove	 	= vde_remove,
-	.add_address	= NULL,
-	.delete_address = NULL,
-	.mtu		= ETH_MAX_PACKET,
-	.max_packet	= ETH_MAX_PACKET + ETH_HEADER_OTHER,
-};
-
-void vde_init_libstuff(struct vde_data *vpri, struct vde_init *init)
-{
-	struct vde_open_args *args;
-
-	vpri->args = uml_kmalloc(sizeof(struct vde_open_args), UM_GFP_KERNEL);
-	if (vpri->args == NULL) {
-		printk(UM_KERN_ERR "vde_init_libstuff - vde_open_args "
-		       "allocation failed");
-		return;
-	}
-
-	args = vpri->args;
-
-	args->port = init->port;
-	args->group = init->group;
-	args->mode = init->mode ? init->mode : 0700;
-
-	args->port ?  printk("port %d", args->port) :
-		printk("undefined port");
-}
-
-int vde_user_read(void *conn, void *buf, int len)
-{
-	VDECONN *vconn = conn;
-	int rv;
-
-	if (vconn == NULL)
-		return 0;
-
-	rv = vde_recv(vconn, buf, len, 0);
-	if (rv < 0) {
-		if (errno == EAGAIN)
-			return 0;
-		return -errno;
-	}
-	else if (rv == 0)
-		return -ENOTCONN;
-
-	return rv;
-}
-
-int vde_user_write(void *conn, void *buf, int len)
-{
-	VDECONN *vconn = conn;
-
-	if (vconn == NULL)
-		return 0;
-
-	return vde_send(vconn, buf, len, 0);
-}
-
diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c
index b97bb52dd562..5226d2c52e6a 100644
--- a/arch/um/drivers/vector_kern.c
+++ b/arch/um/drivers/vector_kern.c
@@ -8,6 +8,8 @@
  * Copyright (C) 2001 by various other people who didn't put their name here.
  */
 
+#define pr_fmt(fmt) "uml-vector: " fmt
+
 #include <linux/memblock.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
@@ -27,7 +29,6 @@
 #include <init.h>
 #include <irq_kern.h>
 #include <irq_user.h>
-#include <net_kern.h>
 #include <os.h>
 #include "mconsole_kern.h"
 #include "vector_user.h"
@@ -1539,7 +1540,41 @@ static void vector_timer_expire(struct timer_list *t)
 	napi_schedule(&vp->napi);
 }
 
+static void vector_setup_etheraddr(struct net_device *dev, char *str)
+{
+	u8 addr[ETH_ALEN];
+
+	if (str == NULL)
+		goto random;
+
+	if (!mac_pton(str, addr)) {
+		netdev_err(dev,
+			"Failed to parse '%s' as an ethernet address\n", str);
+		goto random;
+	}
+	if (is_multicast_ether_addr(addr)) {
+		netdev_err(dev,
+			"Attempt to assign a multicast ethernet address to a device disallowed\n");
+		goto random;
+	}
+	if (!is_valid_ether_addr(addr)) {
+		netdev_err(dev,
+			"Attempt to assign an invalid ethernet address to a device disallowed\n");
+		goto random;
+	}
+	if (!is_local_ether_addr(addr)) {
+		netdev_warn(dev, "Warning: Assigning a globally valid ethernet address to a device\n");
+		netdev_warn(dev, "You should set the 2nd rightmost bit in the first byte of the MAC,\n");
+		netdev_warn(dev, "i.e. %02x:%02x:%02x:%02x:%02x:%02x\n",
+			addr[0] | 0x02, addr[1], addr[2], addr[3], addr[4], addr[5]);
+	}
+	eth_hw_addr_set(dev, addr);
+	return;
 
+random:
+	netdev_info(dev, "Choosing a random ethernet address\n");
+	eth_hw_addr_random(dev);
+}
 
 static void vector_eth_configure(
 		int n,
@@ -1553,14 +1588,12 @@ static void vector_eth_configure(
 
 	device = kzalloc(sizeof(*device), GFP_KERNEL);
 	if (device == NULL) {
-		printk(KERN_ERR "eth_configure failed to allocate struct "
-				 "vector_device\n");
+		pr_err("Failed to allocate struct vector_device for vec%d\n", n);
 		return;
 	}
 	dev = alloc_etherdev(sizeof(struct vector_private));
 	if (dev == NULL) {
-		printk(KERN_ERR "eth_configure: failed to allocate struct "
-				 "net_device for vec%d\n", n);
+		pr_err("Failed to allocate struct net_device for vec%d\n", n);
 		goto out_free_device;
 	}
 
@@ -1574,7 +1607,7 @@ static void vector_eth_configure(
 	 * and fail.
 	 */
 	snprintf(dev->name, sizeof(dev->name), "vec%d", n);
-	uml_net_setup_etheraddr(dev, uml_vector_fetch_arg(def, "mac"));
+	vector_setup_etheraddr(dev, uml_vector_fetch_arg(def, "mac"));
 	vp = netdev_priv(dev);
 
 	/* sysfs register */
@@ -1690,8 +1723,7 @@ static int __init vector_setup(char *str)
 
 	err = vector_parse(str, &n, &str, &error);
 	if (err) {
-		printk(KERN_ERR "vector_setup - Couldn't parse '%s' : %s\n",
-				 str, error);
+		pr_err("Couldn't parse '%s': %s\n", str, error);
 		return 1;
 	}
 	new = memblock_alloc_or_panic(sizeof(*new), SMP_CACHE_BYTES);
diff --git a/arch/um/drivers/vfio_kern.c b/arch/um/drivers/vfio_kern.c
new file mode 100644
index 000000000000..b51fc9888ae1
--- /dev/null
+++ b/arch/um/drivers/vfio_kern.c
@@ -0,0 +1,642 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 Ant Group
+ * Author: Tiwei Bie <tiwei.btw@antgroup.com>
+ */
+
+#define pr_fmt(fmt) "vfio-uml: " fmt
+
+#include <linux/module.h>
+#include <linux/logic_iomem.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/string.h>
+#include <linux/unaligned.h>
+#include <irq_kern.h>
+#include <init.h>
+#include <os.h>
+
+#include "virt-pci.h"
+#include "vfio_user.h"
+
+#define to_vdev(_pdev) container_of(_pdev, struct uml_vfio_device, pdev)
+
+struct uml_vfio_intr_ctx {
+	struct uml_vfio_device *dev;
+	int irq;
+};
+
+struct uml_vfio_device {
+	const char *name;
+	int group;
+
+	struct um_pci_device pdev;
+	struct uml_vfio_user_device udev;
+	struct uml_vfio_intr_ctx *intr_ctx;
+
+	int msix_cap;
+	int msix_bar;
+	int msix_offset;
+	int msix_size;
+	u32 *msix_data;
+
+	struct list_head list;
+};
+
+struct uml_vfio_group {
+	int id;
+	int fd;
+	int users;
+	struct list_head list;
+};
+
+static struct {
+	int fd;
+	int users;
+} uml_vfio_container = { .fd = -1 };
+static DEFINE_MUTEX(uml_vfio_container_mtx);
+
+static LIST_HEAD(uml_vfio_groups);
+static DEFINE_MUTEX(uml_vfio_groups_mtx);
+
+static LIST_HEAD(uml_vfio_devices);
+
+static int uml_vfio_set_container(int group_fd)
+{
+	int err;
+
+	guard(mutex)(&uml_vfio_container_mtx);
+
+	err = uml_vfio_user_set_container(uml_vfio_container.fd, group_fd);
+	if (err)
+		return err;
+
+	uml_vfio_container.users++;
+	if (uml_vfio_container.users > 1)
+		return 0;
+
+	err = uml_vfio_user_setup_iommu(uml_vfio_container.fd);
+	if (err) {
+		uml_vfio_user_unset_container(uml_vfio_container.fd, group_fd);
+		uml_vfio_container.users--;
+	}
+	return err;
+}
+
+static void uml_vfio_unset_container(int group_fd)
+{
+	guard(mutex)(&uml_vfio_container_mtx);
+
+	uml_vfio_user_unset_container(uml_vfio_container.fd, group_fd);
+	uml_vfio_container.users--;
+}
+
+static int uml_vfio_open_group(int group_id)
+{
+	struct uml_vfio_group *group;
+	int err;
+
+	guard(mutex)(&uml_vfio_groups_mtx);
+
+	list_for_each_entry(group, &uml_vfio_groups, list) {
+		if (group->id == group_id) {
+			group->users++;
+			return group->fd;
+		}
+	}
+
+	group = kzalloc(sizeof(*group), GFP_KERNEL);
+	if (!group)
+		return -ENOMEM;
+
+	group->fd = uml_vfio_user_open_group(group_id);
+	if (group->fd < 0) {
+		err = group->fd;
+		goto free_group;
+	}
+
+	err = uml_vfio_set_container(group->fd);
+	if (err)
+		goto close_group;
+
+	group->id = group_id;
+	group->users = 1;
+
+	list_add(&group->list, &uml_vfio_groups);
+
+	return group->fd;
+
+close_group:
+	os_close_file(group->fd);
+free_group:
+	kfree(group);
+	return err;
+}
+
+static int uml_vfio_release_group(int group_fd)
+{
+	struct uml_vfio_group *group;
+
+	guard(mutex)(&uml_vfio_groups_mtx);
+
+	list_for_each_entry(group, &uml_vfio_groups, list) {
+		if (group->fd == group_fd) {
+			group->users--;
+			if (group->users == 0) {
+				uml_vfio_unset_container(group_fd);
+				os_close_file(group_fd);
+				list_del(&group->list);
+				kfree(group);
+			}
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
+static irqreturn_t uml_vfio_interrupt(int unused, void *opaque)
+{
+	struct uml_vfio_intr_ctx *ctx = opaque;
+	struct uml_vfio_device *dev = ctx->dev;
+	int index = ctx - dev->intr_ctx;
+	int irqfd = dev->udev.irqfd[index];
+	int irq = dev->msix_data[index];
+	uint64_t v;
+	int r;
+
+	do {
+		r = os_read_file(irqfd, &v, sizeof(v));
+		if (r == sizeof(v))
+			generic_handle_irq(irq);
+	} while (r == sizeof(v) || r == -EINTR);
+	WARN(r != -EAGAIN, "read returned %d\n", r);
+
+	return IRQ_HANDLED;
+}
+
+static int uml_vfio_activate_irq(struct uml_vfio_device *dev, int index)
+{
+	struct uml_vfio_intr_ctx *ctx = &dev->intr_ctx[index];
+	int err, irqfd;
+
+	if (ctx->irq >= 0)
+		return 0;
+
+	irqfd = uml_vfio_user_activate_irq(&dev->udev, index);
+	if (irqfd < 0)
+		return irqfd;
+
+	ctx->irq = um_request_irq(UM_IRQ_ALLOC, irqfd, IRQ_READ,
+				  uml_vfio_interrupt, 0,
+				  "vfio-uml", ctx);
+	if (ctx->irq < 0) {
+		err = ctx->irq;
+		goto deactivate;
+	}
+
+	err = add_sigio_fd(irqfd);
+	if (err)
+		goto free_irq;
+
+	return 0;
+
+free_irq:
+	um_free_irq(ctx->irq, ctx);
+	ctx->irq = -1;
+deactivate:
+	uml_vfio_user_deactivate_irq(&dev->udev, index);
+	return err;
+}
+
+static int uml_vfio_deactivate_irq(struct uml_vfio_device *dev, int index)
+{
+	struct uml_vfio_intr_ctx *ctx = &dev->intr_ctx[index];
+
+	if (ctx->irq >= 0) {
+		ignore_sigio_fd(dev->udev.irqfd[index]);
+		um_free_irq(ctx->irq, ctx);
+		uml_vfio_user_deactivate_irq(&dev->udev, index);
+		ctx->irq = -1;
+	}
+	return 0;
+}
+
+static int uml_vfio_update_msix_cap(struct uml_vfio_device *dev,
+				    unsigned int offset, int size,
+				    unsigned long val)
+{
+	/*
+	 * Here, we handle only the operations we care about,
+	 * ignoring the rest.
+	 */
+	if (size == 2 && offset == dev->msix_cap + PCI_MSIX_FLAGS) {
+		switch (val & ~PCI_MSIX_FLAGS_QSIZE) {
+		case PCI_MSIX_FLAGS_ENABLE:
+		case 0:
+			return uml_vfio_user_update_irqs(&dev->udev);
+		}
+	}
+	return 0;
+}
+
+static int uml_vfio_update_msix_table(struct uml_vfio_device *dev,
+				      unsigned int offset, int size,
+				      unsigned long val)
+{
+	int index;
+
+	/*
+	 * Here, we handle only the operations we care about,
+	 * ignoring the rest.
+	 */
+	offset -= dev->msix_offset + PCI_MSIX_ENTRY_DATA;
+
+	if (size != 4 || offset % PCI_MSIX_ENTRY_SIZE != 0)
+		return 0;
+
+	index = offset / PCI_MSIX_ENTRY_SIZE;
+	if (index >= dev->udev.irq_count)
+		return -EINVAL;
+
+	dev->msix_data[index] = val;
+
+	return val ? uml_vfio_activate_irq(dev, index) :
+		uml_vfio_deactivate_irq(dev, index);
+}
+
+static unsigned long __uml_vfio_cfgspace_read(struct uml_vfio_device *dev,
+					      unsigned int offset, int size)
+{
+	u8 data[8];
+
+	memset(data, 0xff, sizeof(data));
+
+	if (uml_vfio_user_cfgspace_read(&dev->udev, offset, data, size))
+		return ULONG_MAX;
+
+	switch (size) {
+	case 1:
+		return data[0];
+	case 2:
+		return le16_to_cpup((void *)data);
+	case 4:
+		return le32_to_cpup((void *)data);
+#ifdef CONFIG_64BIT
+	case 8:
+		return le64_to_cpup((void *)data);
+#endif
+	default:
+		return ULONG_MAX;
+	}
+}
+
+static unsigned long uml_vfio_cfgspace_read(struct um_pci_device *pdev,
+					    unsigned int offset, int size)
+{
+	struct uml_vfio_device *dev = to_vdev(pdev);
+
+	return __uml_vfio_cfgspace_read(dev, offset, size);
+}
+
+static void __uml_vfio_cfgspace_write(struct uml_vfio_device *dev,
+				      unsigned int offset, int size,
+				      unsigned long val)
+{
+	u8 data[8];
+
+	switch (size) {
+	case 1:
+		data[0] = (u8)val;
+		break;
+	case 2:
+		put_unaligned_le16(val, (void *)data);
+		break;
+	case 4:
+		put_unaligned_le32(val, (void *)data);
+		break;
+#ifdef CONFIG_64BIT
+	case 8:
+		put_unaligned_le64(val, (void *)data);
+		break;
+#endif
+	}
+
+	WARN_ON(uml_vfio_user_cfgspace_write(&dev->udev, offset, data, size));
+}
+
+static void uml_vfio_cfgspace_write(struct um_pci_device *pdev,
+				    unsigned int offset, int size,
+				    unsigned long val)
+{
+	struct uml_vfio_device *dev = to_vdev(pdev);
+
+	if (offset < dev->msix_cap + PCI_CAP_MSIX_SIZEOF &&
+	    offset + size > dev->msix_cap)
+		WARN_ON(uml_vfio_update_msix_cap(dev, offset, size, val));
+
+	__uml_vfio_cfgspace_write(dev, offset, size, val);
+}
+
+static void uml_vfio_bar_copy_from(struct um_pci_device *pdev, int bar,
+				   void *buffer, unsigned int offset, int size)
+{
+	struct uml_vfio_device *dev = to_vdev(pdev);
+
+	memset(buffer, 0xff, size);
+	uml_vfio_user_bar_read(&dev->udev, bar, offset, buffer, size);
+}
+
+static unsigned long uml_vfio_bar_read(struct um_pci_device *pdev, int bar,
+				       unsigned int offset, int size)
+{
+	u8 data[8];
+
+	uml_vfio_bar_copy_from(pdev, bar, data, offset, size);
+
+	switch (size) {
+	case 1:
+		return data[0];
+	case 2:
+		return le16_to_cpup((void *)data);
+	case 4:
+		return le32_to_cpup((void *)data);
+#ifdef CONFIG_64BIT
+	case 8:
+		return le64_to_cpup((void *)data);
+#endif
+	default:
+		return ULONG_MAX;
+	}
+}
+
+static void uml_vfio_bar_copy_to(struct um_pci_device *pdev, int bar,
+				 unsigned int offset, const void *buffer,
+				 int size)
+{
+	struct uml_vfio_device *dev = to_vdev(pdev);
+
+	uml_vfio_user_bar_write(&dev->udev, bar, offset, buffer, size);
+}
+
+static void uml_vfio_bar_write(struct um_pci_device *pdev, int bar,
+			       unsigned int offset, int size,
+			       unsigned long val)
+{
+	struct uml_vfio_device *dev = to_vdev(pdev);
+	u8 data[8];
+
+	if (bar == dev->msix_bar && offset + size > dev->msix_offset &&
+	    offset < dev->msix_offset + dev->msix_size)
+		WARN_ON(uml_vfio_update_msix_table(dev, offset, size, val));
+
+	switch (size) {
+	case 1:
+		data[0] = (u8)val;
+		break;
+	case 2:
+		put_unaligned_le16(val, (void *)data);
+		break;
+	case 4:
+		put_unaligned_le32(val, (void *)data);
+		break;
+#ifdef CONFIG_64BIT
+	case 8:
+		put_unaligned_le64(val, (void *)data);
+		break;
+#endif
+	}
+
+	uml_vfio_bar_copy_to(pdev, bar, offset, data, size);
+}
+
+static void uml_vfio_bar_set(struct um_pci_device *pdev, int bar,
+			     unsigned int offset, u8 value, int size)
+{
+	struct uml_vfio_device *dev = to_vdev(pdev);
+	int i;
+
+	for (i = 0; i < size; i++)
+		uml_vfio_user_bar_write(&dev->udev, bar, offset + i, &value, 1);
+}
+
+static const struct um_pci_ops uml_vfio_um_pci_ops = {
+	.cfgspace_read	= uml_vfio_cfgspace_read,
+	.cfgspace_write	= uml_vfio_cfgspace_write,
+	.bar_read	= uml_vfio_bar_read,
+	.bar_write	= uml_vfio_bar_write,
+	.bar_copy_from	= uml_vfio_bar_copy_from,
+	.bar_copy_to	= uml_vfio_bar_copy_to,
+	.bar_set	= uml_vfio_bar_set,
+};
+
+static u8 uml_vfio_find_capability(struct uml_vfio_device *dev, u8 cap)
+{
+	u8 id, pos;
+	u16 ent;
+	int ttl = 48; /* PCI_FIND_CAP_TTL */
+
+	pos = __uml_vfio_cfgspace_read(dev, PCI_CAPABILITY_LIST, sizeof(pos));
+
+	while (pos && ttl--) {
+		ent = __uml_vfio_cfgspace_read(dev, pos, sizeof(ent));
+
+		id = ent & 0xff;
+		if (id == 0xff)
+			break;
+		if (id == cap)
+			return pos;
+
+		pos = ent >> 8;
+	}
+
+	return 0;
+}
+
+static int uml_vfio_read_msix_table(struct uml_vfio_device *dev)
+{
+	unsigned int off;
+	u16 flags;
+	u32 tbl;
+
+	off = uml_vfio_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (!off)
+		return -ENOTSUPP;
+
+	dev->msix_cap = off;
+
+	tbl = __uml_vfio_cfgspace_read(dev, off + PCI_MSIX_TABLE, sizeof(tbl));
+	flags = __uml_vfio_cfgspace_read(dev, off + PCI_MSIX_FLAGS, sizeof(flags));
+
+	dev->msix_bar = tbl & PCI_MSIX_TABLE_BIR;
+	dev->msix_offset = tbl & PCI_MSIX_TABLE_OFFSET;
+	dev->msix_size = ((flags & PCI_MSIX_FLAGS_QSIZE) + 1) * PCI_MSIX_ENTRY_SIZE;
+
+	dev->msix_data = kzalloc(dev->msix_size, GFP_KERNEL);
+	if (!dev->msix_data)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void uml_vfio_open_device(struct uml_vfio_device *dev)
+{
+	struct uml_vfio_intr_ctx *ctx;
+	int err, group_id, i;
+
+	group_id = uml_vfio_user_get_group_id(dev->name);
+	if (group_id < 0) {
+		pr_err("Failed to get group id (%s), error %d\n",
+		       dev->name, group_id);
+		goto free_dev;
+	}
+
+	dev->group = uml_vfio_open_group(group_id);
+	if (dev->group < 0) {
+		pr_err("Failed to open group %d (%s), error %d\n",
+		       group_id, dev->name, dev->group);
+		goto free_dev;
+	}
+
+	err = uml_vfio_user_setup_device(&dev->udev, dev->group, dev->name);
+	if (err) {
+		pr_err("Failed to setup device (%s), error %d\n",
+		       dev->name, err);
+		goto release_group;
+	}
+
+	err = uml_vfio_read_msix_table(dev);
+	if (err) {
+		pr_err("Failed to read MSI-X table (%s), error %d\n",
+		       dev->name, err);
+		goto teardown_udev;
+	}
+
+	dev->intr_ctx = kmalloc_array(dev->udev.irq_count,
+				      sizeof(struct uml_vfio_intr_ctx),
+				      GFP_KERNEL);
+	if (!dev->intr_ctx) {
+		pr_err("Failed to allocate interrupt context (%s)\n",
+		       dev->name);
+		goto free_msix;
+	}
+
+	for (i = 0; i < dev->udev.irq_count; i++) {
+		ctx = &dev->intr_ctx[i];
+		ctx->dev = dev;
+		ctx->irq = -1;
+	}
+
+	dev->pdev.ops = &uml_vfio_um_pci_ops;
+
+	err = um_pci_device_register(&dev->pdev);
+	if (err) {
+		pr_err("Failed to register UM PCI device (%s), error %d\n",
+		       dev->name, err);
+		goto free_intr_ctx;
+	}
+
+	return;
+
+free_intr_ctx:
+	kfree(dev->intr_ctx);
+free_msix:
+	kfree(dev->msix_data);
+teardown_udev:
+	uml_vfio_user_teardown_device(&dev->udev);
+release_group:
+	uml_vfio_release_group(dev->group);
+free_dev:
+	list_del(&dev->list);
+	kfree(dev->name);
+	kfree(dev);
+}
+
+static void uml_vfio_release_device(struct uml_vfio_device *dev)
+{
+	int i;
+
+	for (i = 0; i < dev->udev.irq_count; i++)
+		uml_vfio_deactivate_irq(dev, i);
+	uml_vfio_user_update_irqs(&dev->udev);
+
+	um_pci_device_unregister(&dev->pdev);
+	kfree(dev->intr_ctx);
+	kfree(dev->msix_data);
+	uml_vfio_user_teardown_device(&dev->udev);
+	uml_vfio_release_group(dev->group);
+	list_del(&dev->list);
+	kfree(dev->name);
+	kfree(dev);
+}
+
+static int uml_vfio_cmdline_set(const char *device, const struct kernel_param *kp)
+{
+	struct uml_vfio_device *dev;
+	int fd;
+
+	if (uml_vfio_container.fd < 0) {
+		fd = uml_vfio_user_open_container();
+		if (fd < 0)
+			return fd;
+		uml_vfio_container.fd = fd;
+	}
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->name = kstrdup(device, GFP_KERNEL);
+	if (!dev->name) {
+		kfree(dev);
+		return -ENOMEM;
+	}
+
+	list_add_tail(&dev->list, &uml_vfio_devices);
+	return 0;
+}
+
+static int uml_vfio_cmdline_get(char *buffer, const struct kernel_param *kp)
+{
+	return 0;
+}
+
+static const struct kernel_param_ops uml_vfio_cmdline_param_ops = {
+	.set = uml_vfio_cmdline_set,
+	.get = uml_vfio_cmdline_get,
+};
+
+device_param_cb(device, &uml_vfio_cmdline_param_ops, NULL, 0400);
+__uml_help(uml_vfio_cmdline_param_ops,
+"vfio_uml.device=<domain:bus:slot.function>\n"
+"    Pass through a PCI device to UML via VFIO. Currently, only MSI-X\n"
+"    capable devices are supported, and it is assumed that drivers will\n"
+"    use MSI-X. This parameter can be specified multiple times to pass\n"
+"    through multiple PCI devices to UML.\n\n"
+);
+
+static int __init uml_vfio_init(void)
+{
+	struct uml_vfio_device *dev, *n;
+
+	sigio_broken();
+
+	/* If the opening fails, the device will be released. */
+	list_for_each_entry_safe(dev, n, &uml_vfio_devices, list)
+		uml_vfio_open_device(dev);
+
+	return 0;
+}
+late_initcall(uml_vfio_init);
+
+static void __exit uml_vfio_exit(void)
+{
+	struct uml_vfio_device *dev, *n;
+
+	list_for_each_entry_safe(dev, n, &uml_vfio_devices, list)
+		uml_vfio_release_device(dev);
+
+	if (uml_vfio_container.fd >= 0)
+		os_close_file(uml_vfio_container.fd);
+}
+module_exit(uml_vfio_exit);
diff --git a/arch/um/drivers/vfio_user.c b/arch/um/drivers/vfio_user.c
new file mode 100644
index 000000000000..6a45d8e14582
--- /dev/null
+++ b/arch/um/drivers/vfio_user.c
@@ -0,0 +1,327 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 Ant Group
+ * Author: Tiwei Bie <tiwei.btw@antgroup.com>
+ */
+#include <errno.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/eventfd.h>
+#include <linux/limits.h>
+#include <linux/vfio.h>
+#include <linux/pci_regs.h>
+#include <as-layout.h>
+#include <um_malloc.h>
+
+#include "vfio_user.h"
+
+int uml_vfio_user_open_container(void)
+{
+	int r, fd;
+
+	fd = open("/dev/vfio/vfio", O_RDWR);
+	if (fd < 0)
+		return -errno;
+
+	r = ioctl(fd, VFIO_GET_API_VERSION);
+	if (r != VFIO_API_VERSION) {
+		r = r < 0 ? -errno : -EINVAL;
+		goto error;
+	}
+
+	r = ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU);
+	if (r <= 0) {
+		r = r < 0 ? -errno : -EINVAL;
+		goto error;
+	}
+
+	return fd;
+
+error:
+	close(fd);
+	return r;
+}
+
+int uml_vfio_user_setup_iommu(int container)
+{
+	/*
+	 * This is a bit tricky. See the big comment in
+	 * vhost_user_set_mem_table() in virtio_uml.c.
+	 */
+	unsigned long reserved = uml_reserved - uml_physmem;
+	struct vfio_iommu_type1_dma_map dma_map = {
+		.argsz = sizeof(dma_map),
+		.flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE,
+		.vaddr = uml_reserved,
+		.iova = reserved,
+		.size = physmem_size - reserved,
+	};
+
+	if (ioctl(container, VFIO_SET_IOMMU, VFIO_TYPE1_IOMMU) < 0)
+		return -errno;
+
+	if (ioctl(container, VFIO_IOMMU_MAP_DMA, &dma_map) < 0)
+		return -errno;
+
+	return 0;
+}
+
+int uml_vfio_user_get_group_id(const char *device)
+{
+	char *path, *buf, *end;
+	const char *name;
+	int r;
+
+	path = uml_kmalloc(PATH_MAX, UM_GFP_KERNEL);
+	if (!path)
+		return -ENOMEM;
+
+	sprintf(path, "/sys/bus/pci/devices/%s/iommu_group", device);
+
+	buf = uml_kmalloc(PATH_MAX + 1, UM_GFP_KERNEL);
+	if (!buf) {
+		r = -ENOMEM;
+		goto free_path;
+	}
+
+	r = readlink(path, buf, PATH_MAX);
+	if (r < 0) {
+		r = -errno;
+		goto free_buf;
+	}
+	buf[r] = '\0';
+
+	name = basename(buf);
+
+	r = strtoul(name, &end, 10);
+	if (*end != '\0' || end == name) {
+		r = -EINVAL;
+		goto free_buf;
+	}
+
+free_buf:
+	kfree(buf);
+free_path:
+	kfree(path);
+	return r;
+}
+
+int uml_vfio_user_open_group(int group_id)
+{
+	char *path;
+	int fd;
+
+	path = uml_kmalloc(PATH_MAX, UM_GFP_KERNEL);
+	if (!path)
+		return -ENOMEM;
+
+	sprintf(path, "/dev/vfio/%d", group_id);
+
+	fd = open(path, O_RDWR);
+	if (fd < 0) {
+		fd = -errno;
+		goto out;
+	}
+
+out:
+	kfree(path);
+	return fd;
+}
+
+int uml_vfio_user_set_container(int container, int group)
+{
+	if (ioctl(group, VFIO_GROUP_SET_CONTAINER, &container) < 0)
+		return -errno;
+	return 0;
+}
+
+int uml_vfio_user_unset_container(int container, int group)
+{
+	if (ioctl(group, VFIO_GROUP_UNSET_CONTAINER, &container) < 0)
+		return -errno;
+	return 0;
+}
+
+static int vfio_set_irqs(int device, int start, int count, int *irqfd)
+{
+	struct vfio_irq_set *irq_set;
+	int argsz = sizeof(*irq_set) + sizeof(*irqfd) * count;
+	int err = 0;
+
+	irq_set = uml_kmalloc(argsz, UM_GFP_KERNEL);
+	if (!irq_set)
+		return -ENOMEM;
+
+	irq_set->argsz = argsz;
+	irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER;
+	irq_set->index = VFIO_PCI_MSIX_IRQ_INDEX;
+	irq_set->start = start;
+	irq_set->count = count;
+	memcpy(irq_set->data, irqfd, sizeof(*irqfd) * count);
+
+	if (ioctl(device, VFIO_DEVICE_SET_IRQS, irq_set) < 0) {
+		err = -errno;
+		goto out;
+	}
+
+out:
+	kfree(irq_set);
+	return err;
+}
+
+int uml_vfio_user_setup_device(struct uml_vfio_user_device *dev,
+			       int group, const char *device)
+{
+	struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
+	struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info) };
+	int err, i;
+
+	dev->device = ioctl(group, VFIO_GROUP_GET_DEVICE_FD, device);
+	if (dev->device < 0)
+		return -errno;
+
+	if (ioctl(dev->device, VFIO_DEVICE_GET_INFO, &device_info) < 0) {
+		err = -errno;
+		goto close_device;
+	}
+
+	dev->num_regions = device_info.num_regions;
+	if (dev->num_regions > VFIO_PCI_CONFIG_REGION_INDEX + 1)
+		dev->num_regions = VFIO_PCI_CONFIG_REGION_INDEX + 1;
+
+	dev->region = uml_kmalloc(sizeof(*dev->region) * dev->num_regions,
+				  UM_GFP_KERNEL);
+	if (!dev->region) {
+		err = -ENOMEM;
+		goto close_device;
+	}
+
+	for (i = 0; i < dev->num_regions; i++) {
+		struct vfio_region_info region = {
+			.argsz = sizeof(region),
+			.index = i,
+		};
+		if (ioctl(dev->device, VFIO_DEVICE_GET_REGION_INFO, &region) < 0) {
+			err = -errno;
+			goto free_region;
+		}
+		dev->region[i].size = region.size;
+		dev->region[i].offset = region.offset;
+	}
+
+	/* Only MSI-X is supported currently. */
+	irq_info.index = VFIO_PCI_MSIX_IRQ_INDEX;
+	if (ioctl(dev->device, VFIO_DEVICE_GET_IRQ_INFO, &irq_info) < 0) {
+		err = -errno;
+		goto free_region;
+	}
+
+	dev->irq_count = irq_info.count;
+
+	dev->irqfd = uml_kmalloc(sizeof(int) * dev->irq_count, UM_GFP_KERNEL);
+	if (!dev->irqfd) {
+		err = -ENOMEM;
+		goto free_region;
+	}
+
+	memset(dev->irqfd, -1, sizeof(int) * dev->irq_count);
+
+	err = vfio_set_irqs(dev->device, 0, dev->irq_count, dev->irqfd);
+	if (err)
+		goto free_irqfd;
+
+	return 0;
+
+free_irqfd:
+	kfree(dev->irqfd);
+free_region:
+	kfree(dev->region);
+close_device:
+	close(dev->device);
+	return err;
+}
+
+void uml_vfio_user_teardown_device(struct uml_vfio_user_device *dev)
+{
+	kfree(dev->irqfd);
+	kfree(dev->region);
+	close(dev->device);
+}
+
+int uml_vfio_user_activate_irq(struct uml_vfio_user_device *dev, int index)
+{
+	int irqfd;
+
+	irqfd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC);
+	if (irqfd < 0)
+		return -errno;
+
+	dev->irqfd[index] = irqfd;
+	return irqfd;
+}
+
+void uml_vfio_user_deactivate_irq(struct uml_vfio_user_device *dev, int index)
+{
+	close(dev->irqfd[index]);
+	dev->irqfd[index] = -1;
+}
+
+int uml_vfio_user_update_irqs(struct uml_vfio_user_device *dev)
+{
+	return vfio_set_irqs(dev->device, 0, dev->irq_count, dev->irqfd);
+}
+
+static int vfio_region_read(struct uml_vfio_user_device *dev, unsigned int index,
+			    uint64_t offset, void *buf, uint64_t size)
+{
+	if (index >= dev->num_regions || offset + size > dev->region[index].size)
+		return -EINVAL;
+
+	if (pread(dev->device, buf, size, dev->region[index].offset + offset) < 0)
+		return -errno;
+
+	return 0;
+}
+
+static int vfio_region_write(struct uml_vfio_user_device *dev, unsigned int index,
+			     uint64_t offset, const void *buf, uint64_t size)
+{
+	if (index >= dev->num_regions || offset + size > dev->region[index].size)
+		return -EINVAL;
+
+	if (pwrite(dev->device, buf, size, dev->region[index].offset + offset) < 0)
+		return -errno;
+
+	return 0;
+}
+
+int uml_vfio_user_cfgspace_read(struct uml_vfio_user_device *dev,
+				unsigned int offset, void *buf, int size)
+{
+	return vfio_region_read(dev, VFIO_PCI_CONFIG_REGION_INDEX,
+				offset, buf, size);
+}
+
+int uml_vfio_user_cfgspace_write(struct uml_vfio_user_device *dev,
+				 unsigned int offset, const void *buf, int size)
+{
+	return vfio_region_write(dev, VFIO_PCI_CONFIG_REGION_INDEX,
+				 offset, buf, size);
+}
+
+int uml_vfio_user_bar_read(struct uml_vfio_user_device *dev, int bar,
+			   unsigned int offset, void *buf, int size)
+{
+	return vfio_region_read(dev, bar, offset, buf, size);
+}
+
+int uml_vfio_user_bar_write(struct uml_vfio_user_device *dev, int bar,
+			    unsigned int offset, const void *buf, int size)
+{
+	return vfio_region_write(dev, bar, offset, buf, size);
+}
diff --git a/arch/um/drivers/vfio_user.h b/arch/um/drivers/vfio_user.h
new file mode 100644
index 000000000000..75535e05059b
--- /dev/null
+++ b/arch/um/drivers/vfio_user.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __UM_VFIO_USER_H
+#define __UM_VFIO_USER_H
+
+struct uml_vfio_user_device {
+	int device;
+
+	struct {
+		uint64_t size;
+		uint64_t offset;
+	} *region;
+	int num_regions;
+
+	int32_t *irqfd;
+	int irq_count;
+};
+
+int uml_vfio_user_open_container(void);
+int uml_vfio_user_setup_iommu(int container);
+
+int uml_vfio_user_get_group_id(const char *device);
+int uml_vfio_user_open_group(int group_id);
+int uml_vfio_user_set_container(int container, int group);
+int uml_vfio_user_unset_container(int container, int group);
+
+int uml_vfio_user_setup_device(struct uml_vfio_user_device *dev,
+			       int group, const char *device);
+void uml_vfio_user_teardown_device(struct uml_vfio_user_device *dev);
+
+int uml_vfio_user_activate_irq(struct uml_vfio_user_device *dev, int index);
+void uml_vfio_user_deactivate_irq(struct uml_vfio_user_device *dev, int index);
+int uml_vfio_user_update_irqs(struct uml_vfio_user_device *dev);
+
+int uml_vfio_user_cfgspace_read(struct uml_vfio_user_device *dev,
+				unsigned int offset, void *buf, int size);
+int uml_vfio_user_cfgspace_write(struct uml_vfio_user_device *dev,
+				 unsigned int offset, const void *buf, int size);
+
+int uml_vfio_user_bar_read(struct uml_vfio_user_device *dev, int bar,
+			   unsigned int offset, void *buf, int size);
+int uml_vfio_user_bar_write(struct uml_vfio_user_device *dev, int bar,
+			    unsigned int offset, const void *buf, int size);
+
+#endif /* __UM_VFIO_USER_H */
diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c
index b83b5a765d4e..0fe207ca4b72 100644
--- a/arch/um/drivers/virt-pci.c
+++ b/arch/um/drivers/virt-pci.c
@@ -538,11 +538,6 @@ void um_pci_platform_device_unregister(struct um_pci_device *dev)
 
 static int __init um_pci_init(void)
 {
-	struct irq_domain_info inner_domain_info = {
-		.size		= MAX_MSI_VECTORS,
-		.hwirq_max	= MAX_MSI_VECTORS,
-		.ops		= &um_pci_inner_domain_ops,
-	};
 	int err, i;
 
 	WARN_ON(logic_iomem_add_region(&virt_cfgspace_resource,
@@ -564,10 +559,10 @@ static int __init um_pci_init(void)
 		goto free;
 	}
 
-	inner_domain_info.fwnode = um_pci_fwnode;
-	um_pci_inner_domain = irq_domain_instantiate(&inner_domain_info);
-	if (IS_ERR(um_pci_inner_domain)) {
-		err = PTR_ERR(um_pci_inner_domain);
+	um_pci_inner_domain = irq_domain_create_linear(um_pci_fwnode, MAX_MSI_VECTORS,
+						       &um_pci_inner_domain_ops, NULL);
+	if (!um_pci_inner_domain) {
+		err = -ENOMEM;
 		goto free;
 	}
 
@@ -602,7 +597,7 @@ static int __init um_pci_init(void)
 	return 0;
 
 free:
-	if (!IS_ERR_OR_NULL(um_pci_inner_domain))
+	if (um_pci_inner_domain)
 		irq_domain_remove(um_pci_inner_domain);
 	if (um_pci_fwnode)
 		irq_domain_free_fwnode(um_pci_fwnode);
diff --git a/arch/um/drivers/xterm.c b/arch/um/drivers/xterm.c
index e4316c7981e8..d05918e422f9 100644
--- a/arch/um/drivers/xterm.c
+++ b/arch/um/drivers/xterm.c
@@ -81,7 +81,7 @@ __uml_setup("xterm=", xterm_setup,
 "    '<switch> command arg1 arg2 ...'.\n"
 "    The default values are 'xterm=" CONFIG_XTERM_CHAN_DEFAULT_EMULATOR
      ",-T,-e'.\n"
-"    Values for gnome-terminal are 'xterm=gnome-terminal,-t,-x'.\n\n"
+"    Values for gnome-terminal are 'xterm=gnome-terminal,-t,--'.\n\n"
 );
 
 static int xterm_open(int input, int output, int primary, void *d,
@@ -97,12 +97,9 @@ static int xterm_open(int input, int output, int primary, void *d,
 	if (access(argv[4], X_OK) < 0)
 		argv[4] = "port-helper";
 
-	/*
-	 * Check that DISPLAY is set, this doesn't guarantee the xterm
-	 * will work but w/o it we can be pretty sure it won't.
-	 */
-	if (getenv("DISPLAY") == NULL) {
-		printk(UM_KERN_ERR "xterm_open: $DISPLAY not set.\n");
+	/* Ensure we are running on Xorg or Wayland. */
+	if (!getenv("DISPLAY") && !getenv("WAYLAND_DISPLAY")) {
+		printk(UM_KERN_ERR "xterm_open : neither $DISPLAY nor $WAYLAND_DISPLAY is set.\n");
 		return -ENODEV;
 	}
 
diff --git a/arch/um/include/asm/asm-prototypes.h b/arch/um/include/asm/asm-prototypes.h
index 5898a26daa0d..408b31d59127 100644
--- a/arch/um/include/asm/asm-prototypes.h
+++ b/arch/um/include/asm/asm-prototypes.h
@@ -1 +1,6 @@
 #include <asm-generic/asm-prototypes.h>
+#include <asm/checksum.h>
+
+#ifdef CONFIG_UML_X86
+extern void cmpxchg8b_emu(void);
+#endif
diff --git a/arch/um/include/asm/irq.h b/arch/um/include/asm/irq.h
index 749dfe8512e8..36dbedd1af48 100644
--- a/arch/um/include/asm/irq.h
+++ b/arch/um/include/asm/irq.h
@@ -13,17 +13,18 @@
 #define TELNETD_IRQ 		8
 #define XTERM_IRQ 		9
 #define RANDOM_IRQ 		10
+#define SIGCHLD_IRQ		11
 
 #ifdef CONFIG_UML_NET_VECTOR
 
-#define VECTOR_BASE_IRQ		(RANDOM_IRQ + 1)
+#define VECTOR_BASE_IRQ		(SIGCHLD_IRQ + 1)
 #define VECTOR_IRQ_SPACE	8
 
 #define UM_FIRST_DYN_IRQ (VECTOR_IRQ_SPACE + VECTOR_BASE_IRQ)
 
 #else
 
-#define UM_FIRST_DYN_IRQ (RANDOM_IRQ + 1)
+#define UM_FIRST_DYN_IRQ (SIGCHLD_IRQ + 1)
 
 #endif
 
diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h
index a3eaca41ff61..4d0e4239f3cc 100644
--- a/arch/um/include/asm/mmu.h
+++ b/arch/um/include/asm/mmu.h
@@ -6,11 +6,14 @@
 #ifndef __ARCH_UM_MMU_H
 #define __ARCH_UM_MMU_H
 
+#include "linux/types.h"
 #include <mm_id.h>
 
 typedef struct mm_context {
 	struct mm_id id;
 
+	struct list_head list;
+
 	/* Address range in need of a TLB sync */
 	unsigned long sync_tlb_range_from;
 	unsigned long sync_tlb_range_to;
diff --git a/arch/um/include/shared/common-offsets.h b/arch/um/include/shared/common-offsets.h
index 73f3a4792ed8..8ca66a1918c3 100644
--- a/arch/um/include/shared/common-offsets.h
+++ b/arch/um/include/shared/common-offsets.h
@@ -14,3 +14,7 @@ DEFINE(UM_THREAD_SIZE, THREAD_SIZE);
 
 DEFINE(UM_NSEC_PER_SEC, NSEC_PER_SEC);
 DEFINE(UM_NSEC_PER_USEC, NSEC_PER_USEC);
+
+DEFINE(UM_KERN_GDT_ENTRY_TLS_ENTRIES, GDT_ENTRY_TLS_ENTRIES);
+
+DEFINE(UM_SECCOMP_ARCH_NATIVE, SECCOMP_ARCH_NATIVE);
diff --git a/arch/um/include/shared/irq_user.h b/arch/um/include/shared/irq_user.h
index 88835b52ae2b..746abc24a5d5 100644
--- a/arch/um/include/shared/irq_user.h
+++ b/arch/um/include/shared/irq_user.h
@@ -17,6 +17,8 @@ enum um_irq_type {
 struct siginfo;
 extern void sigio_handler(int sig, struct siginfo *unused_si,
 			  struct uml_pt_regs *regs, void *mc);
+extern void sigchld_handler(int sig, struct siginfo *unused_si,
+			   struct uml_pt_regs *regs, void *mc);
 void sigio_run_timetravel_handlers(void);
 extern void free_irq_by_fd(int fd);
 extern void deactivate_fd(int fd, int irqnum);
diff --git a/arch/um/include/shared/net_kern.h b/arch/um/include/shared/net_kern.h
deleted file mode 100644
index 67b2e9a1f2e5..000000000000
--- a/arch/um/include/shared/net_kern.h
+++ /dev/null
@@ -1,69 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2002 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#ifndef __UM_NET_KERN_H
-#define __UM_NET_KERN_H
-
-#include <linux/netdevice.h>
-#include <linux/platform_device.h>
-#include <linux/skbuff.h>
-#include <linux/socket.h>
-#include <linux/list.h>
-#include <linux/workqueue.h>
-
-struct uml_net {
-	struct list_head list;
-	struct net_device *dev;
-	struct platform_device pdev;
-	int index;
-};
-
-struct uml_net_private {
-	struct list_head list;
-	spinlock_t lock;
-	struct net_device *dev;
-	struct timer_list tl;
-
-	struct work_struct work;
-	int fd;
-	unsigned char mac[ETH_ALEN];
-	int max_packet;
-	unsigned short (*protocol)(struct sk_buff *);
-	int (*open)(void *);
-	void (*close)(int, void *);
-	void (*remove)(void *);
-	int (*read)(int, struct sk_buff *skb, struct uml_net_private *);
-	int (*write)(int, struct sk_buff *skb, struct uml_net_private *);
-
-	void (*add_address)(unsigned char *, unsigned char *, void *);
-	void (*delete_address)(unsigned char *, unsigned char *, void *);
-	char user[];
-};
-
-struct net_kern_info {
-	void (*init)(struct net_device *, void *);
-	unsigned short (*protocol)(struct sk_buff *);
-	int (*read)(int, struct sk_buff *skb, struct uml_net_private *);
-	int (*write)(int, struct sk_buff *skb, struct uml_net_private *);
-};
-
-struct transport {
-	struct list_head list;
-	const char *name;
-	int (* const setup)(char *, char **, void *);
-	const struct net_user_info *user;
-	const struct net_kern_info *kern;
-	const int private_size;
-	const int setup_size;
-};
-
-extern int tap_setup_common(char *str, char *type, char **dev_name,
-			    char **mac_out, char **gate_addr);
-extern void register_transport(struct transport *new);
-extern unsigned short eth_protocol(struct sk_buff *skb);
-extern void uml_net_setup_etheraddr(struct net_device *dev, char *str);
-
-
-#endif
diff --git a/arch/um/include/shared/net_user.h b/arch/um/include/shared/net_user.h
deleted file mode 100644
index ba92a4d93531..000000000000
--- a/arch/um/include/shared/net_user.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#ifndef __UM_NET_USER_H__
-#define __UM_NET_USER_H__
-
-#define ETH_ADDR_LEN (6)
-#define ETH_HEADER_ETHERTAP (16)
-#define ETH_HEADER_OTHER (26) /* 14 for ethernet + VLAN + MPLS for crazy people */
-#define ETH_MAX_PACKET (1500)
-
-#define UML_NET_VERSION (4)
-
-struct net_user_info {
-	int (*init)(void *, void *);
-	int (*open)(void *);
-	void (*close)(int, void *);
-	void (*remove)(void *);
-	void (*add_address)(unsigned char *, unsigned char *, void *);
-	void (*delete_address)(unsigned char *, unsigned char *, void *);
-	int max_packet;
-	int mtu;
-};
-
-extern void iter_addresses(void *d, void (*cb)(unsigned char *,
-					       unsigned char *, void *),
-			   void *arg);
-
-extern void *get_output_buffer(int *len_out);
-extern void free_output_buffer(void *buffer);
-
-extern int tap_open_common(void *dev, char *gate_addr);
-extern void tap_check_ips(char *gate_addr, unsigned char *eth_addr);
-
-extern void read_output(int fd, char *output_out, int len);
-
-extern int net_read(int fd, void *buf, int len);
-extern int net_recvfrom(int fd, void *buf, int len);
-extern int net_write(int fd, void *buf, int len);
-extern int net_send(int fd, void *buf, int len);
-extern int net_sendto(int fd, void *buf, int len, void *to, int sock_len);
-
-extern void open_addr(unsigned char *addr, unsigned char *netmask, void *arg);
-extern void close_addr(unsigned char *addr, unsigned char *netmask, void *arg);
-
-extern char *split_if_spec(char *str, ...);
-
-extern int dev_netmask(void *d, void *m);
-
-#endif
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 152a60080d5b..b35cc8ce333b 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -143,7 +143,6 @@ extern int os_access(const char *file, int mode);
 extern int os_set_exec_close(int fd);
 extern int os_ioctl_generic(int fd, unsigned int cmd, unsigned long arg);
 extern int os_get_ifname(int fd, char *namebuf);
-extern int os_set_slip(int fd);
 extern int os_mode_fd(int fd, int mode);
 
 extern int os_seek_file(int fd, unsigned long long offset);
@@ -198,6 +197,7 @@ extern int create_mem_file(unsigned long long len);
 extern void report_enomem(void);
 
 /* process.c */
+pid_t os_reap_child(void);
 extern void os_alarm_process(int pid);
 extern void os_kill_process(int pid, int reap_child);
 extern void os_kill_ptraced_process(int pid, int reap_child);
@@ -286,7 +286,7 @@ int unmap(struct mm_id *mm_idp, unsigned long addr, unsigned long len);
 
 /* skas/process.c */
 extern int is_skas_winch(int pid, int fd, void *data);
-extern int start_userspace(unsigned long stub_stack);
+extern int start_userspace(struct mm_id *mm_id);
 extern void userspace(struct uml_pt_regs *regs);
 extern void new_thread(void *stack, jmp_buf *buf, void (*handler)(void));
 extern void switch_threads(jmp_buf *me, jmp_buf *you);
diff --git a/arch/um/include/shared/skas/mm_id.h b/arch/um/include/shared/skas/mm_id.h
index 140388c282f6..89df9a55fbea 100644
--- a/arch/um/include/shared/skas/mm_id.h
+++ b/arch/um/include/shared/skas/mm_id.h
@@ -6,12 +6,21 @@
 #ifndef __MM_ID_H
 #define __MM_ID_H
 
+#define STUB_MAX_FDS 4
+
 struct mm_id {
 	int pid;
 	unsigned long stack;
 	int syscall_data_len;
+
+	/* Only used with SECCOMP mode */
+	int sock;
+	int syscall_fd_num;
+	int syscall_fd_map[STUB_MAX_FDS];
 };
 
 void __switch_mm(struct mm_id *mm_idp);
 
+void notify_mm_kill(int pid);
+
 #endif
diff --git a/arch/um/include/shared/skas/skas.h b/arch/um/include/shared/skas/skas.h
index 85c50122ab98..7d1de4cab551 100644
--- a/arch/um/include/shared/skas/skas.h
+++ b/arch/um/include/shared/skas/skas.h
@@ -8,6 +8,7 @@
 
 #include <sysdep/ptrace.h>
 
+extern int using_seccomp;
 extern int userspace_pid[];
 
 extern void new_thread_handler(void);
diff --git a/arch/um/include/shared/skas/stub-data.h b/arch/um/include/shared/skas/stub-data.h
index 81a4cace032c..c261a77a32f6 100644
--- a/arch/um/include/shared/skas/stub-data.h
+++ b/arch/um/include/shared/skas/stub-data.h
@@ -11,8 +11,15 @@
 #include <linux/compiler_types.h>
 #include <as-layout.h>
 #include <sysdep/tls.h>
+#include <sysdep/stub-data.h>
+#include <mm_id.h>
+
+#define FUTEX_IN_CHILD 0
+#define FUTEX_IN_KERN 1
 
 struct stub_init_data {
+	int seccomp;
+
 	unsigned long stub_start;
 
 	int stub_code_fd;
@@ -20,7 +27,8 @@ struct stub_init_data {
 	int stub_data_fd;
 	unsigned long stub_data_offset;
 
-	unsigned long segv_handler;
+	unsigned long signal_handler;
+	unsigned long signal_restorer;
 };
 
 #define STUB_NEXT_SYSCALL(s) \
@@ -52,6 +60,16 @@ struct stub_data {
 	/* 128 leaves enough room for additional fields in the struct */
 	struct stub_syscall syscall_data[(UM_KERN_PAGE_SIZE - 128) / sizeof(struct stub_syscall)] __aligned(16);
 
+	/* data shared with signal handler (only used in seccomp mode) */
+	short restart_wait;
+	unsigned int futex;
+	int signal;
+	unsigned short si_offset;
+	unsigned short mctx_offset;
+
+	/* seccomp architecture specific state restore */
+	struct stub_data_arch arch_data;
+
 	/* Stack for our signal handlers and for calling into . */
 	unsigned char sigstack[UM_KERN_PAGE_SIZE] __aligned(UM_KERN_PAGE_SIZE);
 };
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index 4df1cd0d2017..4669db2aa9be 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -25,7 +25,6 @@ obj-$(CONFIG_GPROF)	+= gprof_syms.o
 obj-$(CONFIG_OF) += dtb.o
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
-obj-$(CONFIG_GENERIC_PCI_IOMAP) += ioport.o
 
 USER_OBJS := config.o
 
diff --git a/arch/um/kernel/ioport.c b/arch/um/kernel/ioport.c
deleted file mode 100644
index 7220615b3beb..000000000000
--- a/arch/um/kernel/ioport.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2021 Intel Corporation
- * Author: Johannes Berg <johannes@sipsolutions.net>
- */
-#include <asm/iomap.h>
-#include <asm-generic/pci_iomap.h>
-
-void __iomem *__pci_ioport_map(struct pci_dev *dev, unsigned long port,
-			       unsigned int nr)
-{
-	return NULL;
-}
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index abe8f30a521c..0dfaf96bb7da 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -690,3 +690,9 @@ void __init init_IRQ(void)
 	/* Initialize EPOLL Loop */
 	os_setup_epoll();
 }
+
+void sigchld_handler(int sig, struct siginfo *unused_si,
+		     struct uml_pt_regs *regs, void *mc)
+{
+	do_IRQ(SIGCHLD_IRQ, regs);
+}
diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c
index 0eb5a1d3ba70..849fafa4b54f 100644
--- a/arch/um/kernel/skas/mmu.c
+++ b/arch/um/kernel/skas/mmu.c
@@ -8,6 +8,7 @@
 #include <linux/sched/signal.h>
 #include <linux/slab.h>
 
+#include <shared/irq_kern.h>
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
 #include <asm/mmu_context.h>
@@ -19,6 +20,9 @@
 /* Ensure the stub_data struct covers the allocated area */
 static_assert(sizeof(struct stub_data) == STUB_DATA_PAGES * UM_KERN_PAGE_SIZE);
 
+spinlock_t mm_list_lock;
+struct list_head mm_list;
+
 int init_new_context(struct task_struct *task, struct mm_struct *mm)
 {
 	struct mm_id *new_id = &mm->context.id;
@@ -31,14 +35,14 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm)
 
 	new_id->stack = stack;
 
-	block_signals_trace();
-	new_id->pid = start_userspace(stack);
-	unblock_signals_trace();
+	scoped_guard(spinlock_irqsave, &mm_list_lock) {
+		/* Insert into list, used for lookups when the child dies */
+		list_add(&mm->context.list, &mm_list);
+	}
 
-	if (new_id->pid < 0) {
-		ret = new_id->pid;
+	ret = start_userspace(new_id);
+	if (ret < 0)
 		goto out_free;
-	}
 
 	/* Ensure the new MM is clean and nothing unwanted is mapped */
 	unmap(new_id, 0, STUB_START);
@@ -60,13 +64,82 @@ void destroy_context(struct mm_struct *mm)
 	 * zero, resulting in a kill(0), which will result in the
 	 * whole UML suddenly dying.  Also, cover negative and
 	 * 1 cases, since they shouldn't happen either.
+	 *
+	 * Negative cases happen if the child died unexpectedly.
 	 */
-	if (mmu->id.pid < 2) {
+	if (mmu->id.pid >= 0 && mmu->id.pid < 2) {
 		printk(KERN_ERR "corrupt mm_context - pid = %d\n",
 		       mmu->id.pid);
 		return;
 	}
-	os_kill_ptraced_process(mmu->id.pid, 1);
+
+	if (mmu->id.pid > 0) {
+		os_kill_ptraced_process(mmu->id.pid, 1);
+		mmu->id.pid = -1;
+	}
+
+	if (using_seccomp && mmu->id.sock)
+		os_close_file(mmu->id.sock);
 
 	free_pages(mmu->id.stack, ilog2(STUB_DATA_PAGES));
+
+	guard(spinlock_irqsave)(&mm_list_lock);
+
+	list_del(&mm->context.list);
+}
+
+static irqreturn_t mm_sigchld_irq(int irq, void* dev)
+{
+	struct mm_context *mm_context;
+	pid_t pid;
+
+	guard(spinlock)(&mm_list_lock);
+
+	while ((pid = os_reap_child()) > 0) {
+		/*
+		* A child died, check if we have an MM with the PID. This is
+		* only relevant in SECCOMP mode (as ptrace will fail anyway).
+		*
+		* See wait_stub_done_seccomp for more details.
+		*/
+		list_for_each_entry(mm_context, &mm_list, list) {
+			if (mm_context->id.pid == pid) {
+				struct stub_data *stub_data;
+				printk("Unexpectedly lost MM child! Affected tasks will segfault.");
+
+				/* Marks the MM as dead */
+				mm_context->id.pid = -1;
+
+				/*
+				 * NOTE: If SMP is implemented, a futex_wake
+				 * needs to be added here.
+				 */
+				stub_data = (void *)mm_context->id.stack;
+				stub_data->futex = FUTEX_IN_KERN;
+
+				/*
+				 * NOTE: Currently executing syscalls by
+				 * affected tasks may finish normally.
+				 */
+				break;
+			}
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int __init init_child_tracking(void)
+{
+	int err;
+
+	spin_lock_init(&mm_list_lock);
+	INIT_LIST_HEAD(&mm_list);
+
+	err = request_irq(SIGCHLD_IRQ, mm_sigchld_irq, 0, "SIGCHLD", NULL);
+	if (err < 0)
+		panic("Failed to register SIGCHLD IRQ: %d", err);
+
+	return 0;
 }
+early_initcall(init_child_tracking)
diff --git a/arch/um/kernel/skas/stub.c b/arch/um/kernel/skas/stub.c
index 796fc266d3bb..67cab46a602c 100644
--- a/arch/um/kernel/skas/stub.c
+++ b/arch/um/kernel/skas/stub.c
@@ -5,21 +5,54 @@
 
 #include <sysdep/stub.h>
 
-static __always_inline int syscall_handler(struct stub_data *d)
+#include <linux/futex.h>
+#include <sys/socket.h>
+#include <errno.h>
+
+/*
+ * Known security issues
+ *
+ * Userspace can jump to this address to execute *any* syscall that is
+ * permitted by the stub. As we will return afterwards, it can do
+ * whatever it likes, including:
+ * - Tricking the kernel into handing out the memory FD
+ * - Using this memory FD to read/write all physical memory
+ * - Running in parallel to the kernel processing a syscall
+ *   (possibly creating data races?)
+ * - Blocking e.g. SIGALRM to avoid time based scheduling
+ *
+ * To avoid this, the permitted location for each syscall needs to be
+ * checked for in the SECCOMP filter (which is reasonably simple). Also,
+ * more care will need to go into considerations how the code might be
+ * tricked by using a prepared stack (or even modifying the stack from
+ * another thread in case SMP support is added).
+ *
+ * As for the SIGALRM, the best counter measure will be to check in the
+ * kernel that the process is reporting back the SIGALRM in a timely
+ * fashion.
+ */
+static __always_inline int syscall_handler(int fd_map[STUB_MAX_FDS])
 {
+	struct stub_data *d = get_stub_data();
 	int i;
 	unsigned long res;
+	int fd;
 
 	for (i = 0; i < d->syscall_data_len; i++) {
 		struct stub_syscall *sc = &d->syscall_data[i];
 
 		switch (sc->syscall) {
 		case STUB_SYSCALL_MMAP:
+			if (fd_map)
+				fd = fd_map[sc->mem.fd];
+			else
+				fd = sc->mem.fd;
+
 			res = stub_syscall6(STUB_MMAP_NR,
 					    sc->mem.addr, sc->mem.length,
 					    sc->mem.prot,
 					    MAP_SHARED | MAP_FIXED,
-					    sc->mem.fd, sc->mem.offset);
+					    fd, sc->mem.offset);
 			if (res != sc->mem.addr) {
 				d->err = res;
 				d->syscall_data_len = i;
@@ -51,9 +84,98 @@ static __always_inline int syscall_handler(struct stub_data *d)
 void __section(".__syscall_stub")
 stub_syscall_handler(void)
 {
+	syscall_handler(NULL);
+
+	trap_myself();
+}
+
+void __section(".__syscall_stub")
+stub_signal_interrupt(int sig, siginfo_t *info, void *p)
+{
 	struct stub_data *d = get_stub_data();
+	char rcv_data;
+	union {
+		char data[CMSG_SPACE(sizeof(int) * STUB_MAX_FDS)];
+		struct cmsghdr align;
+	} ctrl = {};
+	struct iovec iov = {
+		.iov_base = &rcv_data,
+		.iov_len = 1,
+	};
+	struct msghdr msghdr = {
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+		.msg_control = &ctrl,
+		.msg_controllen = sizeof(ctrl),
+	};
+	ucontext_t *uc = p;
+	struct cmsghdr *fd_msg;
+	int *fd_map;
+	int num_fds;
+	long res;
 
-	syscall_handler(d);
+	d->signal = sig;
+	d->si_offset = (unsigned long)info - (unsigned long)&d->sigstack[0];
+	d->mctx_offset = (unsigned long)&uc->uc_mcontext - (unsigned long)&d->sigstack[0];
 
-	trap_myself();
+restart_wait:
+	d->futex = FUTEX_IN_KERN;
+	do {
+		res = stub_syscall3(__NR_futex, (unsigned long)&d->futex,
+				    FUTEX_WAKE, 1);
+	} while (res == -EINTR);
+
+	do {
+		res = stub_syscall4(__NR_futex, (unsigned long)&d->futex,
+				    FUTEX_WAIT, FUTEX_IN_KERN, 0);
+	} while (res == -EINTR || d->futex == FUTEX_IN_KERN);
+
+	if (res < 0 && res != -EAGAIN)
+		stub_syscall1(__NR_exit_group, 1);
+
+	if (d->syscall_data_len) {
+		/* Read passed FDs (if any) */
+		do {
+			res = stub_syscall3(__NR_recvmsg, 0, (unsigned long)&msghdr, 0);
+		} while (res == -EINTR);
+
+		/* We should never have a receive error (other than -EAGAIN) */
+		if (res < 0 && res != -EAGAIN)
+			stub_syscall1(__NR_exit_group, 1);
+
+		/* Receive the FDs */
+		num_fds = 0;
+		fd_msg = msghdr.msg_control;
+		fd_map = (void *)&CMSG_DATA(fd_msg);
+		if (res == iov.iov_len && msghdr.msg_controllen > sizeof(struct cmsghdr))
+			num_fds = (fd_msg->cmsg_len - CMSG_LEN(0)) / sizeof(int);
+
+		/* Try running queued syscalls. */
+		res = syscall_handler(fd_map);
+
+		while (num_fds)
+			stub_syscall2(__NR_close, fd_map[--num_fds], 0);
+	} else {
+		res = 0;
+	}
+
+	if (res < 0 || d->restart_wait) {
+		/* Report SIGSYS if we restart. */
+		d->signal = SIGSYS;
+		d->restart_wait = 0;
+
+		goto restart_wait;
+	}
+
+	/* Restore arch dependent state that is not part of the mcontext */
+	stub_seccomp_restore_state(&d->arch_data);
+
+	/* Return so that the host modified mcontext is restored. */
+}
+
+void __section(".__syscall_stub")
+stub_signal_restorer(void)
+{
+	/* We must not have anything on the stack when doing rt_sigreturn */
+	stub_syscall0(__NR_rt_sigreturn);
 }
diff --git a/arch/um/kernel/skas/stub_exe.c b/arch/um/kernel/skas/stub_exe.c
index 23c99b285e82..cbafaa684e66 100644
--- a/arch/um/kernel/skas/stub_exe.c
+++ b/arch/um/kernel/skas/stub_exe.c
@@ -1,8 +1,12 @@
 #include <sys/ptrace.h>
 #include <sys/prctl.h>
+#include <sys/fcntl.h>
 #include <asm/unistd.h>
 #include <sysdep/stub.h>
 #include <stub-data.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <generated/asm-offsets.h>
 
 void _start(void);
 
@@ -25,8 +29,6 @@ noinline static void real_init(void)
 	} sa = {
 		/* Need to set SA_RESTORER (but the handler never returns) */
 		.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO | 0x04000000,
-		/* no need to mask any signals */
-		.sa_mask = 0,
 	};
 
 	/* set a nice name */
@@ -35,13 +37,20 @@ noinline static void real_init(void)
 	/* Make sure this process dies if the kernel dies */
 	stub_syscall2(__NR_prctl, PR_SET_PDEATHSIG, SIGKILL);
 
+	/* Needed in SECCOMP mode (and safe to do anyway) */
+	stub_syscall5(__NR_prctl, PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+
 	/* read information from STDIN and close it */
 	res = stub_syscall3(__NR_read, 0,
 			    (unsigned long)&init_data, sizeof(init_data));
 	if (res != sizeof(init_data))
 		stub_syscall1(__NR_exit, 10);
 
-	stub_syscall1(__NR_close, 0);
+	/* In SECCOMP mode, FD 0 is a socket and is later used for FD passing */
+	if (!init_data.seccomp)
+		stub_syscall1(__NR_close, 0);
+	else
+		stub_syscall3(__NR_fcntl, 0, F_SETFL, O_NONBLOCK);
 
 	/* map stub code + data */
 	res = stub_syscall6(STUB_MMAP_NR,
@@ -59,22 +68,148 @@ noinline static void real_init(void)
 	if (res != init_data.stub_start + UM_KERN_PAGE_SIZE)
 		stub_syscall1(__NR_exit, 12);
 
+	/* In SECCOMP mode, we only need the signalling FD from now on */
+	if (init_data.seccomp) {
+		res = stub_syscall3(__NR_close_range, 1, ~0U, 0);
+		if (res != 0)
+			stub_syscall1(__NR_exit, 13);
+	}
+
 	/* setup signal stack inside stub data */
 	stack.ss_sp = (void *)init_data.stub_start + UM_KERN_PAGE_SIZE;
 	stub_syscall2(__NR_sigaltstack, (unsigned long)&stack, 0);
 
-	/* register SIGSEGV handler */
-	sa.sa_handler_ = (void *) init_data.segv_handler;
-	res = stub_syscall4(__NR_rt_sigaction, SIGSEGV, (unsigned long)&sa, 0,
-			    sizeof(sa.sa_mask));
-	if (res != 0)
-		stub_syscall1(__NR_exit, 13);
+	/* register signal handlers */
+	sa.sa_handler_ = (void *) init_data.signal_handler;
+	sa.sa_restorer = (void *) init_data.signal_restorer;
+	if (!init_data.seccomp) {
+		/* In ptrace mode, the SIGSEGV handler never returns */
+		sa.sa_mask = 0;
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGSEGV,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 14);
+	} else {
+		/* SECCOMP mode uses rt_sigreturn, need to mask all signals */
+		sa.sa_mask = ~0ULL;
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGSEGV,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 15);
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGSYS,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 16);
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGALRM,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 17);
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGTRAP,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 18);
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGILL,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 19);
+
+		res = stub_syscall4(__NR_rt_sigaction, SIGFPE,
+				    (unsigned long)&sa, 0, sizeof(sa.sa_mask));
+		if (res != 0)
+			stub_syscall1(__NR_exit, 20);
+	}
+
+	/*
+	 * If in seccomp mode, install the SECCOMP filter and trigger a syscall.
+	 * Otherwise set PTRACE_TRACEME and do a SIGSTOP.
+	 */
+	if (init_data.seccomp) {
+		struct sock_filter filter[] = {
+#if __BITS_PER_LONG > 32
+			/* [0] Load upper 32bit of instruction pointer from seccomp_data */
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 (offsetof(struct seccomp_data, instruction_pointer) + 4)),
+
+			/* [1] Jump forward 3 instructions if the upper address is not identical */
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, (init_data.stub_start) >> 32, 0, 3),
+#endif
+			/* [2] Load lower 32bit of instruction pointer from seccomp_data */
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 (offsetof(struct seccomp_data, instruction_pointer))),
+
+			/* [3] Mask out lower bits */
+			BPF_STMT(BPF_ALU | BPF_AND | BPF_K, 0xfffff000),
+
+			/* [4] Jump to [6] if the lower bits are not on the expected page */
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, (init_data.stub_start) & 0xfffff000, 1, 0),
+
+			/* [5] Trap call, allow */
+			BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_TRAP),
+
+			/* [6,7] Check architecture */
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 offsetof(struct seccomp_data, arch)),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K,
+				 UM_SECCOMP_ARCH_NATIVE, 1, 0),
+
+			/* [8] Kill (for architecture check) */
+			BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_KILL_PROCESS),
+
+			/* [9] Load syscall number */
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 offsetof(struct seccomp_data, nr)),
+
+			/* [10-16] Check against permitted syscalls */
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_futex,
+				 7, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K,__NR_recvmsg,
+				 6, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K,__NR_close,
+				 5, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, STUB_MMAP_NR,
+				 4, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_munmap,
+				 3, 0),
+#ifdef __i386__
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_set_thread_area,
+				 2, 0),
+#else
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_arch_prctl,
+				 2, 0),
+#endif
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_rt_sigreturn,
+				 1, 0),
+
+			/* [17] Not one of the permitted syscalls */
+			BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_KILL_PROCESS),
+
+			/* [18] Permitted call for the stub */
+			BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_ALLOW),
+		};
+		struct sock_fprog prog = {
+			.len = sizeof(filter) / sizeof(filter[0]),
+			.filter = filter,
+		};
+
+		if (stub_syscall3(__NR_seccomp, SECCOMP_SET_MODE_FILTER,
+				  SECCOMP_FILTER_FLAG_TSYNC,
+				  (unsigned long)&prog) != 0)
+			stub_syscall1(__NR_exit, 21);
 
-	stub_syscall4(__NR_ptrace, PTRACE_TRACEME, 0, 0, 0);
+		/* Fall through, the exit syscall will cause SIGSYS */
+	} else {
+		stub_syscall4(__NR_ptrace, PTRACE_TRACEME, 0, 0, 0);
 
-	stub_syscall2(__NR_kill, stub_syscall0(__NR_getpid), SIGSTOP);
+		stub_syscall2(__NR_kill, stub_syscall0(__NR_getpid), SIGSTOP);
+	}
 
-	stub_syscall1(__NR_exit, 14);
+	stub_syscall1(__NR_exit, 30);
 
 	__builtin_unreachable();
 }
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index 1394568c0210..ae0fa2173778 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -856,11 +856,16 @@ static struct clock_event_device timer_clockevent = {
 
 static irqreturn_t um_timer(int irq, void *dev)
 {
-	if (get_current()->mm != NULL)
-	{
-        /* userspace - relay signal, results in correct userspace timers */
+	/*
+	 * Interrupt the (possibly) running userspace process, technically this
+	 * should only happen if userspace is currently executing.
+	 * With infinite CPU time-travel, we can only get here when userspace
+	 * is not executing. Do not notify there and avoid spurious scheduling.
+	 */
+	if (time_travel_mode != TT_MODE_INFCPU &&
+	    time_travel_mode != TT_MODE_EXTERNAL &&
+	    get_current()->mm)
 		os_alarm_process(get_current()->mm->context.id.pid);
-	}
 
 	(*timer_clockevent.event_handler)(&timer_clockevent);
 
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index ef2272e92a43..5b80a3a89c20 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -16,7 +16,122 @@
 #include <kern_util.h>
 #include <os.h>
 #include <skas.h>
-#include <arch.h>
+
+/*
+ * NOTE: UML does not have exception tables. As such, this is almost a copy
+ * of the code in mm/memory.c, only adjusting the logic to simply check whether
+ * we are coming from the kernel instead of doing an additional lookup in the
+ * exception table.
+ * We can do this simplification because we never get here if the exception was
+ * fixable.
+ */
+static inline bool get_mmap_lock_carefully(struct mm_struct *mm, bool is_user)
+{
+	if (likely(mmap_read_trylock(mm)))
+		return true;
+
+	if (!is_user)
+		return false;
+
+	return !mmap_read_lock_killable(mm);
+}
+
+static inline bool mmap_upgrade_trylock(struct mm_struct *mm)
+{
+	/*
+	 * We don't have this operation yet.
+	 *
+	 * It should be easy enough to do: it's basically a
+	 *    atomic_long_try_cmpxchg_acquire()
+	 * from RWSEM_READER_BIAS -> RWSEM_WRITER_LOCKED, but
+	 * it also needs the proper lockdep magic etc.
+	 */
+	return false;
+}
+
+static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, bool is_user)
+{
+	mmap_read_unlock(mm);
+	if (!is_user)
+		return false;
+
+	return !mmap_write_lock_killable(mm);
+}
+
+/*
+ * Helper for page fault handling.
+ *
+ * This is kind of equivalend to "mmap_read_lock()" followed
+ * by "find_extend_vma()", except it's a lot more careful about
+ * the locking (and will drop the lock on failure).
+ *
+ * For example, if we have a kernel bug that causes a page
+ * fault, we don't want to just use mmap_read_lock() to get
+ * the mm lock, because that would deadlock if the bug were
+ * to happen while we're holding the mm lock for writing.
+ *
+ * So this checks the exception tables on kernel faults in
+ * order to only do this all for instructions that are actually
+ * expected to fault.
+ *
+ * We can also actually take the mm lock for writing if we
+ * need to extend the vma, which helps the VM layer a lot.
+ */
+static struct vm_area_struct *
+um_lock_mm_and_find_vma(struct mm_struct *mm,
+			unsigned long addr, bool is_user)
+{
+	struct vm_area_struct *vma;
+
+	if (!get_mmap_lock_carefully(mm, is_user))
+		return NULL;
+
+	vma = find_vma(mm, addr);
+	if (likely(vma && (vma->vm_start <= addr)))
+		return vma;
+
+	/*
+	 * Well, dang. We might still be successful, but only
+	 * if we can extend a vma to do so.
+	 */
+	if (!vma || !(vma->vm_flags & VM_GROWSDOWN)) {
+		mmap_read_unlock(mm);
+		return NULL;
+	}
+
+	/*
+	 * We can try to upgrade the mmap lock atomically,
+	 * in which case we can continue to use the vma
+	 * we already looked up.
+	 *
+	 * Otherwise we'll have to drop the mmap lock and
+	 * re-take it, and also look up the vma again,
+	 * re-checking it.
+	 */
+	if (!mmap_upgrade_trylock(mm)) {
+		if (!upgrade_mmap_lock_carefully(mm, is_user))
+			return NULL;
+
+		vma = find_vma(mm, addr);
+		if (!vma)
+			goto fail;
+		if (vma->vm_start <= addr)
+			goto success;
+		if (!(vma->vm_flags & VM_GROWSDOWN))
+			goto fail;
+	}
+
+	if (expand_stack_locked(vma, addr))
+		goto fail;
+
+success:
+	mmap_write_downgrade(mm);
+	return vma;
+
+fail:
+	mmap_write_unlock(mm);
+	return NULL;
+}
 
 /*
  * Note this is constrained to return 0, -EFAULT, -EACCES, -ENOMEM by
@@ -44,21 +159,10 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	if (is_user)
 		flags |= FAULT_FLAG_USER;
 retry:
-	mmap_read_lock(mm);
-	vma = find_vma(mm, address);
-	if (!vma)
-		goto out;
-	if (vma->vm_start <= address)
-		goto good_area;
-	if (!(vma->vm_flags & VM_GROWSDOWN))
-		goto out;
-	if (is_user && !ARCH_IS_STACKGROW(address))
-		goto out;
-	vma = expand_stack(mm, address);
+	vma = um_lock_mm_and_find_vma(mm, address, is_user);
 	if (!vma)
 		goto out_nosemaphore;
 
-good_area:
 	*code_out = SEGV_ACCERR;
 	if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))
diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile
index 049dfa5bc9c6..fae836713487 100644
--- a/arch/um/os-Linux/Makefile
+++ b/arch/um/os-Linux/Makefile
@@ -8,7 +8,7 @@ KCOV_INSTRUMENT                := n
 
 obj-y = execvp.o file.o helper.o irq.o main.o mem.o process.o \
 	registers.o sigio.o signal.o start_up.o time.o tty.o \
-	umid.o user_syms.o util.o drivers/ skas/
+	umid.o user_syms.o util.o skas/
 
 CFLAGS_signal.o += -Wframe-larger-than=4096
 
diff --git a/arch/um/os-Linux/drivers/Makefile b/arch/um/os-Linux/drivers/Makefile
deleted file mode 100644
index cf2d75bb1884..000000000000
--- a/arch/um/os-Linux/drivers/Makefile
+++ /dev/null
@@ -1,13 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-# 
-# Copyright (C) 2000, 2002 Jeff Dike (jdike@karaya.com)
-#
-
-ethertap-objs := ethertap_kern.o ethertap_user.o
-tuntap-objs := tuntap_kern.o tuntap_user.o
-
-obj-y = 
-obj-$(CONFIG_UML_NET_ETHERTAP) += ethertap.o
-obj-$(CONFIG_UML_NET_TUNTAP) += tuntap.o
-
-include $(srctree)/arch/um/scripts/Makefile.rules
diff --git a/arch/um/os-Linux/drivers/etap.h b/arch/um/os-Linux/drivers/etap.h
deleted file mode 100644
index a475259f90e1..000000000000
--- a/arch/um/os-Linux/drivers/etap.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* 
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#ifndef __DRIVERS_ETAP_H
-#define __DRIVERS_ETAP_H
-
-#include <net_user.h>
-
-struct ethertap_data {
-	char *dev_name;
-	char *gate_addr;
-	int data_fd;
-	int control_fd;
-	void *dev;
-};
-
-extern const struct net_user_info ethertap_user_info;
-
-#endif
diff --git a/arch/um/os-Linux/drivers/ethertap_kern.c b/arch/um/os-Linux/drivers/ethertap_kern.c
deleted file mode 100644
index 5e5ee40680ce..000000000000
--- a/arch/um/os-Linux/drivers/ethertap_kern.c
+++ /dev/null
@@ -1,100 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and
- * James Leu (jleu@mindspring.net).
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Copyright (C) 2001 by various other people who didn't put their name here.
- */
-
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include "etap.h"
-#include <net_kern.h>
-
-struct ethertap_init {
-	char *dev_name;
-	char *gate_addr;
-};
-
-static void etap_init(struct net_device *dev, void *data)
-{
-	struct uml_net_private *pri;
-	struct ethertap_data *epri;
-	struct ethertap_init *init = data;
-
-	pri = netdev_priv(dev);
-	epri = (struct ethertap_data *) pri->user;
-	epri->dev_name = init->dev_name;
-	epri->gate_addr = init->gate_addr;
-	epri->data_fd = -1;
-	epri->control_fd = -1;
-	epri->dev = dev;
-
-	printk(KERN_INFO "ethertap backend - %s", epri->dev_name);
-	if (epri->gate_addr != NULL)
-		printk(KERN_CONT ", IP = %s", epri->gate_addr);
-	printk(KERN_CONT "\n");
-}
-
-static int etap_read(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	int len;
-
-	len = net_recvfrom(fd, skb_mac_header(skb),
-			   skb->dev->mtu + 2 + ETH_HEADER_ETHERTAP);
-	if (len <= 0)
-		return(len);
-
-	skb_pull(skb, 2);
-	len -= 2;
-	return len;
-}
-
-static int etap_write(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	skb_push(skb, 2);
-	return net_send(fd, skb->data, skb->len);
-}
-
-const struct net_kern_info ethertap_kern_info = {
-	.init			= etap_init,
-	.protocol		= eth_protocol,
-	.read			= etap_read,
-	.write 			= etap_write,
-};
-
-static int ethertap_setup(char *str, char **mac_out, void *data)
-{
-	struct ethertap_init *init = data;
-
-	*init = ((struct ethertap_init)
-		{ .dev_name 	= NULL,
-		  .gate_addr 	= NULL });
-	if (tap_setup_common(str, "ethertap", &init->dev_name, mac_out,
-			    &init->gate_addr))
-		return 0;
-	if (init->dev_name == NULL) {
-		printk(KERN_ERR "ethertap_setup : Missing tap device name\n");
-		return 0;
-	}
-
-	return 1;
-}
-
-static struct transport ethertap_transport = {
-	.list 		= LIST_HEAD_INIT(ethertap_transport.list),
-	.name 		= "ethertap",
-	.setup  	= ethertap_setup,
-	.user 		= &ethertap_user_info,
-	.kern 		= &ethertap_kern_info,
-	.private_size 	= sizeof(struct ethertap_data),
-	.setup_size 	= sizeof(struct ethertap_init),
-};
-
-static int register_ethertap(void)
-{
-	register_transport(&ethertap_transport);
-	return 0;
-}
-
-late_initcall(register_ethertap);
diff --git a/arch/um/os-Linux/drivers/ethertap_user.c b/arch/um/os-Linux/drivers/ethertap_user.c
deleted file mode 100644
index bdf215c0eca7..000000000000
--- a/arch/um/os-Linux/drivers/ethertap_user.c
+++ /dev/null
@@ -1,248 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and
- * James Leu (jleu@mindspring.net).
- * Copyright (C) 2001 by various other people who didn't put their name here.
- */
-
-#include <stdio.h>
-#include <unistd.h>
-#include <errno.h>
-#include <string.h>
-#include <sys/socket.h>
-#include <sys/wait.h>
-#include "etap.h"
-#include <os.h>
-#include <net_user.h>
-#include <um_malloc.h>
-
-#define MAX_PACKET ETH_MAX_PACKET
-
-static int etap_user_init(void *data, void *dev)
-{
-	struct ethertap_data *pri = data;
-
-	pri->dev = dev;
-	return 0;
-}
-
-struct addr_change {
-	enum { ADD_ADDR, DEL_ADDR } what;
-	unsigned char addr[4];
-	unsigned char netmask[4];
-};
-
-static void etap_change(int op, unsigned char *addr, unsigned char *netmask,
-			int fd)
-{
-	struct addr_change change;
-	char *output;
-	int n;
-
-	change.what = op;
-	memcpy(change.addr, addr, sizeof(change.addr));
-	memcpy(change.netmask, netmask, sizeof(change.netmask));
-	CATCH_EINTR(n = write(fd, &change, sizeof(change)));
-	if (n != sizeof(change)) {
-		printk(UM_KERN_ERR "etap_change - request failed, err = %d\n",
-		       errno);
-		return;
-	}
-
-	output = uml_kmalloc(UM_KERN_PAGE_SIZE, UM_GFP_KERNEL);
-	if (output == NULL)
-		printk(UM_KERN_ERR "etap_change : Failed to allocate output "
-		       "buffer\n");
-	read_output(fd, output, UM_KERN_PAGE_SIZE);
-	if (output != NULL) {
-		printk("%s", output);
-		kfree(output);
-	}
-}
-
-static void etap_open_addr(unsigned char *addr, unsigned char *netmask,
-			   void *arg)
-{
-	etap_change(ADD_ADDR, addr, netmask, *((int *) arg));
-}
-
-static void etap_close_addr(unsigned char *addr, unsigned char *netmask,
-			    void *arg)
-{
-	etap_change(DEL_ADDR, addr, netmask, *((int *) arg));
-}
-
-struct etap_pre_exec_data {
-	int control_remote;
-	int control_me;
-	int data_me;
-};
-
-static void etap_pre_exec(void *arg)
-{
-	struct etap_pre_exec_data *data = arg;
-
-	dup2(data->control_remote, 1);
-	close(data->data_me);
-	close(data->control_me);
-}
-
-static int etap_tramp(char *dev, char *gate, int control_me,
-		      int control_remote, int data_me, int data_remote)
-{
-	struct etap_pre_exec_data pe_data;
-	int pid, err, n;
-	char version_buf[sizeof("nnnnn\0")];
-	char data_fd_buf[sizeof("nnnnnn\0")];
-	char gate_buf[sizeof("nnn.nnn.nnn.nnn\0")];
-	char *setup_args[] = { "uml_net", version_buf, "ethertap", dev,
-			       data_fd_buf, gate_buf, NULL };
-	char *nosetup_args[] = { "uml_net", version_buf, "ethertap",
-				 dev, data_fd_buf, NULL };
-	char **args, c;
-
-	sprintf(data_fd_buf, "%d", data_remote);
-	sprintf(version_buf, "%d", UML_NET_VERSION);
-	if (gate != NULL) {
-		strscpy(gate_buf, gate);
-		args = setup_args;
-	}
-	else args = nosetup_args;
-
-	err = 0;
-	pe_data.control_remote = control_remote;
-	pe_data.control_me = control_me;
-	pe_data.data_me = data_me;
-	pid = run_helper(etap_pre_exec, &pe_data, args);
-
-	if (pid < 0)
-		err = pid;
-	close(data_remote);
-	close(control_remote);
-	CATCH_EINTR(n = read(control_me, &c, sizeof(c)));
-	if (n != sizeof(c)) {
-		err = -errno;
-		printk(UM_KERN_ERR "etap_tramp : read of status failed, "
-		       "err = %d\n", -err);
-		return err;
-	}
-	if (c != 1) {
-		printk(UM_KERN_ERR "etap_tramp : uml_net failed\n");
-		err = helper_wait(pid);
-	}
-	return err;
-}
-
-static int etap_open(void *data)
-{
-	struct ethertap_data *pri = data;
-	char *output;
-	int data_fds[2], control_fds[2], err, output_len;
-
-	err = tap_open_common(pri->dev, pri->gate_addr);
-	if (err)
-		return err;
-
-	err = socketpair(AF_UNIX, SOCK_DGRAM, 0, data_fds);
-	if (err) {
-		err = -errno;
-		printk(UM_KERN_ERR "etap_open - data socketpair failed - "
-		       "err = %d\n", errno);
-		return err;
-	}
-
-	err = socketpair(AF_UNIX, SOCK_STREAM, 0, control_fds);
-	if (err) {
-		err = -errno;
-		printk(UM_KERN_ERR "etap_open - control socketpair failed - "
-		       "err = %d\n", errno);
-		goto out_close_data;
-	}
-
-	err = etap_tramp(pri->dev_name, pri->gate_addr, control_fds[0],
-			 control_fds[1], data_fds[0], data_fds[1]);
-	output_len = UM_KERN_PAGE_SIZE;
-	output = uml_kmalloc(output_len, UM_GFP_KERNEL);
-	read_output(control_fds[0], output, output_len);
-
-	if (output == NULL)
-		printk(UM_KERN_ERR "etap_open : failed to allocate output "
-		       "buffer\n");
-	else {
-		printk("%s", output);
-		kfree(output);
-	}
-
-	if (err < 0) {
-		printk(UM_KERN_ERR "etap_tramp failed - err = %d\n", -err);
-		goto out_close_control;
-	}
-
-	pri->data_fd = data_fds[0];
-	pri->control_fd = control_fds[0];
-	iter_addresses(pri->dev, etap_open_addr, &pri->control_fd);
-	return data_fds[0];
-
-out_close_control:
-	close(control_fds[0]);
-	close(control_fds[1]);
-out_close_data:
-	close(data_fds[0]);
-	close(data_fds[1]);
-	return err;
-}
-
-static void etap_close(int fd, void *data)
-{
-	struct ethertap_data *pri = data;
-
-	iter_addresses(pri->dev, etap_close_addr, &pri->control_fd);
-	close(fd);
-
-	if (shutdown(pri->data_fd, SHUT_RDWR) < 0)
-		printk(UM_KERN_ERR "etap_close - shutdown data socket failed, "
-		       "errno = %d\n", errno);
-
-	if (shutdown(pri->control_fd, SHUT_RDWR) < 0)
-		printk(UM_KERN_ERR "etap_close - shutdown control socket "
-		       "failed, errno = %d\n", errno);
-
-	close(pri->data_fd);
-	pri->data_fd = -1;
-	close(pri->control_fd);
-	pri->control_fd = -1;
-}
-
-static void etap_add_addr(unsigned char *addr, unsigned char *netmask,
-			  void *data)
-{
-	struct ethertap_data *pri = data;
-
-	tap_check_ips(pri->gate_addr, addr);
-	if (pri->control_fd == -1)
-		return;
-	etap_open_addr(addr, netmask, &pri->control_fd);
-}
-
-static void etap_del_addr(unsigned char *addr, unsigned char *netmask,
-			  void *data)
-{
-	struct ethertap_data *pri = data;
-
-	if (pri->control_fd == -1)
-		return;
-
-	etap_close_addr(addr, netmask, &pri->control_fd);
-}
-
-const struct net_user_info ethertap_user_info = {
-	.init		= etap_user_init,
-	.open		= etap_open,
-	.close	 	= etap_close,
-	.remove	 	= NULL,
-	.add_address	= etap_add_addr,
-	.delete_address = etap_del_addr,
-	.mtu		= ETH_MAX_PACKET,
-	.max_packet	= ETH_MAX_PACKET + ETH_HEADER_ETHERTAP,
-};
diff --git a/arch/um/os-Linux/drivers/tuntap.h b/arch/um/os-Linux/drivers/tuntap.h
deleted file mode 100644
index e364e42abfc5..000000000000
--- a/arch/um/os-Linux/drivers/tuntap.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* 
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#ifndef __UM_TUNTAP_H
-#define __UM_TUNTAP_H
-
-#include <net_user.h>
-
-struct tuntap_data {
-	char *dev_name;
-	int fixed_config;
-	char *gate_addr;
-	int fd;
-	void *dev;
-};
-
-extern const struct net_user_info tuntap_user_info;
-
-#endif
diff --git a/arch/um/os-Linux/drivers/tuntap_kern.c b/arch/um/os-Linux/drivers/tuntap_kern.c
deleted file mode 100644
index ff022d9cf0dd..000000000000
--- a/arch/um/os-Linux/drivers/tuntap_kern.c
+++ /dev/null
@@ -1,86 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#include <linux/netdevice.h>
-#include <linux/init.h>
-#include <linux/skbuff.h>
-#include <asm/errno.h>
-#include <net_kern.h>
-#include "tuntap.h"
-
-struct tuntap_init {
-	char *dev_name;
-	char *gate_addr;
-};
-
-static void tuntap_init(struct net_device *dev, void *data)
-{
-	struct uml_net_private *pri;
-	struct tuntap_data *tpri;
-	struct tuntap_init *init = data;
-
-	pri = netdev_priv(dev);
-	tpri = (struct tuntap_data *) pri->user;
-	tpri->dev_name = init->dev_name;
-	tpri->fixed_config = (init->dev_name != NULL);
-	tpri->gate_addr = init->gate_addr;
-	tpri->fd = -1;
-	tpri->dev = dev;
-
-	printk(KERN_INFO "TUN/TAP backend - ");
-	if (tpri->gate_addr != NULL)
-		printk(KERN_CONT "IP = %s", tpri->gate_addr);
-	printk(KERN_CONT "\n");
-}
-
-static int tuntap_read(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	return net_read(fd, skb_mac_header(skb),
-			skb->dev->mtu + ETH_HEADER_OTHER);
-}
-
-static int tuntap_write(int fd, struct sk_buff *skb, struct uml_net_private *lp)
-{
-	return net_write(fd, skb->data, skb->len);
-}
-
-const struct net_kern_info tuntap_kern_info = {
-	.init			= tuntap_init,
-	.protocol		= eth_protocol,
-	.read			= tuntap_read,
-	.write 			= tuntap_write,
-};
-
-static int tuntap_setup(char *str, char **mac_out, void *data)
-{
-	struct tuntap_init *init = data;
-
-	*init = ((struct tuntap_init)
-		{ .dev_name 	= NULL,
-		  .gate_addr 	= NULL });
-	if (tap_setup_common(str, "tuntap", &init->dev_name, mac_out,
-			    &init->gate_addr))
-		return 0;
-
-	return 1;
-}
-
-static struct transport tuntap_transport = {
-	.list 		= LIST_HEAD_INIT(tuntap_transport.list),
-	.name 		= "tuntap",
-	.setup  	= tuntap_setup,
-	.user 		= &tuntap_user_info,
-	.kern 		= &tuntap_kern_info,
-	.private_size 	= sizeof(struct tuntap_data),
-	.setup_size 	= sizeof(struct tuntap_init),
-};
-
-static int register_tuntap(void)
-{
-	register_transport(&tuntap_transport);
-	return 0;
-}
-
-late_initcall(register_tuntap);
diff --git a/arch/um/os-Linux/drivers/tuntap_user.c b/arch/um/os-Linux/drivers/tuntap_user.c
deleted file mode 100644
index 91f0e27ca3a6..000000000000
--- a/arch/um/os-Linux/drivers/tuntap_user.c
+++ /dev/null
@@ -1,215 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* 
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#include <stdio.h>
-#include <unistd.h>
-#include <errno.h>
-#include <string.h>
-#include <linux/if_tun.h>
-#include <net/if.h>
-#include <sys/ioctl.h>
-#include <sys/socket.h>
-#include <sys/wait.h>
-#include <sys/uio.h>
-#include <kern_util.h>
-#include <os.h>
-#include "tuntap.h"
-
-static int tuntap_user_init(void *data, void *dev)
-{
-	struct tuntap_data *pri = data;
-
-	pri->dev = dev;
-	return 0;
-}
-
-static void tuntap_add_addr(unsigned char *addr, unsigned char *netmask,
-			    void *data)
-{
-	struct tuntap_data *pri = data;
-
-	tap_check_ips(pri->gate_addr, addr);
-	if ((pri->fd == -1) || pri->fixed_config)
-		return;
-	open_addr(addr, netmask, pri->dev_name);
-}
-
-static void tuntap_del_addr(unsigned char *addr, unsigned char *netmask,
-			    void *data)
-{
-	struct tuntap_data *pri = data;
-
-	if ((pri->fd == -1) || pri->fixed_config)
-		return;
-	close_addr(addr, netmask, pri->dev_name);
-}
-
-struct tuntap_pre_exec_data {
-	int stdout_fd;
-	int close_me;
-};
-
-static void tuntap_pre_exec(void *arg)
-{
-	struct tuntap_pre_exec_data *data = arg;
-
-	dup2(data->stdout_fd, 1);
-	close(data->close_me);
-}
-
-static int tuntap_open_tramp(char *gate, int *fd_out, int me, int remote,
-			     char *buffer, int buffer_len, int *used_out)
-{
-	struct tuntap_pre_exec_data data;
-	char version_buf[sizeof("nnnnn\0")];
-	char *argv[] = { "uml_net", version_buf, "tuntap", "up", gate,
-			 NULL };
-	char buf[CMSG_SPACE(sizeof(*fd_out))];
-	struct msghdr msg;
-	struct cmsghdr *cmsg;
-	struct iovec iov;
-	int pid, n, err;
-
-	sprintf(version_buf, "%d", UML_NET_VERSION);
-
-	data.stdout_fd = remote;
-	data.close_me = me;
-
-	pid = run_helper(tuntap_pre_exec, &data, argv);
-
-	if (pid < 0)
-		return pid;
-
-	close(remote);
-
-	msg.msg_name = NULL;
-	msg.msg_namelen = 0;
-	if (buffer != NULL) {
-		iov = ((struct iovec) { buffer, buffer_len });
-		msg.msg_iov = &iov;
-		msg.msg_iovlen = 1;
-	}
-	else {
-		msg.msg_iov = NULL;
-		msg.msg_iovlen = 0;
-	}
-	msg.msg_control = buf;
-	msg.msg_controllen = sizeof(buf);
-	msg.msg_flags = 0;
-	n = recvmsg(me, &msg, 0);
-	*used_out = n;
-	if (n < 0) {
-		err = -errno;
-		printk(UM_KERN_ERR "tuntap_open_tramp : recvmsg failed - "
-		       "errno = %d\n", errno);
-		return err;
-	}
-	helper_wait(pid);
-
-	cmsg = CMSG_FIRSTHDR(&msg);
-	if (cmsg == NULL) {
-		printk(UM_KERN_ERR "tuntap_open_tramp : didn't receive a "
-		       "message\n");
-		return -EINVAL;
-	}
-	if ((cmsg->cmsg_level != SOL_SOCKET) ||
-	   (cmsg->cmsg_type != SCM_RIGHTS)) {
-		printk(UM_KERN_ERR "tuntap_open_tramp : didn't receive a "
-		       "descriptor\n");
-		return -EINVAL;
-	}
-	*fd_out = ((int *) CMSG_DATA(cmsg))[0];
-	os_set_exec_close(*fd_out);
-	return 0;
-}
-
-static int tuntap_open(void *data)
-{
-	struct ifreq ifr;
-	struct tuntap_data *pri = data;
-	char *output, *buffer;
-	int err, fds[2], len, used;
-
-	err = tap_open_common(pri->dev, pri->gate_addr);
-	if (err < 0)
-		return err;
-
-	if (pri->fixed_config) {
-		pri->fd = os_open_file("/dev/net/tun",
-				       of_cloexec(of_rdwr(OPENFLAGS())), 0);
-		if (pri->fd < 0) {
-			printk(UM_KERN_ERR "Failed to open /dev/net/tun, "
-			       "err = %d\n", -pri->fd);
-			return pri->fd;
-		}
-		memset(&ifr, 0, sizeof(ifr));
-		ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
-		strscpy(ifr.ifr_name, pri->dev_name);
-		if (ioctl(pri->fd, TUNSETIFF, &ifr) < 0) {
-			err = -errno;
-			printk(UM_KERN_ERR "TUNSETIFF failed, errno = %d\n",
-			       errno);
-			close(pri->fd);
-			return err;
-		}
-	}
-	else {
-		err = socketpair(AF_UNIX, SOCK_DGRAM, 0, fds);
-		if (err) {
-			err = -errno;
-			printk(UM_KERN_ERR "tuntap_open : socketpair failed - "
-			       "errno = %d\n", errno);
-			return err;
-		}
-
-		buffer = get_output_buffer(&len);
-		if (buffer != NULL)
-			len--;
-		used = 0;
-
-		err = tuntap_open_tramp(pri->gate_addr, &pri->fd, fds[0],
-					fds[1], buffer, len, &used);
-
-		output = buffer;
-		if (err < 0) {
-			printk("%s", output);
-			free_output_buffer(buffer);
-			printk(UM_KERN_ERR "tuntap_open_tramp failed - "
-			       "err = %d\n", -err);
-			return err;
-		}
-
-		pri->dev_name = uml_strdup(buffer);
-		output += IFNAMSIZ;
-		printk("%s", output);
-		free_output_buffer(buffer);
-
-		close(fds[0]);
-		iter_addresses(pri->dev, open_addr, pri->dev_name);
-	}
-
-	return pri->fd;
-}
-
-static void tuntap_close(int fd, void *data)
-{
-	struct tuntap_data *pri = data;
-
-	if (!pri->fixed_config)
-		iter_addresses(pri->dev, close_addr, pri->dev_name);
-	close(fd);
-	pri->fd = -1;
-}
-
-const struct net_user_info tuntap_user_info = {
-	.init		= tuntap_user_init,
-	.open		= tuntap_open,
-	.close	 	= tuntap_close,
-	.remove	 	= NULL,
-	.add_address	= tuntap_add_addr,
-	.delete_address = tuntap_del_addr,
-	.mtu		= ETH_MAX_PACKET,
-	.max_packet	= ETH_MAX_PACKET + ETH_HEADER_OTHER,
-};
diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c
index a0d01c68ce3e..617886d1fb1e 100644
--- a/arch/um/os-Linux/file.c
+++ b/arch/um/os-Linux/file.c
@@ -106,21 +106,6 @@ int os_get_ifname(int fd, char* namebuf)
 	return 0;
 }
 
-int os_set_slip(int fd)
-{
-	int disc, sencap;
-
-	disc = N_SLIP;
-	if (ioctl(fd, TIOCSETD, &disc) < 0)
-		return -errno;
-
-	sencap = 0;
-	if (ioctl(fd, SIOCSIFENCAP, &sencap) < 0)
-		return -errno;
-
-	return 0;
-}
-
 int os_mode_fd(int fd, int mode)
 {
 	int err;
diff --git a/arch/um/os-Linux/internal.h b/arch/um/os-Linux/internal.h
index 317fca190c2b..5d8d3b0817a9 100644
--- a/arch/um/os-Linux/internal.h
+++ b/arch/um/os-Linux/internal.h
@@ -2,6 +2,9 @@
 #ifndef __UM_OS_LINUX_INTERNAL_H
 #define __UM_OS_LINUX_INTERNAL_H
 
+#include <mm_id.h>
+#include <stub-data.h>
+
 /*
  * elf_aux.c
  */
@@ -16,5 +19,5 @@ void check_tmpexec(void);
  * skas/process.c
  */
 void wait_stub_done(int pid);
-
+void wait_stub_done_seccomp(struct mm_id *mm_idp, int running, int wait_sigsys);
 #endif /* __UM_OS_LINUX_INTERNAL_H */
diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c
index 184566edeee9..00b49e90d05f 100644
--- a/arch/um/os-Linux/process.c
+++ b/arch/um/os-Linux/process.c
@@ -18,17 +18,29 @@
 #include <init.h>
 #include <longjmp.h>
 #include <os.h>
+#include <skas/skas.h>
 
 void os_alarm_process(int pid)
 {
+	if (pid <= 0)
+		return;
+
 	kill(pid, SIGALRM);
 }
 
 void os_kill_process(int pid, int reap_child)
 {
+	if (pid <= 0)
+		return;
+
+	/* Block signals until child is reaped */
+	block_signals();
+
 	kill(pid, SIGKILL);
 	if (reap_child)
 		CATCH_EINTR(waitpid(pid, NULL, __WALL));
+
+	unblock_signals();
 }
 
 /* Kill off a ptraced child by all means available.  kill it normally first,
@@ -38,11 +50,27 @@ void os_kill_process(int pid, int reap_child)
 
 void os_kill_ptraced_process(int pid, int reap_child)
 {
+	if (pid <= 0)
+		return;
+
+	/* Block signals until child is reaped */
+	block_signals();
+
 	kill(pid, SIGKILL);
 	ptrace(PTRACE_KILL, pid);
 	ptrace(PTRACE_CONT, pid);
 	if (reap_child)
 		CATCH_EINTR(waitpid(pid, NULL, __WALL));
+
+	unblock_signals();
+}
+
+pid_t os_reap_child(void)
+{
+	int status;
+
+	/* Try to reap a child */
+	return waitpid(-1, &status, WNOHANG);
 }
 
 /* Don't use the glibc version, which caches the result in TLS. It misses some
@@ -151,6 +179,9 @@ void init_new_thread_signals(void)
 	set_handler(SIGBUS);
 	signal(SIGHUP, SIG_IGN);
 	set_handler(SIGIO);
+	/* We (currently) only use the child reaper IRQ in seccomp mode */
+	if (using_seccomp)
+		set_handler(SIGCHLD);
 	signal(SIGWINCH, SIG_IGN);
 }
 
diff --git a/arch/um/os-Linux/registers.c b/arch/um/os-Linux/registers.c
index d7ca148807b2..bfba2cbc9478 100644
--- a/arch/um/os-Linux/registers.c
+++ b/arch/um/os-Linux/registers.c
@@ -14,8 +14,8 @@
 
 /* This is set once at boot time and not changed thereafter */
 
-static unsigned long exec_regs[MAX_REG_NR];
-static unsigned long *exec_fp_regs;
+unsigned long exec_regs[MAX_REG_NR];
+unsigned long *exec_fp_regs;
 
 int init_pid_registers(int pid)
 {
diff --git a/arch/um/os-Linux/sigio.c b/arch/um/os-Linux/sigio.c
index a05a6ecee756..6de145f8fe3d 100644
--- a/arch/um/os-Linux/sigio.c
+++ b/arch/um/os-Linux/sigio.c
@@ -12,6 +12,7 @@
 #include <signal.h>
 #include <string.h>
 #include <sys/epoll.h>
+#include <asm/unistd.h>
 #include <kern_util.h>
 #include <init.h>
 #include <os.h>
@@ -46,7 +47,7 @@ static void *write_sigio_thread(void *unused)
 			       __func__, errno);
 		}
 
-		CATCH_EINTR(r = tgkill(pid, pid, SIGIO));
+		CATCH_EINTR(r = syscall(__NR_tgkill, pid, pid, SIGIO));
 		if (r < 0)
 			printk(UM_KERN_ERR "%s: tgkill failed, errno = %d\n",
 			       __func__, errno);
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index e71e5b4878d1..11f07f498270 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -29,6 +29,7 @@ void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *, void *mc) =
 	[SIGBUS]	= relay_signal,
 	[SIGSEGV]	= segv_handler,
 	[SIGIO]		= sigio_handler,
+	[SIGCHLD]	= sigchld_handler,
 };
 
 static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
@@ -44,7 +45,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
 	}
 
 	/* enable signals if sig isn't IRQ signal */
-	if ((sig != SIGIO) && (sig != SIGWINCH))
+	if ((sig != SIGIO) && (sig != SIGWINCH) && (sig != SIGCHLD))
 		unblock_signals_trace();
 
 	(*sig_info[sig])(sig, si, &r, mc);
@@ -64,6 +65,9 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
 #define SIGALRM_BIT 1
 #define SIGALRM_MASK (1 << SIGALRM_BIT)
 
+#define SIGCHLD_BIT 2
+#define SIGCHLD_MASK (1 << SIGCHLD_BIT)
+
 int signals_enabled;
 #if IS_ENABLED(CONFIG_UML_TIME_TRAVEL_SUPPORT)
 static int signals_blocked, signals_blocked_pending;
@@ -102,6 +106,11 @@ static void sig_handler(int sig, struct siginfo *si, mcontext_t *mc)
 		return;
 	}
 
+	if (!enabled && (sig == SIGCHLD)) {
+		signals_pending |= SIGCHLD_MASK;
+		return;
+	}
+
 	block_signals_trace();
 
 	sig_handler_common(sig, si, mc);
@@ -181,6 +190,8 @@ static void (*handlers[_NSIG])(int sig, struct siginfo *si, mcontext_t *mc) = {
 
 	[SIGIO] = sig_handler,
 	[SIGWINCH] = sig_handler,
+	/* SIGCHLD is only actually registered in seccomp mode. */
+	[SIGCHLD] = sig_handler,
 	[SIGALRM] = timer_alarm_handler,
 
 	[SIGUSR1] = sigusr1_handler,
@@ -309,6 +320,12 @@ void unblock_signals(void)
 		if (save_pending & SIGIO_MASK)
 			sig_handler_common(SIGIO, NULL, NULL);
 
+		if (save_pending & SIGCHLD_MASK) {
+			struct uml_pt_regs regs = {};
+
+			sigchld_handler(SIGCHLD, NULL, &regs, NULL);
+		}
+
 		/* Do not reenter the handler */
 
 		if ((save_pending & SIGALRM_MASK) && (!(signals_active & SIGALRM_MASK)))
diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c
index d7f1814b0e5a..8b9921ac3ef8 100644
--- a/arch/um/os-Linux/skas/mem.c
+++ b/arch/um/os-Linux/skas/mem.c
@@ -43,6 +43,16 @@ void syscall_stub_dump_error(struct mm_id *mm_idp)
 
 	print_hex_dump(UM_KERN_ERR, "    syscall data: ", 0,
 		       16, 4, sc, sizeof(*sc), 0);
+
+	if (using_seccomp) {
+		printk(UM_KERN_ERR "%s: FD map num: %d", __func__,
+		       mm_idp->syscall_fd_num);
+		print_hex_dump(UM_KERN_ERR,
+				"    FD map: ", 0, 16,
+				sizeof(mm_idp->syscall_fd_map[0]),
+				mm_idp->syscall_fd_map,
+				sizeof(mm_idp->syscall_fd_map), 0);
+	}
 }
 
 static inline unsigned long *check_init_stack(struct mm_id * mm_idp,
@@ -80,27 +90,32 @@ static inline long do_syscall_stub(struct mm_id *mm_idp)
 	int n, i;
 	int err, pid = mm_idp->pid;
 
-	n = ptrace_setregs(pid, syscall_regs);
-	if (n < 0) {
-		printk(UM_KERN_ERR "Registers - \n");
-		for (i = 0; i < MAX_REG_NR; i++)
-			printk(UM_KERN_ERR "\t%d\t0x%lx\n", i, syscall_regs[i]);
-		panic("%s : PTRACE_SETREGS failed, errno = %d\n",
-		      __func__, -n);
-	}
-
 	/* Inform process how much we have filled in. */
 	proc_data->syscall_data_len = mm_idp->syscall_data_len;
 
-	err = ptrace(PTRACE_CONT, pid, 0, 0);
-	if (err)
-		panic("Failed to continue stub, pid = %d, errno = %d\n", pid,
-		      errno);
-
-	wait_stub_done(pid);
+	if (using_seccomp) {
+		proc_data->restart_wait = 1;
+		wait_stub_done_seccomp(mm_idp, 0, 1);
+	} else {
+		n = ptrace_setregs(pid, syscall_regs);
+		if (n < 0) {
+			printk(UM_KERN_ERR "Registers -\n");
+			for (i = 0; i < MAX_REG_NR; i++)
+				printk(UM_KERN_ERR "\t%d\t0x%lx\n", i, syscall_regs[i]);
+			panic("%s : PTRACE_SETREGS failed, errno = %d\n",
+			      __func__, -n);
+		}
+
+		err = ptrace(PTRACE_CONT, pid, 0, 0);
+		if (err)
+			panic("Failed to continue stub, pid = %d, errno = %d\n",
+			      pid, errno);
+
+		wait_stub_done(pid);
+	}
 
 	/*
-	 * proc_data->err will be non-zero if there was an (unexpected) error.
+	 * proc_data->err will be negative if there was an (unexpected) error.
 	 * In that case, syscall_data_len points to the last executed syscall,
 	 * otherwise it will be zero (but we do not need to rely on that).
 	 */
@@ -113,6 +128,9 @@ static inline long do_syscall_stub(struct mm_id *mm_idp)
 		mm_idp->syscall_data_len = 0;
 	}
 
+	if (using_seccomp)
+		mm_idp->syscall_fd_num = 0;
+
 	return mm_idp->syscall_data_len;
 }
 
@@ -175,6 +193,44 @@ static struct stub_syscall *syscall_stub_get_previous(struct mm_id *mm_idp,
 	return NULL;
 }
 
+static int get_stub_fd(struct mm_id *mm_idp, int fd)
+{
+	int i;
+
+	/* Find an FD slot (or flush and use first) */
+	if (!using_seccomp)
+		return fd;
+
+	/* Already crashed, value does not matter */
+	if (mm_idp->syscall_data_len < 0)
+		return 0;
+
+	/* Find existing FD in map if we can allocate another syscall */
+	if (mm_idp->syscall_data_len <
+	    ARRAY_SIZE(((struct stub_data *)NULL)->syscall_data)) {
+		for (i = 0; i < mm_idp->syscall_fd_num; i++) {
+			if (mm_idp->syscall_fd_map[i] == fd)
+				return i;
+		}
+
+		if (mm_idp->syscall_fd_num < STUB_MAX_FDS) {
+			i = mm_idp->syscall_fd_num;
+			mm_idp->syscall_fd_map[i] = fd;
+
+			mm_idp->syscall_fd_num++;
+
+			return i;
+		}
+	}
+
+	/* FD map full or no syscall space available, continue after flush */
+	do_syscall_stub(mm_idp);
+	mm_idp->syscall_fd_map[0] = fd;
+	mm_idp->syscall_fd_num = 1;
+
+	return 0;
+}
+
 int map(struct mm_id *mm_idp, unsigned long virt, unsigned long len, int prot,
 	int phys_fd, unsigned long long offset)
 {
@@ -182,12 +238,21 @@ int map(struct mm_id *mm_idp, unsigned long virt, unsigned long len, int prot,
 
 	/* Compress with previous syscall if that is possible */
 	sc = syscall_stub_get_previous(mm_idp, STUB_SYSCALL_MMAP, virt);
-	if (sc && sc->mem.prot == prot && sc->mem.fd == phys_fd &&
+	if (sc && sc->mem.prot == prot &&
 	    sc->mem.offset == MMAP_OFFSET(offset - sc->mem.length)) {
-		sc->mem.length += len;
-		return 0;
+		int prev_fd = sc->mem.fd;
+
+		if (using_seccomp)
+			prev_fd = mm_idp->syscall_fd_map[sc->mem.fd];
+
+		if (phys_fd == prev_fd) {
+			sc->mem.length += len;
+			return 0;
+		}
 	}
 
+	phys_fd = get_stub_fd(mm_idp, phys_fd);
+
 	sc = syscall_stub_alloc(mm_idp);
 	sc->syscall = STUB_SYSCALL_MMAP;
 	sc->mem.addr = virt;
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index ae2aea062f06..e42ffac23e3c 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
+ * Copyright (C) 2021 Benjamin Berg <benjamin@sipsolutions.net>
  * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de)
  * Copyright (C) 2002- 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  */
@@ -15,6 +16,7 @@
 #include <sys/mman.h>
 #include <sys/wait.h>
 #include <sys/stat.h>
+#include <sys/socket.h>
 #include <asm/unistd.h>
 #include <as-layout.h>
 #include <init.h>
@@ -25,8 +27,11 @@
 #include <registers.h>
 #include <skas.h>
 #include <sysdep/stub.h>
+#include <sysdep/mcontext.h>
+#include <linux/futex.h>
 #include <linux/threads.h>
 #include <timetravel.h>
+#include <asm-generic/rwonce.h>
 #include "../internal.h"
 
 int is_skas_winch(int pid, int fd, void *data)
@@ -142,6 +147,105 @@ bad_wait:
 	fatal_sigsegv();
 }
 
+void wait_stub_done_seccomp(struct mm_id *mm_idp, int running, int wait_sigsys)
+{
+	struct stub_data *data = (void *)mm_idp->stack;
+	int ret;
+
+	do {
+		const char byte = 0;
+		struct iovec iov = {
+			.iov_base = (void *)&byte,
+			.iov_len = sizeof(byte),
+		};
+		union {
+			char data[CMSG_SPACE(sizeof(mm_idp->syscall_fd_map))];
+			struct cmsghdr align;
+		} ctrl;
+		struct msghdr msgh = {
+			.msg_iov = &iov,
+			.msg_iovlen = 1,
+		};
+
+		if (!running) {
+			if (mm_idp->syscall_fd_num) {
+				unsigned int fds_size =
+					sizeof(int) * mm_idp->syscall_fd_num;
+				struct cmsghdr *cmsg;
+
+				msgh.msg_control = ctrl.data;
+				msgh.msg_controllen = CMSG_SPACE(fds_size);
+				cmsg = CMSG_FIRSTHDR(&msgh);
+				cmsg->cmsg_level = SOL_SOCKET;
+				cmsg->cmsg_type = SCM_RIGHTS;
+				cmsg->cmsg_len = CMSG_LEN(fds_size);
+				memcpy(CMSG_DATA(cmsg), mm_idp->syscall_fd_map,
+				       fds_size);
+
+				CATCH_EINTR(syscall(__NR_sendmsg, mm_idp->sock,
+						&msgh, 0));
+			}
+
+			data->signal = 0;
+			data->futex = FUTEX_IN_CHILD;
+			CATCH_EINTR(syscall(__NR_futex, &data->futex,
+					    FUTEX_WAKE, 1, NULL, NULL, 0));
+		}
+
+		do {
+			/*
+			 * We need to check whether the child is still alive
+			 * before and after the FUTEX_WAIT call. Before, in
+			 * case it just died but we still updated data->futex
+			 * to FUTEX_IN_CHILD. And after, in case it died while
+			 * we were waiting (and SIGCHLD woke us up, see the
+			 * IRQ handler in mmu.c).
+			 *
+			 * Either way, if PID is negative, then we have no
+			 * choice but to kill the task.
+			 */
+			if (__READ_ONCE(mm_idp->pid) < 0)
+				goto out_kill;
+
+			ret = syscall(__NR_futex, &data->futex,
+				      FUTEX_WAIT, FUTEX_IN_CHILD,
+				      NULL, NULL, 0);
+			if (ret < 0 && errno != EINTR && errno != EAGAIN) {
+				printk(UM_KERN_ERR "%s : FUTEX_WAIT failed, errno = %d\n",
+				       __func__, errno);
+				goto out_kill;
+			}
+		} while (data->futex == FUTEX_IN_CHILD);
+
+		if (__READ_ONCE(mm_idp->pid) < 0)
+			goto out_kill;
+
+		running = 0;
+
+		/* We may receive a SIGALRM before SIGSYS, iterate again. */
+	} while (wait_sigsys && data->signal == SIGALRM);
+
+	if (data->mctx_offset > sizeof(data->sigstack) - sizeof(mcontext_t)) {
+		printk(UM_KERN_ERR "%s : invalid mcontext offset", __func__);
+		goto out_kill;
+	}
+
+	if (wait_sigsys && data->signal != SIGSYS) {
+		printk(UM_KERN_ERR "%s : expected SIGSYS but got %d",
+		       __func__, data->signal);
+		goto out_kill;
+	}
+
+	return;
+
+out_kill:
+	printk(UM_KERN_ERR "%s : failed to wait for stub, pid = %d, errno = %d\n",
+	       __func__, mm_idp->pid, errno);
+	/* This is not true inside start_userspace */
+	if (current_mm_id() == mm_idp)
+		fatal_sigsegv();
+}
+
 extern unsigned long current_stub_stack(void);
 
 static void get_skas_faultinfo(int pid, struct faultinfo *fi)
@@ -163,12 +267,6 @@ static void get_skas_faultinfo(int pid, struct faultinfo *fi)
 	memcpy(fi, (void *)current_stub_stack(), sizeof(*fi));
 }
 
-static void handle_segv(int pid, struct uml_pt_regs *regs)
-{
-	get_skas_faultinfo(pid, &regs->faultinfo);
-	segv(regs->faultinfo, 0, 1, NULL, NULL);
-}
-
 static void handle_trap(int pid, struct uml_pt_regs *regs)
 {
 	if ((UPT_IP(regs) >= STUB_START) && (UPT_IP(regs) < STUB_END))
@@ -181,29 +279,48 @@ extern char __syscall_stub_start[];
 
 static int stub_exe_fd;
 
+struct tramp_data {
+	struct stub_data *stub_data;
+	/* 0 is inherited, 1 is the kernel side */
+	int sockpair[2];
+};
+
 #ifndef CLOSE_RANGE_CLOEXEC
 #define CLOSE_RANGE_CLOEXEC	(1U << 2)
 #endif
 
-static int userspace_tramp(void *stack)
+static int userspace_tramp(void *data)
 {
+	struct tramp_data *tramp_data = data;
 	char *const argv[] = { "uml-userspace", NULL };
-	int pipe_fds[2];
 	unsigned long long offset;
 	struct stub_init_data init_data = {
+		.seccomp = using_seccomp,
 		.stub_start = STUB_START,
-		.segv_handler = STUB_CODE +
-				(unsigned long) stub_segv_handler -
-				(unsigned long) __syscall_stub_start,
 	};
 	struct iomem_region *iomem;
 	int ret;
 
+	if (using_seccomp) {
+		init_data.signal_handler = STUB_CODE +
+					   (unsigned long) stub_signal_interrupt -
+					   (unsigned long) __syscall_stub_start;
+		init_data.signal_restorer = STUB_CODE +
+					   (unsigned long) stub_signal_restorer -
+					   (unsigned long) __syscall_stub_start;
+	} else {
+		init_data.signal_handler = STUB_CODE +
+					   (unsigned long) stub_segv_handler -
+					   (unsigned long) __syscall_stub_start;
+		init_data.signal_restorer = 0;
+	}
+
 	init_data.stub_code_fd = phys_mapping(uml_to_phys(__syscall_stub_start),
 					      &offset);
 	init_data.stub_code_offset = MMAP_OFFSET(offset);
 
-	init_data.stub_data_fd = phys_mapping(uml_to_phys(stack), &offset);
+	init_data.stub_data_fd = phys_mapping(uml_to_phys(tramp_data->stub_data),
+					      &offset);
 	init_data.stub_data_offset = MMAP_OFFSET(offset);
 
 	/*
@@ -214,20 +331,21 @@ static int userspace_tramp(void *stack)
 	syscall(__NR_close_range, 0, ~0U, CLOSE_RANGE_CLOEXEC);
 
 	fcntl(init_data.stub_data_fd, F_SETFD, 0);
-	for (iomem = iomem_regions; iomem; iomem = iomem->next)
-		fcntl(iomem->fd, F_SETFD, 0);
 
-	/* Create a pipe for init_data (no CLOEXEC) and dup2 to STDIN */
-	if (pipe(pipe_fds))
-		exit(2);
+	/* In SECCOMP mode, these FDs are passed when needed */
+	if (!using_seccomp) {
+		for (iomem = iomem_regions; iomem; iomem = iomem->next)
+			fcntl(iomem->fd, F_SETFD, 0);
+	}
 
-	if (dup2(pipe_fds[0], 0) < 0)
+	/* dup2 signaling FD/socket to STDIN */
+	if (dup2(tramp_data->sockpair[0], 0) < 0)
 		exit(3);
-	close(pipe_fds[0]);
+	close(tramp_data->sockpair[0]);
 
 	/* Write init_data and close write side */
-	ret = write(pipe_fds[1], &init_data, sizeof(init_data));
-	close(pipe_fds[1]);
+	ret = write(tramp_data->sockpair[1], &init_data, sizeof(init_data));
+	close(tramp_data->sockpair[1]);
 
 	if (ret != sizeof(init_data))
 		exit(4);
@@ -315,11 +433,12 @@ static int __init init_stub_exe_fd(void)
 }
 __initcall(init_stub_exe_fd);
 
+int using_seccomp;
 int userspace_pid[NR_CPUS];
 
 /**
  * start_userspace() - prepare a new userspace process
- * @stub_stack:	pointer to the stub stack.
+ * @mm_id: The corresponding struct mm_id
  *
  * Setups a new temporary stack page that is used while userspace_tramp() runs
  * Clones the kernel process into a new userspace process, with FDs only.
@@ -328,11 +447,15 @@ int userspace_pid[NR_CPUS];
  *         when negative: an error number.
  * FIXME: can PIDs become negative?!
  */
-int start_userspace(unsigned long stub_stack)
+int start_userspace(struct mm_id *mm_id)
 {
+	struct stub_data *proc_data = (void *)mm_id->stack;
+	struct tramp_data tramp_data = {
+		.stub_data = proc_data,
+	};
 	void *stack;
 	unsigned long sp;
-	int pid, status, n, err;
+	int status, n, err;
 
 	/* setup a temporary stack page */
 	stack = mmap(NULL, UM_KERN_PAGE_SIZE,
@@ -348,40 +471,55 @@ int start_userspace(unsigned long stub_stack)
 	/* set stack pointer to the end of the stack page, so it can grow downwards */
 	sp = (unsigned long)stack + UM_KERN_PAGE_SIZE;
 
-	/* clone into new userspace process */
-	pid = clone(userspace_tramp, (void *) sp,
+	/* socket pair for init data and SECCOMP FD passing (no CLOEXEC here) */
+	if (socketpair(AF_UNIX, SOCK_STREAM, 0, tramp_data.sockpair)) {
+		err = -errno;
+		printk(UM_KERN_ERR "%s : socketpair failed, errno = %d\n",
+		       __func__, errno);
+		return err;
+	}
+
+	if (using_seccomp)
+		proc_data->futex = FUTEX_IN_CHILD;
+
+	mm_id->pid = clone(userspace_tramp, (void *) sp,
 		    CLONE_VFORK | CLONE_VM | SIGCHLD,
-		    (void *)stub_stack);
-	if (pid < 0) {
+		    (void *)&tramp_data);
+	if (mm_id->pid < 0) {
 		err = -errno;
 		printk(UM_KERN_ERR "%s : clone failed, errno = %d\n",
 		       __func__, errno);
-		return err;
+		goto out_close;
 	}
 
-	do {
-		CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED | __WALL));
-		if (n < 0) {
+	if (using_seccomp) {
+		wait_stub_done_seccomp(mm_id, 1, 1);
+	} else {
+		do {
+			CATCH_EINTR(n = waitpid(mm_id->pid, &status,
+						WUNTRACED | __WALL));
+			if (n < 0) {
+				err = -errno;
+				printk(UM_KERN_ERR "%s : wait failed, errno = %d\n",
+				       __func__, errno);
+				goto out_kill;
+			}
+		} while (WIFSTOPPED(status) && (WSTOPSIG(status) == SIGALRM));
+
+		if (!WIFSTOPPED(status) || (WSTOPSIG(status) != SIGSTOP)) {
+			err = -EINVAL;
+			printk(UM_KERN_ERR "%s : expected SIGSTOP, got status = %d\n",
+			       __func__, status);
+			goto out_kill;
+		}
+
+		if (ptrace(PTRACE_SETOPTIONS, mm_id->pid, NULL,
+			   (void *) PTRACE_O_TRACESYSGOOD) < 0) {
 			err = -errno;
-			printk(UM_KERN_ERR "%s : wait failed, errno = %d\n",
+			printk(UM_KERN_ERR "%s : PTRACE_SETOPTIONS failed, errno = %d\n",
 			       __func__, errno);
 			goto out_kill;
 		}
-	} while (WIFSTOPPED(status) && (WSTOPSIG(status) == SIGALRM));
-
-	if (!WIFSTOPPED(status) || (WSTOPSIG(status) != SIGSTOP)) {
-		err = -EINVAL;
-		printk(UM_KERN_ERR "%s : expected SIGSTOP, got status = %d\n",
-		       __func__, status);
-		goto out_kill;
-	}
-
-	if (ptrace(PTRACE_SETOPTIONS, pid, NULL,
-		   (void *) PTRACE_O_TRACESYSGOOD) < 0) {
-		err = -errno;
-		printk(UM_KERN_ERR "%s : PTRACE_SETOPTIONS failed, errno = %d\n",
-		       __func__, errno);
-		goto out_kill;
 	}
 
 	if (munmap(stack, UM_KERN_PAGE_SIZE) < 0) {
@@ -391,10 +529,22 @@ int start_userspace(unsigned long stub_stack)
 		goto out_kill;
 	}
 
-	return pid;
+	close(tramp_data.sockpair[0]);
+	if (using_seccomp)
+		mm_id->sock = tramp_data.sockpair[1];
+	else
+		close(tramp_data.sockpair[1]);
+
+	return 0;
+
+out_kill:
+	os_kill_ptraced_process(mm_id->pid, 1);
+out_close:
+	close(tramp_data.sockpair[0]);
+	close(tramp_data.sockpair[1]);
+
+	mm_id->pid = -1;
 
- out_kill:
-	os_kill_ptraced_process(pid, 1);
 	return err;
 }
 
@@ -404,7 +554,9 @@ extern unsigned long tt_extra_sched_jiffies;
 void userspace(struct uml_pt_regs *regs)
 {
 	int err, status, op, pid = userspace_pid[0];
-	siginfo_t si;
+	siginfo_t si_ptrace;
+	siginfo_t *si;
+	int sig;
 
 	/* Handle any immediate reschedules or signals */
 	interrupt_end();
@@ -437,103 +589,177 @@ void userspace(struct uml_pt_regs *regs)
 
 		current_mm_sync();
 
-		/* Flush out any pending syscalls */
-		err = syscall_stub_flush(current_mm_id());
-		if (err) {
-			if (err == -ENOMEM)
-				report_enomem();
+		if (using_seccomp) {
+			struct mm_id *mm_id = current_mm_id();
+			struct stub_data *proc_data = (void *) mm_id->stack;
+			int ret;
 
-			printk(UM_KERN_ERR "%s - Error flushing stub syscalls: %d",
-				__func__, -err);
-			fatal_sigsegv();
-		}
+			ret = set_stub_state(regs, proc_data, singlestepping());
+			if (ret) {
+				printk(UM_KERN_ERR "%s - failed to set regs: %d",
+				       __func__, ret);
+				fatal_sigsegv();
+			}
 
-		/*
-		 * This can legitimately fail if the process loads a
-		 * bogus value into a segment register.  It will
-		 * segfault and PTRACE_GETREGS will read that value
-		 * out of the process.  However, PTRACE_SETREGS will
-		 * fail.  In this case, there is nothing to do but
-		 * just kill the process.
-		 */
-		if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp)) {
-			printk(UM_KERN_ERR "%s - ptrace set regs failed, errno = %d\n",
-			       __func__, errno);
-			fatal_sigsegv();
-		}
+			/* Must have been reset by the syscall caller */
+			if (proc_data->restart_wait != 0)
+				panic("Programming error: Flag to only run syscalls in child was not cleared!");
 
-		if (put_fp_registers(pid, regs->fp)) {
-			printk(UM_KERN_ERR "%s - ptrace set fp regs failed, errno = %d\n",
-			       __func__, errno);
-			fatal_sigsegv();
-		}
+			/* Mark pending syscalls for flushing */
+			proc_data->syscall_data_len = mm_id->syscall_data_len;
 
-		if (singlestepping())
-			op = PTRACE_SYSEMU_SINGLESTEP;
-		else
-			op = PTRACE_SYSEMU;
+			wait_stub_done_seccomp(mm_id, 0, 0);
 
-		if (ptrace(op, pid, 0, 0)) {
-			printk(UM_KERN_ERR "%s - ptrace continue failed, op = %d, errno = %d\n",
-			       __func__, op, errno);
-			fatal_sigsegv();
-		}
+			sig = proc_data->signal;
 
-		CATCH_EINTR(err = waitpid(pid, &status, WUNTRACED | __WALL));
-		if (err < 0) {
-			printk(UM_KERN_ERR "%s - wait failed, errno = %d\n",
-			       __func__, errno);
-			fatal_sigsegv();
-		}
+			if (sig == SIGTRAP && proc_data->err != 0) {
+				printk(UM_KERN_ERR "%s - Error flushing stub syscalls",
+				       __func__);
+				syscall_stub_dump_error(mm_id);
+				mm_id->syscall_data_len = proc_data->err;
+				fatal_sigsegv();
+			}
 
-		regs->is_user = 1;
-		if (ptrace(PTRACE_GETREGS, pid, 0, regs->gp)) {
-			printk(UM_KERN_ERR "%s - PTRACE_GETREGS failed, errno = %d\n",
-			       __func__, errno);
-			fatal_sigsegv();
-		}
+			mm_id->syscall_data_len = 0;
+			mm_id->syscall_fd_num = 0;
 
-		if (get_fp_registers(pid, regs->fp)) {
-			printk(UM_KERN_ERR "%s -  get_fp_registers failed, errno = %d\n",
-			       __func__, errno);
-			fatal_sigsegv();
-		}
+			ret = get_stub_state(regs, proc_data, NULL);
+			if (ret) {
+				printk(UM_KERN_ERR "%s - failed to get regs: %d",
+				       __func__, ret);
+				fatal_sigsegv();
+			}
 
-		UPT_SYSCALL_NR(regs) = -1; /* Assume: It's not a syscall */
+			if (proc_data->si_offset > sizeof(proc_data->sigstack) - sizeof(*si))
+				panic("%s - Invalid siginfo offset from child",
+				      __func__);
+			si = (void *)&proc_data->sigstack[proc_data->si_offset];
+
+			regs->is_user = 1;
+
+			/* Fill in ORIG_RAX and extract fault information */
+			PT_SYSCALL_NR(regs->gp) = si->si_syscall;
+			if (sig == SIGSEGV) {
+				mcontext_t *mcontext = (void *)&proc_data->sigstack[proc_data->mctx_offset];
 
-		if (WIFSTOPPED(status)) {
-			int sig = WSTOPSIG(status);
+				GET_FAULTINFO_FROM_MC(regs->faultinfo, mcontext);
+			}
+		} else {
+			/* Flush out any pending syscalls */
+			err = syscall_stub_flush(current_mm_id());
+			if (err) {
+				if (err == -ENOMEM)
+					report_enomem();
+
+				printk(UM_KERN_ERR "%s - Error flushing stub syscalls: %d",
+					__func__, -err);
+				fatal_sigsegv();
+			}
 
-			/* These signal handlers need the si argument.
-			 * The SIGIO and SIGALARM handlers which constitute the
-			 * majority of invocations, do not use it.
+			/*
+			 * This can legitimately fail if the process loads a
+			 * bogus value into a segment register.  It will
+			 * segfault and PTRACE_GETREGS will read that value
+			 * out of the process.  However, PTRACE_SETREGS will
+			 * fail.  In this case, there is nothing to do but
+			 * just kill the process.
 			 */
-			switch (sig) {
-			case SIGSEGV:
-			case SIGTRAP:
-			case SIGILL:
-			case SIGBUS:
-			case SIGFPE:
-			case SIGWINCH:
-				ptrace(PTRACE_GETSIGINFO, pid, 0, (struct siginfo *)&si);
-				break;
+			if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp)) {
+				printk(UM_KERN_ERR "%s - ptrace set regs failed, errno = %d\n",
+				       __func__, errno);
+				fatal_sigsegv();
 			}
 
-			switch (sig) {
-			case SIGSEGV:
-				if (PTRACE_FULL_FAULTINFO) {
+			if (put_fp_registers(pid, regs->fp)) {
+				printk(UM_KERN_ERR "%s - ptrace set fp regs failed, errno = %d\n",
+				       __func__, errno);
+				fatal_sigsegv();
+			}
+
+			if (singlestepping())
+				op = PTRACE_SYSEMU_SINGLESTEP;
+			else
+				op = PTRACE_SYSEMU;
+
+			if (ptrace(op, pid, 0, 0)) {
+				printk(UM_KERN_ERR "%s - ptrace continue failed, op = %d, errno = %d\n",
+				       __func__, op, errno);
+				fatal_sigsegv();
+			}
+
+			CATCH_EINTR(err = waitpid(pid, &status, WUNTRACED | __WALL));
+			if (err < 0) {
+				printk(UM_KERN_ERR "%s - wait failed, errno = %d\n",
+				       __func__, errno);
+				fatal_sigsegv();
+			}
+
+			regs->is_user = 1;
+			if (ptrace(PTRACE_GETREGS, pid, 0, regs->gp)) {
+				printk(UM_KERN_ERR "%s - PTRACE_GETREGS failed, errno = %d\n",
+				       __func__, errno);
+				fatal_sigsegv();
+			}
+
+			if (get_fp_registers(pid, regs->fp)) {
+				printk(UM_KERN_ERR "%s -  get_fp_registers failed, errno = %d\n",
+				       __func__, errno);
+				fatal_sigsegv();
+			}
+
+			if (WIFSTOPPED(status)) {
+				sig = WSTOPSIG(status);
+
+				/*
+				 * These signal handlers need the si argument
+				 * and SIGSEGV needs the faultinfo.
+				 * The SIGIO and SIGALARM handlers which constitute
+				 * the majority of invocations, do not use it.
+				 */
+				switch (sig) {
+				case SIGSEGV:
 					get_skas_faultinfo(pid,
 							   &regs->faultinfo);
-					(*sig_info[SIGSEGV])(SIGSEGV, (struct siginfo *)&si,
-							     regs, NULL);
+					fallthrough;
+				case SIGTRAP:
+				case SIGILL:
+				case SIGBUS:
+				case SIGFPE:
+				case SIGWINCH:
+					ptrace(PTRACE_GETSIGINFO, pid, 0,
+					       (struct siginfo *)&si_ptrace);
+					si = &si_ptrace;
+					break;
+				default:
+					si = NULL;
+					break;
 				}
-				else handle_segv(pid, regs);
+			} else {
+				sig = 0;
+			}
+		}
+
+		UPT_SYSCALL_NR(regs) = -1; /* Assume: It's not a syscall */
+
+		if (sig) {
+			switch (sig) {
+			case SIGSEGV:
+				if (using_seccomp || PTRACE_FULL_FAULTINFO)
+					(*sig_info[SIGSEGV])(SIGSEGV,
+							     (struct siginfo *)si,
+							     regs, NULL);
+				else
+					segv(regs->faultinfo, 0, 1, NULL, NULL);
+
+				break;
+			case SIGSYS:
+				handle_syscall(regs);
 				break;
 			case SIGTRAP + 0x80:
 				handle_trap(pid, regs);
 				break;
 			case SIGTRAP:
-				relay_signal(SIGTRAP, (struct siginfo *)&si, regs, NULL);
+				relay_signal(SIGTRAP, (struct siginfo *)si, regs, NULL);
 				break;
 			case SIGALRM:
 				break;
@@ -543,7 +769,7 @@ void userspace(struct uml_pt_regs *regs)
 			case SIGFPE:
 			case SIGWINCH:
 				block_signals_trace();
-				(*sig_info[sig])(sig, (struct siginfo *)&si, regs, NULL);
+				(*sig_info[sig])(sig, (struct siginfo *)si, regs, NULL);
 				unblock_signals_trace();
 				break;
 			default:
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index 93fc82c01aba..a827c2e01aa5 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
+ * Copyright (C) 2021 Benjamin Berg <benjamin@sipsolutions.net>
  * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
  */
 
@@ -24,6 +25,13 @@
 #include <kern_util.h>
 #include <mem_user.h>
 #include <ptrace_user.h>
+#include <stdbool.h>
+#include <stub-data.h>
+#include <sys/prctl.h>
+#include <linux/seccomp.h>
+#include <linux/filter.h>
+#include <sysdep/mcontext.h>
+#include <sysdep/stub.h>
 #include <registers.h>
 #include <skas.h>
 #include "internal.h"
@@ -224,6 +232,140 @@ static void __init check_ptrace(void)
 	check_sysemu();
 }
 
+extern unsigned long host_fp_size;
+extern unsigned long exec_regs[MAX_REG_NR];
+extern unsigned long *exec_fp_regs;
+
+__initdata static struct stub_data *seccomp_test_stub_data;
+
+static void __init sigsys_handler(int sig, siginfo_t *info, void *p)
+{
+	ucontext_t *uc = p;
+
+	/* Stow away the location of the mcontext in the stack */
+	seccomp_test_stub_data->mctx_offset = (unsigned long)&uc->uc_mcontext -
+					      (unsigned long)&seccomp_test_stub_data->sigstack[0];
+
+	/* Prevent libc from clearing memory (mctx_offset in particular) */
+	syscall(__NR_exit, 0);
+}
+
+static int __init seccomp_helper(void *data)
+{
+	static struct sock_filter filter[] = {
+		BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+			 offsetof(struct seccomp_data, nr)),
+		BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_clock_nanosleep, 1, 0),
+		BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_ALLOW),
+		BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_TRAP),
+	};
+	static struct sock_fprog prog = {
+		.len = ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+	struct sigaction sa;
+
+	/* close_range is needed for the stub */
+	if (stub_syscall3(__NR_close_range, 1, ~0U, 0))
+		exit(1);
+
+	set_sigstack(seccomp_test_stub_data->sigstack,
+			sizeof(seccomp_test_stub_data->sigstack));
+
+	sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO;
+	sa.sa_sigaction = (void *) sigsys_handler;
+	sa.sa_restorer = NULL;
+	if (sigaction(SIGSYS, &sa, NULL) < 0)
+		exit(2);
+
+	prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	if (syscall(__NR_seccomp, SECCOMP_SET_MODE_FILTER,
+			SECCOMP_FILTER_FLAG_TSYNC, &prog) != 0)
+		exit(3);
+
+	sleep(0);
+
+	/* Never reached. */
+	_exit(4);
+}
+
+static bool __init init_seccomp(void)
+{
+	int pid;
+	int status;
+	int n;
+	unsigned long sp;
+
+	/*
+	 * We check that we can install a seccomp filter and then exit(0)
+	 * from a trapped syscall.
+	 *
+	 * Note that we cannot verify that no seccomp filter already exists
+	 * for a syscall that results in the process/thread to be killed.
+	 */
+
+	os_info("Checking that seccomp filters can be installed...");
+
+	seccomp_test_stub_data = mmap(0, sizeof(*seccomp_test_stub_data),
+				      PROT_READ | PROT_WRITE,
+				      MAP_SHARED | MAP_ANON, 0, 0);
+
+	/* Use the syscall data area as stack, we just need something */
+	sp = (unsigned long)&seccomp_test_stub_data->syscall_data +
+	     sizeof(seccomp_test_stub_data->syscall_data) -
+	     sizeof(void *);
+	pid = clone(seccomp_helper, (void *)sp, CLONE_VFORK | CLONE_VM, NULL);
+
+	if (pid < 0)
+		fatal_perror("check_seccomp : clone failed");
+
+	CATCH_EINTR(n = waitpid(pid, &status, __WCLONE));
+	if (n < 0)
+		fatal_perror("check_seccomp : waitpid failed");
+
+	if (WIFEXITED(status) && WEXITSTATUS(status) == 0) {
+		struct uml_pt_regs *regs;
+		unsigned long fp_size;
+		int r;
+
+		/* Fill in the host_fp_size from the mcontext. */
+		regs = calloc(1, sizeof(struct uml_pt_regs));
+		get_stub_state(regs, seccomp_test_stub_data, &fp_size);
+		host_fp_size = fp_size;
+		free(regs);
+
+		/* Repeat with the correct size */
+		regs = calloc(1, sizeof(struct uml_pt_regs) + host_fp_size);
+		r = get_stub_state(regs, seccomp_test_stub_data, NULL);
+
+		/* Store as the default startup registers */
+		exec_fp_regs = malloc(host_fp_size);
+		memcpy(exec_regs, regs->gp, sizeof(exec_regs));
+		memcpy(exec_fp_regs, regs->fp, host_fp_size);
+
+		munmap(seccomp_test_stub_data, sizeof(*seccomp_test_stub_data));
+
+		free(regs);
+
+		if (r) {
+			os_info("failed to fetch registers: %d\n", r);
+			return false;
+		}
+
+		os_info("OK\n");
+		return true;
+	}
+
+	if (WIFEXITED(status) && WEXITSTATUS(status) == 2)
+		os_info("missing\n");
+	else
+		os_info("error\n");
+
+	munmap(seccomp_test_stub_data, sizeof(*seccomp_test_stub_data));
+	return false;
+}
+
+
 static void __init check_coredump_limit(void)
 {
 	struct rlimit lim;
@@ -278,6 +420,44 @@ void  __init get_host_cpu_features(
 	}
 }
 
+static int seccomp_config __initdata;
+
+static int __init uml_seccomp_config(char *line, int *add)
+{
+	*add = 0;
+
+	if (strcmp(line, "off") == 0)
+		seccomp_config = 0;
+	else if (strcmp(line, "auto") == 0)
+		seccomp_config = 1;
+	else if (strcmp(line, "on") == 0)
+		seccomp_config = 2;
+	else
+		fatal("Invalid seccomp option '%s', expected on/auto/off\n",
+		      line);
+
+	return 0;
+}
+
+__uml_setup("seccomp=", uml_seccomp_config,
+"seccomp=<on/auto/off>\n"
+"    Configure whether or not SECCOMP is used. With SECCOMP, userspace\n"
+"    processes work collaboratively with the kernel instead of being\n"
+"    traced using ptrace. All syscalls from the application are caught and\n"
+"    redirected using a signal. This signal handler in turn is permitted to\n"
+"    do the selected set of syscalls to communicate with the UML kernel and\n"
+"    do the required memory management.\n"
+"\n"
+"    This method is overall faster than the ptrace based userspace, primarily\n"
+"    because it reduces the number of context switches for (minor) page faults.\n"
+"\n"
+"    However, the SECCOMP filter is not (yet) restrictive enough to prevent\n"
+"    userspace from reading and writing all physical memory. Userspace\n"
+"    processes could also trick the stub into disabling SIGALRM which\n"
+"    prevents it from being interrupted for scheduling purposes.\n"
+"\n"
+"    This is insecure and should only be used with a trusted userspace\n\n"
+);
 
 void __init os_early_checks(void)
 {
@@ -286,13 +466,24 @@ void __init os_early_checks(void)
 	/* Print out the core dump limits early */
 	check_coredump_limit();
 
-	check_ptrace();
-
 	/* Need to check this early because mmapping happens before the
 	 * kernel is running.
 	 */
 	check_tmpexec();
 
+	if (seccomp_config) {
+		if (init_seccomp()) {
+			using_seccomp = 1;
+			return;
+		}
+
+		if (seccomp_config == 2)
+			fatal("SECCOMP userspace requested but not functional!\n");
+	}
+
+	using_seccomp = 0;
+	check_ptrace();
+
 	pid = start_ptraced_child();
 	if (init_pid_registers(pid))
 		fatal("Failed to initialize default registers");
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index fbc1215d2746..b6db4e0b936b 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -869,12 +869,12 @@ static void *snp_alloc_vmsa_page(int cpu)
 	return page_address(p + 1);
 }
 
-static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
+static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip, unsigned int cpu)
 {
 	struct sev_es_save_area *cur_vmsa, *vmsa;
 	struct svsm_ca *caa;
 	u8 sipi_vector;
-	int cpu, ret;
+	int ret;
 	u64 cr4;
 
 	/*
@@ -895,15 +895,6 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 
 	/* Override start_ip with known protected guest start IP */
 	start_ip = real_mode_header->sev_es_trampoline_start;
-
-	/* Find the logical CPU for the APIC ID */
-	for_each_present_cpu(cpu) {
-		if (arch_match_cpu_phys_id(cpu, apic_id))
-			break;
-	}
-	if (cpu >= nr_cpu_ids)
-		return -EINVAL;
-
 	cur_vmsa = per_cpu(sev_vmsa, cpu);
 
 	/*
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 5d27194a2efa..3d1d3547095a 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -391,40 +391,6 @@ static void __init hv_stimer_setup_percpu_clockev(void)
 		old_setup_percpu_clockev();
 }
 
-#if IS_ENABLED(CONFIG_HYPERV_VTL_MODE)
-static u8 __init get_vtl(void)
-{
-	u64 control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_REGISTERS;
-	struct hv_input_get_vp_registers *input;
-	struct hv_output_get_vp_registers *output;
-	unsigned long flags;
-	u64 ret;
-
-	local_irq_save(flags);
-	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
-	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
-
-	memset(input, 0, struct_size(input, names, 1));
-	input->partition_id = HV_PARTITION_ID_SELF;
-	input->vp_index = HV_VP_INDEX_SELF;
-	input->input_vtl.as_uint8 = 0;
-	input->names[0] = HV_REGISTER_VSM_VP_STATUS;
-
-	ret = hv_do_hypercall(control, input, output);
-	if (hv_result_success(ret)) {
-		ret = output->values[0].reg8 & HV_X64_VTL_MASK;
-	} else {
-		pr_err("Failed to get VTL(error: %lld) exiting...\n", ret);
-		BUG();
-	}
-
-	local_irq_restore(flags);
-	return ret;
-}
-#else
-static inline u8 get_vtl(void) { return 0; }
-#endif
-
 /*
  * This function is to be invoked early in the boot sequence after the
  * hypervisor has been detected.
@@ -707,3 +673,36 @@ bool hv_is_hyperv_initialized(void)
 	return hypercall_msr.enable;
 }
 EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
+
+int hv_apicid_to_vp_index(u32 apic_id)
+{
+	u64 control;
+	u64 status;
+	unsigned long irq_flags;
+	struct hv_get_vp_from_apic_id_in *input;
+	u32 *output, ret;
+
+	local_irq_save(irq_flags);
+
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	memset(input, 0, sizeof(*input));
+	input->partition_id = HV_PARTITION_ID_SELF;
+	input->apic_ids[0] = apic_id;
+
+	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+	control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_INDEX_FROM_APIC_ID;
+	status = hv_do_hypercall(control, input, output);
+	ret = output[0];
+
+	local_irq_restore(irq_flags);
+
+	if (!hv_result_success(status)) {
+		pr_err("failed to get vp index from apic id %d, status %#llx\n",
+		       apic_id, status);
+		return -EINVAL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hv_apicid_to_vp_index);
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 4580936dcb03..042e8712d8de 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -56,7 +56,12 @@ static void  __noreturn hv_vtl_restart(char __maybe_unused *cmd)
 
 void __init hv_vtl_init_platform(void)
 {
-	pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
+	/*
+	 * This function is a no-op if the VTL mode is not enabled.
+	 * If it is, this function runs if and only the kernel boots in
+	 * VTL2 which the x86 hv initialization path makes sure of.
+	 */
+	pr_info("Linux runs in Hyper-V Virtual Trust Level %d\n", ms_hyperv.vtl);
 
 	x86_platform.realmode_reserve = x86_init_noop;
 	x86_platform.realmode_init = x86_init_noop;
@@ -207,63 +212,23 @@ free_lock:
 	return ret;
 }
 
-static int hv_vtl_apicid_to_vp_id(u32 apic_id)
-{
-	u64 control;
-	u64 status;
-	unsigned long irq_flags;
-	struct hv_get_vp_from_apic_id_in *input;
-	u32 *output, ret;
-
-	local_irq_save(irq_flags);
-
-	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
-	memset(input, 0, sizeof(*input));
-	input->partition_id = HV_PARTITION_ID_SELF;
-	input->apic_ids[0] = apic_id;
-
-	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
-
-	control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID;
-	status = hv_do_hypercall(control, input, output);
-	ret = output[0];
-
-	local_irq_restore(irq_flags);
-
-	if (!hv_result_success(status)) {
-		pr_err("failed to get vp id from apic id %d, status %#llx\n",
-		       apic_id, status);
-		return -EINVAL;
-	}
-
-	return ret;
-}
-
-static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip)
+static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip, unsigned int cpu)
 {
-	int vp_id, cpu;
-
-	/* Find the logical CPU for the APIC ID */
-	for_each_present_cpu(cpu) {
-		if (arch_match_cpu_phys_id(cpu, apicid))
-			break;
-	}
-	if (cpu >= nr_cpu_ids)
-		return -EINVAL;
+	int vp_index;
 
 	pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid);
-	vp_id = hv_vtl_apicid_to_vp_id(apicid);
+	vp_index = hv_apicid_to_vp_index(apicid);
 
-	if (vp_id < 0) {
+	if (vp_index < 0) {
 		pr_err("Couldn't find CPU with APIC ID %d\n", apicid);
 		return -EINVAL;
 	}
-	if (vp_id > ms_hyperv.max_vp_index) {
-		pr_err("Invalid CPU id %d for APIC ID %d\n", vp_id, apicid);
+	if (vp_index > ms_hyperv.max_vp_index) {
+		pr_err("Invalid CPU id %d for APIC ID %d\n", vp_index, apicid);
 		return -EINVAL;
 	}
 
-	return hv_vtl_bringup_vcpu(vp_id, cpu, start_eip);
+	return hv_vtl_bringup_vcpu(vp_index, cpu, start_eip);
 }
 
 int __init hv_vtl_early_init(void)
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 09a165a3c41e..e93a2f488ff7 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -9,6 +9,7 @@
 #include <linux/bitfield.h>
 #include <linux/types.h>
 #include <linux/slab.h>
+#include <linux/cpu.h>
 #include <asm/svm.h>
 #include <asm/sev.h>
 #include <asm/io.h>
@@ -289,7 +290,7 @@ static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa)
 		free_page((unsigned long)vmsa);
 }
 
-int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
+int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip, unsigned int cpu)
 {
 	struct sev_es_save_area *vmsa = (struct sev_es_save_area *)
 		__get_free_page(GFP_KERNEL | __GFP_ZERO);
@@ -298,10 +299,16 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
 	u64 ret, retry = 5;
 	struct hv_enable_vp_vtl *start_vp_input;
 	unsigned long flags;
+	int vp_index;
 
 	if (!vmsa)
 		return -ENOMEM;
 
+	/* Find the Hyper-V VP index which might be not the same as APIC ID */
+	vp_index = hv_apicid_to_vp_index(apic_id);
+	if (vp_index < 0 || vp_index > ms_hyperv.max_vp_index)
+		return -EINVAL;
+
 	native_store_gdt(&gdtr);
 
 	vmsa->gdtr.base = gdtr.address;
@@ -349,7 +356,7 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
 	start_vp_input = (struct hv_enable_vp_vtl *)ap_start_input_arg;
 	memset(start_vp_input, 0, sizeof(*start_vp_input));
 	start_vp_input->partition_id = -1;
-	start_vp_input->vp_index = cpu;
+	start_vp_input->vp_index = vp_index;
 	start_vp_input->target_vtl.target_vtl = ms_hyperv.vtl;
 	*(u64 *)&start_vp_input->vp_context = __pa(vmsa) | 1;
 
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 68e10e30fe9b..23d86c9750b9 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -313,9 +313,9 @@ struct apic {
 	u32	(*get_apic_id)(u32 id);
 
 	/* wakeup_secondary_cpu */
-	int	(*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
+	int	(*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip, unsigned int cpu);
 	/* wakeup secondary CPU using 64-bit wakeup point */
-	int	(*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip);
+	int	(*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip, unsigned int cpu);
 
 	char	*name;
 };
@@ -333,8 +333,8 @@ struct apic_override {
 	void	(*send_IPI_self)(int vector);
 	u64	(*icr_read)(void);
 	void	(*icr_write)(u32 low, u32 high);
-	int	(*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
-	int	(*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip);
+	int	(*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip, unsigned int cpu);
+	int	(*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip, unsigned int cpu);
 };
 
 /*
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 778444310cfb..e1752ba47e67 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -269,11 +269,12 @@ int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 bool hv_ghcb_negotiate_protocol(void);
 void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason);
-int hv_snp_boot_ap(u32 cpu, unsigned long start_ip);
+int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip, unsigned int cpu);
 #else
 static inline bool hv_ghcb_negotiate_protocol(void) { return false; }
 static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {}
-static inline int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) { return 0; }
+static inline int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip,
+		unsigned int cpu) { return 0; }
 #endif
 
 #if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST)
@@ -307,6 +308,7 @@ static __always_inline u64 hv_raw_get_msr(unsigned int reg)
 {
 	return native_rdmsrq(reg);
 }
+int hv_apicid_to_vp_index(u32 apic_id);
 
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
@@ -328,6 +330,7 @@ static inline void hv_set_msr(unsigned int reg, u64 value) { }
 static inline u64 hv_get_msr(unsigned int reg) { return 0; }
 static inline void hv_set_non_nested_msr(unsigned int reg, u64 value) { }
 static inline u64 hv_get_non_nested_msr(unsigned int reg) { return 0; }
+static inline int hv_apicid_to_vp_index(u32 apic_id) { return -EINVAL; }
 #endif /* CONFIG_HYPERV */
 
 
diff --git a/arch/x86/kernel/acpi/madt_wakeup.c b/arch/x86/kernel/acpi/madt_wakeup.c
index f36f28405dcc..6d7603511f52 100644
--- a/arch/x86/kernel/acpi/madt_wakeup.c
+++ b/arch/x86/kernel/acpi/madt_wakeup.c
@@ -126,7 +126,7 @@ static int __init acpi_mp_setup_reset(u64 reset_vector)
 	return 0;
 }
 
-static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip)
+static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip, unsigned int cpu)
 {
 	if (!acpi_mp_wake_mailbox_paddr) {
 		pr_warn_once("No MADT mailbox: cannot bringup secondary CPUs. Booting with kexec?\n");
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index b5bb7a2e8340..58abb941c45b 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -27,7 +27,13 @@ static void noop_send_IPI_allbutself(int vector) { }
 static void noop_send_IPI_all(int vector) { }
 static void noop_send_IPI_self(int vector) { }
 static void noop_apic_icr_write(u32 low, u32 id) { }
-static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { return -1; }
+
+static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip,
+	unsigned int cpu)
+{
+	return -1;
+}
+
 static u64 noop_apic_icr_read(void) { return 0; }
 static u32 noop_get_apic_id(u32 apicid) { return 0; }
 static void noop_apic_eoi(void) { }
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index e272bc7fdc8e..5c5be2d58242 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -57,7 +57,7 @@ static void numachip2_apic_icr_write(int apicid, unsigned int val)
 	numachip2_write32_lcsr(NUMACHIP2_APIC_ICR, (apicid << 12) | val);
 }
 
-static int numachip_wakeup_secondary(u32 phys_apicid, unsigned long start_rip)
+static int numachip_wakeup_secondary(u32 phys_apicid, unsigned long start_rip, unsigned int cpu)
 {
 	numachip_apic_icr_write(phys_apicid, APIC_DM_INIT);
 	numachip_apic_icr_write(phys_apicid, APIC_DM_STARTUP |
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 7fef504ca508..15209f220e1f 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -667,7 +667,7 @@ static __init void build_uv_gr_table(void)
 	}
 }
 
-static int uv_wakeup_secondary(u32 phys_apicid, unsigned long start_rip)
+static int uv_wakeup_secondary(u32 phys_apicid, unsigned long start_rip, unsigned int cpu)
 {
 	unsigned long val;
 	int pnode;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 1ba92ac9441d..fc78c2325fd2 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -695,7 +695,7 @@ static void send_init_sequence(u32 phys_apicid)
 /*
  * Wake up AP by INIT, INIT, STARTUP sequence.
  */
-static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip)
+static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip, unsigned int cpu)
 {
 	unsigned long send_status = 0, accept_status = 0;
 	int num_starts, j, maxlvt;
@@ -842,7 +842,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
  * Returns zero if startup was successfully sent, else error code from
  * ->wakeup_secondary_cpu.
  */
-static int do_boot_cpu(u32 apicid, int cpu, struct task_struct *idle)
+static int do_boot_cpu(u32 apicid, unsigned int cpu, struct task_struct *idle)
 {
 	unsigned long start_ip = real_mode_header->trampoline_start;
 	int ret;
@@ -896,11 +896,11 @@ static int do_boot_cpu(u32 apicid, int cpu, struct task_struct *idle)
 	 * - Use an INIT boot APIC message
 	 */
 	if (apic->wakeup_secondary_cpu_64)
-		ret = apic->wakeup_secondary_cpu_64(apicid, start_ip);
+		ret = apic->wakeup_secondary_cpu_64(apicid, start_ip, cpu);
 	else if (apic->wakeup_secondary_cpu)
-		ret = apic->wakeup_secondary_cpu(apicid, start_ip);
+		ret = apic->wakeup_secondary_cpu(apicid, start_ip, cpu);
 	else
-		ret = wakeup_secondary_cpu_via_init(apicid, start_ip);
+		ret = wakeup_secondary_cpu_via_init(apicid, start_ip, cpu);
 
 	/* If the wakeup mechanism failed, cleanup the warm reset vector */
 	if (ret)
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 4933fb337983..c1efd5b0d198 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -8,13 +8,13 @@ obj-$(CONFIG_PCI_OLPC)		+= olpc.o
 obj-$(CONFIG_PCI_XEN)		+= xen.o
 
 obj-y				+= fixup.o
-obj-$(CONFIG_X86_INTEL_CE)      += ce4100.o
 obj-$(CONFIG_ACPI)		+= acpi.o
 obj-y				+= legacy.o irq.o
 
-obj-$(CONFIG_X86_NUMACHIP)	+= numachip.o
+obj-$(CONFIG_X86_INTEL_CE)	+= ce4100.o
+obj-$(CONFIG_X86_INTEL_MID)	+= intel_mid.o
 
-obj-$(CONFIG_X86_INTEL_MID)	+= intel_mid_pci.o
+obj-$(CONFIG_X86_NUMACHIP)	+= numachip.o
 
 obj-y				+= common.o early.o
 obj-y				+= bus_numa.o
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid.c
index b433b1753016..b433b1753016 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid.c
diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h
index b07824500363..ddc144657efa 100644
--- a/arch/x86/um/asm/checksum.h
+++ b/arch/x86/um/asm/checksum.h
@@ -20,6 +20,9 @@
  */
 extern __wsum csum_partial(const void *buff, int len, __wsum sum);
 
+/* Do not call this directly. Declared for export type visibility. */
+extern __visible __wsum csum_partial_copy_generic(const void *src, void *dst, int len);
+
 /**
  * csum_fold - Fold and invert a 32bit checksum.
  * sum: 32bit unfolded sum
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
index 478710384b34..e222d2ae28fd 100644
--- a/arch/x86/um/asm/processor.h
+++ b/arch/x86/um/asm/processor.h
@@ -21,10 +21,10 @@
 
 #include <asm/user.h>
 
-/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static __always_inline void rep_nop(void)
+/* PAUSE is a good thing to insert into busy-wait loops. */
+static __always_inline void native_pause(void)
 {
-	__asm__ __volatile__("rep;nop": : :"memory");
+	__asm__ __volatile__("pause": : :"memory");
 }
 
 static __always_inline void cpu_relax(void)
@@ -33,7 +33,7 @@ static __always_inline void cpu_relax(void)
 	    time_travel_mode == TT_MODE_EXTERNAL)
 		time_travel_ndelay(1);
 	else
-		rep_nop();
+		native_pause();
 }
 
 #define task_pt_regs(t) (&(t)->thread.regs)
diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c
index 37decaa74761..a21403df6663 100644
--- a/arch/x86/um/os-Linux/mcontext.c
+++ b/arch/x86/um/os-Linux/mcontext.c
@@ -1,7 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <sys/ucontext.h>
 #define __FRAME_OFFSETS
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <sys/ucontext.h>
 #include <asm/ptrace.h>
+#include <asm/sigcontext.h>
 #include <sysdep/ptrace.h>
 #include <sysdep/mcontext.h>
 #include <arch.h>
@@ -18,6 +21,10 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
 	COPY2(UESP, ESP); /* sic */
 	COPY(EBX); COPY(EDX); COPY(ECX); COPY(EAX);
 	COPY(EIP); COPY_SEG_CPL3(CS); COPY(EFL); COPY_SEG_CPL3(SS);
+#undef COPY2
+#undef COPY
+#undef COPY_SEG
+#undef COPY_SEG_CPL3
 #else
 #define COPY2(X,Y) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##Y]
 #define COPY(X) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##X]
@@ -29,6 +36,8 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
 	COPY2(EFLAGS, EFL);
 	COPY2(CS, CSGSFS);
 	regs->gp[SS / sizeof(unsigned long)] = mc->gregs[REG_CSGSFS] >> 48;
+#undef COPY2
+#undef COPY
 #endif
 }
 
@@ -42,3 +51,210 @@ void mc_set_rip(void *_mc, void *target)
 	mc->gregs[REG_RIP] = (unsigned long)target;
 #endif
 }
+
+/* Same thing, but the copy macros are turned around. */
+void get_mc_from_regs(struct uml_pt_regs *regs, mcontext_t *mc, int single_stepping)
+{
+#ifdef __i386__
+#define COPY2(X,Y) mc->gregs[REG_##Y] = regs->gp[X]
+#define COPY(X) mc->gregs[REG_##X] = regs->gp[X]
+#define COPY_SEG(X) mc->gregs[REG_##X] = regs->gp[X] & 0xffff;
+#define COPY_SEG_CPL3(X) mc->gregs[REG_##X] = (regs->gp[X] & 0xffff) | 3;
+	COPY_SEG(GS); COPY_SEG(FS); COPY_SEG(ES); COPY_SEG(DS);
+	COPY(EDI); COPY(ESI); COPY(EBP);
+	COPY2(UESP, ESP); /* sic */
+	COPY(EBX); COPY(EDX); COPY(ECX); COPY(EAX);
+	COPY(EIP); COPY_SEG_CPL3(CS); COPY(EFL); COPY_SEG_CPL3(SS);
+#else
+#define COPY2(X,Y) mc->gregs[REG_##Y] = regs->gp[X/sizeof(unsigned long)]
+#define COPY(X) mc->gregs[REG_##X] = regs->gp[X/sizeof(unsigned long)]
+	COPY(R8); COPY(R9); COPY(R10); COPY(R11);
+	COPY(R12); COPY(R13); COPY(R14); COPY(R15);
+	COPY(RDI); COPY(RSI); COPY(RBP); COPY(RBX);
+	COPY(RDX); COPY(RAX); COPY(RCX); COPY(RSP);
+	COPY(RIP);
+	COPY2(EFLAGS, EFL);
+	mc->gregs[REG_CSGSFS] = mc->gregs[REG_CSGSFS] & 0xffffffffffffl;
+	mc->gregs[REG_CSGSFS] |= (regs->gp[SS / sizeof(unsigned long)] & 0xffff) << 48;
+#endif
+
+	if (single_stepping)
+		mc->gregs[REG_EFL] |= X86_EFLAGS_TF;
+	else
+		mc->gregs[REG_EFL] &= ~X86_EFLAGS_TF;
+}
+
+#ifdef CONFIG_X86_32
+struct _xstate_64 {
+	struct _fpstate_64		fpstate;
+	struct _header			xstate_hdr;
+	struct _ymmh_state		ymmh;
+	/* New processor state extensions go here: */
+};
+
+/* Not quite the right structures as these contain more information */
+int um_i387_from_fxsr(struct _fpstate_32 *i387,
+		      const struct _fpstate_64 *fxsave);
+int um_fxsr_from_i387(struct _fpstate_64 *fxsave,
+		      const struct _fpstate_32 *from);
+#else
+#define _xstate_64 _xstate
+#endif
+
+static struct _fpstate *get_fpstate(struct stub_data *data,
+				    mcontext_t *mcontext,
+				    int *fp_size)
+{
+	struct _fpstate *res;
+
+	/* Assume floating point registers are on the same page */
+	res = (void *)(((unsigned long)mcontext->fpregs &
+			(UM_KERN_PAGE_SIZE - 1)) +
+		       (unsigned long)&data->sigstack[0]);
+
+	if ((void *)res + sizeof(struct _fpstate) >
+	    (void *)data->sigstack + sizeof(data->sigstack))
+		return NULL;
+
+	if (res->sw_reserved.magic1 != FP_XSTATE_MAGIC1) {
+		*fp_size = sizeof(struct _fpstate);
+	} else {
+		char *magic2_addr;
+
+		magic2_addr = (void *)res;
+		magic2_addr += res->sw_reserved.extended_size;
+		magic2_addr -= FP_XSTATE_MAGIC2_SIZE;
+
+		/* We still need to be within our stack */
+		if ((void *)magic2_addr >
+		    (void *)data->sigstack + sizeof(data->sigstack))
+			return NULL;
+
+		/* If we do not read MAGIC2, then we did something wrong */
+		if (*(__u32 *)magic2_addr != FP_XSTATE_MAGIC2)
+			return NULL;
+
+		/* Remove MAGIC2 from the size, we do not save/restore it */
+		*fp_size = res->sw_reserved.extended_size -
+			   FP_XSTATE_MAGIC2_SIZE;
+	}
+
+	return res;
+}
+
+int get_stub_state(struct uml_pt_regs *regs, struct stub_data *data,
+		   unsigned long *fp_size_out)
+{
+	mcontext_t *mcontext;
+	struct _fpstate *fpstate_stub;
+	struct _xstate_64 *xstate_stub;
+	int fp_size, xstate_size;
+
+	/* mctx_offset is verified by wait_stub_done_seccomp */
+	mcontext = (void *)&data->sigstack[data->mctx_offset];
+
+	get_regs_from_mc(regs, mcontext);
+
+	fpstate_stub = get_fpstate(data, mcontext, &fp_size);
+	if (!fpstate_stub)
+		return -EINVAL;
+
+#ifdef CONFIG_X86_32
+	xstate_stub = (void *)&fpstate_stub->_fxsr_env;
+	xstate_size = fp_size - offsetof(struct _fpstate_32, _fxsr_env);
+#else
+	xstate_stub = (void *)fpstate_stub;
+	xstate_size = fp_size;
+#endif
+
+	if (fp_size_out)
+		*fp_size_out = xstate_size;
+
+	if (xstate_size > host_fp_size)
+		return -ENOSPC;
+
+	memcpy(&regs->fp, xstate_stub, xstate_size);
+
+	/* We do not need to read the x86_64 FS_BASE/GS_BASE registers as
+	 * we do not permit userspace to set them directly.
+	 */
+
+#ifdef CONFIG_X86_32
+	/* Read the i387 legacy FP registers */
+	if (um_fxsr_from_i387((void *)&regs->fp, fpstate_stub))
+		return -EINVAL;
+#endif
+
+	return 0;
+}
+
+/* Copied because we cannot include regset.h here. */
+struct task_struct;
+struct user_regset;
+struct membuf {
+	void *p;
+	size_t left;
+};
+
+int fpregs_legacy_get(struct task_struct *target,
+		      const struct user_regset *regset,
+		      struct membuf to);
+
+int set_stub_state(struct uml_pt_regs *regs, struct stub_data *data,
+		   int single_stepping)
+{
+	mcontext_t *mcontext;
+	struct _fpstate *fpstate_stub;
+	struct _xstate_64 *xstate_stub;
+	int fp_size, xstate_size;
+
+	/* mctx_offset is verified by wait_stub_done_seccomp */
+	mcontext = (void *)&data->sigstack[data->mctx_offset];
+
+	if ((unsigned long)mcontext < (unsigned long)data->sigstack ||
+	    (unsigned long)mcontext >
+			(unsigned long) data->sigstack +
+			sizeof(data->sigstack) - sizeof(*mcontext))
+		return -EINVAL;
+
+	get_mc_from_regs(regs, mcontext, single_stepping);
+
+	fpstate_stub = get_fpstate(data, mcontext, &fp_size);
+	if (!fpstate_stub)
+		return -EINVAL;
+
+#ifdef CONFIG_X86_32
+	xstate_stub = (void *)&fpstate_stub->_fxsr_env;
+	xstate_size = fp_size - offsetof(struct _fpstate_32, _fxsr_env);
+#else
+	xstate_stub = (void *)fpstate_stub;
+	xstate_size = fp_size;
+#endif
+
+	memcpy(xstate_stub, &regs->fp, xstate_size);
+
+#ifdef __i386__
+	/*
+	 * On x86, the GDT entries are updated by arch_set_tls.
+	 */
+
+	/* Store the i387 legacy FP registers which the host will use */
+	if (um_i387_from_fxsr(fpstate_stub, (void *)&regs->fp))
+		return -EINVAL;
+#else
+	/*
+	 * On x86_64, we need to sync the FS_BASE/GS_BASE registers using the
+	 * arch specific data.
+	 */
+	if (data->arch_data.fs_base != regs->gp[FS_BASE / sizeof(unsigned long)]) {
+		data->arch_data.fs_base = regs->gp[FS_BASE / sizeof(unsigned long)];
+		data->arch_data.sync |= STUB_SYNC_FS_BASE;
+	}
+	if (data->arch_data.gs_base != regs->gp[GS_BASE / sizeof(unsigned long)]) {
+		data->arch_data.gs_base = regs->gp[GS_BASE / sizeof(unsigned long)];
+		data->arch_data.sync |= STUB_SYNC_GS_BASE;
+	}
+#endif
+
+	return 0;
+}
diff --git a/arch/x86/um/ptrace.c b/arch/x86/um/ptrace.c
index 57c504fd5626..3275870330fe 100644
--- a/arch/x86/um/ptrace.c
+++ b/arch/x86/um/ptrace.c
@@ -25,7 +25,8 @@ static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
 	return tmp;
 }
 
-static inline unsigned long twd_fxsr_to_i387(struct user_fxsr_struct *fxsave)
+static inline unsigned long
+twd_fxsr_to_i387(const struct user_fxsr_struct *fxsave)
 {
 	struct _fpxreg *st = NULL;
 	unsigned long twd = (unsigned long) fxsave->twd;
@@ -69,12 +70,16 @@ static inline unsigned long twd_fxsr_to_i387(struct user_fxsr_struct *fxsave)
 	return ret;
 }
 
-/* Get/set the old 32bit i387 registers (pre-FPX) */
-static int fpregs_legacy_get(struct task_struct *target,
-			     const struct user_regset *regset,
-			     struct membuf to)
+/*
+ * Get/set the old 32bit i387 registers (pre-FPX)
+ *
+ * We provide simple wrappers for mcontext.c, they are only defined locally
+ * because mcontext.c is userspace facing and needs to a different definition
+ * of the structures.
+ */
+static int _um_i387_from_fxsr(struct membuf to,
+			      const struct user_fxsr_struct *fxsave)
 {
-	struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp;
 	int i;
 
 	membuf_store(&to, (unsigned long)fxsave->cwd | 0xffff0000ul);
@@ -91,23 +96,36 @@ static int fpregs_legacy_get(struct task_struct *target,
 	return 0;
 }
 
-static int fpregs_legacy_set(struct task_struct *target,
+int um_i387_from_fxsr(struct user_i387_struct *i387,
+		      const struct user_fxsr_struct *fxsave);
+
+int um_i387_from_fxsr(struct user_i387_struct *i387,
+		      const struct user_fxsr_struct *fxsave)
+{
+	struct membuf to = {
+		.p = i387,
+		.left = sizeof(*i387),
+	};
+
+	return _um_i387_from_fxsr(to, fxsave);
+}
+
+static int fpregs_legacy_get(struct task_struct *target,
 			     const struct user_regset *regset,
-			     unsigned int pos, unsigned int count,
-			     const void *kbuf, const void __user *ubuf)
+			     struct membuf to)
 {
 	struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp;
-	const struct user_i387_struct *from;
-	struct user_i387_struct buf;
-	int i;
 
-	if (ubuf) {
-		if (copy_from_user(&buf, ubuf, sizeof(buf)))
-			return -EFAULT;
-		from = &buf;
-	} else {
-		from = kbuf;
-	}
+	return _um_i387_from_fxsr(to, fxsave);
+}
+
+int um_fxsr_from_i387(struct user_fxsr_struct *fxsave,
+		      const struct user_i387_struct *from);
+
+int um_fxsr_from_i387(struct user_fxsr_struct *fxsave,
+		      const struct user_i387_struct *from)
+{
+	int i;
 
 	fxsave->cwd = (unsigned short)(from->cwd & 0xffff);
 	fxsave->swd = (unsigned short)(from->swd & 0xffff);
@@ -125,6 +143,26 @@ static int fpregs_legacy_set(struct task_struct *target,
 
 	return 0;
 }
+
+static int fpregs_legacy_set(struct task_struct *target,
+			     const struct user_regset *regset,
+			     unsigned int pos, unsigned int count,
+			     const void *kbuf, const void __user *ubuf)
+{
+	struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp;
+	const struct user_i387_struct *from;
+	struct user_i387_struct buf;
+
+	if (ubuf) {
+		if (copy_from_user(&buf, ubuf, sizeof(buf)))
+			return -EFAULT;
+		from = &buf;
+	} else {
+		from = kbuf;
+	}
+
+	return um_fxsr_from_i387(fxsave, &buf);
+}
 #endif
 
 static int genregs_get(struct task_struct *target,
diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h
index 48de3a71f845..6fd1ed400399 100644
--- a/arch/x86/um/shared/sysdep/kernel-offsets.h
+++ b/arch/x86/um/shared/sysdep/kernel-offsets.h
@@ -4,7 +4,9 @@
 #include <linux/elf.h>
 #include <linux/crypto.h>
 #include <linux/kbuild.h>
+#include <linux/audit.h>
 #include <asm/mman.h>
+#include <asm/seccomp.h>
 
 /* workaround for a warning with -Wmissing-prototypes */
 void foo(void);
diff --git a/arch/x86/um/shared/sysdep/mcontext.h b/arch/x86/um/shared/sysdep/mcontext.h
index b724c54da316..6fe490cc5b98 100644
--- a/arch/x86/um/shared/sysdep/mcontext.h
+++ b/arch/x86/um/shared/sysdep/mcontext.h
@@ -6,7 +6,16 @@
 #ifndef __SYS_SIGCONTEXT_X86_H
 #define __SYS_SIGCONTEXT_X86_H
 
+#include <stub-data.h>
+
 extern void get_regs_from_mc(struct uml_pt_regs *, mcontext_t *);
+extern void get_mc_from_regs(struct uml_pt_regs *regs, mcontext_t *mc,
+			     int single_stepping);
+
+extern int get_stub_state(struct uml_pt_regs *regs, struct stub_data *data,
+			  unsigned long *fp_size_out);
+extern int set_stub_state(struct uml_pt_regs *regs, struct stub_data *data,
+			  int single_stepping);
 
 #ifdef __i386__
 
diff --git a/arch/x86/um/shared/sysdep/stub-data.h b/arch/x86/um/shared/sysdep/stub-data.h
new file mode 100644
index 000000000000..82b1b7f8ac3d
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/stub-data.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ARCH_STUB_DATA_H
+#define __ARCH_STUB_DATA_H
+
+#ifdef __i386__
+#include <generated/asm-offsets.h>
+#include <asm/ldt.h>
+
+struct stub_data_arch {
+	int sync;
+	struct user_desc tls[UM_KERN_GDT_ENTRY_TLS_ENTRIES];
+};
+#else
+#define STUB_SYNC_FS_BASE (1 << 0)
+#define STUB_SYNC_GS_BASE (1 << 1)
+struct stub_data_arch {
+	int sync;
+	unsigned long fs_base;
+	unsigned long gs_base;
+};
+#endif
+
+#endif /* __ARCH_STUB_DATA_H */
diff --git a/arch/x86/um/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub.h
index dc89f4423454..4fa58f5b4fca 100644
--- a/arch/x86/um/shared/sysdep/stub.h
+++ b/arch/x86/um/shared/sysdep/stub.h
@@ -13,3 +13,5 @@
 
 extern void stub_segv_handler(int, siginfo_t *, void *);
 extern void stub_syscall_handler(void);
+extern void stub_signal_interrupt(int, siginfo_t *, void *);
+extern void stub_signal_restorer(void);
diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h
index 390988132c0a..df568fc3ceb4 100644
--- a/arch/x86/um/shared/sysdep/stub_32.h
+++ b/arch/x86/um/shared/sysdep/stub_32.h
@@ -131,4 +131,17 @@ static __always_inline void *get_stub_data(void)
 		"call *%%eax ;"						\
 		:: "i" ((1 + STUB_DATA_PAGES) * UM_KERN_PAGE_SIZE),	\
 		   "i" (&fn))
+
+static __always_inline void
+stub_seccomp_restore_state(struct stub_data_arch *arch)
+{
+	for (int i = 0; i < sizeof(arch->tls) / sizeof(arch->tls[0]); i++) {
+		if (arch->sync & (1 << i))
+			stub_syscall1(__NR_set_thread_area,
+				      (unsigned long) &arch->tls[i]);
+	}
+
+	arch->sync = 0;
+}
+
 #endif
diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h
index 294affbec742..9cfd31afa769 100644
--- a/arch/x86/um/shared/sysdep/stub_64.h
+++ b/arch/x86/um/shared/sysdep/stub_64.h
@@ -10,6 +10,7 @@
 #include <sysdep/ptrace_user.h>
 #include <generated/asm-offsets.h>
 #include <linux/stddef.h>
+#include <asm/prctl.h>
 
 #define STUB_MMAP_NR __NR_mmap
 #define MMAP_OFFSET(o) (o)
@@ -134,4 +135,20 @@ static __always_inline void *get_stub_data(void)
 		"call *%%rax ;"						\
 		:: "i" ((1 + STUB_DATA_PAGES) * UM_KERN_PAGE_SIZE),	\
 		   "i" (&fn))
+
+static __always_inline void
+stub_seccomp_restore_state(struct stub_data_arch *arch)
+{
+	/*
+	 * We could use _writefsbase_u64/_writegsbase_u64 if the host reports
+	 * support in the hwcaps (HWCAP2_FSGSBASE).
+	 */
+	if (arch->sync & STUB_SYNC_FS_BASE)
+		stub_syscall2(__NR_arch_prctl, ARCH_SET_FS, arch->fs_base);
+	if (arch->sync & STUB_SYNC_GS_BASE)
+		stub_syscall2(__NR_arch_prctl, ARCH_SET_GS, arch->gs_base);
+
+	arch->sync = 0;
+}
+
 #endif
diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c
index fbb129023080..cb3f17627d16 100644
--- a/arch/x86/um/tls_32.c
+++ b/arch/x86/um/tls_32.c
@@ -12,6 +12,7 @@
 #include <skas.h>
 #include <sysdep/tls.h>
 #include <asm/desc.h>
+#include <stub-data.h>
 
 /*
  * If needed we can detect when it's uninitialized.
@@ -21,14 +22,25 @@
 static int host_supports_tls = -1;
 int host_gdt_entry_tls_min;
 
-static int do_set_thread_area(struct user_desc *info)
+static int do_set_thread_area(struct task_struct* task, struct user_desc *info)
 {
 	int ret;
-	u32 cpu;
 
-	cpu = get_cpu();
-	ret = os_set_thread_area(info, userspace_pid[cpu]);
-	put_cpu();
+	if (info->entry_number < host_gdt_entry_tls_min ||
+	    info->entry_number >= host_gdt_entry_tls_min + GDT_ENTRY_TLS_ENTRIES)
+		return -EINVAL;
+
+	if (using_seccomp) {
+		int idx = info->entry_number - host_gdt_entry_tls_min;
+		struct stub_data *data = (void *)task->mm->context.id.stack;
+
+		data->arch_data.tls[idx] = *info;
+		data->arch_data.sync |= BIT(idx);
+
+		return 0;
+	}
+
+	ret = os_set_thread_area(info, task->mm->context.id.pid);
 
 	if (ret)
 		printk(KERN_ERR "PTRACE_SET_THREAD_AREA failed, err = %d, "
@@ -97,7 +109,7 @@ static int load_TLS(int flags, struct task_struct *to)
 		if (!(flags & O_FORCE) && curr->flushed)
 			continue;
 
-		ret = do_set_thread_area(&curr->tls);
+		ret = do_set_thread_area(current, &curr->tls);
 		if (ret)
 			goto out;
 
@@ -275,7 +287,7 @@ SYSCALL_DEFINE1(set_thread_area, struct user_desc __user *, user_desc)
 			return -EFAULT;
 	}
 
-	ret = do_set_thread_area(&info);
+	ret = do_set_thread_area(current, &info);
 	if (ret)
 		return ret;
 	return set_tls_entry(current, &info, idx, 1);
diff --git a/arch/xtensa/Kbuild b/arch/xtensa/Kbuild
index fd12f61745ba..015baeb765b9 100644
--- a/arch/xtensa/Kbuild
+++ b/arch/xtensa/Kbuild
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y += kernel/ mm/ platforms/ boot/dts/
+obj-y += kernel/ mm/ platforms/
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index d3db28f2f811..f2f9cd9cde50 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -20,6 +20,7 @@ config XTENSA
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_TABLE_SORT
+	select GENERIC_BUILTIN_DTB
 	select CLONE_BACKWARDS
 	select COMMON_CLK
 	select DMA_NONCOHERENT_MMAP if MMU
@@ -462,7 +463,7 @@ config USE_OF
 	help
 	  Include support for flattened device tree machine descriptions.
 
-config BUILTIN_DTB_SOURCE
+config BUILTIN_DTB_NAME
 	string "DTB to build into the kernel image"
 	depends on OF
 
diff --git a/arch/xtensa/boot/dts/Makefile b/arch/xtensa/boot/dts/Makefile
index d6408c16d74e..7271294ce523 100644
--- a/arch/xtensa/boot/dts/Makefile
+++ b/arch/xtensa/boot/dts/Makefile
@@ -7,7 +7,7 @@
 #
 #
 
-obj-$(CONFIG_OF) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_SOURCE))
+dtb-$(CONFIG_OF) += $(addsuffix .dtb, $(CONFIG_BUILTIN_DTB_NAME))
 
 # for CONFIG_OF_ALL_DTBS test
 dtb-	:= $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts))
diff --git a/arch/xtensa/configs/audio_kc705_defconfig b/arch/xtensa/configs/audio_kc705_defconfig
index 436b7cac9694..f2af1a32c9c7 100644
--- a/arch/xtensa/configs/audio_kc705_defconfig
+++ b/arch/xtensa/configs/audio_kc705_defconfig
@@ -30,7 +30,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0"
 CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="kc705"
+CONFIG_BUILTIN_DTB_NAME="kc705"
 # CONFIG_COMPACTION is not set
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_PM=y
diff --git a/arch/xtensa/configs/cadence_csp_defconfig b/arch/xtensa/configs/cadence_csp_defconfig
index 49f50d1bd724..88ed5284e21c 100644
--- a/arch/xtensa/configs/cadence_csp_defconfig
+++ b/arch/xtensa/configs/cadence_csp_defconfig
@@ -34,7 +34,7 @@ CONFIG_HIGHMEM=y
 # CONFIG_PCI is not set
 CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="csp"
+CONFIG_BUILTIN_DTB_NAME="csp"
 # CONFIG_COMPACTION is not set
 CONFIG_XTFPGA_LCD=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
diff --git a/arch/xtensa/configs/common_defconfig b/arch/xtensa/configs/common_defconfig
index fa9389869154..09e4a1d9d1f3 100644
--- a/arch/xtensa/configs/common_defconfig
+++ b/arch/xtensa/configs/common_defconfig
@@ -32,7 +32,6 @@ CONFIG_NET_SCH_TEQL=m
 CONFIG_NET_SCH_TBF=m
 CONFIG_NET_SCH_GRED=m
 CONFIG_NET_SCH_DSMARK=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
diff --git a/arch/xtensa/configs/generic_kc705_defconfig b/arch/xtensa/configs/generic_kc705_defconfig
index e376238bc5ca..4427907becca 100644
--- a/arch/xtensa/configs/generic_kc705_defconfig
+++ b/arch/xtensa/configs/generic_kc705_defconfig
@@ -29,7 +29,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0"
 CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="kc705"
+CONFIG_BUILTIN_DTB_NAME="kc705"
 # CONFIG_COMPACTION is not set
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_NET=y
diff --git a/arch/xtensa/configs/nommu_kc705_defconfig b/arch/xtensa/configs/nommu_kc705_defconfig
index c2ab4306ee20..5828228522ba 100644
--- a/arch/xtensa/configs/nommu_kc705_defconfig
+++ b/arch/xtensa/configs/nommu_kc705_defconfig
@@ -36,7 +36,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0x9d050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=256M@0x60000000"
 CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="kc705_nommu"
+CONFIG_BUILTIN_DTB_NAME="kc705_nommu"
 CONFIG_BINFMT_FLAT=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig
index 63b56ce79f83..326966ca7831 100644
--- a/arch/xtensa/configs/smp_lx200_defconfig
+++ b/arch/xtensa/configs/smp_lx200_defconfig
@@ -33,7 +33,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=96M@0"
 CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="lx200mx"
+CONFIG_BUILTIN_DTB_NAME="lx200mx"
 # CONFIG_COMPACTION is not set
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_NET=y
diff --git a/arch/xtensa/configs/virt_defconfig b/arch/xtensa/configs/virt_defconfig
index 98acb7191cb7..e37048985b47 100644
--- a/arch/xtensa/configs/virt_defconfig
+++ b/arch/xtensa/configs/virt_defconfig
@@ -24,7 +24,7 @@ CONFIG_HIGHMEM=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x80000000@0"
 CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="virt"
+CONFIG_BUILTIN_DTB_NAME="virt"
 # CONFIG_PARSE_BOOTPARAM is not set
 CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
diff --git a/arch/xtensa/configs/xip_kc705_defconfig b/arch/xtensa/configs/xip_kc705_defconfig
index 165652c45b85..ee47438f9b51 100644
--- a/arch/xtensa/configs/xip_kc705_defconfig
+++ b/arch/xtensa/configs/xip_kc705_defconfig
@@ -29,7 +29,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0"
 CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="kc705"
+CONFIG_BUILTIN_DTB_NAME="kc705"
 # CONFIG_PARSE_BOOTPARAM is not set
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 # CONFIG_COMPACTION is not set
diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h
index 86c70117371b..4871e5a4d6fb 100644
--- a/arch/xtensa/include/asm/ptrace.h
+++ b/arch/xtensa/include/asm/ptrace.h
@@ -72,13 +72,10 @@ struct pt_regs {
 	/* Additional configurable registers that are used by the compiler. */
 	xtregs_opt_t xtregs_opt;
 
-	/* Make sure the areg field is 16 bytes aligned. */
-	int align[0] __attribute__ ((aligned(16)));
-
 	/* current register frame.
 	 * Note: The ESF for kernel exceptions ends after 16 registers!
 	 */
-	unsigned long areg[XCHAL_NUM_AREGS];
+	unsigned long areg[XCHAL_NUM_AREGS] __aligned(16);
 };
 
 # define arch_has_single_step()	(1)
diff --git a/block/blk-crypto-profile.c b/block/blk-crypto-profile.c
index 94a155912bf1..81918f6e0cae 100644
--- a/block/blk-crypto-profile.c
+++ b/block/blk-crypto-profile.c
@@ -501,6 +501,7 @@ int blk_crypto_derive_sw_secret(struct block_device *bdev,
 	blk_crypto_hw_exit(profile);
 	return err;
 }
+EXPORT_SYMBOL_GPL(blk_crypto_derive_sw_secret);
 
 int blk_crypto_import_key(struct blk_crypto_profile *profile,
 			  const u8 *raw_key, size_t raw_key_size,
@@ -520,6 +521,7 @@ int blk_crypto_import_key(struct blk_crypto_profile *profile,
 	blk_crypto_hw_exit(profile);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(blk_crypto_import_key);
 
 int blk_crypto_generate_key(struct blk_crypto_profile *profile,
 			    u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE])
@@ -537,6 +539,7 @@ int blk_crypto_generate_key(struct blk_crypto_profile *profile,
 	blk_crypto_hw_exit(profile);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(blk_crypto_generate_key);
 
 int blk_crypto_prepare_key(struct blk_crypto_profile *profile,
 			   const u8 *lt_key, size_t lt_key_size,
@@ -556,6 +559,7 @@ int blk_crypto_prepare_key(struct blk_crypto_profile *profile,
 	blk_crypto_hw_exit(profile);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(blk_crypto_prepare_key);
 
 /**
  * blk_crypto_intersect_capabilities() - restrict supported crypto capabilities
diff --git a/drivers/accel/qaic/Kconfig b/drivers/accel/qaic/Kconfig
index a9f866230058..5e405a19c157 100644
--- a/drivers/accel/qaic/Kconfig
+++ b/drivers/accel/qaic/Kconfig
@@ -8,7 +8,6 @@ config DRM_ACCEL_QAIC
 	depends on DRM_ACCEL
 	depends on PCI && HAS_IOMEM
 	depends on MHI_BUS
-	depends on MMU
 	select CRC32
 	help
 	  Enables driver for Qualcomm's Cloud AI accelerator PCIe cards that are
diff --git a/drivers/acpi/irq.c b/drivers/acpi/irq.c
index 1687483ff319..76a856c32c4d 100644
--- a/drivers/acpi/irq.c
+++ b/drivers/acpi/irq.c
@@ -12,7 +12,7 @@
 
 enum acpi_irq_model_id acpi_irq_model;
 
-static struct fwnode_handle *(*acpi_get_gsi_domain_id)(u32 gsi);
+static acpi_gsi_domain_disp_fn acpi_get_gsi_domain_id;
 static u32 (*acpi_gsi_to_irq_fallback)(u32 gsi);
 
 /**
@@ -307,12 +307,24 @@ EXPORT_SYMBOL_GPL(acpi_irq_get);
  *	for a given GSI
  */
 void __init acpi_set_irq_model(enum acpi_irq_model_id model,
-			       struct fwnode_handle *(*fn)(u32))
+			       acpi_gsi_domain_disp_fn fn)
 {
 	acpi_irq_model = model;
 	acpi_get_gsi_domain_id = fn;
 }
 
+/*
+ * acpi_get_gsi_dispatcher() - Get the GSI dispatcher function
+ *
+ * Return the dispatcher function that computes the domain fwnode for
+ * a given GSI.
+ */
+acpi_gsi_domain_disp_fn acpi_get_gsi_dispatcher(void)
+{
+	return acpi_get_gsi_domain_id;
+}
+EXPORT_SYMBOL_GPL(acpi_get_gsi_dispatcher);
+
 /**
  * acpi_set_gsi_to_irq_fallback - Register a GSI transfer
  * callback to fallback to arch specified implementation.
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 773799cfd443..79b20da0a256 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -6682,12 +6682,6 @@ const struct ata_port_info ata_dummy_port_info = {
 };
 EXPORT_SYMBOL_GPL(ata_dummy_port_info);
 
-void ata_print_version(const struct device *dev, const char *version)
-{
-	dev_printk(KERN_DEBUG, dev, "version %s\n", version);
-}
-EXPORT_SYMBOL(ata_print_version);
-
 EXPORT_TRACEPOINT_SYMBOL_GPL(ata_tf_load);
 EXPORT_TRACEPOINT_SYMBOL_GPL(ata_exec_command);
 EXPORT_TRACEPOINT_SYMBOL_GPL(ata_bmdma_setup);
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index b990c1ee0b12..c11d8e634bf7 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -3432,7 +3432,7 @@ static int ata_eh_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 	struct ata_eh_context *ehc = &link->eh_context;
 	struct ata_device *dev, *link_dev = NULL, *lpm_dev = NULL;
 	enum ata_lpm_policy old_policy = link->lpm_policy;
-	bool no_dipm = link->ap->flags & ATA_FLAG_NO_DIPM;
+	bool host_has_dipm = !(link->ap->flags & ATA_FLAG_NO_DIPM);
 	unsigned int hints = ATA_LPM_EMPTY | ATA_LPM_HIPM;
 	unsigned int err_mask;
 	int rc;
@@ -3443,28 +3443,35 @@ static int ata_eh_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 		return 0;
 
 	/*
-	 * DIPM is enabled only for MIN_POWER as some devices
-	 * misbehave when the host NACKs transition to SLUMBER.  Order
-	 * device and link configurations such that the host always
-	 * allows DIPM requests.
+	 * This function currently assumes that it will never be supplied policy
+	 * ATA_LPM_UNKNOWN.
+	 */
+	if (WARN_ON_ONCE(policy == ATA_LPM_UNKNOWN))
+		return 0;
+
+	/*
+	 * DIPM is enabled only for ATA_LPM_MIN_POWER,
+	 * ATA_LPM_MIN_POWER_WITH_PARTIAL, and ATA_LPM_MED_POWER_WITH_DIPM, as
+	 * some devices misbehave when the host NACKs transition to SLUMBER.
 	 */
 	ata_for_each_dev(dev, link, ENABLED) {
-		bool hipm = ata_id_has_hipm(dev->id);
-		bool dipm = ata_id_has_dipm(dev->id) && !no_dipm;
+		bool dev_has_hipm = ata_id_has_hipm(dev->id);
+		bool dev_has_dipm = ata_id_has_dipm(dev->id);
 
 		/* find the first enabled and LPM enabled devices */
 		if (!link_dev)
 			link_dev = dev;
 
-		if (!lpm_dev && (hipm || dipm))
+		if (!lpm_dev &&
+		    (dev_has_hipm || (dev_has_dipm && host_has_dipm)))
 			lpm_dev = dev;
 
 		hints &= ~ATA_LPM_EMPTY;
-		if (!hipm)
+		if (!dev_has_hipm)
 			hints &= ~ATA_LPM_HIPM;
 
 		/* disable DIPM before changing link config */
-		if (policy < ATA_LPM_MED_POWER_WITH_DIPM && dipm) {
+		if (dev_has_dipm) {
 			err_mask = ata_dev_set_feature(dev,
 					SETFEATURES_SATA_DISABLE, SATA_DIPM);
 			if (err_mask && err_mask != AC_ERR_DEV) {
@@ -3505,10 +3512,16 @@ static int ata_eh_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 	if (ap && ap->slave_link)
 		ap->slave_link->lpm_policy = policy;
 
-	/* host config updated, enable DIPM if transitioning to MIN_POWER */
+	/*
+	 * Host config updated, enable DIPM if transitioning to
+	 * ATA_LPM_MIN_POWER, ATA_LPM_MIN_POWER_WITH_PARTIAL, or
+	 * ATA_LPM_MED_POWER_WITH_DIPM.
+	 */
 	ata_for_each_dev(dev, link, ENABLED) {
-		if (policy >= ATA_LPM_MED_POWER_WITH_DIPM && !no_dipm &&
-		    ata_id_has_dipm(dev->id)) {
+		bool dev_has_dipm = ata_id_has_dipm(dev->id);
+
+		if (policy >= ATA_LPM_MED_POWER_WITH_DIPM && host_has_dipm &&
+		    dev_has_dipm) {
 			err_mask = ata_dev_set_feature(dev,
 					SETFEATURES_SATA_ENABLE, SATA_DIPM);
 			if (err_mask && err_mask != AC_ERR_DEV) {
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index 2e4463d3a356..cb46ce276bb1 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -1509,9 +1509,10 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link)
 	struct ata_queued_cmd *qc;
 	unsigned int err_mask, tag;
 	u8 *sense, sk = 0, asc = 0, ascq = 0;
-	u64 sense_valid, val;
 	u16 extended_sense;
 	bool aux_icc_valid;
+	u32 sense_valid;
+	u64 val;
 	int ret = 0;
 
 	err_mask = ata_read_log_page(dev, ATA_LOG_SENSE_NCQ, 0, buf, 2);
@@ -1529,8 +1530,7 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link)
 		return -EIO;
 	}
 
-	sense_valid = (u64)buf[8] | ((u64)buf[9] << 8) |
-		((u64)buf[10] << 16) | ((u64)buf[11] << 24);
+	sense_valid = get_unaligned_le32(&buf[8]);
 	extended_sense = get_unaligned_le16(&buf[14]);
 	aux_icc_valid = extended_sense & BIT(15);
 
@@ -1545,7 +1545,7 @@ int ata_eh_get_ncq_success_sense(struct ata_link *link)
 		 * If the command does not have any sense data, clear ATA_SENSE.
 		 * Keep ATA_QCFLAG_EH_SUCCESS_CMD so that command is finished.
 		 */
-		if (!(sense_valid & (1ULL << tag))) {
+		if (!(sense_valid & BIT(tag))) {
 			qc->result_tf.status &= ~ATA_SENSE;
 			continue;
 		}
@@ -1634,7 +1634,7 @@ void ata_eh_analyze_ncq_error(struct ata_link *link)
 		return;
 	}
 
-	if (!(link->sactive & (1 << tag))) {
+	if (!(link->sactive & BIT(tag))) {
 		ata_link_err(link, "log page 10h reported inactive tag %d\n",
 			     tag);
 		return;
@@ -1659,8 +1659,6 @@ void ata_eh_analyze_ncq_error(struct ata_link *link)
 		if (ata_scsi_sense_is_valid(sense_key, asc, ascq)) {
 			ata_scsi_set_sense(dev, qc->scsicmd, sense_key, asc,
 					   ascq);
-			ata_scsi_set_sense_information(dev, qc->scsicmd,
-						       &qc->result_tf);
 			qc->flags |= ATA_QCFLAG_SENSE_VALID;
 		}
 	}
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index c0eb8c67a9ff..a21c9895408d 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -216,17 +216,21 @@ void ata_scsi_set_sense(struct ata_device *dev, struct scsi_cmnd *cmd,
 	scsi_build_sense(cmd, d_sense, sk, asc, ascq);
 }
 
-void ata_scsi_set_sense_information(struct ata_device *dev,
-				    struct scsi_cmnd *cmd,
-				    const struct ata_taskfile *tf)
+static void ata_scsi_set_sense_information(struct ata_queued_cmd *qc)
 {
 	u64 information;
 
-	information = ata_tf_read_block(tf, dev);
+	if (!(qc->flags & ATA_QCFLAG_RTF_FILLED)) {
+		ata_dev_dbg(qc->dev,
+			    "missing result TF: can't set INFORMATION sense field\n");
+		return;
+	}
+
+	information = ata_tf_read_block(&qc->result_tf, qc->dev);
 	if (information == U64_MAX)
 		return;
 
-	scsi_set_sense_information(cmd->sense_buffer,
+	scsi_set_sense_information(qc->scsicmd->sense_buffer,
 				   SCSI_SENSE_BUFFERSIZE, information);
 }
 
@@ -971,8 +975,7 @@ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc)
  *	ata_gen_ata_sense - generate a SCSI fixed sense block
  *	@qc: Command that we are erroring out
  *
- *	Generate sense block for a failed ATA command @qc.  Descriptor
- *	format is used to accommodate LBA48 block address.
+ *	Generate sense block for a failed ATA command @qc.
  *
  *	LOCKING:
  *	None.
@@ -982,8 +985,6 @@ static void ata_gen_ata_sense(struct ata_queued_cmd *qc)
 	struct ata_device *dev = qc->dev;
 	struct scsi_cmnd *cmd = qc->scsicmd;
 	struct ata_taskfile *tf = &qc->result_tf;
-	unsigned char *sb = cmd->sense_buffer;
-	u64 block;
 	u8 sense_key, asc, ascq;
 
 	if (ata_dev_disabled(dev)) {
@@ -1014,12 +1015,6 @@ static void ata_gen_ata_sense(struct ata_queued_cmd *qc)
 		ata_scsi_set_sense(dev, cmd, ABORTED_COMMAND, 0, 0);
 		return;
 	}
-
-	block = ata_tf_read_block(&qc->result_tf, dev);
-	if (block == U64_MAX)
-		return;
-
-	scsi_set_sense_information(sb, SCSI_SENSE_BUFFERSIZE, block);
 }
 
 void ata_scsi_sdev_config(struct scsi_device *sdev)
@@ -1679,8 +1674,10 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc)
 		ata_scsi_set_passthru_sense_fields(qc);
 		if (is_ck_cond_request)
 			set_status_byte(qc->scsicmd, SAM_STAT_CHECK_CONDITION);
-	} else if (is_error && !have_sense) {
-		ata_gen_ata_sense(qc);
+	} else if (is_error) {
+		if (!have_sense)
+			ata_gen_ata_sense(qc);
+		ata_scsi_set_sense_information(qc);
 	}
 
 	ata_qc_done(qc);
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 0337be4faec7..ce5c628fa6fd 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -141,9 +141,6 @@ extern int ata_scsi_offline_dev(struct ata_device *dev);
 extern bool ata_scsi_sense_is_valid(u8 sk, u8 asc, u8 ascq);
 extern void ata_scsi_set_sense(struct ata_device *dev,
 			       struct scsi_cmnd *cmd, u8 sk, u8 asc, u8 ascq);
-extern void ata_scsi_set_sense_information(struct ata_device *dev,
-					   struct scsi_cmnd *cmd,
-					   const struct ata_taskfile *tf);
 extern void ata_scsi_media_change_notify(struct ata_device *dev);
 extern void ata_scsi_hotplug(struct work_struct *work);
 extern void ata_scsi_dev_rescan(struct work_struct *work);
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index c3042eca6332..f7f5131af937 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -1301,32 +1301,32 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
 	}
 
 	if (dimm_test) {
-		u8 test_parttern1[40] =
+		u8 test_pattern1[40] =
 			{0x55,0xAA,'P','r','o','m','i','s','e',' ',
 			'N','o','t',' ','Y','e','t',' ',
 			'D','e','f','i','n','e','d',' ',
 			'1','.','1','0',
 			'9','8','0','3','1','6','1','2',0,0};
-		u8 test_parttern2[40] = {0};
+		u8 test_pattern2[40] = {0};
 
-		pdc20621_put_to_dimm(host, test_parttern2, 0x10040, 40);
-		pdc20621_put_to_dimm(host, test_parttern2, 0x40, 40);
+		pdc20621_put_to_dimm(host, test_pattern2, 0x10040, 40);
+		pdc20621_put_to_dimm(host, test_pattern2, 0x40, 40);
 
-		pdc20621_put_to_dimm(host, test_parttern1, 0x10040, 40);
-		pdc20621_get_from_dimm(host, test_parttern2, 0x40, 40);
-		dev_info(host->dev, "DIMM test pattern 1: %x, %x, %s\n", test_parttern2[0],
-		       test_parttern2[1], &(test_parttern2[2]));
-		pdc20621_get_from_dimm(host, test_parttern2, 0x10040,
+		pdc20621_put_to_dimm(host, test_pattern1, 0x10040, 40);
+		pdc20621_get_from_dimm(host, test_pattern2, 0x40, 40);
+		dev_info(host->dev, "DIMM test pattern 1: %x, %x, %s\n", test_pattern2[0],
+		       test_pattern2[1], &(test_pattern2[2]));
+		pdc20621_get_from_dimm(host, test_pattern2, 0x10040,
 				       40);
 		dev_info(host->dev, "DIMM test pattern 2: %x, %x, %s\n",
-			 test_parttern2[0],
-			 test_parttern2[1], &(test_parttern2[2]));
+			 test_pattern2[0],
+			 test_pattern2[1], &(test_pattern2[2]));
 
-		pdc20621_put_to_dimm(host, test_parttern1, 0x40, 40);
-		pdc20621_get_from_dimm(host, test_parttern2, 0x40, 40);
+		pdc20621_put_to_dimm(host, test_pattern1, 0x40, 40);
+		pdc20621_get_from_dimm(host, test_pattern2, 0x40, 40);
 		dev_info(host->dev, "DIMM test pattern 3: %x, %x, %s\n",
-			 test_parttern2[0],
-			 test_parttern2[1], &(test_parttern2[2]));
+			 test_pattern2[0],
+			 test_pattern2[1], &(test_pattern2[2]));
 	}
 
 	/* ECC initiliazation. */
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 19fd55b8ac77..77c7a99f0870 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -638,6 +638,13 @@ static int dpm_async_with_cleanup(struct device *dev, void *fn)
 static void dpm_async_resume_children(struct device *dev, async_func_t func)
 {
 	/*
+	 * Prevent racing with dpm_clear_async_state() during initial list
+	 * walks in dpm_noirq_resume_devices(), dpm_resume_early(), and
+	 * dpm_resume().
+	 */
+	guard(mutex)(&dpm_list_mtx);
+
+	/*
 	 * Start processing "async" children of the device unless it's been
 	 * started already for them.
 	 *
@@ -985,6 +992,8 @@ static void device_resume(struct device *dev, pm_message_t state, bool async)
 	if (!dev->power.is_suspended)
 		goto Complete;
 
+	dev->power.is_suspended = false;
+
 	if (dev->power.direct_complete) {
 		/*
 		 * Allow new children to be added under the device after this
@@ -1047,7 +1056,6 @@ static void device_resume(struct device *dev, pm_message_t state, bool async)
 
  End:
 	error = dpm_run_callback(callback, dev, state, info);
-	dev->power.is_suspended = false;
 
 	device_unlock(dev);
 	dpm_watchdog_clear(&wd);
@@ -1451,7 +1459,7 @@ static int dpm_noirq_suspend_devices(pm_message_t state)
 			 * Move all devices to the target list to resume them
 			 * properly.
 			 */
-			list_splice(&dpm_late_early_list, &dpm_noirq_list);
+			list_splice_init(&dpm_late_early_list, &dpm_noirq_list);
 			break;
 		}
 	}
@@ -1653,7 +1661,7 @@ int dpm_suspend_late(pm_message_t state)
 			 * Move all devices to the target list to resume them
 			 * properly.
 			 */
-			list_splice(&dpm_suspended_list, &dpm_late_early_list);
+			list_splice_init(&dpm_suspended_list, &dpm_late_early_list);
 			break;
 		}
 	}
@@ -1946,7 +1954,7 @@ int dpm_suspend(pm_message_t state)
 			 * Move all devices to the target list to resume them
 			 * properly.
 			 */
-			list_splice(&dpm_prepared_list, &dpm_suspended_list);
+			list_splice_init(&dpm_prepared_list, &dpm_suspended_list);
 			break;
 		}
 	}
diff --git a/drivers/base/property.c b/drivers/base/property.c
index c1392743df9c..805f75b35115 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -928,22 +928,22 @@ bool fwnode_device_is_available(const struct fwnode_handle *fwnode)
 EXPORT_SYMBOL_GPL(fwnode_device_is_available);
 
 /**
- * device_get_child_node_count - return the number of child nodes for device
- * @dev: Device to count the child nodes for
+ * fwnode_get_child_node_count - return the number of child nodes for a given firmware node
+ * @fwnode: Pointer to the parent firmware node
  *
- * Return: the number of child nodes for a given device.
+ * Return: the number of child nodes for a given firmware node.
  */
-unsigned int device_get_child_node_count(const struct device *dev)
+unsigned int fwnode_get_child_node_count(const struct fwnode_handle *fwnode)
 {
 	struct fwnode_handle *child;
 	unsigned int count = 0;
 
-	device_for_each_child_node(dev, child)
+	fwnode_for_each_child_node(fwnode, child)
 		count++;
 
 	return count;
 }
-EXPORT_SYMBOL_GPL(device_get_child_node_count);
+EXPORT_SYMBOL_GPL(fwnode_get_child_node_count);
 
 bool device_dma_supported(const struct device *dev)
 {
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 0d619df03fa9..66ce6b81c7d9 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3717,7 +3717,7 @@ static int mtip_pci_probe(struct pci_dev *pdev,
 	rv = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (rv) {
 		dev_warn(&pdev->dev, "64-bit DMA enable failed\n");
-		goto setmask_err;
+		goto iomap_err;
 	}
 
 	/* Copy the info we may need later into the private data structure. */
@@ -3733,7 +3733,7 @@ static int mtip_pci_probe(struct pci_dev *pdev,
 	if (!dd->isr_workq) {
 		dev_warn(&pdev->dev, "Can't create wq %d\n", dd->instance);
 		rv = -ENOMEM;
-		goto setmask_err;
+		goto iomap_err;
 	}
 
 	memset(cpu_list, 0, sizeof(cpu_list));
@@ -3830,8 +3830,6 @@ msi_initialize_err:
 		drop_cpu(dd->work[1].cpu_binding);
 		drop_cpu(dd->work[2].cpu_binding);
 	}
-setmask_err:
-	pcim_iounmap_regions(pdev, 1 << MTIP_ABAR);
 
 iomap_err:
 	kfree(dd);
@@ -3907,7 +3905,6 @@ static void mtip_pci_remove(struct pci_dev *pdev)
 
 	pci_disable_msi(pdev);
 
-	pcim_iounmap_regions(pdev, 1 << MTIP_ABAR);
 	pci_set_drvdata(pdev, NULL);
 
 	put_disk(dd->disk);
diff --git a/drivers/block/zram/backend_deflate.c b/drivers/block/zram/backend_deflate.c
index 0f7f252c12f4..b75016e0e654 100644
--- a/drivers/block/zram/backend_deflate.c
+++ b/drivers/block/zram/backend_deflate.c
@@ -8,7 +8,7 @@
 #include "backend_deflate.h"
 
 /* Use the same value as crypto API */
-#define DEFLATE_DEF_WINBITS		11
+#define DEFLATE_DEF_WINBITS		(-11)
 #define DEFLATE_DEF_MEMLEVEL		MAX_MEM_LEVEL
 
 struct deflate_ctx {
@@ -22,8 +22,10 @@ static void deflate_release_params(struct zcomp_params *params)
 
 static int deflate_setup_params(struct zcomp_params *params)
 {
-	if (params->level == ZCOMP_PARAM_NO_LEVEL)
+	if (params->level == ZCOMP_PARAM_NOT_SET)
 		params->level = Z_DEFAULT_COMPRESSION;
+	if (params->deflate.winbits == ZCOMP_PARAM_NOT_SET)
+		params->deflate.winbits = DEFLATE_DEF_WINBITS;
 
 	return 0;
 }
@@ -57,13 +59,13 @@ static int deflate_create(struct zcomp_params *params, struct zcomp_ctx *ctx)
 		return -ENOMEM;
 
 	ctx->context = zctx;
-	sz = zlib_deflate_workspacesize(-DEFLATE_DEF_WINBITS, MAX_MEM_LEVEL);
+	sz = zlib_deflate_workspacesize(params->deflate.winbits, MAX_MEM_LEVEL);
 	zctx->cctx.workspace = vzalloc(sz);
 	if (!zctx->cctx.workspace)
 		goto error;
 
 	ret = zlib_deflateInit2(&zctx->cctx, params->level, Z_DEFLATED,
-				-DEFLATE_DEF_WINBITS, DEFLATE_DEF_MEMLEVEL,
+				params->deflate.winbits, DEFLATE_DEF_MEMLEVEL,
 				Z_DEFAULT_STRATEGY);
 	if (ret != Z_OK)
 		goto error;
@@ -73,7 +75,7 @@ static int deflate_create(struct zcomp_params *params, struct zcomp_ctx *ctx)
 	if (!zctx->dctx.workspace)
 		goto error;
 
-	ret = zlib_inflateInit2(&zctx->dctx, -DEFLATE_DEF_WINBITS);
+	ret = zlib_inflateInit2(&zctx->dctx, params->deflate.winbits);
 	if (ret != Z_OK)
 		goto error;
 
diff --git a/drivers/block/zram/backend_lz4.c b/drivers/block/zram/backend_lz4.c
index 847f3334eb38..daccd60857eb 100644
--- a/drivers/block/zram/backend_lz4.c
+++ b/drivers/block/zram/backend_lz4.c
@@ -18,7 +18,7 @@ static void lz4_release_params(struct zcomp_params *params)
 
 static int lz4_setup_params(struct zcomp_params *params)
 {
-	if (params->level == ZCOMP_PARAM_NO_LEVEL)
+	if (params->level == ZCOMP_PARAM_NOT_SET)
 		params->level = LZ4_ACCELERATION_DEFAULT;
 
 	return 0;
diff --git a/drivers/block/zram/backend_lz4hc.c b/drivers/block/zram/backend_lz4hc.c
index 5f37d5abcaeb..9e8a35dfa56d 100644
--- a/drivers/block/zram/backend_lz4hc.c
+++ b/drivers/block/zram/backend_lz4hc.c
@@ -18,7 +18,7 @@ static void lz4hc_release_params(struct zcomp_params *params)
 
 static int lz4hc_setup_params(struct zcomp_params *params)
 {
-	if (params->level == ZCOMP_PARAM_NO_LEVEL)
+	if (params->level == ZCOMP_PARAM_NOT_SET)
 		params->level = LZ4HC_DEFAULT_CLEVEL;
 
 	return 0;
diff --git a/drivers/block/zram/backend_zstd.c b/drivers/block/zram/backend_zstd.c
index 22c8067536f3..81defb98ed09 100644
--- a/drivers/block/zram/backend_zstd.c
+++ b/drivers/block/zram/backend_zstd.c
@@ -58,7 +58,7 @@ static int zstd_setup_params(struct zcomp_params *params)
 		return -ENOMEM;
 
 	params->drv_data = zp;
-	if (params->level == ZCOMP_PARAM_NO_LEVEL)
+	if (params->level == ZCOMP_PARAM_NOT_SET)
 		params->level = zstd_default_clevel();
 
 	zp->cprm = zstd_get_params(params->level, PAGE_SIZE);
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
index 25339ed1e07e..4acffe671a5e 100644
--- a/drivers/block/zram/zcomp.h
+++ b/drivers/block/zram/zcomp.h
@@ -5,7 +5,11 @@
 
 #include <linux/mutex.h>
 
-#define ZCOMP_PARAM_NO_LEVEL	INT_MIN
+#define ZCOMP_PARAM_NOT_SET	INT_MIN
+
+struct deflate_params {
+	s32 winbits;
+};
 
 /*
  * Immutable driver (backend) parameters. The driver may attach private
@@ -17,6 +21,9 @@ struct zcomp_params {
 	void *dict;
 	size_t dict_sz;
 	s32 level;
+	union {
+		struct deflate_params deflate;
+	};
 
 	void *drv_data;
 };
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 94e6e9b80bf0..54c57103715f 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1276,13 +1276,15 @@ static void comp_params_reset(struct zram *zram, u32 prio)
 	struct zcomp_params *params = &zram->params[prio];
 
 	vfree(params->dict);
-	params->level = ZCOMP_PARAM_NO_LEVEL;
+	params->level = ZCOMP_PARAM_NOT_SET;
+	params->deflate.winbits = ZCOMP_PARAM_NOT_SET;
 	params->dict_sz = 0;
 	params->dict = NULL;
 }
 
 static int comp_params_store(struct zram *zram, u32 prio, s32 level,
-			     const char *dict_path)
+			     const char *dict_path,
+			     struct deflate_params *deflate_params)
 {
 	ssize_t sz = 0;
 
@@ -1300,6 +1302,7 @@ static int comp_params_store(struct zram *zram, u32 prio, s32 level,
 
 	zram->params[prio].dict_sz = sz;
 	zram->params[prio].level = level;
+	zram->params[prio].deflate.winbits = deflate_params->winbits;
 	return 0;
 }
 
@@ -1308,11 +1311,14 @@ static ssize_t algorithm_params_store(struct device *dev,
 				      const char *buf,
 				      size_t len)
 {
-	s32 prio = ZRAM_PRIMARY_COMP, level = ZCOMP_PARAM_NO_LEVEL;
+	s32 prio = ZRAM_PRIMARY_COMP, level = ZCOMP_PARAM_NOT_SET;
 	char *args, *param, *val, *algo = NULL, *dict_path = NULL;
+	struct deflate_params deflate_params;
 	struct zram *zram = dev_to_zram(dev);
 	int ret;
 
+	deflate_params.winbits = ZCOMP_PARAM_NOT_SET;
+
 	args = skip_spaces(buf);
 	while (*args) {
 		args = next_arg(args, &param, &val);
@@ -1343,6 +1349,13 @@ static ssize_t algorithm_params_store(struct device *dev,
 			dict_path = val;
 			continue;
 		}
+
+		if (!strcmp(param, "deflate.winbits")) {
+			ret = kstrtoint(val, 10, &deflate_params.winbits);
+			if (ret)
+				return ret;
+			continue;
+		}
 	}
 
 	/* Lookup priority by algorithm name */
@@ -1364,7 +1377,7 @@ static ssize_t algorithm_params_store(struct device *dev,
 	if (prio < ZRAM_PRIMARY_COMP || prio >= ZRAM_MAX_COMPS)
 		return -EINVAL;
 
-	ret = comp_params_store(zram, prio, level, dict_path);
+	ret = comp_params_store(zram, prio, level, dict_path, &deflate_params);
 	return ret ? ret : len;
 }
 
diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index b34623a69b8a..6b13feed06df 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -533,6 +533,8 @@ static int ps_setup(struct hci_dev *hdev)
 					ps_host_wakeup_irq_handler,
 					IRQF_ONESHOT | IRQF_TRIGGER_FALLING,
 					dev_name(&serdev->dev), nxpdev);
+		if (ret)
+			bt_dev_info(hdev, "error setting wakeup IRQ handler, ignoring\n");
 		disable_irq(psdata->irq_handler);
 		device_init_wakeup(&serdev->dev, true);
 	}
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index e00590ba24fd..a2dc39c005f4 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -2415,14 +2415,14 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 
 		qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable",
 					       GPIOD_OUT_LOW);
-		if (IS_ERR(qcadev->bt_en) &&
-		    (data->soc_type == QCA_WCN6750 ||
-		     data->soc_type == QCA_WCN6855)) {
-			dev_err(&serdev->dev, "failed to acquire BT_EN gpio\n");
-			return PTR_ERR(qcadev->bt_en);
-		}
+		if (IS_ERR(qcadev->bt_en))
+			return dev_err_probe(&serdev->dev,
+					     PTR_ERR(qcadev->bt_en),
+					     "failed to acquire BT_EN gpio\n");
 
-		if (!qcadev->bt_en)
+		if (!qcadev->bt_en &&
+		    (data->soc_type == QCA_WCN6750 ||
+		     data->soc_type == QCA_WCN6855))
 			power_ctrl_enabled = false;
 
 		qcadev->sw_ctrl = devm_gpiod_get_optional(&serdev->dev, "swctrl",
diff --git a/drivers/clocksource/timer-stm32-lp.c b/drivers/clocksource/timer-stm32-lp.c
index 928da2f6de69..6e7944ffd7c0 100644
--- a/drivers/clocksource/timer-stm32-lp.c
+++ b/drivers/clocksource/timer-stm32-lp.c
@@ -5,6 +5,7 @@
  *	    Pascal Paillet <p.paillet@st.com> for STMicroelectronics.
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
@@ -27,6 +28,7 @@ struct stm32_lp_private {
 	u32 psc;
 	struct device *dev;
 	struct clk *clk;
+	u32 version;
 };
 
 static struct stm32_lp_private*
@@ -47,12 +49,46 @@ static int stm32_clkevent_lp_shutdown(struct clock_event_device *clkevt)
 	return 0;
 }
 
-static int stm32_clkevent_lp_set_timer(unsigned long evt,
-				       struct clock_event_device *clkevt,
-				       int is_periodic)
+static int stm32mp25_clkevent_lp_set_evt(struct stm32_lp_private *priv, unsigned long evt)
 {
-	struct stm32_lp_private *priv = to_priv(clkevt);
+	int ret;
+	u32 val;
+
+	regmap_read(priv->reg, STM32_LPTIM_CR, &val);
+	if (!FIELD_GET(STM32_LPTIM_ENABLE, val)) {
+		/* Enable LPTIMER to be able to write into IER and ARR registers */
+		regmap_write(priv->reg, STM32_LPTIM_CR, STM32_LPTIM_ENABLE);
+		/*
+		 * After setting the ENABLE bit, a delay of two counter clock cycles is needed
+		 * before the LPTIM is actually enabled. For 32KHz rate, this makes approximately
+		 * 62.5 micro-seconds, round it up.
+		 */
+		udelay(63);
+	}
+	/* set next event counter */
+	regmap_write(priv->reg, STM32_LPTIM_ARR, evt);
+	/* enable ARR interrupt */
+	regmap_write(priv->reg, STM32_LPTIM_IER, STM32_LPTIM_ARRMIE);
+
+	/* Poll DIEROK and ARROK to ensure register access has completed */
+	ret = regmap_read_poll_timeout_atomic(priv->reg, STM32_LPTIM_ISR, val,
+					      (val & STM32_LPTIM_DIEROK_ARROK) ==
+					      STM32_LPTIM_DIEROK_ARROK,
+					      10, 500);
+	if (ret) {
+		dev_err(priv->dev, "access to LPTIM timed out\n");
+		/* Disable LPTIMER */
+		regmap_write(priv->reg, STM32_LPTIM_CR, 0);
+		return ret;
+	}
+	/* Clear DIEROK and ARROK flags */
+	regmap_write(priv->reg, STM32_LPTIM_ICR, STM32_LPTIM_DIEROKCF_ARROKCF);
 
+	return 0;
+}
+
+static void stm32_clkevent_lp_set_evt(struct stm32_lp_private *priv, unsigned long evt)
+{
 	/* disable LPTIMER to be able to write into IER register*/
 	regmap_write(priv->reg, STM32_LPTIM_CR, 0);
 	/* enable ARR interrupt */
@@ -61,6 +97,22 @@ static int stm32_clkevent_lp_set_timer(unsigned long evt,
 	regmap_write(priv->reg, STM32_LPTIM_CR, STM32_LPTIM_ENABLE);
 	/* set next event counter */
 	regmap_write(priv->reg, STM32_LPTIM_ARR, evt);
+}
+
+static int stm32_clkevent_lp_set_timer(unsigned long evt,
+				       struct clock_event_device *clkevt,
+				       int is_periodic)
+{
+	struct stm32_lp_private *priv = to_priv(clkevt);
+	int ret;
+
+	if (priv->version == STM32_LPTIM_VERR_23) {
+		ret = stm32mp25_clkevent_lp_set_evt(priv, evt);
+		if (ret)
+			return ret;
+	} else {
+		stm32_clkevent_lp_set_evt(priv, evt);
+	}
 
 	/* start counter */
 	if (is_periodic)
@@ -176,6 +228,7 @@ static int stm32_clkevent_lp_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	priv->reg = ddata->regmap;
+	priv->version = ddata->version;
 	priv->clk = ddata->clk;
 	ret = clk_prepare_enable(priv->clk);
 	if (ret)
diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig
index cf1ba673b8c2..48b7314afdb8 100644
--- a/drivers/cxl/Kconfig
+++ b/drivers/cxl/Kconfig
@@ -114,6 +114,77 @@ config CXL_FEATURES
 
 	  If unsure say 'n'
 
+config CXL_EDAC_MEM_FEATURES
+	bool "CXL: EDAC Memory Features"
+	depends on EXPERT
+	depends on CXL_MEM
+	depends on CXL_FEATURES
+	depends on EDAC >= CXL_BUS
+	help
+	  The CXL EDAC memory feature is optional and allows host to
+	  control the EDAC memory features configurations of CXL memory
+	  expander devices.
+
+	  Say 'y' if you have an expert need to change default settings
+	  of a memory RAS feature established by the platform/device.
+	  Otherwise say 'n'.
+
+config CXL_EDAC_SCRUB
+	bool "Enable CXL Patrol Scrub Control (Patrol Read)"
+	depends on CXL_EDAC_MEM_FEATURES
+	depends on EDAC_SCRUB
+	help
+	  The CXL EDAC scrub control is optional and allows host to
+	  control the scrub feature configurations of CXL memory expander
+	  devices.
+
+	  When enabled 'cxl_mem' and 'cxl_region' EDAC devices are
+	  published with memory scrub control attributes as described by
+	  Documentation/ABI/testing/sysfs-edac-scrub.
+
+	  Say 'y' if you have an expert need to change default settings
+	  of a memory scrub feature established by the platform/device
+	  (e.g. scrub rates for the patrol scrub feature).
+	  Otherwise say 'n'.
+
+config CXL_EDAC_ECS
+	bool "Enable CXL Error Check Scrub (Repair)"
+	depends on CXL_EDAC_MEM_FEATURES
+	depends on EDAC_ECS
+	help
+	  The CXL EDAC ECS control is optional and allows host to
+	  control the ECS feature configurations of CXL memory expander
+	  devices.
+
+	  When enabled 'cxl_mem' EDAC devices are published with memory
+	  ECS control attributes as described by
+	  Documentation/ABI/testing/sysfs-edac-ecs.
+
+	  Say 'y' if you have an expert need to change default settings
+	  of a memory ECS feature established by the platform/device.
+	  Otherwise say 'n'.
+
+config CXL_EDAC_MEM_REPAIR
+	bool "Enable CXL Memory Repair"
+	depends on CXL_EDAC_MEM_FEATURES
+	depends on EDAC_MEM_REPAIR
+	help
+	  The CXL EDAC memory repair control is optional and allows host
+	  to control the memory repair features (e.g. sparing, PPR)
+	  configurations of CXL memory expander devices.
+
+	  When enabled, the memory repair feature requires an additional
+	  memory of approximately 43KB to store CXL DRAM and CXL general
+	  media event records.
+
+	  When enabled 'cxl_mem' EDAC devices are published with memory
+	  repair control attributes as described by
+	  Documentation/ABI/testing/sysfs-edac-memory-repair.
+
+	  Say 'y' if you have an expert need to change default settings
+	  of a memory repair feature established by the platform/device.
+	  Otherwise say 'n'.
+
 config CXL_PORT
 	default CXL_BUS
 	tristate
diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index cb14829bb9be..a1a99ec3f12c 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -11,8 +11,6 @@
 #include "cxlpci.h"
 #include "cxl.h"
 
-#define CXL_RCRB_SIZE	SZ_8K
-
 struct cxl_cxims_data {
 	int nr_maps;
 	u64 xormaps[] __counted_by(nr_maps);
@@ -421,7 +419,15 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
 	rc = cxl_decoder_add(cxld, target_map);
 	if (rc)
 		return rc;
-	return cxl_root_decoder_autoremove(dev, no_free_ptr(cxlrd));
+
+	rc = cxl_root_decoder_autoremove(dev, no_free_ptr(cxlrd));
+	if (rc)
+		return rc;
+
+	dev_dbg(root_port->dev.parent, "%s added to %s\n",
+		dev_name(&cxld->dev), dev_name(&root_port->dev));
+
+	return 0;
 }
 
 static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg,
@@ -479,7 +485,11 @@ static int cxl_get_chbs_iter(union acpi_subtable_headers *header, void *arg,
 	chbs = (struct acpi_cedt_chbs *) header;
 
 	if (chbs->cxl_version == ACPI_CEDT_CHBS_VERSION_CXL11 &&
-	    chbs->length != CXL_RCRB_SIZE)
+	    chbs->length != ACPI_CEDT_CHBS_LENGTH_CXL11)
+		return 0;
+
+	if (chbs->cxl_version == ACPI_CEDT_CHBS_VERSION_CXL20 &&
+	    chbs->length != ACPI_CEDT_CHBS_LENGTH_CXL20)
 		return 0;
 
 	if (!chbs->base)
@@ -739,10 +749,10 @@ static void remove_cxl_resources(void *data)
  * expanding its boundaries to ensure that any conflicting resources become
  * children. If a window is expanded it may then conflict with a another window
  * entry and require the window to be truncated or trimmed. Consider this
- * situation:
+ * situation::
  *
- * |-- "CXL Window 0" --||----- "CXL Window 1" -----|
- * |--------------- "System RAM" -------------|
+ *	|-- "CXL Window 0" --||----- "CXL Window 1" -----|
+ *	|--------------- "System RAM" -------------|
  *
  * ...where platform firmware has established as System RAM resource across 2
  * windows, but has left some portion of window 1 for dynamic CXL region
diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile
index 086df97a0fcf..79e2ef81fde8 100644
--- a/drivers/cxl/core/Makefile
+++ b/drivers/cxl/core/Makefile
@@ -20,3 +20,4 @@ cxl_core-$(CONFIG_TRACING) += trace.o
 cxl_core-$(CONFIG_CXL_REGION) += region.o
 cxl_core-$(CONFIG_CXL_MCE) += mce.o
 cxl_core-$(CONFIG_CXL_FEATURES) += features.o
+cxl_core-$(CONFIG_CXL_EDAC_MEM_FEATURES) += edac.o
diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index edb4f41eeacc..0ccef2f2a26a 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -28,7 +28,7 @@ static u32 cdat_normalize(u16 entry, u64 base, u8 type)
 	 */
 	if (entry == 0xffff || !entry)
 		return 0;
-	else if (base > (UINT_MAX / (entry)))
+	if (base > (UINT_MAX / (entry)))
 		return 0;
 
 	/*
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 17b692eb3257..29b61828a847 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -76,7 +76,7 @@ void __iomem *devm_cxl_iomap_block(struct device *dev, resource_size_t addr,
 struct dentry *cxl_debugfs_create_dir(const char *dir);
 int cxl_dpa_set_part(struct cxl_endpoint_decoder *cxled,
 		     enum cxl_partition_mode mode);
-int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size);
+int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, u64 size);
 int cxl_dpa_free(struct cxl_endpoint_decoder *cxled);
 resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled);
 resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled);
@@ -124,6 +124,8 @@ int cxl_acpi_get_extended_linear_cache_size(struct resource *backing_res,
 					    int nid, resource_size_t *size);
 
 #ifdef CONFIG_CXL_FEATURES
+struct cxl_feat_entry *
+cxl_feature_info(struct cxl_features_state *cxlfs, const uuid_t *uuid);
 size_t cxl_get_feature(struct cxl_mailbox *cxl_mbox, const uuid_t *feat_uuid,
 		       enum cxl_get_feat_selection selection,
 		       void *feat_out, size_t feat_out_size, u16 offset,
diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c
new file mode 100644
index 000000000000..2cbc664e5d62
--- /dev/null
+++ b/drivers/cxl/core/edac.c
@@ -0,0 +1,2102 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * CXL EDAC memory feature driver.
+ *
+ * Copyright (c) 2024-2025 HiSilicon Limited.
+ *
+ *  - Supports functions to configure EDAC features of the
+ *    CXL memory devices.
+ *  - Registers with the EDAC device subsystem driver to expose
+ *    the features sysfs attributes to the user for configuring
+ *    CXL memory RAS feature.
+ */
+
+#include <linux/cleanup.h>
+#include <linux/edac.h>
+#include <linux/limits.h>
+#include <linux/unaligned.h>
+#include <linux/xarray.h>
+#include <cxl/features.h>
+#include <cxl.h>
+#include <cxlmem.h>
+#include "core.h"
+#include "trace.h"
+
+#define CXL_NR_EDAC_DEV_FEATURES 7
+
+#define CXL_SCRUB_NO_REGION -1
+
+struct cxl_patrol_scrub_context {
+	u8 instance;
+	u16 get_feat_size;
+	u16 set_feat_size;
+	u8 get_version;
+	u8 set_version;
+	u16 effects;
+	struct cxl_memdev *cxlmd;
+	struct cxl_region *cxlr;
+};
+
+/*
+ * See CXL spec rev 3.2 @8.2.10.9.11.1 Table 8-222 Device Patrol Scrub Control
+ * Feature Readable Attributes.
+ */
+struct cxl_scrub_rd_attrbs {
+	u8 scrub_cycle_cap;
+	__le16 scrub_cycle_hours;
+	u8 scrub_flags;
+} __packed;
+
+/*
+ * See CXL spec rev 3.2 @8.2.10.9.11.1 Table 8-223 Device Patrol Scrub Control
+ * Feature Writable Attributes.
+ */
+struct cxl_scrub_wr_attrbs {
+	u8 scrub_cycle_hours;
+	u8 scrub_flags;
+} __packed;
+
+#define CXL_SCRUB_CONTROL_CHANGEABLE BIT(0)
+#define CXL_SCRUB_CONTROL_REALTIME BIT(1)
+#define CXL_SCRUB_CONTROL_CYCLE_MASK GENMASK(7, 0)
+#define CXL_SCRUB_CONTROL_MIN_CYCLE_MASK GENMASK(15, 8)
+#define CXL_SCRUB_CONTROL_ENABLE BIT(0)
+
+#define CXL_GET_SCRUB_CYCLE_CHANGEABLE(cap) \
+	FIELD_GET(CXL_SCRUB_CONTROL_CHANGEABLE, cap)
+#define CXL_GET_SCRUB_CYCLE(cycle) \
+	FIELD_GET(CXL_SCRUB_CONTROL_CYCLE_MASK, cycle)
+#define CXL_GET_SCRUB_MIN_CYCLE(cycle) \
+	FIELD_GET(CXL_SCRUB_CONTROL_MIN_CYCLE_MASK, cycle)
+#define CXL_GET_SCRUB_EN_STS(flags) FIELD_GET(CXL_SCRUB_CONTROL_ENABLE, flags)
+
+#define CXL_SET_SCRUB_CYCLE(cycle) \
+	FIELD_PREP(CXL_SCRUB_CONTROL_CYCLE_MASK, cycle)
+#define CXL_SET_SCRUB_EN(en) FIELD_PREP(CXL_SCRUB_CONTROL_ENABLE, en)
+
+static int cxl_mem_scrub_get_attrbs(struct cxl_mailbox *cxl_mbox, u8 *cap,
+				    u16 *cycle, u8 *flags, u8 *min_cycle)
+{
+	size_t rd_data_size = sizeof(struct cxl_scrub_rd_attrbs);
+	size_t data_size;
+	struct cxl_scrub_rd_attrbs *rd_attrbs __free(kfree) =
+		kzalloc(rd_data_size, GFP_KERNEL);
+	if (!rd_attrbs)
+		return -ENOMEM;
+
+	data_size = cxl_get_feature(cxl_mbox, &CXL_FEAT_PATROL_SCRUB_UUID,
+				    CXL_GET_FEAT_SEL_CURRENT_VALUE, rd_attrbs,
+				    rd_data_size, 0, NULL);
+	if (!data_size)
+		return -EIO;
+
+	*cap = rd_attrbs->scrub_cycle_cap;
+	*cycle = le16_to_cpu(rd_attrbs->scrub_cycle_hours);
+	*flags = rd_attrbs->scrub_flags;
+	if (min_cycle)
+		*min_cycle = CXL_GET_SCRUB_MIN_CYCLE(*cycle);
+
+	return 0;
+}
+
+static int cxl_scrub_get_attrbs(struct cxl_patrol_scrub_context *cxl_ps_ctx,
+				u8 *cap, u16 *cycle, u8 *flags, u8 *min_cycle)
+{
+	struct cxl_mailbox *cxl_mbox;
+	u8 min_scrub_cycle = U8_MAX;
+	struct cxl_region_params *p;
+	struct cxl_memdev *cxlmd;
+	struct cxl_region *cxlr;
+	int i, ret;
+
+	if (!cxl_ps_ctx->cxlr) {
+		cxl_mbox = &cxl_ps_ctx->cxlmd->cxlds->cxl_mbox;
+		return cxl_mem_scrub_get_attrbs(cxl_mbox, cap, cycle,
+						flags, min_cycle);
+	}
+
+	struct rw_semaphore *region_lock __free(rwsem_read_release) =
+		rwsem_read_intr_acquire(&cxl_region_rwsem);
+	if (!region_lock)
+		return -EINTR;
+
+	cxlr = cxl_ps_ctx->cxlr;
+	p = &cxlr->params;
+
+	for (i = 0; i < p->nr_targets; i++) {
+		struct cxl_endpoint_decoder *cxled = p->targets[i];
+
+		cxlmd = cxled_to_memdev(cxled);
+		cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+		ret = cxl_mem_scrub_get_attrbs(cxl_mbox, cap, cycle, flags,
+					       min_cycle);
+		if (ret)
+			return ret;
+
+		if (min_cycle)
+			min_scrub_cycle = min(*min_cycle, min_scrub_cycle);
+	}
+
+	if (min_cycle)
+		*min_cycle = min_scrub_cycle;
+
+	return 0;
+}
+
+static int cxl_scrub_set_attrbs_region(struct device *dev,
+				       struct cxl_patrol_scrub_context *cxl_ps_ctx,
+				       u8 cycle, u8 flags)
+{
+	struct cxl_scrub_wr_attrbs wr_attrbs;
+	struct cxl_mailbox *cxl_mbox;
+	struct cxl_region_params *p;
+	struct cxl_memdev *cxlmd;
+	struct cxl_region *cxlr;
+	int ret, i;
+
+	struct rw_semaphore *region_lock __free(rwsem_read_release) =
+		rwsem_read_intr_acquire(&cxl_region_rwsem);
+	if (!region_lock)
+		return -EINTR;
+
+	cxlr = cxl_ps_ctx->cxlr;
+	p = &cxlr->params;
+	wr_attrbs.scrub_cycle_hours = cycle;
+	wr_attrbs.scrub_flags = flags;
+
+	for (i = 0; i < p->nr_targets; i++) {
+		struct cxl_endpoint_decoder *cxled = p->targets[i];
+
+		cxlmd = cxled_to_memdev(cxled);
+		cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+		ret = cxl_set_feature(cxl_mbox, &CXL_FEAT_PATROL_SCRUB_UUID,
+				      cxl_ps_ctx->set_version, &wr_attrbs,
+				      sizeof(wr_attrbs),
+				      CXL_SET_FEAT_FLAG_DATA_SAVED_ACROSS_RESET,
+				      0, NULL);
+		if (ret)
+			return ret;
+
+		if (cycle != cxlmd->scrub_cycle) {
+			if (cxlmd->scrub_region_id != CXL_SCRUB_NO_REGION)
+				dev_info(dev,
+					 "Device scrub rate(%d hours) set by region%d rate overwritten by region%d scrub rate(%d hours)\n",
+					 cxlmd->scrub_cycle,
+					 cxlmd->scrub_region_id, cxlr->id,
+					 cycle);
+
+			cxlmd->scrub_cycle = cycle;
+			cxlmd->scrub_region_id = cxlr->id;
+		}
+	}
+
+	return 0;
+}
+
+static int cxl_scrub_set_attrbs_device(struct device *dev,
+				       struct cxl_patrol_scrub_context *cxl_ps_ctx,
+				       u8 cycle, u8 flags)
+{
+	struct cxl_scrub_wr_attrbs wr_attrbs;
+	struct cxl_mailbox *cxl_mbox;
+	struct cxl_memdev *cxlmd;
+	int ret;
+
+	wr_attrbs.scrub_cycle_hours = cycle;
+	wr_attrbs.scrub_flags = flags;
+
+	cxlmd = cxl_ps_ctx->cxlmd;
+	cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+	ret = cxl_set_feature(cxl_mbox, &CXL_FEAT_PATROL_SCRUB_UUID,
+			      cxl_ps_ctx->set_version, &wr_attrbs,
+			      sizeof(wr_attrbs),
+			      CXL_SET_FEAT_FLAG_DATA_SAVED_ACROSS_RESET, 0,
+			      NULL);
+	if (ret)
+		return ret;
+
+	if (cycle != cxlmd->scrub_cycle) {
+		if (cxlmd->scrub_region_id != CXL_SCRUB_NO_REGION)
+			dev_info(dev,
+				 "Device scrub rate(%d hours) set by region%d rate overwritten with device local scrub rate(%d hours)\n",
+				 cxlmd->scrub_cycle, cxlmd->scrub_region_id,
+				 cycle);
+
+		cxlmd->scrub_cycle = cycle;
+		cxlmd->scrub_region_id = CXL_SCRUB_NO_REGION;
+	}
+
+	return 0;
+}
+
+static int cxl_scrub_set_attrbs(struct device *dev,
+				struct cxl_patrol_scrub_context *cxl_ps_ctx,
+				u8 cycle, u8 flags)
+{
+	if (cxl_ps_ctx->cxlr)
+		return cxl_scrub_set_attrbs_region(dev, cxl_ps_ctx, cycle, flags);
+
+	return cxl_scrub_set_attrbs_device(dev, cxl_ps_ctx, cycle, flags);
+}
+
+static int cxl_patrol_scrub_get_enabled_bg(struct device *dev, void *drv_data,
+					   bool *enabled)
+{
+	struct cxl_patrol_scrub_context *ctx = drv_data;
+	u8 cap, flags;
+	u16 cycle;
+	int ret;
+
+	ret = cxl_scrub_get_attrbs(ctx, &cap, &cycle, &flags, NULL);
+	if (ret)
+		return ret;
+
+	*enabled = CXL_GET_SCRUB_EN_STS(flags);
+
+	return 0;
+}
+
+static int cxl_patrol_scrub_set_enabled_bg(struct device *dev, void *drv_data,
+					   bool enable)
+{
+	struct cxl_patrol_scrub_context *ctx = drv_data;
+	u8 cap, flags, wr_cycle;
+	u16 rd_cycle;
+	int ret;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	ret = cxl_scrub_get_attrbs(ctx, &cap, &rd_cycle, &flags, NULL);
+	if (ret)
+		return ret;
+
+	wr_cycle = CXL_GET_SCRUB_CYCLE(rd_cycle);
+	flags = CXL_SET_SCRUB_EN(enable);
+
+	return cxl_scrub_set_attrbs(dev, ctx, wr_cycle, flags);
+}
+
+static int cxl_patrol_scrub_get_min_scrub_cycle(struct device *dev,
+						void *drv_data, u32 *min)
+{
+	struct cxl_patrol_scrub_context *ctx = drv_data;
+	u8 cap, flags, min_cycle;
+	u16 cycle;
+	int ret;
+
+	ret = cxl_scrub_get_attrbs(ctx, &cap, &cycle, &flags, &min_cycle);
+	if (ret)
+		return ret;
+
+	*min = min_cycle * 3600;
+
+	return 0;
+}
+
+static int cxl_patrol_scrub_get_max_scrub_cycle(struct device *dev,
+						void *drv_data, u32 *max)
+{
+	*max = U8_MAX * 3600; /* Max set by register size */
+
+	return 0;
+}
+
+static int cxl_patrol_scrub_get_scrub_cycle(struct device *dev, void *drv_data,
+					    u32 *scrub_cycle_secs)
+{
+	struct cxl_patrol_scrub_context *ctx = drv_data;
+	u8 cap, flags;
+	u16 cycle;
+	int ret;
+
+	ret = cxl_scrub_get_attrbs(ctx, &cap, &cycle, &flags, NULL);
+	if (ret)
+		return ret;
+
+	*scrub_cycle_secs = CXL_GET_SCRUB_CYCLE(cycle) * 3600;
+
+	return 0;
+}
+
+static int cxl_patrol_scrub_set_scrub_cycle(struct device *dev, void *drv_data,
+					    u32 scrub_cycle_secs)
+{
+	struct cxl_patrol_scrub_context *ctx = drv_data;
+	u8 scrub_cycle_hours = scrub_cycle_secs / 3600;
+	u8 cap, wr_cycle, flags, min_cycle;
+	u16 rd_cycle;
+	int ret;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	ret = cxl_scrub_get_attrbs(ctx, &cap, &rd_cycle, &flags, &min_cycle);
+	if (ret)
+		return ret;
+
+	if (!CXL_GET_SCRUB_CYCLE_CHANGEABLE(cap))
+		return -EOPNOTSUPP;
+
+	if (scrub_cycle_hours < min_cycle) {
+		dev_dbg(dev, "Invalid CXL patrol scrub cycle(%d) to set\n",
+			scrub_cycle_hours);
+		dev_dbg(dev,
+			"Minimum supported CXL patrol scrub cycle in hour %d\n",
+			min_cycle);
+		return -EINVAL;
+	}
+	wr_cycle = CXL_SET_SCRUB_CYCLE(scrub_cycle_hours);
+
+	return cxl_scrub_set_attrbs(dev, ctx, wr_cycle, flags);
+}
+
+static const struct edac_scrub_ops cxl_ps_scrub_ops = {
+	.get_enabled_bg = cxl_patrol_scrub_get_enabled_bg,
+	.set_enabled_bg = cxl_patrol_scrub_set_enabled_bg,
+	.get_min_cycle = cxl_patrol_scrub_get_min_scrub_cycle,
+	.get_max_cycle = cxl_patrol_scrub_get_max_scrub_cycle,
+	.get_cycle_duration = cxl_patrol_scrub_get_scrub_cycle,
+	.set_cycle_duration = cxl_patrol_scrub_set_scrub_cycle,
+};
+
+static int cxl_memdev_scrub_init(struct cxl_memdev *cxlmd,
+				 struct edac_dev_feature *ras_feature,
+				 u8 scrub_inst)
+{
+	struct cxl_patrol_scrub_context *cxl_ps_ctx;
+	struct cxl_feat_entry *feat_entry;
+	u8 cap, flags;
+	u16 cycle;
+	int rc;
+
+	feat_entry = cxl_feature_info(to_cxlfs(cxlmd->cxlds),
+				      &CXL_FEAT_PATROL_SCRUB_UUID);
+	if (IS_ERR(feat_entry))
+		return -EOPNOTSUPP;
+
+	if (!(le32_to_cpu(feat_entry->flags) & CXL_FEATURE_F_CHANGEABLE))
+		return -EOPNOTSUPP;
+
+	cxl_ps_ctx = devm_kzalloc(&cxlmd->dev, sizeof(*cxl_ps_ctx), GFP_KERNEL);
+	if (!cxl_ps_ctx)
+		return -ENOMEM;
+
+	*cxl_ps_ctx = (struct cxl_patrol_scrub_context){
+		.get_feat_size = le16_to_cpu(feat_entry->get_feat_size),
+		.set_feat_size = le16_to_cpu(feat_entry->set_feat_size),
+		.get_version = feat_entry->get_feat_ver,
+		.set_version = feat_entry->set_feat_ver,
+		.effects = le16_to_cpu(feat_entry->effects),
+		.instance = scrub_inst,
+		.cxlmd = cxlmd,
+	};
+
+	rc = cxl_mem_scrub_get_attrbs(&cxlmd->cxlds->cxl_mbox, &cap, &cycle,
+				      &flags, NULL);
+	if (rc)
+		return rc;
+
+	cxlmd->scrub_cycle = CXL_GET_SCRUB_CYCLE(cycle);
+	cxlmd->scrub_region_id = CXL_SCRUB_NO_REGION;
+
+	ras_feature->ft_type = RAS_FEAT_SCRUB;
+	ras_feature->instance = cxl_ps_ctx->instance;
+	ras_feature->scrub_ops = &cxl_ps_scrub_ops;
+	ras_feature->ctx = cxl_ps_ctx;
+
+	return 0;
+}
+
+static int cxl_region_scrub_init(struct cxl_region *cxlr,
+				 struct edac_dev_feature *ras_feature,
+				 u8 scrub_inst)
+{
+	struct cxl_patrol_scrub_context *cxl_ps_ctx;
+	struct cxl_region_params *p = &cxlr->params;
+	struct cxl_feat_entry *feat_entry = NULL;
+	struct cxl_memdev *cxlmd;
+	u8 cap, flags;
+	u16 cycle;
+	int i, rc;
+
+	/*
+	 * The cxl_region_rwsem must be held if the code below is used in a context
+	 * other than when the region is in the probe state, as shown here.
+	 */
+	for (i = 0; i < p->nr_targets; i++) {
+		struct cxl_endpoint_decoder *cxled = p->targets[i];
+
+		cxlmd = cxled_to_memdev(cxled);
+		feat_entry = cxl_feature_info(to_cxlfs(cxlmd->cxlds),
+					      &CXL_FEAT_PATROL_SCRUB_UUID);
+		if (IS_ERR(feat_entry))
+			return -EOPNOTSUPP;
+
+		if (!(le32_to_cpu(feat_entry->flags) &
+		      CXL_FEATURE_F_CHANGEABLE))
+			return -EOPNOTSUPP;
+
+		rc = cxl_mem_scrub_get_attrbs(&cxlmd->cxlds->cxl_mbox, &cap,
+					      &cycle, &flags, NULL);
+		if (rc)
+			return rc;
+
+		cxlmd->scrub_cycle = CXL_GET_SCRUB_CYCLE(cycle);
+		cxlmd->scrub_region_id = CXL_SCRUB_NO_REGION;
+	}
+
+	cxl_ps_ctx = devm_kzalloc(&cxlr->dev, sizeof(*cxl_ps_ctx), GFP_KERNEL);
+	if (!cxl_ps_ctx)
+		return -ENOMEM;
+
+	*cxl_ps_ctx = (struct cxl_patrol_scrub_context){
+		.get_feat_size = le16_to_cpu(feat_entry->get_feat_size),
+		.set_feat_size = le16_to_cpu(feat_entry->set_feat_size),
+		.get_version = feat_entry->get_feat_ver,
+		.set_version = feat_entry->set_feat_ver,
+		.effects = le16_to_cpu(feat_entry->effects),
+		.instance = scrub_inst,
+		.cxlr = cxlr,
+	};
+
+	ras_feature->ft_type = RAS_FEAT_SCRUB;
+	ras_feature->instance = cxl_ps_ctx->instance;
+	ras_feature->scrub_ops = &cxl_ps_scrub_ops;
+	ras_feature->ctx = cxl_ps_ctx;
+
+	return 0;
+}
+
+struct cxl_ecs_context {
+	u16 num_media_frus;
+	u16 get_feat_size;
+	u16 set_feat_size;
+	u8 get_version;
+	u8 set_version;
+	u16 effects;
+	struct cxl_memdev *cxlmd;
+};
+
+/*
+ * See CXL spec rev 3.2 @8.2.10.9.11.2 Table 8-225 DDR5 ECS Control Feature
+ * Readable Attributes.
+ */
+struct cxl_ecs_fru_rd_attrbs {
+	u8 ecs_cap;
+	__le16 ecs_config;
+	u8 ecs_flags;
+} __packed;
+
+struct cxl_ecs_rd_attrbs {
+	u8 ecs_log_cap;
+	struct cxl_ecs_fru_rd_attrbs fru_attrbs[];
+} __packed;
+
+/*
+ * See CXL spec rev 3.2 @8.2.10.9.11.2 Table 8-226 DDR5 ECS Control Feature
+ * Writable Attributes.
+ */
+struct cxl_ecs_fru_wr_attrbs {
+	__le16 ecs_config;
+} __packed;
+
+struct cxl_ecs_wr_attrbs {
+	u8 ecs_log_cap;
+	struct cxl_ecs_fru_wr_attrbs fru_attrbs[];
+} __packed;
+
+#define CXL_ECS_LOG_ENTRY_TYPE_MASK GENMASK(1, 0)
+#define CXL_ECS_REALTIME_REPORT_CAP_MASK BIT(0)
+#define CXL_ECS_THRESHOLD_COUNT_MASK GENMASK(2, 0)
+#define CXL_ECS_COUNT_MODE_MASK BIT(3)
+#define CXL_ECS_RESET_COUNTER_MASK BIT(4)
+#define CXL_ECS_RESET_COUNTER 1
+
+enum {
+	ECS_THRESHOLD_256 = 256,
+	ECS_THRESHOLD_1024 = 1024,
+	ECS_THRESHOLD_4096 = 4096,
+};
+
+enum {
+	ECS_THRESHOLD_IDX_256 = 3,
+	ECS_THRESHOLD_IDX_1024 = 4,
+	ECS_THRESHOLD_IDX_4096 = 5,
+};
+
+static const u16 ecs_supp_threshold[] = {
+	[ECS_THRESHOLD_IDX_256] = 256,
+	[ECS_THRESHOLD_IDX_1024] = 1024,
+	[ECS_THRESHOLD_IDX_4096] = 4096,
+};
+
+enum {
+	ECS_LOG_ENTRY_TYPE_DRAM = 0x0,
+	ECS_LOG_ENTRY_TYPE_MEM_MEDIA_FRU = 0x1,
+};
+
+enum cxl_ecs_count_mode {
+	ECS_MODE_COUNTS_ROWS = 0,
+	ECS_MODE_COUNTS_CODEWORDS = 1,
+};
+
+static int cxl_mem_ecs_get_attrbs(struct device *dev,
+				  struct cxl_ecs_context *cxl_ecs_ctx,
+				  int fru_id, u8 *log_cap, u16 *config)
+{
+	struct cxl_memdev *cxlmd = cxl_ecs_ctx->cxlmd;
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+	struct cxl_ecs_fru_rd_attrbs *fru_rd_attrbs;
+	size_t rd_data_size;
+	size_t data_size;
+
+	rd_data_size = cxl_ecs_ctx->get_feat_size;
+
+	struct cxl_ecs_rd_attrbs *rd_attrbs __free(kvfree) =
+		kvzalloc(rd_data_size, GFP_KERNEL);
+	if (!rd_attrbs)
+		return -ENOMEM;
+
+	data_size = cxl_get_feature(cxl_mbox, &CXL_FEAT_ECS_UUID,
+				    CXL_GET_FEAT_SEL_CURRENT_VALUE, rd_attrbs,
+				    rd_data_size, 0, NULL);
+	if (!data_size)
+		return -EIO;
+
+	fru_rd_attrbs = rd_attrbs->fru_attrbs;
+	*log_cap = rd_attrbs->ecs_log_cap;
+	*config = le16_to_cpu(fru_rd_attrbs[fru_id].ecs_config);
+
+	return 0;
+}
+
+static int cxl_mem_ecs_set_attrbs(struct device *dev,
+				  struct cxl_ecs_context *cxl_ecs_ctx,
+				  int fru_id, u8 log_cap, u16 config)
+{
+	struct cxl_memdev *cxlmd = cxl_ecs_ctx->cxlmd;
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+	struct cxl_ecs_fru_rd_attrbs *fru_rd_attrbs;
+	struct cxl_ecs_fru_wr_attrbs *fru_wr_attrbs;
+	size_t rd_data_size, wr_data_size;
+	u16 num_media_frus, count;
+	size_t data_size;
+
+	num_media_frus = cxl_ecs_ctx->num_media_frus;
+	rd_data_size = cxl_ecs_ctx->get_feat_size;
+	wr_data_size = cxl_ecs_ctx->set_feat_size;
+	struct cxl_ecs_rd_attrbs *rd_attrbs __free(kvfree) =
+		kvzalloc(rd_data_size, GFP_KERNEL);
+	if (!rd_attrbs)
+		return -ENOMEM;
+
+	data_size = cxl_get_feature(cxl_mbox, &CXL_FEAT_ECS_UUID,
+				    CXL_GET_FEAT_SEL_CURRENT_VALUE, rd_attrbs,
+				    rd_data_size, 0, NULL);
+	if (!data_size)
+		return -EIO;
+
+	struct cxl_ecs_wr_attrbs *wr_attrbs __free(kvfree) =
+		kvzalloc(wr_data_size, GFP_KERNEL);
+	if (!wr_attrbs)
+		return -ENOMEM;
+
+	/*
+	 * Fill writable attributes from the current attributes read
+	 * for all the media FRUs.
+	 */
+	fru_rd_attrbs = rd_attrbs->fru_attrbs;
+	fru_wr_attrbs = wr_attrbs->fru_attrbs;
+	wr_attrbs->ecs_log_cap = log_cap;
+	for (count = 0; count < num_media_frus; count++)
+		fru_wr_attrbs[count].ecs_config =
+			fru_rd_attrbs[count].ecs_config;
+
+	fru_wr_attrbs[fru_id].ecs_config = cpu_to_le16(config);
+
+	return cxl_set_feature(cxl_mbox, &CXL_FEAT_ECS_UUID,
+			       cxl_ecs_ctx->set_version, wr_attrbs,
+			       wr_data_size,
+			       CXL_SET_FEAT_FLAG_DATA_SAVED_ACROSS_RESET,
+			       0, NULL);
+}
+
+static u8 cxl_get_ecs_log_entry_type(u8 log_cap, u16 config)
+{
+	return FIELD_GET(CXL_ECS_LOG_ENTRY_TYPE_MASK, log_cap);
+}
+
+static u16 cxl_get_ecs_threshold(u8 log_cap, u16 config)
+{
+	u8 index = FIELD_GET(CXL_ECS_THRESHOLD_COUNT_MASK, config);
+
+	return ecs_supp_threshold[index];
+}
+
+static u8 cxl_get_ecs_count_mode(u8 log_cap, u16 config)
+{
+	return FIELD_GET(CXL_ECS_COUNT_MODE_MASK, config);
+}
+
+#define CXL_ECS_GET_ATTR(attrb)						    \
+	static int cxl_ecs_get_##attrb(struct device *dev, void *drv_data,  \
+				       int fru_id, u32 *val)		    \
+	{								    \
+		struct cxl_ecs_context *ctx = drv_data;			    \
+		u8 log_cap;						    \
+		u16 config;						    \
+		int ret;						    \
+									    \
+		ret = cxl_mem_ecs_get_attrbs(dev, ctx, fru_id, &log_cap,    \
+					     &config);			    \
+		if (ret)						    \
+			return ret;					    \
+									    \
+		*val = cxl_get_ecs_##attrb(log_cap, config);		    \
+									    \
+		return 0;						    \
+	}
+
+CXL_ECS_GET_ATTR(log_entry_type)
+CXL_ECS_GET_ATTR(count_mode)
+CXL_ECS_GET_ATTR(threshold)
+
+static int cxl_set_ecs_log_entry_type(struct device *dev, u8 *log_cap,
+				      u16 *config, u32 val)
+{
+	if (val != ECS_LOG_ENTRY_TYPE_DRAM &&
+	    val != ECS_LOG_ENTRY_TYPE_MEM_MEDIA_FRU)
+		return -EINVAL;
+
+	*log_cap = FIELD_PREP(CXL_ECS_LOG_ENTRY_TYPE_MASK, val);
+
+	return 0;
+}
+
+static int cxl_set_ecs_threshold(struct device *dev, u8 *log_cap, u16 *config,
+				 u32 val)
+{
+	*config &= ~CXL_ECS_THRESHOLD_COUNT_MASK;
+
+	switch (val) {
+	case ECS_THRESHOLD_256:
+		*config |= FIELD_PREP(CXL_ECS_THRESHOLD_COUNT_MASK,
+				      ECS_THRESHOLD_IDX_256);
+		break;
+	case ECS_THRESHOLD_1024:
+		*config |= FIELD_PREP(CXL_ECS_THRESHOLD_COUNT_MASK,
+				      ECS_THRESHOLD_IDX_1024);
+		break;
+	case ECS_THRESHOLD_4096:
+		*config |= FIELD_PREP(CXL_ECS_THRESHOLD_COUNT_MASK,
+				      ECS_THRESHOLD_IDX_4096);
+		break;
+	default:
+		dev_dbg(dev, "Invalid CXL ECS threshold count(%d) to set\n",
+			val);
+		dev_dbg(dev, "Supported ECS threshold counts: %u, %u, %u\n",
+			ECS_THRESHOLD_256, ECS_THRESHOLD_1024,
+			ECS_THRESHOLD_4096);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int cxl_set_ecs_count_mode(struct device *dev, u8 *log_cap, u16 *config,
+				  u32 val)
+{
+	if (val != ECS_MODE_COUNTS_ROWS && val != ECS_MODE_COUNTS_CODEWORDS) {
+		dev_dbg(dev, "Invalid CXL ECS scrub mode(%d) to set\n", val);
+		dev_dbg(dev,
+			"Supported ECS Modes: 0: ECS counts rows with errors,"
+			" 1: ECS counts codewords with errors\n");
+		return -EINVAL;
+	}
+
+	*config &= ~CXL_ECS_COUNT_MODE_MASK;
+	*config |= FIELD_PREP(CXL_ECS_COUNT_MODE_MASK, val);
+
+	return 0;
+}
+
+static int cxl_set_ecs_reset_counter(struct device *dev, u8 *log_cap,
+				     u16 *config, u32 val)
+{
+	if (val != CXL_ECS_RESET_COUNTER)
+		return -EINVAL;
+
+	*config &= ~CXL_ECS_RESET_COUNTER_MASK;
+	*config |= FIELD_PREP(CXL_ECS_RESET_COUNTER_MASK, val);
+
+	return 0;
+}
+
+#define CXL_ECS_SET_ATTR(attrb)						    \
+	static int cxl_ecs_set_##attrb(struct device *dev, void *drv_data,  \
+					int fru_id, u32 val)		    \
+	{								    \
+		struct cxl_ecs_context *ctx = drv_data;			    \
+		u8 log_cap;						    \
+		u16 config;						    \
+		int ret;						    \
+									    \
+		if (!capable(CAP_SYS_RAWIO))				    \
+			return -EPERM;					    \
+									    \
+		ret = cxl_mem_ecs_get_attrbs(dev, ctx, fru_id, &log_cap,    \
+					     &config);			    \
+		if (ret)						    \
+			return ret;					    \
+									    \
+		ret = cxl_set_ecs_##attrb(dev, &log_cap, &config, val);     \
+		if (ret)						    \
+			return ret;					    \
+									    \
+		return cxl_mem_ecs_set_attrbs(dev, ctx, fru_id, log_cap,    \
+					      config);			    \
+	}
+CXL_ECS_SET_ATTR(log_entry_type)
+CXL_ECS_SET_ATTR(count_mode)
+CXL_ECS_SET_ATTR(reset_counter)
+CXL_ECS_SET_ATTR(threshold)
+
+static const struct edac_ecs_ops cxl_ecs_ops = {
+	.get_log_entry_type = cxl_ecs_get_log_entry_type,
+	.set_log_entry_type = cxl_ecs_set_log_entry_type,
+	.get_mode = cxl_ecs_get_count_mode,
+	.set_mode = cxl_ecs_set_count_mode,
+	.reset = cxl_ecs_set_reset_counter,
+	.get_threshold = cxl_ecs_get_threshold,
+	.set_threshold = cxl_ecs_set_threshold,
+};
+
+static int cxl_memdev_ecs_init(struct cxl_memdev *cxlmd,
+			       struct edac_dev_feature *ras_feature)
+{
+	struct cxl_ecs_context *cxl_ecs_ctx;
+	struct cxl_feat_entry *feat_entry;
+	int num_media_frus;
+
+	feat_entry =
+		cxl_feature_info(to_cxlfs(cxlmd->cxlds), &CXL_FEAT_ECS_UUID);
+	if (IS_ERR(feat_entry))
+		return -EOPNOTSUPP;
+
+	if (!(le32_to_cpu(feat_entry->flags) & CXL_FEATURE_F_CHANGEABLE))
+		return -EOPNOTSUPP;
+
+	num_media_frus = (le16_to_cpu(feat_entry->get_feat_size) -
+			  sizeof(struct cxl_ecs_rd_attrbs)) /
+			 sizeof(struct cxl_ecs_fru_rd_attrbs);
+	if (!num_media_frus)
+		return -EOPNOTSUPP;
+
+	cxl_ecs_ctx =
+		devm_kzalloc(&cxlmd->dev, sizeof(*cxl_ecs_ctx), GFP_KERNEL);
+	if (!cxl_ecs_ctx)
+		return -ENOMEM;
+
+	*cxl_ecs_ctx = (struct cxl_ecs_context){
+		.get_feat_size = le16_to_cpu(feat_entry->get_feat_size),
+		.set_feat_size = le16_to_cpu(feat_entry->set_feat_size),
+		.get_version = feat_entry->get_feat_ver,
+		.set_version = feat_entry->set_feat_ver,
+		.effects = le16_to_cpu(feat_entry->effects),
+		.num_media_frus = num_media_frus,
+		.cxlmd = cxlmd,
+	};
+
+	ras_feature->ft_type = RAS_FEAT_ECS;
+	ras_feature->ecs_ops = &cxl_ecs_ops;
+	ras_feature->ctx = cxl_ecs_ctx;
+	ras_feature->ecs_info.num_media_frus = num_media_frus;
+
+	return 0;
+}
+
+/*
+ * Perform Maintenance CXL 3.2 Spec 8.2.10.7.1
+ */
+
+/*
+ * Perform Maintenance input payload
+ * CXL rev 3.2 section 8.2.10.7.1 Table 8-117
+ */
+struct cxl_mbox_maintenance_hdr {
+	u8 op_class;
+	u8 op_subclass;
+} __packed;
+
+static int cxl_perform_maintenance(struct cxl_mailbox *cxl_mbox, u8 class,
+				   u8 subclass, void *data_in,
+				   size_t data_in_size)
+{
+	struct cxl_memdev_maintenance_pi {
+		struct cxl_mbox_maintenance_hdr hdr;
+		u8 data[];
+	} __packed;
+	struct cxl_mbox_cmd mbox_cmd;
+	size_t hdr_size;
+
+	struct cxl_memdev_maintenance_pi *pi __free(kvfree) =
+		kvzalloc(cxl_mbox->payload_size, GFP_KERNEL);
+	if (!pi)
+		return -ENOMEM;
+
+	pi->hdr.op_class = class;
+	pi->hdr.op_subclass = subclass;
+	hdr_size = sizeof(pi->hdr);
+	/*
+	 * Check minimum mbox payload size is available for
+	 * the maintenance data transfer.
+	 */
+	if (hdr_size + data_in_size > cxl_mbox->payload_size)
+		return -ENOMEM;
+
+	memcpy(pi->data, data_in, data_in_size);
+	mbox_cmd = (struct cxl_mbox_cmd){
+		.opcode = CXL_MBOX_OP_DO_MAINTENANCE,
+		.size_in = hdr_size + data_in_size,
+		.payload_in = pi,
+	};
+
+	return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+}
+
+/*
+ * Support for finding a memory operation attributes
+ * are from the current boot or not.
+ */
+
+struct cxl_mem_err_rec {
+	struct xarray rec_gen_media;
+	struct xarray rec_dram;
+};
+
+enum cxl_mem_repair_type {
+	CXL_PPR,
+	CXL_CACHELINE_SPARING,
+	CXL_ROW_SPARING,
+	CXL_BANK_SPARING,
+	CXL_RANK_SPARING,
+	CXL_REPAIR_MAX,
+};
+
+/**
+ * struct cxl_mem_repair_attrbs - CXL memory repair attributes
+ * @dpa: DPA of memory to repair
+ * @nibble_mask: nibble mask, identifies one or more nibbles on the memory bus
+ * @row: row of memory to repair
+ * @column: column of memory to repair
+ * @channel: channel of memory to repair
+ * @sub_channel: sub channel of memory to repair
+ * @rank: rank of memory to repair
+ * @bank_group: bank group of memory to repair
+ * @bank: bank of memory to repair
+ * @repair_type: repair type. For eg. PPR, memory sparing etc.
+ */
+struct cxl_mem_repair_attrbs {
+	u64 dpa;
+	u32 nibble_mask;
+	u32 row;
+	u16 column;
+	u8 channel;
+	u8 sub_channel;
+	u8 rank;
+	u8 bank_group;
+	u8 bank;
+	enum cxl_mem_repair_type repair_type;
+};
+
+static struct cxl_event_gen_media *
+cxl_find_rec_gen_media(struct cxl_memdev *cxlmd,
+		       struct cxl_mem_repair_attrbs *attrbs)
+{
+	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
+	struct cxl_event_gen_media *rec;
+
+	if (!array_rec)
+		return NULL;
+
+	rec = xa_load(&array_rec->rec_gen_media, attrbs->dpa);
+	if (!rec)
+		return NULL;
+
+	if (attrbs->repair_type == CXL_PPR)
+		return rec;
+
+	return NULL;
+}
+
+static struct cxl_event_dram *
+cxl_find_rec_dram(struct cxl_memdev *cxlmd,
+		  struct cxl_mem_repair_attrbs *attrbs)
+{
+	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
+	struct cxl_event_dram *rec;
+	u16 validity_flags;
+
+	if (!array_rec)
+		return NULL;
+
+	rec = xa_load(&array_rec->rec_dram, attrbs->dpa);
+	if (!rec)
+		return NULL;
+
+	validity_flags = get_unaligned_le16(rec->media_hdr.validity_flags);
+	if (!(validity_flags & CXL_DER_VALID_CHANNEL) ||
+	    !(validity_flags & CXL_DER_VALID_RANK))
+		return NULL;
+
+	switch (attrbs->repair_type) {
+	case CXL_PPR:
+		if (!(validity_flags & CXL_DER_VALID_NIBBLE) ||
+		    get_unaligned_le24(rec->nibble_mask) == attrbs->nibble_mask)
+			return rec;
+		break;
+	case CXL_CACHELINE_SPARING:
+		if (!(validity_flags & CXL_DER_VALID_BANK_GROUP) ||
+		    !(validity_flags & CXL_DER_VALID_BANK) ||
+		    !(validity_flags & CXL_DER_VALID_ROW) ||
+		    !(validity_flags & CXL_DER_VALID_COLUMN))
+			return NULL;
+
+		if (rec->media_hdr.channel == attrbs->channel &&
+		    rec->media_hdr.rank == attrbs->rank &&
+		    rec->bank_group == attrbs->bank_group &&
+		    rec->bank == attrbs->bank &&
+		    get_unaligned_le24(rec->row) == attrbs->row &&
+		    get_unaligned_le16(rec->column) == attrbs->column &&
+		    (!(validity_flags & CXL_DER_VALID_NIBBLE) ||
+		     get_unaligned_le24(rec->nibble_mask) ==
+			     attrbs->nibble_mask) &&
+		    (!(validity_flags & CXL_DER_VALID_SUB_CHANNEL) ||
+		     rec->sub_channel == attrbs->sub_channel))
+			return rec;
+		break;
+	case CXL_ROW_SPARING:
+		if (!(validity_flags & CXL_DER_VALID_BANK_GROUP) ||
+		    !(validity_flags & CXL_DER_VALID_BANK) ||
+		    !(validity_flags & CXL_DER_VALID_ROW))
+			return NULL;
+
+		if (rec->media_hdr.channel == attrbs->channel &&
+		    rec->media_hdr.rank == attrbs->rank &&
+		    rec->bank_group == attrbs->bank_group &&
+		    rec->bank == attrbs->bank &&
+		    get_unaligned_le24(rec->row) == attrbs->row &&
+		    (!(validity_flags & CXL_DER_VALID_NIBBLE) ||
+		     get_unaligned_le24(rec->nibble_mask) ==
+			     attrbs->nibble_mask))
+			return rec;
+		break;
+	case CXL_BANK_SPARING:
+		if (!(validity_flags & CXL_DER_VALID_BANK_GROUP) ||
+		    !(validity_flags & CXL_DER_VALID_BANK))
+			return NULL;
+
+		if (rec->media_hdr.channel == attrbs->channel &&
+		    rec->media_hdr.rank == attrbs->rank &&
+		    rec->bank_group == attrbs->bank_group &&
+		    rec->bank == attrbs->bank &&
+		    (!(validity_flags & CXL_DER_VALID_NIBBLE) ||
+		     get_unaligned_le24(rec->nibble_mask) ==
+			     attrbs->nibble_mask))
+			return rec;
+		break;
+	case CXL_RANK_SPARING:
+		if (rec->media_hdr.channel == attrbs->channel &&
+		    rec->media_hdr.rank == attrbs->rank &&
+		    (!(validity_flags & CXL_DER_VALID_NIBBLE) ||
+		     get_unaligned_le24(rec->nibble_mask) ==
+			     attrbs->nibble_mask))
+			return rec;
+		break;
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#define CXL_MAX_STORAGE_DAYS 10
+#define CXL_MAX_STORAGE_TIME_SECS (CXL_MAX_STORAGE_DAYS * 24 * 60 * 60)
+
+static void cxl_del_expired_gmedia_recs(struct xarray *rec_xarray,
+					struct cxl_event_gen_media *cur_rec)
+{
+	u64 cur_ts = le64_to_cpu(cur_rec->media_hdr.hdr.timestamp);
+	struct cxl_event_gen_media *rec;
+	unsigned long index;
+	u64 delta_ts_secs;
+
+	xa_for_each(rec_xarray, index, rec) {
+		delta_ts_secs = (cur_ts -
+			le64_to_cpu(rec->media_hdr.hdr.timestamp)) / 1000000000ULL;
+		if (delta_ts_secs >= CXL_MAX_STORAGE_TIME_SECS) {
+			xa_erase(rec_xarray, index);
+			kfree(rec);
+		}
+	}
+}
+
+static void cxl_del_expired_dram_recs(struct xarray *rec_xarray,
+				      struct cxl_event_dram *cur_rec)
+{
+	u64 cur_ts = le64_to_cpu(cur_rec->media_hdr.hdr.timestamp);
+	struct cxl_event_dram *rec;
+	unsigned long index;
+	u64 delta_secs;
+
+	xa_for_each(rec_xarray, index, rec) {
+		delta_secs = (cur_ts -
+			le64_to_cpu(rec->media_hdr.hdr.timestamp)) / 1000000000ULL;
+		if (delta_secs >= CXL_MAX_STORAGE_TIME_SECS) {
+			xa_erase(rec_xarray, index);
+			kfree(rec);
+		}
+	}
+}
+
+#define CXL_MAX_REC_STORAGE_COUNT 200
+
+static void cxl_del_overflow_old_recs(struct xarray *rec_xarray)
+{
+	void *err_rec;
+	unsigned long index, count = 0;
+
+	xa_for_each(rec_xarray, index, err_rec)
+		count++;
+
+	if (count <= CXL_MAX_REC_STORAGE_COUNT)
+		return;
+
+	count -= CXL_MAX_REC_STORAGE_COUNT;
+	xa_for_each(rec_xarray, index, err_rec) {
+		xa_erase(rec_xarray, index);
+		kfree(err_rec);
+		count--;
+		if (!count)
+			break;
+	}
+}
+
+int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt)
+{
+	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
+	struct cxl_event_gen_media *rec;
+	void *old_rec;
+
+	if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec)
+		return 0;
+
+	rec = kmemdup(&evt->gen_media, sizeof(*rec), GFP_KERNEL);
+	if (!rec)
+		return -ENOMEM;
+
+	old_rec = xa_store(&array_rec->rec_gen_media,
+			   le64_to_cpu(rec->media_hdr.phys_addr), rec,
+			   GFP_KERNEL);
+	if (xa_is_err(old_rec))
+		return xa_err(old_rec);
+
+	kfree(old_rec);
+
+	cxl_del_expired_gmedia_recs(&array_rec->rec_gen_media, rec);
+	cxl_del_overflow_old_recs(&array_rec->rec_gen_media);
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_store_rec_gen_media, "CXL");
+
+int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt)
+{
+	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
+	struct cxl_event_dram *rec;
+	void *old_rec;
+
+	if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec)
+		return 0;
+
+	rec = kmemdup(&evt->dram, sizeof(*rec), GFP_KERNEL);
+	if (!rec)
+		return -ENOMEM;
+
+	old_rec = xa_store(&array_rec->rec_dram,
+			   le64_to_cpu(rec->media_hdr.phys_addr), rec,
+			   GFP_KERNEL);
+	if (xa_is_err(old_rec))
+		return xa_err(old_rec);
+
+	kfree(old_rec);
+
+	cxl_del_expired_dram_recs(&array_rec->rec_dram, rec);
+	cxl_del_overflow_old_recs(&array_rec->rec_dram);
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_store_rec_dram, "CXL");
+
+static bool cxl_is_memdev_memory_online(const struct cxl_memdev *cxlmd)
+{
+	struct cxl_port *port = cxlmd->endpoint;
+
+	if (port && cxl_num_decoders_committed(port))
+		return true;
+
+	return false;
+}
+
+/*
+ * CXL memory sparing control
+ */
+enum cxl_mem_sparing_granularity {
+	CXL_MEM_SPARING_CACHELINE,
+	CXL_MEM_SPARING_ROW,
+	CXL_MEM_SPARING_BANK,
+	CXL_MEM_SPARING_RANK,
+	CXL_MEM_SPARING_MAX
+};
+
+struct cxl_mem_sparing_context {
+	struct cxl_memdev *cxlmd;
+	uuid_t repair_uuid;
+	u16 get_feat_size;
+	u16 set_feat_size;
+	u16 effects;
+	u8 instance;
+	u8 get_version;
+	u8 set_version;
+	u8 op_class;
+	u8 op_subclass;
+	bool cap_safe_when_in_use;
+	bool cap_hard_sparing;
+	bool cap_soft_sparing;
+	u8 channel;
+	u8 rank;
+	u8 bank_group;
+	u32 nibble_mask;
+	u64 dpa;
+	u32 row;
+	u16 column;
+	u8 bank;
+	u8 sub_channel;
+	enum edac_mem_repair_type repair_type;
+	bool persist_mode;
+};
+
+#define CXL_SPARING_RD_CAP_SAFE_IN_USE_MASK BIT(0)
+#define CXL_SPARING_RD_CAP_HARD_SPARING_MASK BIT(1)
+#define CXL_SPARING_RD_CAP_SOFT_SPARING_MASK BIT(2)
+
+#define CXL_SPARING_WR_DEVICE_INITIATED_MASK BIT(0)
+
+#define CXL_SPARING_QUERY_RESOURCE_FLAG BIT(0)
+#define CXL_SET_HARD_SPARING_FLAG BIT(1)
+#define CXL_SPARING_SUB_CHNL_VALID_FLAG BIT(2)
+#define CXL_SPARING_NIB_MASK_VALID_FLAG BIT(3)
+
+#define CXL_GET_SPARING_SAFE_IN_USE(flags) \
+	(FIELD_GET(CXL_SPARING_RD_CAP_SAFE_IN_USE_MASK, \
+		  flags) ^ 1)
+#define CXL_GET_CAP_HARD_SPARING(flags) \
+	FIELD_GET(CXL_SPARING_RD_CAP_HARD_SPARING_MASK, \
+		  flags)
+#define CXL_GET_CAP_SOFT_SPARING(flags) \
+	FIELD_GET(CXL_SPARING_RD_CAP_SOFT_SPARING_MASK, \
+		  flags)
+
+#define CXL_SET_SPARING_QUERY_RESOURCE(val) \
+	FIELD_PREP(CXL_SPARING_QUERY_RESOURCE_FLAG, val)
+#define CXL_SET_HARD_SPARING(val) \
+	FIELD_PREP(CXL_SET_HARD_SPARING_FLAG, val)
+#define CXL_SET_SPARING_SUB_CHNL_VALID(val) \
+	FIELD_PREP(CXL_SPARING_SUB_CHNL_VALID_FLAG, val)
+#define CXL_SET_SPARING_NIB_MASK_VALID(val) \
+	FIELD_PREP(CXL_SPARING_NIB_MASK_VALID_FLAG, val)
+
+/*
+ * See CXL spec rev 3.2 @8.2.10.7.2.3 Table 8-134 Memory Sparing Feature
+ * Readable Attributes.
+ */
+struct cxl_memdev_repair_rd_attrbs_hdr {
+	u8 max_op_latency;
+	__le16 op_cap;
+	__le16 op_mode;
+	u8 op_class;
+	u8 op_subclass;
+	u8 rsvd[9];
+} __packed;
+
+struct cxl_memdev_sparing_rd_attrbs {
+	struct cxl_memdev_repair_rd_attrbs_hdr hdr;
+	u8 rsvd;
+	__le16 restriction_flags;
+} __packed;
+
+/*
+ * See CXL spec rev 3.2 @8.2.10.7.1.4 Table 8-120 Memory Sparing Input Payload.
+ */
+struct cxl_memdev_sparing_in_payload {
+	u8 flags;
+	u8 channel;
+	u8 rank;
+	u8 nibble_mask[3];
+	u8 bank_group;
+	u8 bank;
+	u8 row[3];
+	__le16 column;
+	u8 sub_channel;
+} __packed;
+
+static int
+cxl_mem_sparing_get_attrbs(struct cxl_mem_sparing_context *cxl_sparing_ctx)
+{
+	size_t rd_data_size = sizeof(struct cxl_memdev_sparing_rd_attrbs);
+	struct cxl_memdev *cxlmd = cxl_sparing_ctx->cxlmd;
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+	u16 restriction_flags;
+	size_t data_size;
+	u16 return_code;
+	struct cxl_memdev_sparing_rd_attrbs *rd_attrbs __free(kfree) =
+		kzalloc(rd_data_size, GFP_KERNEL);
+	if (!rd_attrbs)
+		return -ENOMEM;
+
+	data_size = cxl_get_feature(cxl_mbox, &cxl_sparing_ctx->repair_uuid,
+				    CXL_GET_FEAT_SEL_CURRENT_VALUE, rd_attrbs,
+				    rd_data_size, 0, &return_code);
+	if (!data_size)
+		return -EIO;
+
+	cxl_sparing_ctx->op_class = rd_attrbs->hdr.op_class;
+	cxl_sparing_ctx->op_subclass = rd_attrbs->hdr.op_subclass;
+	restriction_flags = le16_to_cpu(rd_attrbs->restriction_flags);
+	cxl_sparing_ctx->cap_safe_when_in_use =
+		CXL_GET_SPARING_SAFE_IN_USE(restriction_flags);
+	cxl_sparing_ctx->cap_hard_sparing =
+		CXL_GET_CAP_HARD_SPARING(restriction_flags);
+	cxl_sparing_ctx->cap_soft_sparing =
+		CXL_GET_CAP_SOFT_SPARING(restriction_flags);
+
+	return 0;
+}
+
+static struct cxl_event_dram *
+cxl_mem_get_rec_dram(struct cxl_memdev *cxlmd,
+		     struct cxl_mem_sparing_context *ctx)
+{
+	struct cxl_mem_repair_attrbs attrbs = { 0 };
+
+	attrbs.dpa = ctx->dpa;
+	attrbs.channel = ctx->channel;
+	attrbs.rank = ctx->rank;
+	attrbs.nibble_mask = ctx->nibble_mask;
+	switch (ctx->repair_type) {
+	case EDAC_REPAIR_CACHELINE_SPARING:
+		attrbs.repair_type = CXL_CACHELINE_SPARING;
+		attrbs.bank_group = ctx->bank_group;
+		attrbs.bank = ctx->bank;
+		attrbs.row = ctx->row;
+		attrbs.column = ctx->column;
+		attrbs.sub_channel = ctx->sub_channel;
+		break;
+	case EDAC_REPAIR_ROW_SPARING:
+		attrbs.repair_type = CXL_ROW_SPARING;
+		attrbs.bank_group = ctx->bank_group;
+		attrbs.bank = ctx->bank;
+		attrbs.row = ctx->row;
+		break;
+	case EDAC_REPAIR_BANK_SPARING:
+		attrbs.repair_type = CXL_BANK_SPARING;
+		attrbs.bank_group = ctx->bank_group;
+		attrbs.bank = ctx->bank;
+	break;
+	case EDAC_REPAIR_RANK_SPARING:
+		attrbs.repair_type = CXL_BANK_SPARING;
+		break;
+	default:
+		return NULL;
+	}
+
+	return cxl_find_rec_dram(cxlmd, &attrbs);
+}
+
+static int
+cxl_mem_perform_sparing(struct device *dev,
+			struct cxl_mem_sparing_context *cxl_sparing_ctx)
+{
+	struct cxl_memdev *cxlmd = cxl_sparing_ctx->cxlmd;
+	struct cxl_memdev_sparing_in_payload sparing_pi;
+	struct cxl_event_dram *rec = NULL;
+	u16 validity_flags = 0;
+
+	struct rw_semaphore *region_lock __free(rwsem_read_release) =
+		rwsem_read_intr_acquire(&cxl_region_rwsem);
+	if (!region_lock)
+		return -EINTR;
+
+	struct rw_semaphore *dpa_lock __free(rwsem_read_release) =
+		rwsem_read_intr_acquire(&cxl_dpa_rwsem);
+	if (!dpa_lock)
+		return -EINTR;
+
+	if (!cxl_sparing_ctx->cap_safe_when_in_use) {
+		/* Memory to repair must be offline */
+		if (cxl_is_memdev_memory_online(cxlmd))
+			return -EBUSY;
+	} else {
+		if (cxl_is_memdev_memory_online(cxlmd)) {
+			rec = cxl_mem_get_rec_dram(cxlmd, cxl_sparing_ctx);
+			if (!rec)
+				return -EINVAL;
+
+			if (!get_unaligned_le16(rec->media_hdr.validity_flags))
+				return -EINVAL;
+		}
+	}
+
+	memset(&sparing_pi, 0, sizeof(sparing_pi));
+	sparing_pi.flags = CXL_SET_SPARING_QUERY_RESOURCE(0);
+	if (cxl_sparing_ctx->persist_mode)
+		sparing_pi.flags |= CXL_SET_HARD_SPARING(1);
+
+	if (rec)
+		validity_flags = get_unaligned_le16(rec->media_hdr.validity_flags);
+
+	switch (cxl_sparing_ctx->repair_type) {
+	case EDAC_REPAIR_CACHELINE_SPARING:
+		sparing_pi.column = cpu_to_le16(cxl_sparing_ctx->column);
+		if (!rec || (validity_flags & CXL_DER_VALID_SUB_CHANNEL)) {
+			sparing_pi.flags |= CXL_SET_SPARING_SUB_CHNL_VALID(1);
+			sparing_pi.sub_channel = cxl_sparing_ctx->sub_channel;
+		}
+		fallthrough;
+	case EDAC_REPAIR_ROW_SPARING:
+		put_unaligned_le24(cxl_sparing_ctx->row, sparing_pi.row);
+		fallthrough;
+	case EDAC_REPAIR_BANK_SPARING:
+		sparing_pi.bank_group = cxl_sparing_ctx->bank_group;
+		sparing_pi.bank = cxl_sparing_ctx->bank;
+		fallthrough;
+	case EDAC_REPAIR_RANK_SPARING:
+		sparing_pi.rank = cxl_sparing_ctx->rank;
+		fallthrough;
+	default:
+		sparing_pi.channel = cxl_sparing_ctx->channel;
+		if ((rec && (validity_flags & CXL_DER_VALID_NIBBLE)) ||
+		    (!rec && (!cxl_sparing_ctx->nibble_mask ||
+			     (cxl_sparing_ctx->nibble_mask & 0xFFFFFF)))) {
+			sparing_pi.flags |= CXL_SET_SPARING_NIB_MASK_VALID(1);
+			put_unaligned_le24(cxl_sparing_ctx->nibble_mask,
+					   sparing_pi.nibble_mask);
+		}
+		break;
+	}
+
+	return cxl_perform_maintenance(&cxlmd->cxlds->cxl_mbox,
+				       cxl_sparing_ctx->op_class,
+				       cxl_sparing_ctx->op_subclass,
+				       &sparing_pi, sizeof(sparing_pi));
+}
+
+static int cxl_mem_sparing_get_repair_type(struct device *dev, void *drv_data,
+					   const char **repair_type)
+{
+	struct cxl_mem_sparing_context *ctx = drv_data;
+
+	switch (ctx->repair_type) {
+	case EDAC_REPAIR_CACHELINE_SPARING:
+	case EDAC_REPAIR_ROW_SPARING:
+	case EDAC_REPAIR_BANK_SPARING:
+	case EDAC_REPAIR_RANK_SPARING:
+		*repair_type = edac_repair_type[ctx->repair_type];
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#define CXL_SPARING_GET_ATTR(attrb, data_type)			    \
+	static int cxl_mem_sparing_get_##attrb(			    \
+		struct device *dev, void *drv_data, data_type *val) \
+	{							    \
+		struct cxl_mem_sparing_context *ctx = drv_data;	    \
+								    \
+		*val = ctx->attrb;				    \
+								    \
+		return 0;					    \
+	}
+CXL_SPARING_GET_ATTR(persist_mode, bool)
+CXL_SPARING_GET_ATTR(dpa, u64)
+CXL_SPARING_GET_ATTR(nibble_mask, u32)
+CXL_SPARING_GET_ATTR(bank_group, u32)
+CXL_SPARING_GET_ATTR(bank, u32)
+CXL_SPARING_GET_ATTR(rank, u32)
+CXL_SPARING_GET_ATTR(row, u32)
+CXL_SPARING_GET_ATTR(column, u32)
+CXL_SPARING_GET_ATTR(channel, u32)
+CXL_SPARING_GET_ATTR(sub_channel, u32)
+
+#define CXL_SPARING_SET_ATTR(attrb, data_type)					\
+	static int cxl_mem_sparing_set_##attrb(struct device *dev,		\
+						void *drv_data, data_type val)	\
+	{									\
+		struct cxl_mem_sparing_context *ctx = drv_data;			\
+										\
+		ctx->attrb = val;						\
+										\
+		return 0;							\
+	}
+CXL_SPARING_SET_ATTR(nibble_mask, u32)
+CXL_SPARING_SET_ATTR(bank_group, u32)
+CXL_SPARING_SET_ATTR(bank, u32)
+CXL_SPARING_SET_ATTR(rank, u32)
+CXL_SPARING_SET_ATTR(row, u32)
+CXL_SPARING_SET_ATTR(column, u32)
+CXL_SPARING_SET_ATTR(channel, u32)
+CXL_SPARING_SET_ATTR(sub_channel, u32)
+
+static int cxl_mem_sparing_set_persist_mode(struct device *dev, void *drv_data,
+					    bool persist_mode)
+{
+	struct cxl_mem_sparing_context *ctx = drv_data;
+
+	if ((persist_mode && ctx->cap_hard_sparing) ||
+	    (!persist_mode && ctx->cap_soft_sparing))
+		ctx->persist_mode = persist_mode;
+	else
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static int cxl_get_mem_sparing_safe_when_in_use(struct device *dev,
+						void *drv_data, bool *safe)
+{
+	struct cxl_mem_sparing_context *ctx = drv_data;
+
+	*safe = ctx->cap_safe_when_in_use;
+
+	return 0;
+}
+
+static int cxl_mem_sparing_get_min_dpa(struct device *dev, void *drv_data,
+				       u64 *min_dpa)
+{
+	struct cxl_mem_sparing_context *ctx = drv_data;
+	struct cxl_memdev *cxlmd = ctx->cxlmd;
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+
+	*min_dpa = cxlds->dpa_res.start;
+
+	return 0;
+}
+
+static int cxl_mem_sparing_get_max_dpa(struct device *dev, void *drv_data,
+				       u64 *max_dpa)
+{
+	struct cxl_mem_sparing_context *ctx = drv_data;
+	struct cxl_memdev *cxlmd = ctx->cxlmd;
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+
+	*max_dpa = cxlds->dpa_res.end;
+
+	return 0;
+}
+
+static int cxl_mem_sparing_set_dpa(struct device *dev, void *drv_data, u64 dpa)
+{
+	struct cxl_mem_sparing_context *ctx = drv_data;
+	struct cxl_memdev *cxlmd = ctx->cxlmd;
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+
+	if (dpa < cxlds->dpa_res.start || dpa > cxlds->dpa_res.end)
+		return -EINVAL;
+
+	ctx->dpa = dpa;
+
+	return 0;
+}
+
+static int cxl_do_mem_sparing(struct device *dev, void *drv_data, u32 val)
+{
+	struct cxl_mem_sparing_context *ctx = drv_data;
+
+	if (val != EDAC_DO_MEM_REPAIR)
+		return -EINVAL;
+
+	return cxl_mem_perform_sparing(dev, ctx);
+}
+
+#define RANK_OPS                                                             \
+	.get_repair_type = cxl_mem_sparing_get_repair_type,                  \
+	.get_persist_mode = cxl_mem_sparing_get_persist_mode,                \
+	.set_persist_mode = cxl_mem_sparing_set_persist_mode,                \
+	.get_repair_safe_when_in_use = cxl_get_mem_sparing_safe_when_in_use, \
+	.get_min_dpa = cxl_mem_sparing_get_min_dpa,                          \
+	.get_max_dpa = cxl_mem_sparing_get_max_dpa,                          \
+	.get_dpa = cxl_mem_sparing_get_dpa,                                  \
+	.set_dpa = cxl_mem_sparing_set_dpa,                                  \
+	.get_nibble_mask = cxl_mem_sparing_get_nibble_mask,                  \
+	.set_nibble_mask = cxl_mem_sparing_set_nibble_mask,                  \
+	.get_rank = cxl_mem_sparing_get_rank,                                \
+	.set_rank = cxl_mem_sparing_set_rank,                                \
+	.get_channel = cxl_mem_sparing_get_channel,                          \
+	.set_channel = cxl_mem_sparing_set_channel,                          \
+	.do_repair = cxl_do_mem_sparing
+
+#define BANK_OPS                                                    \
+	RANK_OPS, .get_bank_group = cxl_mem_sparing_get_bank_group, \
+		.set_bank_group = cxl_mem_sparing_set_bank_group,   \
+		.get_bank = cxl_mem_sparing_get_bank,               \
+		.set_bank = cxl_mem_sparing_set_bank
+
+#define ROW_OPS                                       \
+	BANK_OPS, .get_row = cxl_mem_sparing_get_row, \
+		.set_row = cxl_mem_sparing_set_row
+
+#define CACHELINE_OPS                                               \
+	ROW_OPS, .get_column = cxl_mem_sparing_get_column,          \
+		.set_column = cxl_mem_sparing_set_column,           \
+		.get_sub_channel = cxl_mem_sparing_get_sub_channel, \
+		.set_sub_channel = cxl_mem_sparing_set_sub_channel
+
+static const struct edac_mem_repair_ops cxl_rank_sparing_ops = {
+	RANK_OPS,
+};
+
+static const struct edac_mem_repair_ops cxl_bank_sparing_ops = {
+	BANK_OPS,
+};
+
+static const struct edac_mem_repair_ops cxl_row_sparing_ops = {
+	ROW_OPS,
+};
+
+static const struct edac_mem_repair_ops cxl_cacheline_sparing_ops = {
+	CACHELINE_OPS,
+};
+
+struct cxl_mem_sparing_desc {
+	const uuid_t repair_uuid;
+	enum edac_mem_repair_type repair_type;
+	const struct edac_mem_repair_ops *repair_ops;
+};
+
+static const struct cxl_mem_sparing_desc mem_sparing_desc[] = {
+	{
+		.repair_uuid = CXL_FEAT_CACHELINE_SPARING_UUID,
+		.repair_type = EDAC_REPAIR_CACHELINE_SPARING,
+		.repair_ops = &cxl_cacheline_sparing_ops,
+	},
+	{
+		.repair_uuid = CXL_FEAT_ROW_SPARING_UUID,
+		.repair_type = EDAC_REPAIR_ROW_SPARING,
+		.repair_ops = &cxl_row_sparing_ops,
+	},
+	{
+		.repair_uuid = CXL_FEAT_BANK_SPARING_UUID,
+		.repair_type = EDAC_REPAIR_BANK_SPARING,
+		.repair_ops = &cxl_bank_sparing_ops,
+	},
+	{
+		.repair_uuid = CXL_FEAT_RANK_SPARING_UUID,
+		.repair_type = EDAC_REPAIR_RANK_SPARING,
+		.repair_ops = &cxl_rank_sparing_ops,
+	},
+};
+
+static int cxl_memdev_sparing_init(struct cxl_memdev *cxlmd,
+				   struct edac_dev_feature *ras_feature,
+				   const struct cxl_mem_sparing_desc *desc,
+				   u8 repair_inst)
+{
+	struct cxl_mem_sparing_context *cxl_sparing_ctx;
+	struct cxl_feat_entry *feat_entry;
+	int ret;
+
+	feat_entry = cxl_feature_info(to_cxlfs(cxlmd->cxlds),
+				      &desc->repair_uuid);
+	if (IS_ERR(feat_entry))
+		return -EOPNOTSUPP;
+
+	if (!(le32_to_cpu(feat_entry->flags) & CXL_FEATURE_F_CHANGEABLE))
+		return -EOPNOTSUPP;
+
+	cxl_sparing_ctx = devm_kzalloc(&cxlmd->dev, sizeof(*cxl_sparing_ctx),
+				       GFP_KERNEL);
+	if (!cxl_sparing_ctx)
+		return -ENOMEM;
+
+	*cxl_sparing_ctx = (struct cxl_mem_sparing_context){
+		.get_feat_size = le16_to_cpu(feat_entry->get_feat_size),
+		.set_feat_size = le16_to_cpu(feat_entry->set_feat_size),
+		.get_version = feat_entry->get_feat_ver,
+		.set_version = feat_entry->set_feat_ver,
+		.effects = le16_to_cpu(feat_entry->effects),
+		.cxlmd = cxlmd,
+		.repair_type = desc->repair_type,
+		.instance = repair_inst++,
+	};
+	uuid_copy(&cxl_sparing_ctx->repair_uuid, &desc->repair_uuid);
+
+	ret = cxl_mem_sparing_get_attrbs(cxl_sparing_ctx);
+	if (ret)
+		return ret;
+
+	if ((cxl_sparing_ctx->cap_soft_sparing &&
+	     cxl_sparing_ctx->cap_hard_sparing) ||
+	    cxl_sparing_ctx->cap_soft_sparing)
+		cxl_sparing_ctx->persist_mode = 0;
+	else if (cxl_sparing_ctx->cap_hard_sparing)
+		cxl_sparing_ctx->persist_mode = 1;
+	else
+		return -EOPNOTSUPP;
+
+	ras_feature->ft_type = RAS_FEAT_MEM_REPAIR;
+	ras_feature->instance = cxl_sparing_ctx->instance;
+	ras_feature->mem_repair_ops = desc->repair_ops;
+	ras_feature->ctx = cxl_sparing_ctx;
+
+	return 0;
+}
+
+/*
+ * CXL memory soft PPR & hard PPR control
+ */
+struct cxl_ppr_context {
+	uuid_t repair_uuid;
+	u8 instance;
+	u16 get_feat_size;
+	u16 set_feat_size;
+	u8 get_version;
+	u8 set_version;
+	u16 effects;
+	u8 op_class;
+	u8 op_subclass;
+	bool cap_dpa;
+	bool cap_nib_mask;
+	bool media_accessible;
+	bool data_retained;
+	struct cxl_memdev *cxlmd;
+	enum edac_mem_repair_type repair_type;
+	bool persist_mode;
+	u64 dpa;
+	u32 nibble_mask;
+};
+
+/*
+ * See CXL rev 3.2 @8.2.10.7.2.1 Table 8-128 sPPR Feature Readable Attributes
+ *
+ * See CXL rev 3.2 @8.2.10.7.2.2 Table 8-131 hPPR Feature Readable Attributes
+ */
+
+#define CXL_PPR_OP_CAP_DEVICE_INITIATED BIT(0)
+#define CXL_PPR_OP_MODE_DEV_INITIATED BIT(0)
+
+#define CXL_PPR_FLAG_DPA_SUPPORT_MASK BIT(0)
+#define CXL_PPR_FLAG_NIB_SUPPORT_MASK BIT(1)
+#define CXL_PPR_FLAG_MEM_SPARING_EV_REC_SUPPORT_MASK BIT(2)
+#define CXL_PPR_FLAG_DEV_INITED_PPR_AT_BOOT_CAP_MASK BIT(3)
+
+#define CXL_PPR_RESTRICTION_FLAG_MEDIA_ACCESSIBLE_MASK BIT(0)
+#define CXL_PPR_RESTRICTION_FLAG_DATA_RETAINED_MASK BIT(2)
+
+#define CXL_PPR_SPARING_EV_REC_EN_MASK BIT(0)
+#define CXL_PPR_DEV_INITED_PPR_AT_BOOT_EN_MASK BIT(1)
+
+#define CXL_PPR_GET_CAP_DPA(flags) \
+	FIELD_GET(CXL_PPR_FLAG_DPA_SUPPORT_MASK, flags)
+#define CXL_PPR_GET_CAP_NIB_MASK(flags) \
+	FIELD_GET(CXL_PPR_FLAG_NIB_SUPPORT_MASK, flags)
+#define CXL_PPR_GET_MEDIA_ACCESSIBLE(restriction_flags) \
+	(FIELD_GET(CXL_PPR_RESTRICTION_FLAG_MEDIA_ACCESSIBLE_MASK, \
+		   restriction_flags) ^ 1)
+#define CXL_PPR_GET_DATA_RETAINED(restriction_flags) \
+	(FIELD_GET(CXL_PPR_RESTRICTION_FLAG_DATA_RETAINED_MASK, \
+		   restriction_flags) ^ 1)
+
+struct cxl_memdev_ppr_rd_attrbs {
+	struct cxl_memdev_repair_rd_attrbs_hdr hdr;
+	u8 ppr_flags;
+	__le16 restriction_flags;
+	u8 ppr_op_mode;
+} __packed;
+
+/*
+ * See CXL rev 3.2 @8.2.10.7.1.2 Table 8-118 sPPR Maintenance Input Payload
+ *
+ * See CXL rev 3.2 @8.2.10.7.1.3 Table 8-119 hPPR Maintenance Input Payload
+ */
+struct cxl_memdev_ppr_maintenance_attrbs {
+	u8 flags;
+	__le64 dpa;
+	u8 nibble_mask[3];
+} __packed;
+
+static int cxl_mem_ppr_get_attrbs(struct cxl_ppr_context *cxl_ppr_ctx)
+{
+	size_t rd_data_size = sizeof(struct cxl_memdev_ppr_rd_attrbs);
+	struct cxl_memdev *cxlmd = cxl_ppr_ctx->cxlmd;
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+	u16 restriction_flags;
+	size_t data_size;
+	u16 return_code;
+
+	struct cxl_memdev_ppr_rd_attrbs *rd_attrbs __free(kfree) =
+		kmalloc(rd_data_size, GFP_KERNEL);
+	if (!rd_attrbs)
+		return -ENOMEM;
+
+	data_size = cxl_get_feature(cxl_mbox, &cxl_ppr_ctx->repair_uuid,
+				    CXL_GET_FEAT_SEL_CURRENT_VALUE, rd_attrbs,
+				    rd_data_size, 0, &return_code);
+	if (!data_size)
+		return -EIO;
+
+	cxl_ppr_ctx->op_class = rd_attrbs->hdr.op_class;
+	cxl_ppr_ctx->op_subclass = rd_attrbs->hdr.op_subclass;
+	cxl_ppr_ctx->cap_dpa = CXL_PPR_GET_CAP_DPA(rd_attrbs->ppr_flags);
+	cxl_ppr_ctx->cap_nib_mask =
+		CXL_PPR_GET_CAP_NIB_MASK(rd_attrbs->ppr_flags);
+
+	restriction_flags = le16_to_cpu(rd_attrbs->restriction_flags);
+	cxl_ppr_ctx->media_accessible =
+		CXL_PPR_GET_MEDIA_ACCESSIBLE(restriction_flags);
+	cxl_ppr_ctx->data_retained =
+		CXL_PPR_GET_DATA_RETAINED(restriction_flags);
+
+	return 0;
+}
+
+static int cxl_mem_perform_ppr(struct cxl_ppr_context *cxl_ppr_ctx)
+{
+	struct cxl_memdev_ppr_maintenance_attrbs maintenance_attrbs;
+	struct cxl_memdev *cxlmd = cxl_ppr_ctx->cxlmd;
+	struct cxl_mem_repair_attrbs attrbs = { 0 };
+
+	struct rw_semaphore *region_lock __free(rwsem_read_release) =
+		rwsem_read_intr_acquire(&cxl_region_rwsem);
+	if (!region_lock)
+		return -EINTR;
+
+	struct rw_semaphore *dpa_lock __free(rwsem_read_release) =
+		rwsem_read_intr_acquire(&cxl_dpa_rwsem);
+	if (!dpa_lock)
+		return -EINTR;
+
+	if (!cxl_ppr_ctx->media_accessible || !cxl_ppr_ctx->data_retained) {
+		/* Memory to repair must be offline */
+		if (cxl_is_memdev_memory_online(cxlmd))
+			return -EBUSY;
+	} else {
+		if (cxl_is_memdev_memory_online(cxlmd)) {
+			/* Check memory to repair is from the current boot */
+			attrbs.repair_type = CXL_PPR;
+			attrbs.dpa = cxl_ppr_ctx->dpa;
+			attrbs.nibble_mask = cxl_ppr_ctx->nibble_mask;
+			if (!cxl_find_rec_dram(cxlmd, &attrbs) &&
+			    !cxl_find_rec_gen_media(cxlmd, &attrbs))
+				return -EINVAL;
+		}
+	}
+
+	memset(&maintenance_attrbs, 0, sizeof(maintenance_attrbs));
+	maintenance_attrbs.flags = 0;
+	maintenance_attrbs.dpa = cpu_to_le64(cxl_ppr_ctx->dpa);
+	put_unaligned_le24(cxl_ppr_ctx->nibble_mask,
+			   maintenance_attrbs.nibble_mask);
+
+	return cxl_perform_maintenance(&cxlmd->cxlds->cxl_mbox,
+				       cxl_ppr_ctx->op_class,
+				       cxl_ppr_ctx->op_subclass,
+				       &maintenance_attrbs,
+				       sizeof(maintenance_attrbs));
+}
+
+static int cxl_ppr_get_repair_type(struct device *dev, void *drv_data,
+				   const char **repair_type)
+{
+	*repair_type = edac_repair_type[EDAC_REPAIR_PPR];
+
+	return 0;
+}
+
+static int cxl_ppr_get_persist_mode(struct device *dev, void *drv_data,
+				    bool *persist_mode)
+{
+	struct cxl_ppr_context *cxl_ppr_ctx = drv_data;
+
+	*persist_mode = cxl_ppr_ctx->persist_mode;
+
+	return 0;
+}
+
+static int cxl_get_ppr_safe_when_in_use(struct device *dev, void *drv_data,
+					bool *safe)
+{
+	struct cxl_ppr_context *cxl_ppr_ctx = drv_data;
+
+	*safe = cxl_ppr_ctx->media_accessible & cxl_ppr_ctx->data_retained;
+
+	return 0;
+}
+
+static int cxl_ppr_get_min_dpa(struct device *dev, void *drv_data, u64 *min_dpa)
+{
+	struct cxl_ppr_context *cxl_ppr_ctx = drv_data;
+	struct cxl_memdev *cxlmd = cxl_ppr_ctx->cxlmd;
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+
+	*min_dpa = cxlds->dpa_res.start;
+
+	return 0;
+}
+
+static int cxl_ppr_get_max_dpa(struct device *dev, void *drv_data, u64 *max_dpa)
+{
+	struct cxl_ppr_context *cxl_ppr_ctx = drv_data;
+	struct cxl_memdev *cxlmd = cxl_ppr_ctx->cxlmd;
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+
+	*max_dpa = cxlds->dpa_res.end;
+
+	return 0;
+}
+
+static int cxl_ppr_get_dpa(struct device *dev, void *drv_data, u64 *dpa)
+{
+	struct cxl_ppr_context *cxl_ppr_ctx = drv_data;
+
+	*dpa = cxl_ppr_ctx->dpa;
+
+	return 0;
+}
+
+static int cxl_ppr_set_dpa(struct device *dev, void *drv_data, u64 dpa)
+{
+	struct cxl_ppr_context *cxl_ppr_ctx = drv_data;
+	struct cxl_memdev *cxlmd = cxl_ppr_ctx->cxlmd;
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+
+	if (dpa < cxlds->dpa_res.start || dpa > cxlds->dpa_res.end)
+		return -EINVAL;
+
+	cxl_ppr_ctx->dpa = dpa;
+
+	return 0;
+}
+
+static int cxl_ppr_get_nibble_mask(struct device *dev, void *drv_data,
+				   u32 *nibble_mask)
+{
+	struct cxl_ppr_context *cxl_ppr_ctx = drv_data;
+
+	*nibble_mask = cxl_ppr_ctx->nibble_mask;
+
+	return 0;
+}
+
+static int cxl_ppr_set_nibble_mask(struct device *dev, void *drv_data,
+				   u32 nibble_mask)
+{
+	struct cxl_ppr_context *cxl_ppr_ctx = drv_data;
+
+	cxl_ppr_ctx->nibble_mask = nibble_mask;
+
+	return 0;
+}
+
+static int cxl_do_ppr(struct device *dev, void *drv_data, u32 val)
+{
+	struct cxl_ppr_context *cxl_ppr_ctx = drv_data;
+
+	if (!cxl_ppr_ctx->dpa || val != EDAC_DO_MEM_REPAIR)
+		return -EINVAL;
+
+	return cxl_mem_perform_ppr(cxl_ppr_ctx);
+}
+
+static const struct edac_mem_repair_ops cxl_sppr_ops = {
+	.get_repair_type = cxl_ppr_get_repair_type,
+	.get_persist_mode = cxl_ppr_get_persist_mode,
+	.get_repair_safe_when_in_use = cxl_get_ppr_safe_when_in_use,
+	.get_min_dpa = cxl_ppr_get_min_dpa,
+	.get_max_dpa = cxl_ppr_get_max_dpa,
+	.get_dpa = cxl_ppr_get_dpa,
+	.set_dpa = cxl_ppr_set_dpa,
+	.get_nibble_mask = cxl_ppr_get_nibble_mask,
+	.set_nibble_mask = cxl_ppr_set_nibble_mask,
+	.do_repair = cxl_do_ppr,
+};
+
+static int cxl_memdev_soft_ppr_init(struct cxl_memdev *cxlmd,
+				    struct edac_dev_feature *ras_feature,
+				    u8 repair_inst)
+{
+	struct cxl_ppr_context *cxl_sppr_ctx;
+	struct cxl_feat_entry *feat_entry;
+	int ret;
+
+	feat_entry = cxl_feature_info(to_cxlfs(cxlmd->cxlds),
+				      &CXL_FEAT_SPPR_UUID);
+	if (IS_ERR(feat_entry))
+		return -EOPNOTSUPP;
+
+	if (!(le32_to_cpu(feat_entry->flags) & CXL_FEATURE_F_CHANGEABLE))
+		return -EOPNOTSUPP;
+
+	cxl_sppr_ctx =
+		devm_kzalloc(&cxlmd->dev, sizeof(*cxl_sppr_ctx), GFP_KERNEL);
+	if (!cxl_sppr_ctx)
+		return -ENOMEM;
+
+	*cxl_sppr_ctx = (struct cxl_ppr_context){
+		.get_feat_size = le16_to_cpu(feat_entry->get_feat_size),
+		.set_feat_size = le16_to_cpu(feat_entry->set_feat_size),
+		.get_version = feat_entry->get_feat_ver,
+		.set_version = feat_entry->set_feat_ver,
+		.effects = le16_to_cpu(feat_entry->effects),
+		.cxlmd = cxlmd,
+		.repair_type = EDAC_REPAIR_PPR,
+		.persist_mode = 0,
+		.instance = repair_inst,
+	};
+	uuid_copy(&cxl_sppr_ctx->repair_uuid, &CXL_FEAT_SPPR_UUID);
+
+	ret = cxl_mem_ppr_get_attrbs(cxl_sppr_ctx);
+	if (ret)
+		return ret;
+
+	ras_feature->ft_type = RAS_FEAT_MEM_REPAIR;
+	ras_feature->instance = cxl_sppr_ctx->instance;
+	ras_feature->mem_repair_ops = &cxl_sppr_ops;
+	ras_feature->ctx = cxl_sppr_ctx;
+
+	return 0;
+}
+
+int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd)
+{
+	struct edac_dev_feature ras_features[CXL_NR_EDAC_DEV_FEATURES];
+	int num_ras_features = 0;
+	u8 repair_inst = 0;
+	int rc;
+
+	if (IS_ENABLED(CONFIG_CXL_EDAC_SCRUB)) {
+		rc = cxl_memdev_scrub_init(cxlmd, &ras_features[num_ras_features], 0);
+		if (rc < 0 && rc != -EOPNOTSUPP)
+			return rc;
+
+		if (rc != -EOPNOTSUPP)
+			num_ras_features++;
+	}
+
+	if (IS_ENABLED(CONFIG_CXL_EDAC_ECS)) {
+		rc = cxl_memdev_ecs_init(cxlmd, &ras_features[num_ras_features]);
+		if (rc < 0 && rc != -EOPNOTSUPP)
+			return rc;
+
+		if (rc != -EOPNOTSUPP)
+			num_ras_features++;
+	}
+
+	if (IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR)) {
+		for (int i = 0; i < CXL_MEM_SPARING_MAX; i++) {
+			rc = cxl_memdev_sparing_init(cxlmd,
+						     &ras_features[num_ras_features],
+						     &mem_sparing_desc[i], repair_inst);
+			if (rc == -EOPNOTSUPP)
+				continue;
+			if (rc < 0)
+				return rc;
+
+			repair_inst++;
+			num_ras_features++;
+		}
+
+		rc = cxl_memdev_soft_ppr_init(cxlmd, &ras_features[num_ras_features],
+					      repair_inst);
+		if (rc < 0 && rc != -EOPNOTSUPP)
+			return rc;
+
+		if (rc != -EOPNOTSUPP) {
+			repair_inst++;
+			num_ras_features++;
+		}
+
+		if (repair_inst) {
+			struct cxl_mem_err_rec *array_rec =
+				devm_kzalloc(&cxlmd->dev, sizeof(*array_rec),
+					     GFP_KERNEL);
+			if (!array_rec)
+				return -ENOMEM;
+
+			xa_init(&array_rec->rec_gen_media);
+			xa_init(&array_rec->rec_dram);
+			cxlmd->err_rec_array = array_rec;
+		}
+	}
+
+	if (!num_ras_features)
+		return -EINVAL;
+
+	char *cxl_dev_name __free(kfree) =
+		kasprintf(GFP_KERNEL, "cxl_%s", dev_name(&cxlmd->dev));
+	if (!cxl_dev_name)
+		return -ENOMEM;
+
+	return edac_dev_register(&cxlmd->dev, cxl_dev_name, NULL,
+				 num_ras_features, ras_features);
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_memdev_edac_register, "CXL");
+
+int devm_cxl_region_edac_register(struct cxl_region *cxlr)
+{
+	struct edac_dev_feature ras_features[CXL_NR_EDAC_DEV_FEATURES];
+	int num_ras_features = 0;
+	int rc;
+
+	if (!IS_ENABLED(CONFIG_CXL_EDAC_SCRUB))
+		return 0;
+
+	rc = cxl_region_scrub_init(cxlr, &ras_features[num_ras_features], 0);
+	if (rc < 0)
+		return rc;
+
+	num_ras_features++;
+
+	char *cxl_dev_name __free(kfree) =
+		kasprintf(GFP_KERNEL, "cxl_%s", dev_name(&cxlr->dev));
+	if (!cxl_dev_name)
+		return -ENOMEM;
+
+	return edac_dev_register(&cxlr->dev, cxl_dev_name, NULL,
+				 num_ras_features, ras_features);
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_region_edac_register, "CXL");
+
+void devm_cxl_memdev_edac_release(struct cxl_memdev *cxlmd)
+{
+	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
+	struct cxl_event_gen_media *rec_gen_media;
+	struct cxl_event_dram *rec_dram;
+	unsigned long index;
+
+	if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec)
+		return;
+
+	xa_for_each(&array_rec->rec_dram, index, rec_dram)
+		kfree(rec_dram);
+	xa_destroy(&array_rec->rec_dram);
+
+	xa_for_each(&array_rec->rec_gen_media, index, rec_gen_media)
+		kfree(rec_gen_media);
+	xa_destroy(&array_rec->rec_gen_media);
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_memdev_edac_release, "CXL");
diff --git a/drivers/cxl/core/features.c b/drivers/cxl/core/features.c
index 1498e2369c37..6f2eae1eb126 100644
--- a/drivers/cxl/core/features.c
+++ b/drivers/cxl/core/features.c
@@ -9,6 +9,16 @@
 #include "core.h"
 #include "cxlmem.h"
 
+/**
+ * DOC: cxl features
+ *
+ * CXL Features:
+ * A CXL device that includes a mailbox supports commands that allows
+ * listing, getting, and setting of optionally defined features such
+ * as memory sparing or post package sparing. Vendors may define custom
+ * features for the device.
+ */
+
 /* All the features below are exclusive to the kernel */
 static const uuid_t cxl_exclusive_feats[] = {
 	CXL_FEAT_PATROL_SCRUB_UUID,
@@ -36,7 +46,7 @@ static bool is_cxl_feature_exclusive(struct cxl_feat_entry *entry)
 	return is_cxl_feature_exclusive_by_uuid(&entry->uuid);
 }
 
-inline struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds)
+struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds)
 {
 	return cxlds->cxlfs;
 }
@@ -355,17 +365,11 @@ static void cxlctl_close_uctx(struct fwctl_uctx *uctx)
 {
 }
 
-static struct cxl_feat_entry *
-get_support_feature_info(struct cxl_features_state *cxlfs,
-			 const struct fwctl_rpc_cxl *rpc_in)
+struct cxl_feat_entry *
+cxl_feature_info(struct cxl_features_state *cxlfs,
+		 const uuid_t *uuid)
 {
 	struct cxl_feat_entry *feat;
-	const uuid_t *uuid;
-
-	if (rpc_in->op_size < sizeof(uuid))
-		return ERR_PTR(-EINVAL);
-
-	uuid = &rpc_in->set_feat_in.uuid;
 
 	for (int i = 0; i < cxlfs->entries->num_features; i++) {
 		feat = &cxlfs->entries->ent[i];
@@ -416,14 +420,6 @@ static void *cxlctl_get_supported_features(struct cxl_features_state *cxlfs,
 
 	rpc_out->size = struct_size(feat_out, ents, requested);
 	feat_out = &rpc_out->get_sup_feats_out;
-	if (requested == 0) {
-		feat_out->num_entries = cpu_to_le16(requested);
-		feat_out->supported_feats =
-			cpu_to_le16(cxlfs->entries->num_features);
-		rpc_out->retval = CXL_MBOX_CMD_RC_SUCCESS;
-		*out_len = out_size;
-		return no_free_ptr(rpc_out);
-	}
 
 	for (i = start, pos = &feat_out->ents[0];
 	     i < cxlfs->entries->num_features; i++, pos++) {
@@ -547,7 +543,10 @@ static bool cxlctl_validate_set_features(struct cxl_features_state *cxlfs,
 	struct cxl_feat_entry *feat;
 	u32 flags;
 
-	feat = get_support_feature_info(cxlfs, rpc_in);
+	if (rpc_in->op_size < sizeof(uuid_t))
+		return ERR_PTR(-EINVAL);
+
+	feat = cxl_feature_info(cxlfs, &rpc_in->set_feat_in.uuid);
 	if (IS_ERR(feat))
 		return false;
 
@@ -614,11 +613,7 @@ static bool cxlctl_validate_hw_command(struct cxl_features_state *cxlfs,
 	switch (opcode) {
 	case CXL_MBOX_OP_GET_SUPPORTED_FEATURES:
 	case CXL_MBOX_OP_GET_FEATURE:
-		if (cxl_mbox->feat_cap < CXL_FEATURES_RO)
-			return false;
-		if (scope >= FWCTL_RPC_CONFIGURATION)
-			return true;
-		return false;
+		return cxl_mbox->feat_cap >= CXL_FEATURES_RO;
 	case CXL_MBOX_OP_SET_FEATURE:
 		if (cxl_mbox->feat_cap < CXL_FEATURES_RW)
 			return false;
diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index 70cae4ebf8a4..ab1007495f6b 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -34,7 +34,8 @@ static int add_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 	if (rc)
 		return rc;
 
-	dev_dbg(&cxld->dev, "Added to port %s\n", dev_name(&port->dev));
+	dev_dbg(port->uport_dev, "%s added to %s\n",
+		dev_name(&cxld->dev), dev_name(&port->dev));
 
 	return 0;
 }
@@ -603,7 +604,7 @@ int cxl_dpa_set_part(struct cxl_endpoint_decoder *cxled,
 	return 0;
 }
 
-static int __cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size)
+static int __cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, u64 size)
 {
 	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
@@ -666,15 +667,15 @@ static int __cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long lon
 		skip = res->start - skip_start;
 
 	if (size > avail) {
-		dev_dbg(dev, "%pa exceeds available %s capacity: %pa\n", &size,
-			res->name, &avail);
+		dev_dbg(dev, "%llu exceeds available %s capacity: %llu\n", size,
+			res->name, (u64)avail);
 		return -ENOSPC;
 	}
 
 	return __cxl_dpa_reserve(cxled, start, size, skip);
 }
 
-int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size)
+int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, u64 size)
 {
 	struct cxl_port *port = cxled_to_port(cxled);
 	int rc;
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index d72764056ce6..2689e6453c5a 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -922,12 +922,19 @@ void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
 				hpa_alias = hpa - cache_size;
 		}
 
-		if (event_type == CXL_CPER_EVENT_GEN_MEDIA)
+		if (event_type == CXL_CPER_EVENT_GEN_MEDIA) {
+			if (cxl_store_rec_gen_media((struct cxl_memdev *)cxlmd, evt))
+				dev_dbg(&cxlmd->dev, "CXL store rec_gen_media failed\n");
+
 			trace_cxl_general_media(cxlmd, type, cxlr, hpa,
 						hpa_alias, &evt->gen_media);
-		else if (event_type == CXL_CPER_EVENT_DRAM)
+		} else if (event_type == CXL_CPER_EVENT_DRAM) {
+			if (cxl_store_rec_dram((struct cxl_memdev *)cxlmd, evt))
+				dev_dbg(&cxlmd->dev, "CXL store rec_dram failed\n");
+
 			trace_cxl_dram(cxlmd, type, cxlr, hpa, hpa_alias,
 				       &evt->dram);
+		}
 	}
 }
 EXPORT_SYMBOL_NS_GPL(cxl_event_trace_record, "CXL");
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index a16a5886d40a..f88a13adf7fa 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -27,6 +27,7 @@ static void cxl_memdev_release(struct device *dev)
 	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
 
 	ida_free(&cxl_memdev_ida, cxlmd->id);
+	devm_cxl_memdev_edac_release(cxlmd);
 	kfree(cxlmd);
 }
 
@@ -153,8 +154,8 @@ static ssize_t security_state_show(struct device *dev,
 		return sysfs_emit(buf, "frozen\n");
 	if (state & CXL_PMEM_SEC_STATE_LOCKED)
 		return sysfs_emit(buf, "locked\n");
-	else
-		return sysfs_emit(buf, "unlocked\n");
+
+	return sysfs_emit(buf, "unlocked\n");
 }
 static struct device_attribute dev_attr_security_state =
 	__ATTR(state, 0444, security_state_show, NULL);
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 3b80e9a76ba8..b50551601c2e 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -415,17 +415,20 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
 	 */
 	if (global_ctrl & CXL_HDM_DECODER_ENABLE || (!hdm && info->mem_enabled))
 		return devm_cxl_enable_mem(&port->dev, cxlds);
-	else if (!hdm)
-		return -ENODEV;
 
-	root = to_cxl_port(port->dev.parent);
-	while (!is_cxl_root(root) && is_cxl_port(root->dev.parent))
-		root = to_cxl_port(root->dev.parent);
-	if (!is_cxl_root(root)) {
-		dev_err(dev, "Failed to acquire root port for HDM enable\n");
+	/*
+	 * If the HDM Decoder Capability does not exist and DVSEC was
+	 * not setup, the DVSEC based emulation cannot be used.
+	 */
+	if (!hdm)
 		return -ENODEV;
-	}
 
+	/* The HDM Decoder Capability exists but is globally disabled. */
+
+	/*
+	 * If the DVSEC CXL Range registers are not enabled, just
+	 * enable and use the HDM Decoder Capability registers.
+	 */
 	if (!info->mem_enabled) {
 		rc = devm_cxl_enable_hdm(&port->dev, cxlhdm);
 		if (rc)
@@ -434,6 +437,26 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
 		return devm_cxl_enable_mem(&port->dev, cxlds);
 	}
 
+	/*
+	 * Per CXL 2.0 Section 8.1.3.8.3 and 8.1.3.8.4 DVSEC CXL Range 1 Base
+	 * [High,Low] when HDM operation is enabled the range register values
+	 * are ignored by the device, but the spec also recommends matching the
+	 * DVSEC Range 1,2 to HDM Decoder Range 0,1. So, non-zero info->ranges
+	 * are expected even though Linux does not require or maintain that
+	 * match. Check if at least one DVSEC range is enabled and allowed by
+	 * the platform. That is, the DVSEC range must be covered by a locked
+	 * platform window (CFMWS). Fail otherwise as the endpoint's decoders
+	 * cannot be used.
+	 */
+
+	root = to_cxl_port(port->dev.parent);
+	while (!is_cxl_root(root) && is_cxl_port(root->dev.parent))
+		root = to_cxl_port(root->dev.parent);
+	if (!is_cxl_root(root)) {
+		dev_err(dev, "Failed to acquire root port for HDM enable\n");
+		return -ENODEV;
+	}
+
 	for (i = 0, allowed = 0; i < info->ranges; i++) {
 		struct device *cxld_dev;
 
@@ -453,15 +476,6 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
 		return -ENXIO;
 	}
 
-	/*
-	 * Per CXL 2.0 Section 8.1.3.8.3 and 8.1.3.8.4 DVSEC CXL Range 1 Base
-	 * [High,Low] when HDM operation is enabled the range register values
-	 * are ignored by the device, but the spec also recommends matching the
-	 * DVSEC Range 1,2 to HDM Decoder Range 0,1. So, non-zero info->ranges
-	 * are expected even though Linux does not require or maintain that
-	 * match. If at least one DVSEC range is enabled and allowed, skip HDM
-	 * Decoder Capability Enable.
-	 */
 	return 0;
 }
 EXPORT_SYMBOL_NS_GPL(cxl_hdm_decode_init, "CXL");
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 726bd4a7de27..eb46c6764d20 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -602,17 +602,19 @@ struct cxl_port *to_cxl_port(const struct device *dev)
 }
 EXPORT_SYMBOL_NS_GPL(to_cxl_port, "CXL");
 
+struct cxl_port *parent_port_of(struct cxl_port *port)
+{
+	if (!port || !port->parent_dport)
+		return NULL;
+	return port->parent_dport->port;
+}
+
 static void unregister_port(void *_port)
 {
 	struct cxl_port *port = _port;
-	struct cxl_port *parent;
+	struct cxl_port *parent = parent_port_of(port);
 	struct device *lock_dev;
 
-	if (is_cxl_root(port))
-		parent = NULL;
-	else
-		parent = to_cxl_port(port->dev.parent);
-
 	/*
 	 * CXL root port's and the first level of ports are unregistered
 	 * under the platform firmware device lock, all other ports are
@@ -1035,15 +1037,6 @@ struct cxl_root *find_cxl_root(struct cxl_port *port)
 }
 EXPORT_SYMBOL_NS_GPL(find_cxl_root, "CXL");
 
-void put_cxl_root(struct cxl_root *cxl_root)
-{
-	if (!cxl_root)
-		return;
-
-	put_device(&cxl_root->port.dev);
-}
-EXPORT_SYMBOL_NS_GPL(put_cxl_root, "CXL");
-
 static struct cxl_dport *find_dport(struct cxl_port *port, int id)
 {
 	struct cxl_dport *dport;
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index c3f4dc244df7..6e5e1460068d 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -231,11 +231,10 @@ static int cxl_region_invalidate_memregion(struct cxl_region *cxlr)
 				&cxlr->dev,
 				"Bypassing cpu_cache_invalidate_memregion() for testing!\n");
 			return 0;
-		} else {
-			dev_WARN(&cxlr->dev,
-				 "Failed to synchronize CPU cache state\n");
-			return -ENXIO;
 		}
+		dev_WARN(&cxlr->dev,
+			"Failed to synchronize CPU cache state\n");
+		return -ENXIO;
 	}
 
 	cpu_cache_invalidate_memregion(IORES_DESC_CXL);
@@ -865,10 +864,23 @@ static int match_auto_decoder(struct device *dev, const void *data)
 	return 0;
 }
 
+/**
+ * cxl_port_pick_region_decoder() - assign or lookup a decoder for a region
+ * @port: a port in the ancestry of the endpoint implied by @cxled
+ * @cxled: endpoint decoder to be, or currently, mapped by @port
+ * @cxlr: region to establish, or validate, decode @port
+ *
+ * In the region creation path cxl_port_pick_region_decoder() is an
+ * allocator to find a free port. In the region assembly path, it is
+ * recalling the decoder that platform firmware picked for validation
+ * purposes.
+ *
+ * The result is recorded in a 'struct cxl_region_ref' in @port.
+ */
 static struct cxl_decoder *
-cxl_region_find_decoder(struct cxl_port *port,
-			struct cxl_endpoint_decoder *cxled,
-			struct cxl_region *cxlr)
+cxl_port_pick_region_decoder(struct cxl_port *port,
+			     struct cxl_endpoint_decoder *cxled,
+			     struct cxl_region *cxlr)
 {
 	struct device *dev;
 
@@ -916,7 +928,8 @@ static bool auto_order_ok(struct cxl_port *port, struct cxl_region *cxlr_iter,
 
 static struct cxl_region_ref *
 alloc_region_ref(struct cxl_port *port, struct cxl_region *cxlr,
-		 struct cxl_endpoint_decoder *cxled)
+		 struct cxl_endpoint_decoder *cxled,
+		 struct cxl_decoder *cxld)
 {
 	struct cxl_region_params *p = &cxlr->params;
 	struct cxl_region_ref *cxl_rr, *iter;
@@ -930,9 +943,6 @@ alloc_region_ref(struct cxl_port *port, struct cxl_region *cxlr,
 			continue;
 
 		if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
-			struct cxl_decoder *cxld;
-
-			cxld = cxl_region_find_decoder(port, cxled, cxlr);
 			if (auto_order_ok(port, iter->region, cxld))
 				continue;
 		}
@@ -1014,19 +1024,11 @@ static int cxl_rr_ep_add(struct cxl_region_ref *cxl_rr,
 	return 0;
 }
 
-static int cxl_rr_alloc_decoder(struct cxl_port *port, struct cxl_region *cxlr,
-				struct cxl_endpoint_decoder *cxled,
-				struct cxl_region_ref *cxl_rr)
+static int cxl_rr_assign_decoder(struct cxl_port *port, struct cxl_region *cxlr,
+				 struct cxl_endpoint_decoder *cxled,
+				 struct cxl_region_ref *cxl_rr,
+				 struct cxl_decoder *cxld)
 {
-	struct cxl_decoder *cxld;
-
-	cxld = cxl_region_find_decoder(port, cxled, cxlr);
-	if (!cxld) {
-		dev_dbg(&cxlr->dev, "%s: no decoder available\n",
-			dev_name(&port->dev));
-		return -EBUSY;
-	}
-
 	if (cxld->region) {
 		dev_dbg(&cxlr->dev, "%s: %s already attached to %s\n",
 			dev_name(&port->dev), dev_name(&cxld->dev),
@@ -1117,7 +1119,16 @@ static int cxl_port_attach_region(struct cxl_port *port,
 			nr_targets_inc = true;
 		}
 	} else {
-		cxl_rr = alloc_region_ref(port, cxlr, cxled);
+		struct cxl_decoder *cxld;
+
+		cxld = cxl_port_pick_region_decoder(port, cxled, cxlr);
+		if (!cxld) {
+			dev_dbg(&cxlr->dev, "%s: no decoder available\n",
+				dev_name(&port->dev));
+			return -EBUSY;
+		}
+
+		cxl_rr = alloc_region_ref(port, cxlr, cxled, cxld);
 		if (IS_ERR(cxl_rr)) {
 			dev_dbg(&cxlr->dev,
 				"%s: failed to allocate region reference\n",
@@ -1126,7 +1137,7 @@ static int cxl_port_attach_region(struct cxl_port *port,
 		}
 		nr_targets_inc = true;
 
-		rc = cxl_rr_alloc_decoder(port, cxlr, cxled, cxl_rr);
+		rc = cxl_rr_assign_decoder(port, cxlr, cxled, cxl_rr, cxld);
 		if (rc)
 			goto out_erase;
 	}
@@ -1446,7 +1457,7 @@ static int cxl_port_setup_targets(struct cxl_port *port,
 
 	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
 		if (cxld->interleave_ways != iw ||
-		    cxld->interleave_granularity != ig ||
+		    (iw > 1 && cxld->interleave_granularity != ig) ||
 		    !region_res_match_cxl_range(p, &cxld->hpa_range) ||
 		    ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)) {
 			dev_err(&cxlr->dev,
@@ -1748,13 +1759,6 @@ static int cmp_interleave_pos(const void *a, const void *b)
 	return cxled_a->pos - cxled_b->pos;
 }
 
-static struct cxl_port *next_port(struct cxl_port *port)
-{
-	if (!port->parent_dport)
-		return NULL;
-	return port->parent_dport->port;
-}
-
 static int match_switch_decoder_by_range(struct device *dev,
 					 const void *data)
 {
@@ -1781,7 +1785,7 @@ static int find_pos_and_ways(struct cxl_port *port, struct range *range,
 	struct device *dev;
 	int rc = -ENXIO;
 
-	parent = next_port(port);
+	parent = parent_port_of(port);
 	if (!parent)
 		return rc;
 
@@ -1805,6 +1809,13 @@ static int find_pos_and_ways(struct cxl_port *port, struct range *range,
 	}
 	put_device(dev);
 
+	if (rc)
+		dev_err(port->uport_dev,
+			"failed to find %s:%s in target list of %s\n",
+			dev_name(&port->dev),
+			dev_name(port->parent_dport->dport_dev),
+			dev_name(&cxlsd->cxld.dev));
+
 	return rc;
 }
 
@@ -1861,7 +1872,7 @@ static int cxl_calc_interleave_pos(struct cxl_endpoint_decoder *cxled)
 	 */
 
 	/* Iterate from endpoint to root_port refining the position */
-	for (iter = port; iter; iter = next_port(iter)) {
+	for (iter = port; iter; iter = parent_port_of(iter)) {
 		if (is_cxl_root(iter))
 			break;
 
@@ -1940,7 +1951,9 @@ static int cxl_region_attach(struct cxl_region *cxlr,
 	if (p->state > CXL_CONFIG_INTERLEAVE_ACTIVE) {
 		dev_dbg(&cxlr->dev, "region already active\n");
 		return -EBUSY;
-	} else if (p->state < CXL_CONFIG_INTERLEAVE_ACTIVE) {
+	}
+
+	if (p->state < CXL_CONFIG_INTERLEAVE_ACTIVE) {
 		dev_dbg(&cxlr->dev, "interleave config missing\n");
 		return -ENXIO;
 	}
@@ -2160,6 +2173,12 @@ static int attach_target(struct cxl_region *cxlr,
 	rc = cxl_region_attach(cxlr, cxled, pos);
 	up_read(&cxl_dpa_rwsem);
 	up_write(&cxl_region_rwsem);
+
+	if (rc)
+		dev_warn(cxled->cxld.dev.parent,
+			"failed to attach %s to %s: %d\n",
+			dev_name(&cxled->cxld.dev), dev_name(&cxlr->dev), rc);
+
 	return rc;
 }
 
@@ -3196,20 +3215,49 @@ err:
 	return rc;
 }
 
-static int match_root_decoder_by_range(struct device *dev,
-				       const void *data)
+static int match_decoder_by_range(struct device *dev, const void *data)
 {
 	const struct range *r1, *r2 = data;
-	struct cxl_root_decoder *cxlrd;
+	struct cxl_decoder *cxld;
 
-	if (!is_root_decoder(dev))
+	if (!is_switch_decoder(dev))
 		return 0;
 
-	cxlrd = to_cxl_root_decoder(dev);
-	r1 = &cxlrd->cxlsd.cxld.hpa_range;
+	cxld = to_cxl_decoder(dev);
+	r1 = &cxld->hpa_range;
 	return range_contains(r1, r2);
 }
 
+static struct cxl_decoder *
+cxl_port_find_switch_decoder(struct cxl_port *port, struct range *hpa)
+{
+	struct device *cxld_dev = device_find_child(&port->dev, hpa,
+						    match_decoder_by_range);
+
+	return cxld_dev ? to_cxl_decoder(cxld_dev) : NULL;
+}
+
+static struct cxl_root_decoder *
+cxl_find_root_decoder(struct cxl_endpoint_decoder *cxled)
+{
+	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct cxl_port *port = cxled_to_port(cxled);
+	struct cxl_root *cxl_root __free(put_cxl_root) = find_cxl_root(port);
+	struct cxl_decoder *root, *cxld = &cxled->cxld;
+	struct range *hpa = &cxld->hpa_range;
+
+	root = cxl_port_find_switch_decoder(&cxl_root->port, hpa);
+	if (!root) {
+		dev_err(cxlmd->dev.parent,
+			"%s:%s no CXL window for range %#llx:%#llx\n",
+			dev_name(&cxlmd->dev), dev_name(&cxld->dev),
+			cxld->hpa_range.start, cxld->hpa_range.end);
+		return NULL;
+	}
+
+	return to_cxl_root_decoder(&root->dev);
+}
+
 static int match_region_by_range(struct device *dev, const void *data)
 {
 	struct cxl_region_params *p;
@@ -3376,47 +3424,45 @@ static struct cxl_region *construct_region(struct cxl_root_decoder *cxlrd,
 	return cxlr;
 }
 
-int cxl_add_to_region(struct cxl_port *root, struct cxl_endpoint_decoder *cxled)
+static struct cxl_region *
+cxl_find_region_by_range(struct cxl_root_decoder *cxlrd, struct range *hpa)
+{
+	struct device *region_dev;
+
+	region_dev = device_find_child(&cxlrd->cxlsd.cxld.dev, hpa,
+				       match_region_by_range);
+	if (!region_dev)
+		return NULL;
+
+	return to_cxl_region(region_dev);
+}
+
+int cxl_add_to_region(struct cxl_endpoint_decoder *cxled)
 {
-	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
 	struct range *hpa = &cxled->cxld.hpa_range;
-	struct cxl_decoder *cxld = &cxled->cxld;
-	struct device *cxlrd_dev, *region_dev;
-	struct cxl_root_decoder *cxlrd;
 	struct cxl_region_params *p;
-	struct cxl_region *cxlr;
 	bool attach = false;
 	int rc;
 
-	cxlrd_dev = device_find_child(&root->dev, &cxld->hpa_range,
-				      match_root_decoder_by_range);
-	if (!cxlrd_dev) {
-		dev_err(cxlmd->dev.parent,
-			"%s:%s no CXL window for range %#llx:%#llx\n",
-			dev_name(&cxlmd->dev), dev_name(&cxld->dev),
-			cxld->hpa_range.start, cxld->hpa_range.end);
+	struct cxl_root_decoder *cxlrd __free(put_cxl_root_decoder) =
+		cxl_find_root_decoder(cxled);
+	if (!cxlrd)
 		return -ENXIO;
-	}
-
-	cxlrd = to_cxl_root_decoder(cxlrd_dev);
 
 	/*
 	 * Ensure that if multiple threads race to construct_region() for @hpa
 	 * one does the construction and the others add to that.
 	 */
 	mutex_lock(&cxlrd->range_lock);
-	region_dev = device_find_child(&cxlrd->cxlsd.cxld.dev, hpa,
-				       match_region_by_range);
-	if (!region_dev) {
+	struct cxl_region *cxlr __free(put_cxl_region) =
+		cxl_find_region_by_range(cxlrd, hpa);
+	if (!cxlr)
 		cxlr = construct_region(cxlrd, cxled);
-		region_dev = &cxlr->dev;
-	} else
-		cxlr = to_cxl_region(region_dev);
 	mutex_unlock(&cxlrd->range_lock);
 
 	rc = PTR_ERR_OR_ZERO(cxlr);
 	if (rc)
-		goto out;
+		return rc;
 
 	attach_target(cxlr, cxled, -1, TASK_UNINTERRUPTIBLE);
 
@@ -3436,9 +3482,6 @@ int cxl_add_to_region(struct cxl_port *root, struct cxl_endpoint_decoder *cxled)
 				p->res);
 	}
 
-	put_device(region_dev);
-out:
-	put_device(cxlrd_dev);
 	return rc;
 }
 EXPORT_SYMBOL_NS_GPL(cxl_add_to_region, "CXL");
@@ -3537,8 +3580,18 @@ out:
 
 	switch (cxlr->mode) {
 	case CXL_PARTMODE_PMEM:
+		rc = devm_cxl_region_edac_register(cxlr);
+		if (rc)
+			dev_dbg(&cxlr->dev, "CXL EDAC registration for region_id=%d failed\n",
+				cxlr->id);
+
 		return devm_cxl_add_pmem_region(cxlr);
 	case CXL_PARTMODE_RAM:
+		rc = devm_cxl_region_edac_register(cxlr);
+		if (rc)
+			dev_dbg(&cxlr->dev, "CXL EDAC registration for region_id=%d failed\n",
+				cxlr->id);
+
 		/*
 		 * The region can not be manged by CXL if any portion of
 		 * it is already online as 'System RAM'
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index a9ab46eb0610..3f1695c96abc 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -724,6 +724,7 @@ static inline bool is_cxl_root(struct cxl_port *port)
 int cxl_num_decoders_committed(struct cxl_port *port);
 bool is_cxl_port(const struct device *dev);
 struct cxl_port *to_cxl_port(const struct device *dev);
+struct cxl_port *parent_port_of(struct cxl_port *port);
 void cxl_port_commit_reap(struct cxl_decoder *cxld);
 struct pci_bus;
 int devm_cxl_register_pci_bus(struct device *host, struct device *uport_dev,
@@ -736,10 +737,12 @@ struct cxl_port *devm_cxl_add_port(struct device *host,
 struct cxl_root *devm_cxl_add_root(struct device *host,
 				   const struct cxl_root_ops *ops);
 struct cxl_root *find_cxl_root(struct cxl_port *port);
-void put_cxl_root(struct cxl_root *cxl_root);
-DEFINE_FREE(put_cxl_root, struct cxl_root *, if (_T) put_cxl_root(_T))
 
+DEFINE_FREE(put_cxl_root, struct cxl_root *, if (_T) put_device(&_T->port.dev))
 DEFINE_FREE(put_cxl_port, struct cxl_port *, if (!IS_ERR_OR_NULL(_T)) put_device(&_T->dev))
+DEFINE_FREE(put_cxl_root_decoder, struct cxl_root_decoder *, if (!IS_ERR_OR_NULL(_T)) put_device(&_T->cxlsd.cxld.dev))
+DEFINE_FREE(put_cxl_region, struct cxl_region *, if (!IS_ERR_OR_NULL(_T)) put_device(&_T->dev))
+
 int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd);
 void cxl_bus_rescan(void);
 void cxl_bus_drain(void);
@@ -856,8 +859,7 @@ struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_port *port);
 #ifdef CONFIG_CXL_REGION
 bool is_cxl_pmem_region(struct device *dev);
 struct cxl_pmem_region *to_cxl_pmem_region(struct device *dev);
-int cxl_add_to_region(struct cxl_port *root,
-		      struct cxl_endpoint_decoder *cxled);
+int cxl_add_to_region(struct cxl_endpoint_decoder *cxled);
 struct cxl_dax_region *to_cxl_dax_region(struct device *dev);
 u64 cxl_port_get_spa_cache_alias(struct cxl_port *endpoint, u64 spa);
 #else
@@ -869,8 +871,7 @@ static inline struct cxl_pmem_region *to_cxl_pmem_region(struct device *dev)
 {
 	return NULL;
 }
-static inline int cxl_add_to_region(struct cxl_port *root,
-				    struct cxl_endpoint_decoder *cxled)
+static inline int cxl_add_to_region(struct cxl_endpoint_decoder *cxled)
 {
 	return 0;
 }
@@ -912,4 +913,14 @@ bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port);
 
 u16 cxl_gpf_get_dvsec(struct device *dev);
 
+static inline struct rw_semaphore *rwsem_read_intr_acquire(struct rw_semaphore *rwsem)
+{
+	if (down_read_interruptible(rwsem))
+		return NULL;
+
+	return rwsem;
+}
+
+DEFINE_FREE(rwsem_read_release, struct rw_semaphore *, if (_T) up_read(_T))
+
 #endif /* __CXL_H__ */
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index 3ec6b906371b..551b0ba2caa1 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -45,6 +45,11 @@
  * @endpoint: connection to the CXL port topology for this memory device
  * @id: id number of this memdev instance.
  * @depth: endpoint port depth
+ * @scrub_cycle: current scrub cycle set for this device
+ * @scrub_region_id: id number of a backed region (if any) for which current scrub cycle set
+ * @err_rec_array: List of xarrarys to store the memdev error records to
+ *		   check attributes for a memory repair operation are from
+ *		   current boot.
  */
 struct cxl_memdev {
 	struct device dev;
@@ -56,6 +61,9 @@ struct cxl_memdev {
 	struct cxl_port *endpoint;
 	int id;
 	int depth;
+	u8 scrub_cycle;
+	int scrub_region_id;
+	void *err_rec_array;
 };
 
 static inline struct cxl_memdev *to_cxl_memdev(struct device *dev)
@@ -527,6 +535,7 @@ enum cxl_opcode {
 	CXL_MBOX_OP_GET_SUPPORTED_FEATURES	= 0x0500,
 	CXL_MBOX_OP_GET_FEATURE		= 0x0501,
 	CXL_MBOX_OP_SET_FEATURE		= 0x0502,
+	CXL_MBOX_OP_DO_MAINTENANCE	= 0x0600,
 	CXL_MBOX_OP_IDENTIFY		= 0x4000,
 	CXL_MBOX_OP_GET_PARTITION_INFO	= 0x4100,
 	CXL_MBOX_OP_SET_PARTITION_INFO	= 0x4101,
@@ -853,6 +862,27 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd);
 int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa);
 int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa);
 
+#ifdef CONFIG_CXL_EDAC_MEM_FEATURES
+int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd);
+int devm_cxl_region_edac_register(struct cxl_region *cxlr);
+int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt);
+int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt);
+void devm_cxl_memdev_edac_release(struct cxl_memdev *cxlmd);
+#else
+static inline int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd)
+{ return 0; }
+static inline int devm_cxl_region_edac_register(struct cxl_region *cxlr)
+{ return 0; }
+static inline int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd,
+					  union cxl_event *evt)
+{ return 0; }
+static inline int cxl_store_rec_dram(struct cxl_memdev *cxlmd,
+				     union cxl_event *evt)
+{ return 0; }
+static inline void devm_cxl_memdev_edac_release(struct cxl_memdev *cxlmd)
+{ return; }
+#endif
+
 #ifdef CONFIG_CXL_SUSPEND
 void cxl_mem_active_inc(void);
 void cxl_mem_active_dec(void);
diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index 9675243bd05b..6e6777b7bafb 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -180,6 +180,10 @@ static int cxl_mem_probe(struct device *dev)
 			return rc;
 	}
 
+	rc = devm_cxl_memdev_edac_register(cxlmd);
+	if (rc)
+		dev_dbg(dev, "CXL memdev EDAC registration failed rc=%d\n", rc);
+
 	/*
 	 * The kernel may be operating out of CXL memory on this device,
 	 * there is no spec defined way to determine whether this device
diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
index a35fc5552845..fe4b593331da 100644
--- a/drivers/cxl/port.c
+++ b/drivers/cxl/port.c
@@ -30,7 +30,7 @@ static void schedule_detach(void *cxlmd)
 	schedule_cxl_memdev_detach(cxlmd);
 }
 
-static int discover_region(struct device *dev, void *root)
+static int discover_region(struct device *dev, void *unused)
 {
 	struct cxl_endpoint_decoder *cxled;
 	int rc;
@@ -49,7 +49,7 @@ static int discover_region(struct device *dev, void *root)
 	 * Region enumeration is opportunistic, if this add-event fails,
 	 * continue to the next endpoint decoder.
 	 */
-	rc = cxl_add_to_region(root, cxled);
+	rc = cxl_add_to_region(cxled);
 	if (rc)
 		dev_dbg(dev, "failed to add to region: %#llx-%#llx\n",
 			cxled->cxld.hpa_range.start, cxled->cxld.hpa_range.end);
@@ -95,7 +95,6 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
 	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct cxl_hdm *cxlhdm;
-	struct cxl_port *root;
 	int rc;
 
 	rc = cxl_dvsec_rr_decode(cxlds, &info);
@@ -127,18 +126,10 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
 		return rc;
 
 	/*
-	 * This can't fail in practice as CXL root exit unregisters all
-	 * descendant ports and that in turn synchronizes with cxl_port_probe()
-	 */
-	struct cxl_root *cxl_root __free(put_cxl_root) = find_cxl_root(port);
-
-	root = &cxl_root->port;
-
-	/*
 	 * Now that all endpoint decoders are successfully enumerated, try to
 	 * assemble regions from committed decoders
 	 */
-	device_for_each_child(&port->dev, root, discover_region);
+	device_for_each_child(&port->dev, NULL, discover_region);
 
 	return 0;
 }
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index df2d2dc00a05..db87dd2a07f7 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -93,6 +93,14 @@ config APPLE_ADMAC
 	help
 	  Enable support for Audio DMA Controller found on Apple Silicon SoCs.
 
+config ARM_DMA350
+	tristate "Arm DMA-350 support"
+	depends on ARM || ARM64 || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the Arm DMA-350 controller.
+
 config AT_HDMAC
 	tristate "Atmel AHB DMA support"
 	depends on ARCH_AT91
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 19ba465011a6..ba9732644752 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_ALTERA_MSGDMA) += altera-msgdma.o
 obj-$(CONFIG_AMBA_PL08X) += amba-pl08x.o
 obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/
 obj-$(CONFIG_APPLE_ADMAC) += apple-admac.o
+obj-$(CONFIG_ARM_DMA350) += arm-dma350.o
 obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
 obj-$(CONFIG_AT_XDMAC) += at_xdmac.o
 obj-$(CONFIG_AXI_DMAC) += dma-axi-dmac.o
diff --git a/drivers/dma/amd/ptdma/ptdma-dmaengine.c b/drivers/dma/amd/ptdma/ptdma-dmaengine.c
index 81339664036f..628c49ce5de9 100644
--- a/drivers/dma/amd/ptdma/ptdma-dmaengine.c
+++ b/drivers/dma/amd/ptdma/ptdma-dmaengine.c
@@ -566,7 +566,6 @@ int pt_dmaengine_register(struct pt_device *pt)
 	struct ae4_device *ae4 = NULL;
 	struct pt_dma_chan *chan;
 	char *desc_cache_name;
-	char *cmd_cache_name;
 	int ret, i;
 
 	if (pt->ver == AE4_DMA_VERSION)
@@ -582,27 +581,17 @@ int pt_dmaengine_register(struct pt_device *pt)
 	if (!pt->pt_dma_chan)
 		return -ENOMEM;
 
-	cmd_cache_name = devm_kasprintf(pt->dev, GFP_KERNEL,
-					"%s-dmaengine-cmd-cache",
-					dev_name(pt->dev));
-	if (!cmd_cache_name)
-		return -ENOMEM;
-
 	desc_cache_name = devm_kasprintf(pt->dev, GFP_KERNEL,
 					 "%s-dmaengine-desc-cache",
 					 dev_name(pt->dev));
-	if (!desc_cache_name) {
-		ret = -ENOMEM;
-		goto err_cache;
-	}
+	if (!desc_cache_name)
+		return -ENOMEM;
 
 	pt->dma_desc_cache = kmem_cache_create(desc_cache_name,
 					       sizeof(struct pt_dma_desc), 0,
 					       SLAB_HWCACHE_ALIGN, NULL);
-	if (!pt->dma_desc_cache) {
-		ret = -ENOMEM;
-		goto err_cache;
-	}
+	if (!pt->dma_desc_cache)
+		return -ENOMEM;
 
 	dma_dev->dev = pt->dev;
 	dma_dev->src_addr_widths = DMA_SLAVE_BUSWIDTH_64_BYTES;
@@ -656,9 +645,6 @@ int pt_dmaengine_register(struct pt_device *pt)
 err_reg:
 	kmem_cache_destroy(pt->dma_desc_cache);
 
-err_cache:
-	kmem_cache_destroy(pt->dma_cmd_cache);
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(pt_dmaengine_register);
@@ -670,5 +656,4 @@ void pt_dmaengine_unregister(struct pt_device *pt)
 	dma_async_device_unregister(dma_dev);
 
 	kmem_cache_destroy(pt->dma_desc_cache);
-	kmem_cache_destroy(pt->dma_cmd_cache);
 }
diff --git a/drivers/dma/amd/ptdma/ptdma.h b/drivers/dma/amd/ptdma/ptdma.h
index 0a7939105e51..ef3f55632107 100644
--- a/drivers/dma/amd/ptdma/ptdma.h
+++ b/drivers/dma/amd/ptdma/ptdma.h
@@ -254,7 +254,6 @@ struct pt_device {
 	/* Support for the DMA Engine capabilities */
 	struct dma_device dma_dev;
 	struct pt_dma_chan *pt_dma_chan;
-	struct kmem_cache *dma_cmd_cache;
 	struct kmem_cache *dma_desc_cache;
 
 	wait_queue_head_t lsb_queue;
diff --git a/drivers/dma/arm-dma350.c b/drivers/dma/arm-dma350.c
new file mode 100644
index 000000000000..9efe2ca7d5ec
--- /dev/null
+++ b/drivers/dma/arm-dma350.c
@@ -0,0 +1,660 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2024-2025 Arm Limited
+// Arm DMA-350 driver
+
+#include <linux/bitfield.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include "dmaengine.h"
+#include "virt-dma.h"
+
+#define DMAINFO			0x0f00
+
+#define DMA_BUILDCFG0		0xb0
+#define DMA_CFG_DATA_WIDTH	GENMASK(18, 16)
+#define DMA_CFG_ADDR_WIDTH	GENMASK(15, 10)
+#define DMA_CFG_NUM_CHANNELS	GENMASK(9, 4)
+
+#define DMA_BUILDCFG1		0xb4
+#define DMA_CFG_NUM_TRIGGER_IN	GENMASK(8, 0)
+
+#define IIDR			0xc8
+#define IIDR_PRODUCTID		GENMASK(31, 20)
+#define IIDR_VARIANT		GENMASK(19, 16)
+#define IIDR_REVISION		GENMASK(15, 12)
+#define IIDR_IMPLEMENTER	GENMASK(11, 0)
+
+#define PRODUCTID_DMA350	0x3a0
+#define IMPLEMENTER_ARM		0x43b
+
+#define DMACH(n)		(0x1000 + 0x0100 * (n))
+
+#define CH_CMD			0x00
+#define CH_CMD_RESUME		BIT(5)
+#define CH_CMD_PAUSE		BIT(4)
+#define CH_CMD_STOP		BIT(3)
+#define CH_CMD_DISABLE		BIT(2)
+#define CH_CMD_CLEAR		BIT(1)
+#define CH_CMD_ENABLE		BIT(0)
+
+#define CH_STATUS		0x04
+#define CH_STAT_RESUMEWAIT	BIT(21)
+#define CH_STAT_PAUSED		BIT(20)
+#define CH_STAT_STOPPED		BIT(19)
+#define CH_STAT_DISABLED	BIT(18)
+#define CH_STAT_ERR		BIT(17)
+#define CH_STAT_DONE		BIT(16)
+#define CH_STAT_INTR_ERR	BIT(1)
+#define CH_STAT_INTR_DONE	BIT(0)
+
+#define CH_INTREN		0x08
+#define CH_INTREN_ERR		BIT(1)
+#define CH_INTREN_DONE		BIT(0)
+
+#define CH_CTRL			0x0c
+#define CH_CTRL_USEDESTRIGIN	BIT(26)
+#define CH_CTRL_USESRCTRIGIN	BIT(26)
+#define CH_CTRL_DONETYPE	GENMASK(23, 21)
+#define CH_CTRL_REGRELOADTYPE	GENMASK(20, 18)
+#define CH_CTRL_XTYPE		GENMASK(11, 9)
+#define CH_CTRL_TRANSIZE	GENMASK(2, 0)
+
+#define CH_SRCADDR		0x10
+#define CH_SRCADDRHI		0x14
+#define CH_DESADDR		0x18
+#define CH_DESADDRHI		0x1c
+#define CH_XSIZE		0x20
+#define CH_XSIZEHI		0x24
+#define CH_SRCTRANSCFG		0x28
+#define CH_DESTRANSCFG		0x2c
+#define CH_CFG_MAXBURSTLEN	GENMASK(19, 16)
+#define CH_CFG_PRIVATTR		BIT(11)
+#define CH_CFG_SHAREATTR	GENMASK(9, 8)
+#define CH_CFG_MEMATTR		GENMASK(7, 0)
+
+#define TRANSCFG_DEVICE					\
+	FIELD_PREP(CH_CFG_MAXBURSTLEN, 0xf) |		\
+	FIELD_PREP(CH_CFG_SHAREATTR, SHAREATTR_OSH) |	\
+	FIELD_PREP(CH_CFG_MEMATTR, MEMATTR_DEVICE)
+#define TRANSCFG_NC					\
+	FIELD_PREP(CH_CFG_MAXBURSTLEN, 0xf) |		\
+	FIELD_PREP(CH_CFG_SHAREATTR, SHAREATTR_OSH) |	\
+	FIELD_PREP(CH_CFG_MEMATTR, MEMATTR_NC)
+#define TRANSCFG_WB					\
+	FIELD_PREP(CH_CFG_MAXBURSTLEN, 0xf) |		\
+	FIELD_PREP(CH_CFG_SHAREATTR, SHAREATTR_ISH) |	\
+	FIELD_PREP(CH_CFG_MEMATTR, MEMATTR_WB)
+
+#define CH_XADDRINC		0x30
+#define CH_XY_DES		GENMASK(31, 16)
+#define CH_XY_SRC		GENMASK(15, 0)
+
+#define CH_FILLVAL		0x38
+#define CH_SRCTRIGINCFG		0x4c
+#define CH_DESTRIGINCFG		0x50
+#define CH_LINKATTR		0x70
+#define CH_LINK_SHAREATTR	GENMASK(9, 8)
+#define CH_LINK_MEMATTR		GENMASK(7, 0)
+
+#define CH_AUTOCFG		0x74
+#define CH_LINKADDR		0x78
+#define CH_LINKADDR_EN		BIT(0)
+
+#define CH_LINKADDRHI		0x7c
+#define CH_ERRINFO		0x90
+#define CH_ERRINFO_AXIRDPOISERR BIT(18)
+#define CH_ERRINFO_AXIWRRESPERR BIT(17)
+#define CH_ERRINFO_AXIRDRESPERR BIT(16)
+
+#define CH_BUILDCFG0		0xf8
+#define CH_CFG_INC_WIDTH	GENMASK(29, 26)
+#define CH_CFG_DATA_WIDTH	GENMASK(24, 22)
+#define CH_CFG_DATA_BUF_SIZE	GENMASK(7, 0)
+
+#define CH_BUILDCFG1		0xfc
+#define CH_CFG_HAS_CMDLINK	BIT(8)
+#define CH_CFG_HAS_TRIGSEL	BIT(7)
+#define CH_CFG_HAS_TRIGIN	BIT(5)
+#define CH_CFG_HAS_WRAP		BIT(1)
+
+
+#define LINK_REGCLEAR		BIT(0)
+#define LINK_INTREN		BIT(2)
+#define LINK_CTRL		BIT(3)
+#define LINK_SRCADDR		BIT(4)
+#define LINK_SRCADDRHI		BIT(5)
+#define LINK_DESADDR		BIT(6)
+#define LINK_DESADDRHI		BIT(7)
+#define LINK_XSIZE		BIT(8)
+#define LINK_XSIZEHI		BIT(9)
+#define LINK_SRCTRANSCFG	BIT(10)
+#define LINK_DESTRANSCFG	BIT(11)
+#define LINK_XADDRINC		BIT(12)
+#define LINK_FILLVAL		BIT(14)
+#define LINK_SRCTRIGINCFG	BIT(19)
+#define LINK_DESTRIGINCFG	BIT(20)
+#define LINK_AUTOCFG		BIT(29)
+#define LINK_LINKADDR		BIT(30)
+#define LINK_LINKADDRHI		BIT(31)
+
+
+enum ch_ctrl_donetype {
+	CH_CTRL_DONETYPE_NONE = 0,
+	CH_CTRL_DONETYPE_CMD = 1,
+	CH_CTRL_DONETYPE_CYCLE = 3
+};
+
+enum ch_ctrl_xtype {
+	CH_CTRL_XTYPE_DISABLE = 0,
+	CH_CTRL_XTYPE_CONTINUE = 1,
+	CH_CTRL_XTYPE_WRAP = 2,
+	CH_CTRL_XTYPE_FILL = 3
+};
+
+enum ch_cfg_shareattr {
+	SHAREATTR_NSH = 0,
+	SHAREATTR_OSH = 2,
+	SHAREATTR_ISH = 3
+};
+
+enum ch_cfg_memattr {
+	MEMATTR_DEVICE = 0x00,
+	MEMATTR_NC = 0x44,
+	MEMATTR_WB = 0xff
+};
+
+struct d350_desc {
+	struct virt_dma_desc vd;
+	u32 command[16];
+	u16 xsize;
+	u16 xsizehi;
+	u8 tsz;
+};
+
+struct d350_chan {
+	struct virt_dma_chan vc;
+	struct d350_desc *desc;
+	void __iomem *base;
+	int irq;
+	enum dma_status status;
+	dma_cookie_t cookie;
+	u32 residue;
+	u8 tsz;
+	bool has_trig;
+	bool has_wrap;
+	bool coherent;
+};
+
+struct d350 {
+	struct dma_device dma;
+	int nchan;
+	int nreq;
+	struct d350_chan channels[] __counted_by(nchan);
+};
+
+static inline struct d350_chan *to_d350_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct d350_chan, vc.chan);
+}
+
+static inline struct d350_desc *to_d350_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct d350_desc, vd);
+}
+
+static void d350_desc_free(struct virt_dma_desc *vd)
+{
+	kfree(to_d350_desc(vd));
+}
+
+static struct dma_async_tx_descriptor *d350_prep_memcpy(struct dma_chan *chan,
+		dma_addr_t dest, dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	struct d350_desc *desc;
+	u32 *cmd;
+
+	desc = kzalloc(sizeof(*desc), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->tsz = __ffs(len | dest | src | (1 << dch->tsz));
+	desc->xsize = lower_16_bits(len >> desc->tsz);
+	desc->xsizehi = upper_16_bits(len >> desc->tsz);
+
+	cmd = desc->command;
+	cmd[0] = LINK_CTRL | LINK_SRCADDR | LINK_SRCADDRHI | LINK_DESADDR |
+		 LINK_DESADDRHI | LINK_XSIZE | LINK_XSIZEHI | LINK_SRCTRANSCFG |
+		 LINK_DESTRANSCFG | LINK_XADDRINC | LINK_LINKADDR;
+
+	cmd[1] = FIELD_PREP(CH_CTRL_TRANSIZE, desc->tsz) |
+		 FIELD_PREP(CH_CTRL_XTYPE, CH_CTRL_XTYPE_CONTINUE) |
+		 FIELD_PREP(CH_CTRL_DONETYPE, CH_CTRL_DONETYPE_CMD);
+
+	cmd[2] = lower_32_bits(src);
+	cmd[3] = upper_32_bits(src);
+	cmd[4] = lower_32_bits(dest);
+	cmd[5] = upper_32_bits(dest);
+	cmd[6] = FIELD_PREP(CH_XY_SRC, desc->xsize) | FIELD_PREP(CH_XY_DES, desc->xsize);
+	cmd[7] = FIELD_PREP(CH_XY_SRC, desc->xsizehi) | FIELD_PREP(CH_XY_DES, desc->xsizehi);
+	cmd[8] = dch->coherent ? TRANSCFG_WB : TRANSCFG_NC;
+	cmd[9] = dch->coherent ? TRANSCFG_WB : TRANSCFG_NC;
+	cmd[10] = FIELD_PREP(CH_XY_SRC, 1) | FIELD_PREP(CH_XY_DES, 1);
+	cmd[11] = 0;
+
+	return vchan_tx_prep(&dch->vc, &desc->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *d350_prep_memset(struct dma_chan *chan,
+		dma_addr_t dest, int value, size_t len, unsigned long flags)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	struct d350_desc *desc;
+	u32 *cmd;
+
+	desc = kzalloc(sizeof(*desc), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->tsz = __ffs(len | dest | (1 << dch->tsz));
+	desc->xsize = lower_16_bits(len >> desc->tsz);
+	desc->xsizehi = upper_16_bits(len >> desc->tsz);
+
+	cmd = desc->command;
+	cmd[0] = LINK_CTRL | LINK_DESADDR | LINK_DESADDRHI |
+		 LINK_XSIZE | LINK_XSIZEHI | LINK_DESTRANSCFG |
+		 LINK_XADDRINC | LINK_FILLVAL | LINK_LINKADDR;
+
+	cmd[1] = FIELD_PREP(CH_CTRL_TRANSIZE, desc->tsz) |
+		 FIELD_PREP(CH_CTRL_XTYPE, CH_CTRL_XTYPE_FILL) |
+		 FIELD_PREP(CH_CTRL_DONETYPE, CH_CTRL_DONETYPE_CMD);
+
+	cmd[2] = lower_32_bits(dest);
+	cmd[3] = upper_32_bits(dest);
+	cmd[4] = FIELD_PREP(CH_XY_DES, desc->xsize);
+	cmd[5] = FIELD_PREP(CH_XY_DES, desc->xsizehi);
+	cmd[6] = dch->coherent ? TRANSCFG_WB : TRANSCFG_NC;
+	cmd[7] = FIELD_PREP(CH_XY_DES, 1);
+	cmd[8] = (u8)value * 0x01010101;
+	cmd[9] = 0;
+
+	return vchan_tx_prep(&dch->vc, &desc->vd, flags);
+}
+
+static int d350_pause(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dch->vc.lock, flags);
+	if (dch->status == DMA_IN_PROGRESS) {
+		writel_relaxed(CH_CMD_PAUSE, dch->base + CH_CMD);
+		dch->status = DMA_PAUSED;
+	}
+	spin_unlock_irqrestore(&dch->vc.lock, flags);
+
+	return 0;
+}
+
+static int d350_resume(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dch->vc.lock, flags);
+	if (dch->status == DMA_PAUSED) {
+		writel_relaxed(CH_CMD_RESUME, dch->base + CH_CMD);
+		dch->status = DMA_IN_PROGRESS;
+	}
+	spin_unlock_irqrestore(&dch->vc.lock, flags);
+
+	return 0;
+}
+
+static u32 d350_get_residue(struct d350_chan *dch)
+{
+	u32 res, xsize, xsizehi, hi_new;
+	int retries = 3; /* 1st time unlucky, 2nd improbable, 3rd just broken */
+
+	hi_new = readl_relaxed(dch->base + CH_XSIZEHI);
+	do {
+		xsizehi = hi_new;
+		xsize = readl_relaxed(dch->base + CH_XSIZE);
+		hi_new = readl_relaxed(dch->base + CH_XSIZEHI);
+	} while (xsizehi != hi_new && --retries);
+
+	res = FIELD_GET(CH_XY_DES, xsize);
+	res |= FIELD_GET(CH_XY_DES, xsizehi) << 16;
+
+	return res << dch->desc->tsz;
+}
+
+static int d350_terminate_all(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(list);
+
+	spin_lock_irqsave(&dch->vc.lock, flags);
+	writel_relaxed(CH_CMD_STOP, dch->base + CH_CMD);
+	if (dch->desc) {
+		if (dch->status != DMA_ERROR)
+			vchan_terminate_vdesc(&dch->desc->vd);
+		dch->desc = NULL;
+		dch->status = DMA_COMPLETE;
+	}
+	vchan_get_all_descriptors(&dch->vc, &list);
+	list_splice_tail(&list, &dch->vc.desc_terminated);
+	spin_unlock_irqrestore(&dch->vc.lock, flags);
+
+	return 0;
+}
+
+static void d350_synchronize(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+
+	vchan_synchronize(&dch->vc);
+}
+
+static u32 d350_desc_bytes(struct d350_desc *desc)
+{
+	return ((u32)desc->xsizehi << 16 | desc->xsize) << desc->tsz;
+}
+
+static enum dma_status d350_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
+				      struct dma_tx_state *state)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	struct virt_dma_desc *vd;
+	enum dma_status status;
+	unsigned long flags;
+	u32 residue = 0;
+
+	status = dma_cookie_status(chan, cookie, state);
+
+	spin_lock_irqsave(&dch->vc.lock, flags);
+	if (cookie == dch->cookie) {
+		status = dch->status;
+		if (status == DMA_IN_PROGRESS || status == DMA_PAUSED)
+			dch->residue = d350_get_residue(dch);
+		residue = dch->residue;
+	} else if ((vd = vchan_find_desc(&dch->vc, cookie))) {
+		residue = d350_desc_bytes(to_d350_desc(vd));
+	} else if (status == DMA_IN_PROGRESS) {
+		/* Somebody else terminated it? */
+		status = DMA_ERROR;
+	}
+	spin_unlock_irqrestore(&dch->vc.lock, flags);
+
+	dma_set_residue(state, residue);
+	return status;
+}
+
+static void d350_start_next(struct d350_chan *dch)
+{
+	u32 hdr, *reg;
+
+	dch->desc = to_d350_desc(vchan_next_desc(&dch->vc));
+	if (!dch->desc)
+		return;
+
+	list_del(&dch->desc->vd.node);
+	dch->status = DMA_IN_PROGRESS;
+	dch->cookie = dch->desc->vd.tx.cookie;
+	dch->residue = d350_desc_bytes(dch->desc);
+
+	hdr = dch->desc->command[0];
+	reg = &dch->desc->command[1];
+
+	if (hdr & LINK_INTREN)
+		writel_relaxed(*reg++, dch->base + CH_INTREN);
+	if (hdr & LINK_CTRL)
+		writel_relaxed(*reg++, dch->base + CH_CTRL);
+	if (hdr & LINK_SRCADDR)
+		writel_relaxed(*reg++, dch->base + CH_SRCADDR);
+	if (hdr & LINK_SRCADDRHI)
+		writel_relaxed(*reg++, dch->base + CH_SRCADDRHI);
+	if (hdr & LINK_DESADDR)
+		writel_relaxed(*reg++, dch->base + CH_DESADDR);
+	if (hdr & LINK_DESADDRHI)
+		writel_relaxed(*reg++, dch->base + CH_DESADDRHI);
+	if (hdr & LINK_XSIZE)
+		writel_relaxed(*reg++, dch->base + CH_XSIZE);
+	if (hdr & LINK_XSIZEHI)
+		writel_relaxed(*reg++, dch->base + CH_XSIZEHI);
+	if (hdr & LINK_SRCTRANSCFG)
+		writel_relaxed(*reg++, dch->base + CH_SRCTRANSCFG);
+	if (hdr & LINK_DESTRANSCFG)
+		writel_relaxed(*reg++, dch->base + CH_DESTRANSCFG);
+	if (hdr & LINK_XADDRINC)
+		writel_relaxed(*reg++, dch->base + CH_XADDRINC);
+	if (hdr & LINK_FILLVAL)
+		writel_relaxed(*reg++, dch->base + CH_FILLVAL);
+	if (hdr & LINK_SRCTRIGINCFG)
+		writel_relaxed(*reg++, dch->base + CH_SRCTRIGINCFG);
+	if (hdr & LINK_DESTRIGINCFG)
+		writel_relaxed(*reg++, dch->base + CH_DESTRIGINCFG);
+	if (hdr & LINK_AUTOCFG)
+		writel_relaxed(*reg++, dch->base + CH_AUTOCFG);
+	if (hdr & LINK_LINKADDR)
+		writel_relaxed(*reg++, dch->base + CH_LINKADDR);
+	if (hdr & LINK_LINKADDRHI)
+		writel_relaxed(*reg++, dch->base + CH_LINKADDRHI);
+
+	writel(CH_CMD_ENABLE, dch->base + CH_CMD);
+}
+
+static void d350_issue_pending(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dch->vc.lock, flags);
+	if (vchan_issue_pending(&dch->vc) && !dch->desc)
+		d350_start_next(dch);
+	spin_unlock_irqrestore(&dch->vc.lock, flags);
+}
+
+static irqreturn_t d350_irq(int irq, void *data)
+{
+	struct d350_chan *dch = data;
+	struct device *dev = dch->vc.chan.device->dev;
+	struct virt_dma_desc *vd = &dch->desc->vd;
+	u32 ch_status;
+
+	ch_status = readl(dch->base + CH_STATUS);
+	if (!ch_status)
+		return IRQ_NONE;
+
+	if (ch_status & CH_STAT_INTR_ERR) {
+		u32 errinfo = readl_relaxed(dch->base + CH_ERRINFO);
+
+		if (errinfo & (CH_ERRINFO_AXIRDPOISERR | CH_ERRINFO_AXIRDRESPERR))
+			vd->tx_result.result = DMA_TRANS_READ_FAILED;
+		else if (errinfo & CH_ERRINFO_AXIWRRESPERR)
+			vd->tx_result.result = DMA_TRANS_WRITE_FAILED;
+		else
+			vd->tx_result.result = DMA_TRANS_ABORTED;
+
+		vd->tx_result.residue = d350_get_residue(dch);
+	} else if (!(ch_status & CH_STAT_INTR_DONE)) {
+		dev_warn(dev, "Unexpected IRQ source? 0x%08x\n", ch_status);
+	}
+	writel_relaxed(ch_status, dch->base + CH_STATUS);
+
+	spin_lock(&dch->vc.lock);
+	vchan_cookie_complete(vd);
+	if (ch_status & CH_STAT_INTR_DONE) {
+		dch->status = DMA_COMPLETE;
+		dch->residue = 0;
+		d350_start_next(dch);
+	} else {
+		dch->status = DMA_ERROR;
+		dch->residue = vd->tx_result.residue;
+	}
+	spin_unlock(&dch->vc.lock);
+
+	return IRQ_HANDLED;
+}
+
+static int d350_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+	int ret = request_irq(dch->irq, d350_irq, IRQF_SHARED,
+			      dev_name(&dch->vc.chan.dev->device), dch);
+	if (!ret)
+		writel_relaxed(CH_INTREN_DONE | CH_INTREN_ERR, dch->base + CH_INTREN);
+
+	return ret;
+}
+
+static void d350_free_chan_resources(struct dma_chan *chan)
+{
+	struct d350_chan *dch = to_d350_chan(chan);
+
+	writel_relaxed(0, dch->base + CH_INTREN);
+	free_irq(dch->irq, dch);
+	vchan_free_chan_resources(&dch->vc);
+}
+
+static int d350_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct d350 *dmac;
+	void __iomem *base;
+	u32 reg;
+	int ret, nchan, dw, aw, r, p;
+	bool coherent, memset;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	reg = readl_relaxed(base + DMAINFO + IIDR);
+	r = FIELD_GET(IIDR_VARIANT, reg);
+	p = FIELD_GET(IIDR_REVISION, reg);
+	if (FIELD_GET(IIDR_IMPLEMENTER, reg) != IMPLEMENTER_ARM ||
+	    FIELD_GET(IIDR_PRODUCTID, reg) != PRODUCTID_DMA350)
+		return dev_err_probe(dev, -ENODEV, "Not a DMA-350!");
+
+	reg = readl_relaxed(base + DMAINFO + DMA_BUILDCFG0);
+	nchan = FIELD_GET(DMA_CFG_NUM_CHANNELS, reg) + 1;
+	dw = 1 << FIELD_GET(DMA_CFG_DATA_WIDTH, reg);
+	aw = FIELD_GET(DMA_CFG_ADDR_WIDTH, reg) + 1;
+
+	dma_set_mask_and_coherent(dev, DMA_BIT_MASK(aw));
+	coherent = device_get_dma_attr(dev) == DEV_DMA_COHERENT;
+
+	dmac = devm_kzalloc(dev, struct_size(dmac, channels, nchan), GFP_KERNEL);
+	if (!dmac)
+		return -ENOMEM;
+
+	dmac->nchan = nchan;
+
+	reg = readl_relaxed(base + DMAINFO + DMA_BUILDCFG1);
+	dmac->nreq = FIELD_GET(DMA_CFG_NUM_TRIGGER_IN, reg);
+
+	dev_dbg(dev, "DMA-350 r%dp%d with %d channels, %d requests\n", r, p, dmac->nchan, dmac->nreq);
+
+	dmac->dma.dev = dev;
+	for (int i = min(dw, 16); i > 0; i /= 2) {
+		dmac->dma.src_addr_widths |= BIT(i);
+		dmac->dma.dst_addr_widths |= BIT(i);
+	}
+	dmac->dma.directions = BIT(DMA_MEM_TO_MEM);
+	dmac->dma.descriptor_reuse = true;
+	dmac->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+	dmac->dma.device_alloc_chan_resources = d350_alloc_chan_resources;
+	dmac->dma.device_free_chan_resources = d350_free_chan_resources;
+	dma_cap_set(DMA_MEMCPY, dmac->dma.cap_mask);
+	dmac->dma.device_prep_dma_memcpy = d350_prep_memcpy;
+	dmac->dma.device_pause = d350_pause;
+	dmac->dma.device_resume = d350_resume;
+	dmac->dma.device_terminate_all = d350_terminate_all;
+	dmac->dma.device_synchronize = d350_synchronize;
+	dmac->dma.device_tx_status = d350_tx_status;
+	dmac->dma.device_issue_pending = d350_issue_pending;
+	INIT_LIST_HEAD(&dmac->dma.channels);
+
+	/* Would be nice to have per-channel caps for this... */
+	memset = true;
+	for (int i = 0; i < nchan; i++) {
+		struct d350_chan *dch = &dmac->channels[i];
+
+		dch->base = base + DMACH(i);
+		writel_relaxed(CH_CMD_CLEAR, dch->base + CH_CMD);
+
+		reg = readl_relaxed(dch->base + CH_BUILDCFG1);
+		if (!(FIELD_GET(CH_CFG_HAS_CMDLINK, reg))) {
+			dev_warn(dev, "No command link support on channel %d\n", i);
+			continue;
+		}
+		dch->irq = platform_get_irq(pdev, i);
+		if (dch->irq < 0)
+			return dev_err_probe(dev, dch->irq,
+					     "Failed to get IRQ for channel %d\n", i);
+
+		dch->has_wrap = FIELD_GET(CH_CFG_HAS_WRAP, reg);
+		dch->has_trig = FIELD_GET(CH_CFG_HAS_TRIGIN, reg) &
+				FIELD_GET(CH_CFG_HAS_TRIGSEL, reg);
+
+		/* Fill is a special case of Wrap */
+		memset &= dch->has_wrap;
+
+		reg = readl_relaxed(dch->base + CH_BUILDCFG0);
+		dch->tsz = FIELD_GET(CH_CFG_DATA_WIDTH, reg);
+
+		reg = FIELD_PREP(CH_LINK_SHAREATTR, coherent ? SHAREATTR_ISH : SHAREATTR_OSH);
+		reg |= FIELD_PREP(CH_LINK_MEMATTR, coherent ? MEMATTR_WB : MEMATTR_NC);
+		writel_relaxed(reg, dch->base + CH_LINKATTR);
+
+		dch->vc.desc_free = d350_desc_free;
+		vchan_init(&dch->vc, &dmac->dma);
+	}
+
+	if (memset) {
+		dma_cap_set(DMA_MEMSET, dmac->dma.cap_mask);
+		dmac->dma.device_prep_dma_memset = d350_prep_memset;
+	}
+
+	platform_set_drvdata(pdev, dmac);
+
+	ret = dma_async_device_register(&dmac->dma);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to register DMA device\n");
+
+	return 0;
+}
+
+static void d350_remove(struct platform_device *pdev)
+{
+	struct d350 *dmac = platform_get_drvdata(pdev);
+
+	dma_async_device_unregister(&dmac->dma);
+}
+
+static const struct of_device_id d350_of_match[] __maybe_unused = {
+	{ .compatible = "arm,dma-350" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, d350_of_match);
+
+static struct platform_driver d350_driver = {
+	.driver = {
+		.name = "arm-dma350",
+		.of_match_table = of_match_ptr(d350_of_match),
+	},
+	.probe = d350_probe,
+	.remove = d350_remove,
+};
+module_platform_driver(d350_driver);
+
+MODULE_AUTHOR("Robin Murphy <robin.murphy@arm.com>");
+MODULE_DESCRIPTION("Arm DMA-350 driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index ba25c23164e7..3fbc74710a13 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -2033,10 +2033,8 @@ static int at_xdmac_device_terminate_all(struct dma_chan *chan)
 		 * at_xdmac_start_xfer() for this descriptor. Now it's time
 		 * to release it.
 		 */
-		if (desc->active_xfer) {
-			pm_runtime_put_autosuspend(atxdmac->dev);
-			pm_runtime_mark_last_busy(atxdmac->dev);
-		}
+		if (desc->active_xfer)
+			pm_runtime_put_noidle(atxdmac->dev);
 	}
 
 	clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status);
diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c
index 1c6043751dc9..49f09998e5c0 100644
--- a/drivers/dma/dw-edma/dw-edma-pcie.c
+++ b/drivers/dma/dw-edma/dw-edma-pcie.c
@@ -136,7 +136,8 @@ static void dw_edma_pcie_get_vsec_dma_data(struct pci_dev *pdev,
 	map = FIELD_GET(DW_PCIE_VSEC_DMA_MAP, val);
 	if (map != EDMA_MF_EDMA_LEGACY &&
 	    map != EDMA_MF_EDMA_UNROLL &&
-	    map != EDMA_MF_HDMA_COMPAT)
+	    map != EDMA_MF_HDMA_COMPAT &&
+	    map != EDMA_MF_HDMA_NATIVE)
 		return;
 
 	pdata->mf = map;
@@ -291,6 +292,8 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 		pci_dbg(pdev, "Version:\teDMA Unroll (0x%x)\n", chip->mf);
 	else if (chip->mf == EDMA_MF_HDMA_COMPAT)
 		pci_dbg(pdev, "Version:\tHDMA Compatible (0x%x)\n", chip->mf);
+	else if (chip->mf == EDMA_MF_HDMA_NATIVE)
+		pci_dbg(pdev, "Version:\tHDMA Native (0x%x)\n", chip->mf);
 	else
 		pci_dbg(pdev, "Version:\tUnknown (0x%x)\n", chip->mf);
 
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index 443b2430466c..4976d7dde080 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -95,7 +95,7 @@ static void fsl_edma3_enable_request(struct fsl_edma_chan *fsl_chan)
 	}
 
 	val = edma_readl_chreg(fsl_chan, ch_csr);
-	val |= EDMA_V3_CH_CSR_ERQ;
+	val |= EDMA_V3_CH_CSR_ERQ | EDMA_V3_CH_CSR_EEI;
 	edma_writel_chreg(fsl_chan, val, ch_csr);
 }
 
@@ -821,7 +821,7 @@ void fsl_edma_issue_pending(struct dma_chan *chan)
 int fsl_edma_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
-	int ret;
+	int ret = 0;
 
 	if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_HAS_CHCLK)
 		clk_prepare_enable(fsl_chan->clk);
@@ -831,17 +831,29 @@ int fsl_edma_alloc_chan_resources(struct dma_chan *chan)
 				sizeof(struct fsl_edma_hw_tcd64) : sizeof(struct fsl_edma_hw_tcd),
 				32, 0);
 
-	if (fsl_chan->txirq) {
+	if (fsl_chan->txirq)
 		ret = request_irq(fsl_chan->txirq, fsl_chan->irq_handler, IRQF_SHARED,
 				 fsl_chan->chan_name, fsl_chan);
 
-		if (ret) {
-			dma_pool_destroy(fsl_chan->tcd_pool);
-			return ret;
-		}
-	}
+	if (ret)
+		goto err_txirq;
+
+	if (fsl_chan->errirq > 0)
+		ret = request_irq(fsl_chan->errirq, fsl_chan->errirq_handler, IRQF_SHARED,
+				  fsl_chan->errirq_name, fsl_chan);
+
+	if (ret)
+		goto err_errirq;
 
 	return 0;
+
+err_errirq:
+	if (fsl_chan->txirq)
+		free_irq(fsl_chan->txirq, fsl_chan);
+err_txirq:
+	dma_pool_destroy(fsl_chan->tcd_pool);
+
+	return ret;
 }
 
 void fsl_edma_free_chan_resources(struct dma_chan *chan)
@@ -862,6 +874,8 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan)
 
 	if (fsl_chan->txirq)
 		free_irq(fsl_chan->txirq, fsl_chan);
+	if (fsl_chan->errirq)
+		free_irq(fsl_chan->errirq, fsl_chan);
 
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
 	dma_pool_destroy(fsl_chan->tcd_pool);
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index 10a5565ddfd7..205a96489094 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -71,6 +71,18 @@
 #define EDMA_V3_CH_ES_ERR          BIT(31)
 #define EDMA_V3_MP_ES_VLD          BIT(31)
 
+#define EDMA_V3_CH_ERR_DBE	BIT(0)
+#define EDMA_V3_CH_ERR_SBE	BIT(1)
+#define EDMA_V3_CH_ERR_SGE	BIT(2)
+#define EDMA_V3_CH_ERR_NCE	BIT(3)
+#define EDMA_V3_CH_ERR_DOE	BIT(4)
+#define EDMA_V3_CH_ERR_DAE	BIT(5)
+#define EDMA_V3_CH_ERR_SOE	BIT(6)
+#define EDMA_V3_CH_ERR_SAE	BIT(7)
+#define EDMA_V3_CH_ERR_ECX	BIT(8)
+#define EDMA_V3_CH_ERR_UCE	BIT(9)
+#define EDMA_V3_CH_ERR		BIT(31)
+
 enum fsl_edma_pm_state {
 	RUNNING = 0,
 	SUSPENDED,
@@ -162,6 +174,7 @@ struct fsl_edma_chan {
 	u32				dma_dev_size;
 	enum dma_data_direction		dma_dir;
 	char				chan_name[32];
+	char				errirq_name[36];
 	void __iomem			*tcd;
 	void __iomem			*mux_addr;
 	u32				real_count;
@@ -174,7 +187,9 @@ struct fsl_edma_chan {
 	int                             priority;
 	int				hw_chanid;
 	int				txirq;
+	int				errirq;
 	irqreturn_t			(*irq_handler)(int irq, void *dev_id);
+	irqreturn_t			(*errirq_handler)(int irq, void *dev_id);
 	bool				is_rxchan;
 	bool				is_remote;
 	bool				is_multi_fifo;
@@ -208,6 +223,9 @@ struct fsl_edma_desc {
 /* Need clean CHn_CSR DONE before enable TCD's MAJORELINK */
 #define FSL_EDMA_DRV_CLEAR_DONE_E_LINK	BIT(14)
 #define FSL_EDMA_DRV_TCD64		BIT(15)
+/* All channel ERR IRQ share one IRQ line */
+#define FSL_EDMA_DRV_ERRIRQ_SHARE       BIT(16)
+
 
 #define FSL_EDMA_DRV_EDMA3	(FSL_EDMA_DRV_SPLIT_REG |	\
 				 FSL_EDMA_DRV_BUS_8BYTE |	\
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 66bfa28d984e..97583c7d51a2 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -50,6 +50,83 @@ static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static void fsl_edma3_err_check(struct fsl_edma_chan *fsl_chan)
+{
+	unsigned int ch_err;
+	u32 val;
+
+	scoped_guard(spinlock, &fsl_chan->vchan.lock) {
+		ch_err = edma_readl_chreg(fsl_chan, ch_es);
+		if (!(ch_err & EDMA_V3_CH_ERR))
+			return;
+
+		edma_writel_chreg(fsl_chan, EDMA_V3_CH_ERR, ch_es);
+		val = edma_readl_chreg(fsl_chan, ch_csr);
+		val &= ~EDMA_V3_CH_CSR_ERQ;
+		edma_writel_chreg(fsl_chan, val, ch_csr);
+	}
+
+	/* Ignore this interrupt since channel has been disabled already */
+	if (!fsl_chan->edesc)
+		return;
+
+	if (ch_err & EDMA_V3_CH_ERR_DBE)
+		dev_err(&fsl_chan->pdev->dev, "Destination Bus Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_SBE)
+		dev_err(&fsl_chan->pdev->dev, "Source Bus Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_SGE)
+		dev_err(&fsl_chan->pdev->dev, "Scatter/Gather Configuration Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_NCE)
+		dev_err(&fsl_chan->pdev->dev, "NBYTES/CITER Configuration Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_DOE)
+		dev_err(&fsl_chan->pdev->dev, "Destination Offset Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_DAE)
+		dev_err(&fsl_chan->pdev->dev, "Destination Address Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_SOE)
+		dev_err(&fsl_chan->pdev->dev, "Source Offset Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_SAE)
+		dev_err(&fsl_chan->pdev->dev, "Source Address Error interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_ECX)
+		dev_err(&fsl_chan->pdev->dev, "Transfer Canceled interrupt.\n");
+
+	if (ch_err & EDMA_V3_CH_ERR_UCE)
+		dev_err(&fsl_chan->pdev->dev, "Uncorrectable TCD error during channel execution interrupt.\n");
+
+	fsl_chan->status = DMA_ERROR;
+}
+
+static irqreturn_t fsl_edma3_err_handler_per_chan(int irq, void *dev_id)
+{
+	struct fsl_edma_chan *fsl_chan = dev_id;
+
+	fsl_edma3_err_check(fsl_chan);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t fsl_edma3_err_handler_shared(int irq, void *dev_id)
+{
+	struct fsl_edma_engine *fsl_edma = dev_id;
+	unsigned int ch;
+
+	for (ch = 0; ch < fsl_edma->n_chans; ch++) {
+		if (fsl_edma->chan_masked & BIT(ch))
+			continue;
+
+		fsl_edma3_err_check(&fsl_edma->chans[ch]);
+	}
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t fsl_edma3_tx_handler(int irq, void *dev_id)
 {
 	struct fsl_edma_chan *fsl_chan = dev_id;
@@ -309,7 +386,8 @@ fsl_edma_irq_init(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma
 
 static int fsl_edma3_irq_init(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma)
 {
-	int i;
+	char *errirq_name;
+	int i, ret;
 
 	for (i = 0; i < fsl_edma->n_chans; i++) {
 
@@ -324,6 +402,27 @@ static int fsl_edma3_irq_init(struct platform_device *pdev, struct fsl_edma_engi
 			return  -EINVAL;
 
 		fsl_chan->irq_handler = fsl_edma3_tx_handler;
+
+		if (!(fsl_edma->drvdata->flags & FSL_EDMA_DRV_ERRIRQ_SHARE)) {
+			fsl_chan->errirq = fsl_chan->txirq;
+			fsl_chan->errirq_handler = fsl_edma3_err_handler_per_chan;
+		}
+	}
+
+	/* All channel err use one irq number */
+	if (fsl_edma->drvdata->flags & FSL_EDMA_DRV_ERRIRQ_SHARE) {
+		/* last one is error irq */
+		fsl_edma->errirq = platform_get_irq_optional(pdev, fsl_edma->n_chans);
+		if (fsl_edma->errirq < 0)
+			return 0; /* dts miss err irq, treat as no err irq case */
+
+		errirq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s-err",
+					     dev_name(&pdev->dev));
+
+		ret = devm_request_irq(&pdev->dev, fsl_edma->errirq, fsl_edma3_err_handler_shared,
+				       0, errirq_name, fsl_edma);
+		if (ret)
+			return dev_err_probe(&pdev->dev, ret, "Can't register eDMA err IRQ.\n");
 	}
 
 	return 0;
@@ -464,7 +563,8 @@ static struct fsl_edma_drvdata imx7ulp_data = {
 };
 
 static struct fsl_edma_drvdata imx8qm_data = {
-	.flags = FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_MEM_REMOTE,
+	.flags = FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_MEM_REMOTE
+		 | FSL_EDMA_DRV_ERRIRQ_SHARE,
 	.chreg_space_sz = 0x10000,
 	.chreg_off = 0x10000,
 	.setup_irq = fsl_edma3_irq_init,
@@ -481,14 +581,15 @@ static struct fsl_edma_drvdata imx8ulp_data = {
 };
 
 static struct fsl_edma_drvdata imx93_data3 = {
-	.flags = FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA3,
+	.flags = FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_ERRIRQ_SHARE,
 	.chreg_space_sz = 0x10000,
 	.chreg_off = 0x10000,
 	.setup_irq = fsl_edma3_irq_init,
 };
 
 static struct fsl_edma_drvdata imx93_data4 = {
-	.flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4,
+	.flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4
+		 | FSL_EDMA_DRV_ERRIRQ_SHARE,
 	.chreg_space_sz = 0x8000,
 	.chreg_off = 0x10000,
 	.mux_off = 0x10000 + offsetof(struct fsl_edma3_ch_reg, ch_mux),
@@ -498,7 +599,7 @@ static struct fsl_edma_drvdata imx93_data4 = {
 
 static struct fsl_edma_drvdata imx95_data5 = {
 	.flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4 |
-		 FSL_EDMA_DRV_TCD64,
+		 FSL_EDMA_DRV_TCD64 | FSL_EDMA_DRV_ERRIRQ_SHARE,
 	.chreg_space_sz = 0x8000,
 	.chreg_off = 0x10000,
 	.mux_off = 0x200,
@@ -700,6 +801,9 @@ static int fsl_edma_probe(struct platform_device *pdev)
 		snprintf(fsl_chan->chan_name, sizeof(fsl_chan->chan_name), "%s-CH%02d",
 							   dev_name(&pdev->dev), i);
 
+		snprintf(fsl_chan->errirq_name, sizeof(fsl_chan->errirq_name),
+			 "%s-CH%02d-err", dev_name(&pdev->dev), i);
+
 		fsl_chan->edma = fsl_edma;
 		fsl_chan->pm_state = RUNNING;
 		fsl_chan->srcid = 0;
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index b5e7d18b9766..9b126a260267 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -1226,6 +1226,8 @@ static int fsldma_of_probe(struct platform_device *op)
 
 	fdev->dev = &op->dev;
 	INIT_LIST_HEAD(&fdev->common.channels);
+	/* The DMA address bits supported for this device. */
+	fdev->addr_bits = (long)device_get_match_data(fdev->dev);
 
 	/* ioremap the registers for use */
 	fdev->regs = of_iomap(op->dev.of_node, 0);
@@ -1254,7 +1256,7 @@ static int fsldma_of_probe(struct platform_device *op)
 	fdev->common.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	fdev->common.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
 
-	dma_set_mask(&(op->dev), DMA_BIT_MASK(36));
+	dma_set_mask(&(op->dev), DMA_BIT_MASK(fdev->addr_bits));
 
 	platform_set_drvdata(op, fdev);
 
@@ -1387,10 +1389,20 @@ static const struct dev_pm_ops fsldma_pm_ops = {
 };
 #endif
 
+/* The .data field is used for dma-bit-mask. */
 static const struct of_device_id fsldma_of_ids[] = {
-	{ .compatible = "fsl,elo3-dma", },
-	{ .compatible = "fsl,eloplus-dma", },
-	{ .compatible = "fsl,elo-dma", },
+	{
+		.compatible = "fsl,elo3-dma",
+		.data = (void *)40,
+	},
+	{
+		.compatible = "fsl,eloplus-dma",
+		.data = (void *)36,
+	},
+	{
+		.compatible = "fsl,elo-dma",
+		.data = (void *)32,
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(of, fsldma_of_ids);
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index 308bed0a560a..d7b7a3138b85 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -124,6 +124,7 @@ struct fsldma_device {
 	struct fsldma_chan *chan[FSL_DMA_MAX_CHANS_PER_DEVICE];
 	u32 feature;		/* The same as DMA channels */
 	int irq;		/* Channel IRQ */
+	int addr_bits;		/* DMA addressing bits supported */
 };
 
 /* Define macros for fsldma_chan->feature property */
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 6d12033649f8..7e4715f92773 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -349,7 +349,9 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid)
 			set_bit(h, evl->bmap);
 		h = (h + 1) % size;
 	}
-	drain_workqueue(wq->wq);
+	if (wq->wq)
+		drain_workqueue(wq->wq);
+
 	mutex_unlock(&evl->lock);
 }
 
@@ -442,10 +444,12 @@ static int idxd_submit_user_descriptor(struct idxd_user_context *ctx,
 	 * DSA devices are capable of indirect ("batch") command submission.
 	 * On devices where direct user submissions are not safe, we cannot
 	 * allow this since there is no good way for us to verify these
-	 * indirect commands.
+	 * indirect commands. Narrow the restriction of operations with the
+	 * BATCH opcode to only DSA version 1 devices.
 	 */
 	if (is_dsa_dev(idxd_dev) && descriptor.opcode == DSA_OPCODE_BATCH &&
-		!wq->idxd->user_submission_safe)
+	    wq->idxd->hw.version == DEVICE_VERSION_1 &&
+	    !wq->idxd->user_submission_safe)
 		return -EINVAL;
 	/*
 	 * As per the programming specification, the completion address must be
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index 214b8039439f..74e6695881e6 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -19,7 +19,6 @@
 
 #define IDXD_DRIVER_VERSION	"1.00"
 
-extern struct kmem_cache *idxd_desc_pool;
 extern bool tc_override;
 
 struct idxd_wq;
@@ -171,7 +170,6 @@ struct idxd_cdev {
 
 #define DRIVER_NAME_SIZE		128
 
-#define IDXD_ALLOCATED_BATCH_SIZE	128U
 #define WQ_NAME_SIZE   1024
 #define WQ_TYPE_SIZE   10
 
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 6af493f6ba77..9f0701021af0 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -1208,9 +1208,11 @@ static ssize_t op_cap_show_common(struct device *dev, char *buf, unsigned long *
 
 		/* On systems where direct user submissions are not safe, we need to clear out
 		 * the BATCH capability from the capability mask in sysfs since we cannot support
-		 * that command on such systems.
+		 * that command on such systems. Narrow the restriction of operations with the
+		 * BATCH opcode to only DSA version 1 devices.
 		 */
-		if (i == DSA_OPCODE_BATCH/64 && !confdev_to_idxd(dev)->user_submission_safe)
+		if (i == DSA_OPCODE_BATCH/64 && !confdev_to_idxd(dev)->user_submission_safe &&
+		    confdev_to_idxd(dev)->hw.version == DEVICE_VERSION_1)
 			clear_bit(DSA_OPCODE_BATCH % 64, &val);
 
 		pos += sysfs_emit_at(buf, pos, "%*pb", 64, &val);
diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c
index 9235db551026..1f687b08d6b8 100644
--- a/drivers/dma/sh/rz-dmac.c
+++ b/drivers/dma/sh/rz-dmac.c
@@ -14,6 +14,7 @@
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
+#include <linux/irqchip/irq-renesas-rzv2h.h>
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -89,8 +90,14 @@ struct rz_dmac_chan {
 
 #define to_rz_dmac_chan(c)	container_of(c, struct rz_dmac_chan, vc.chan)
 
+struct rz_dmac_icu {
+	struct platform_device *pdev;
+	u8 dmac_index;
+};
+
 struct rz_dmac {
 	struct dma_device engine;
+	struct rz_dmac_icu icu;
 	struct device *dev;
 	struct reset_control *rstc;
 	void __iomem *base;
@@ -99,6 +106,8 @@ struct rz_dmac {
 	unsigned int n_channels;
 	struct rz_dmac_chan *channels;
 
+	bool has_icu;
+
 	DECLARE_BITMAP(modules, 1024);
 };
 
@@ -167,6 +176,9 @@ struct rz_dmac {
 #define RZ_DMAC_MAX_CHANNELS		16
 #define DMAC_NR_LMDESC			64
 
+/* RZ/V2H ICU related */
+#define RZV2H_MAX_DMAC_INDEX		4
+
 /*
  * -----------------------------------------------------------------------------
  * Device access
@@ -324,7 +336,13 @@ static void rz_dmac_prepare_desc_for_memcpy(struct rz_dmac_chan *channel)
 	lmdesc->chext = 0;
 	lmdesc->header = HEADER_LV;
 
-	rz_dmac_set_dmars_register(dmac, channel->index, 0);
+	if (dmac->has_icu) {
+		rzv2h_icu_register_dma_req(dmac->icu.pdev, dmac->icu.dmac_index,
+					   channel->index,
+					   RZV2H_ICU_DMAC_REQ_NO_DEFAULT);
+	} else {
+		rz_dmac_set_dmars_register(dmac, channel->index, 0);
+	}
 
 	channel->chcfg = chcfg;
 	channel->chctrl = CHCTRL_STG | CHCTRL_SETEN;
@@ -375,7 +393,13 @@ static void rz_dmac_prepare_descs_for_slave_sg(struct rz_dmac_chan *channel)
 
 	channel->lmdesc.tail = lmdesc;
 
-	rz_dmac_set_dmars_register(dmac, channel->index, channel->mid_rid);
+	if (dmac->has_icu) {
+		rzv2h_icu_register_dma_req(dmac->icu.pdev, dmac->icu.dmac_index,
+					   channel->index, channel->mid_rid);
+	} else {
+		rz_dmac_set_dmars_register(dmac, channel->index, channel->mid_rid);
+	}
+
 	channel->chctrl = CHCTRL_SETEN;
 }
 
@@ -647,7 +671,13 @@ static void rz_dmac_device_synchronize(struct dma_chan *chan)
 	if (ret < 0)
 		dev_warn(dmac->dev, "DMA Timeout");
 
-	rz_dmac_set_dmars_register(dmac, channel->index, 0);
+	if (dmac->has_icu) {
+		rzv2h_icu_register_dma_req(dmac->icu.pdev, dmac->icu.dmac_index,
+					   channel->index,
+					   RZV2H_ICU_DMAC_REQ_NO_DEFAULT);
+	} else {
+		rz_dmac_set_dmars_register(dmac, channel->index, 0);
+	}
 }
 
 /*
@@ -748,7 +778,8 @@ static struct dma_chan *rz_dmac_of_xlate(struct of_phandle_args *dma_spec,
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
 
-	return dma_request_channel(mask, rz_dmac_chan_filter, dma_spec);
+	return __dma_request_channel(&mask, rz_dmac_chan_filter, dma_spec,
+				     ofdma->of_node);
 }
 
 /*
@@ -823,6 +854,38 @@ static int rz_dmac_chan_probe(struct rz_dmac *dmac,
 	return 0;
 }
 
+static int rz_dmac_parse_of_icu(struct device *dev, struct rz_dmac *dmac)
+{
+	struct device_node *np = dev->of_node;
+	struct of_phandle_args args;
+	uint32_t dmac_index;
+	int ret;
+
+	ret = of_parse_phandle_with_fixed_args(np, "renesas,icu", 1, 0, &args);
+	if (ret == -ENOENT)
+		return 0;
+	if (ret)
+		return ret;
+
+	dmac->has_icu = true;
+
+	dmac->icu.pdev = of_find_device_by_node(args.np);
+	of_node_put(args.np);
+	if (!dmac->icu.pdev) {
+		dev_err(dev, "ICU device not found.\n");
+		return -ENODEV;
+	}
+
+	dmac_index = args.args[0];
+	if (dmac_index > RZV2H_MAX_DMAC_INDEX) {
+		dev_err(dev, "DMAC index %u invalid.\n", dmac_index);
+		return -EINVAL;
+	}
+	dmac->icu.dmac_index = dmac_index;
+
+	return 0;
+}
+
 static int rz_dmac_parse_of(struct device *dev, struct rz_dmac *dmac)
 {
 	struct device_node *np = dev->of_node;
@@ -839,7 +902,7 @@ static int rz_dmac_parse_of(struct device *dev, struct rz_dmac *dmac)
 		return -EINVAL;
 	}
 
-	return 0;
+	return rz_dmac_parse_of_icu(dev, dmac);
 }
 
 static int rz_dmac_probe(struct platform_device *pdev)
@@ -873,9 +936,11 @@ static int rz_dmac_probe(struct platform_device *pdev)
 	if (IS_ERR(dmac->base))
 		return PTR_ERR(dmac->base);
 
-	dmac->ext_base = devm_platform_ioremap_resource(pdev, 1);
-	if (IS_ERR(dmac->ext_base))
-		return PTR_ERR(dmac->ext_base);
+	if (!dmac->has_icu) {
+		dmac->ext_base = devm_platform_ioremap_resource(pdev, 1);
+		if (IS_ERR(dmac->ext_base))
+			return PTR_ERR(dmac->ext_base);
+	}
 
 	/* Register interrupt handler for error */
 	irq = platform_get_irq_byname(pdev, irqname);
@@ -990,9 +1055,12 @@ static void rz_dmac_remove(struct platform_device *pdev)
 	reset_control_assert(dmac->rstc);
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+
+	platform_device_put(dmac->icu.pdev);
 }
 
 static const struct of_device_id of_rz_dmac_match[] = {
+	{ .compatible = "renesas,r9a09g057-dmac", },
 	{ .compatible = "renesas,rz-dmac", },
 	{ /* Sentinel */ }
 };
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index ce80ac4b1a1b..fad896ff29a2 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -27,10 +27,10 @@
 
 #define ADMA_CH_INT_CLEAR				0x1c
 #define ADMA_CH_CTRL					0x24
-#define ADMA_CH_CTRL_DIR(val)				(((val) & 0xf) << 12)
+#define ADMA_CH_CTRL_DIR(val, mask, shift)		(((val) & (mask)) << (shift))
 #define ADMA_CH_CTRL_DIR_AHUB2MEM			2
 #define ADMA_CH_CTRL_DIR_MEM2AHUB			4
-#define ADMA_CH_CTRL_MODE_CONTINUOUS			(2 << 8)
+#define ADMA_CH_CTRL_MODE_CONTINUOUS(shift)		(2 << (shift))
 #define ADMA_CH_CTRL_FLOWCTRL_EN			BIT(1)
 #define ADMA_CH_CTRL_XFER_PAUSE_SHIFT			0
 
@@ -41,15 +41,27 @@
 #define ADMA_CH_CONFIG_MAX_BURST_SIZE                   16
 #define ADMA_CH_CONFIG_WEIGHT_FOR_WRR(val)		((val) & 0xf)
 #define ADMA_CH_CONFIG_MAX_BUFS				8
-#define TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(reqs)	(reqs << 4)
+#define TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(reqs)	((reqs) << 4)
+
+#define ADMA_GLOBAL_CH_CONFIG				0x400
+#define ADMA_GLOBAL_CH_CONFIG_WEIGHT_FOR_WRR(val)	((val) & 0x7)
+#define ADMA_GLOBAL_CH_CONFIG_OUTSTANDING_REQS(reqs)	((reqs) << 8)
 
 #define TEGRA186_ADMA_GLOBAL_PAGE_CHGRP			0x30
 #define TEGRA186_ADMA_GLOBAL_PAGE_RX_REQ		0x70
 #define TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ		0x84
+#define TEGRA264_ADMA_GLOBAL_PAGE_CHGRP_0		0x44
+#define TEGRA264_ADMA_GLOBAL_PAGE_CHGRP_1		0x48
+#define TEGRA264_ADMA_GLOBAL_PAGE_RX_REQ_0		0x100
+#define TEGRA264_ADMA_GLOBAL_PAGE_RX_REQ_1		0x104
+#define TEGRA264_ADMA_GLOBAL_PAGE_TX_REQ_0		0x180
+#define TEGRA264_ADMA_GLOBAL_PAGE_TX_REQ_1		0x184
+#define TEGRA264_ADMA_GLOBAL_PAGE_OFFSET		0x8
 
 #define ADMA_CH_FIFO_CTRL				0x2c
 #define ADMA_CH_TX_FIFO_SIZE_SHIFT			8
 #define ADMA_CH_RX_FIFO_SIZE_SHIFT			0
+#define ADMA_GLOBAL_CH_FIFO_CTRL			0x300
 
 #define ADMA_CH_LOWER_SRC_ADDR				0x34
 #define ADMA_CH_LOWER_TRG_ADDR				0x3c
@@ -73,36 +85,48 @@ struct tegra_adma;
  * @adma_get_burst_config: Function callback used to set DMA burst size.
  * @global_reg_offset: Register offset of DMA global register.
  * @global_int_clear: Register offset of DMA global interrupt clear.
+ * @global_ch_fifo_base: Global channel fifo ctrl base offset
+ * @global_ch_config_base: Global channel config base offset
  * @ch_req_tx_shift: Register offset for AHUB transmit channel select.
  * @ch_req_rx_shift: Register offset for AHUB receive channel select.
+ * @ch_dir_shift: Channel direction bit position.
+ * @ch_mode_shift: Channel mode bit position.
  * @ch_base_offset: Register offset of DMA channel registers.
+ * @ch_tc_offset_diff: From TC register onwards offset differs for Tegra264
  * @ch_fifo_ctrl: Default value for channel FIFO CTRL register.
+ * @ch_config: Outstanding and WRR config values
  * @ch_req_mask: Mask for Tx or Rx channel select.
+ * @ch_dir_mask: Mask for channel direction.
  * @ch_req_max: Maximum number of Tx or Rx channels available.
  * @ch_reg_size: Size of DMA channel register space.
  * @nr_channels: Number of DMA channels available.
  * @ch_fifo_size_mask: Mask for FIFO size field.
  * @sreq_index_offset: Slave channel index offset.
  * @max_page: Maximum ADMA Channel Page.
- * @has_outstanding_reqs: If DMA channel can have outstanding requests.
  * @set_global_pg_config: Global page programming.
  */
 struct tegra_adma_chip_data {
 	unsigned int (*adma_get_burst_config)(unsigned int burst_size);
 	unsigned int global_reg_offset;
 	unsigned int global_int_clear;
+	unsigned int global_ch_fifo_base;
+	unsigned int global_ch_config_base;
 	unsigned int ch_req_tx_shift;
 	unsigned int ch_req_rx_shift;
+	unsigned int ch_dir_shift;
+	unsigned int ch_mode_shift;
 	unsigned int ch_base_offset;
+	unsigned int ch_tc_offset_diff;
 	unsigned int ch_fifo_ctrl;
+	unsigned int ch_config;
 	unsigned int ch_req_mask;
+	unsigned int ch_dir_mask;
 	unsigned int ch_req_max;
 	unsigned int ch_reg_size;
 	unsigned int nr_channels;
 	unsigned int ch_fifo_size_mask;
 	unsigned int sreq_index_offset;
 	unsigned int max_page;
-	bool has_outstanding_reqs;
 	void (*set_global_pg_config)(struct tegra_adma *tdma);
 };
 
@@ -112,6 +136,7 @@ struct tegra_adma_chip_data {
 struct tegra_adma_chan_regs {
 	unsigned int ctrl;
 	unsigned int config;
+	unsigned int global_config;
 	unsigned int src_addr;
 	unsigned int trg_addr;
 	unsigned int fifo_ctrl;
@@ -150,6 +175,9 @@ struct tegra_adma_chan {
 	/* Transfer count and position info */
 	unsigned int			tx_buf_count;
 	unsigned int			tx_buf_pos;
+
+	unsigned int			global_ch_fifo_offset;
+	unsigned int			global_ch_config_offset;
 };
 
 /*
@@ -246,6 +274,29 @@ static void tegra186_adma_global_page_config(struct tegra_adma *tdma)
 	tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ + (tdma->ch_page_no * 0x4), 0xffffff);
 }
 
+static void tegra264_adma_global_page_config(struct tegra_adma *tdma)
+{
+	u32 global_page_offset = tdma->ch_page_no * TEGRA264_ADMA_GLOBAL_PAGE_OFFSET;
+
+	/* If the default page (page1) is not used, then clear page1 registers */
+	if (tdma->ch_page_no) {
+		tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_CHGRP_0, 0);
+		tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_CHGRP_1, 0);
+		tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_RX_REQ_0, 0);
+		tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_RX_REQ_1, 0);
+		tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_TX_REQ_0, 0);
+		tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_TX_REQ_1, 0);
+	}
+
+	/* Program global registers for selected page */
+	tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_CHGRP_0 + global_page_offset, 0xffffffff);
+	tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_CHGRP_1 + global_page_offset, 0xffffffff);
+	tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_RX_REQ_0 + global_page_offset, 0xffffffff);
+	tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_RX_REQ_1 + global_page_offset, 0x1);
+	tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_TX_REQ_0 + global_page_offset, 0xffffffff);
+	tdma_write(tdma, TEGRA264_ADMA_GLOBAL_PAGE_TX_REQ_1 + global_page_offset, 0x1);
+}
+
 static int tegra_adma_init(struct tegra_adma *tdma)
 {
 	u32 status;
@@ -404,11 +455,21 @@ static void tegra_adma_start(struct tegra_adma_chan *tdc)
 
 	tdc->tx_buf_pos = 0;
 	tdc->tx_buf_count = 0;
-	tdma_ch_write(tdc, ADMA_CH_TC, ch_regs->tc);
+	tdma_ch_write(tdc, ADMA_CH_TC - tdc->tdma->cdata->ch_tc_offset_diff, ch_regs->tc);
 	tdma_ch_write(tdc, ADMA_CH_CTRL, ch_regs->ctrl);
-	tdma_ch_write(tdc, ADMA_CH_LOWER_SRC_ADDR, ch_regs->src_addr);
-	tdma_ch_write(tdc, ADMA_CH_LOWER_TRG_ADDR, ch_regs->trg_addr);
-	tdma_ch_write(tdc, ADMA_CH_FIFO_CTRL, ch_regs->fifo_ctrl);
+	tdma_ch_write(tdc, ADMA_CH_LOWER_SRC_ADDR - tdc->tdma->cdata->ch_tc_offset_diff,
+		      ch_regs->src_addr);
+	tdma_ch_write(tdc, ADMA_CH_LOWER_TRG_ADDR - tdc->tdma->cdata->ch_tc_offset_diff,
+		      ch_regs->trg_addr);
+
+	if (!tdc->tdma->cdata->global_ch_fifo_base)
+		tdma_ch_write(tdc, ADMA_CH_FIFO_CTRL, ch_regs->fifo_ctrl);
+	else if (tdc->global_ch_fifo_offset)
+		tdma_write(tdc->tdma, tdc->global_ch_fifo_offset, ch_regs->fifo_ctrl);
+
+	if (tdc->global_ch_config_offset)
+		tdma_write(tdc->tdma, tdc->global_ch_config_offset, ch_regs->global_config);
+
 	tdma_ch_write(tdc, ADMA_CH_CONFIG, ch_regs->config);
 
 	/* Start ADMA */
@@ -421,7 +482,8 @@ static unsigned int tegra_adma_get_residue(struct tegra_adma_chan *tdc)
 {
 	struct tegra_adma_desc *desc = tdc->desc;
 	unsigned int max = ADMA_CH_XFER_STATUS_COUNT_MASK + 1;
-	unsigned int pos = tdma_ch_read(tdc, ADMA_CH_XFER_STATUS);
+	unsigned int pos = tdma_ch_read(tdc, ADMA_CH_XFER_STATUS -
+			tdc->tdma->cdata->ch_tc_offset_diff);
 	unsigned int periods_remaining;
 
 	/*
@@ -627,13 +689,16 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc,
 		return -EINVAL;
 	}
 
-	ch_regs->ctrl |= ADMA_CH_CTRL_DIR(adma_dir) |
-			 ADMA_CH_CTRL_MODE_CONTINUOUS |
+	ch_regs->ctrl |= ADMA_CH_CTRL_DIR(adma_dir, cdata->ch_dir_mask,
+			cdata->ch_dir_shift) |
+			 ADMA_CH_CTRL_MODE_CONTINUOUS(cdata->ch_mode_shift) |
 			 ADMA_CH_CTRL_FLOWCTRL_EN;
 	ch_regs->config |= cdata->adma_get_burst_config(burst_size);
-	ch_regs->config |= ADMA_CH_CONFIG_WEIGHT_FOR_WRR(1);
-	if (cdata->has_outstanding_reqs)
-		ch_regs->config |= TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(8);
+
+	if (cdata->global_ch_config_base)
+		ch_regs->global_config |= cdata->ch_config;
+	else
+		ch_regs->config |= cdata->ch_config;
 
 	/*
 	 * 'sreq_index' represents the current ADMAIF channel number and as per
@@ -788,12 +853,23 @@ static int __maybe_unused tegra_adma_runtime_suspend(struct device *dev)
 		/* skip if channel is not active */
 		if (!ch_reg->cmd)
 			continue;
-		ch_reg->tc = tdma_ch_read(tdc, ADMA_CH_TC);
-		ch_reg->src_addr = tdma_ch_read(tdc, ADMA_CH_LOWER_SRC_ADDR);
-		ch_reg->trg_addr = tdma_ch_read(tdc, ADMA_CH_LOWER_TRG_ADDR);
+		ch_reg->tc = tdma_ch_read(tdc, ADMA_CH_TC - tdma->cdata->ch_tc_offset_diff);
+		ch_reg->src_addr = tdma_ch_read(tdc, ADMA_CH_LOWER_SRC_ADDR -
+						tdma->cdata->ch_tc_offset_diff);
+		ch_reg->trg_addr = tdma_ch_read(tdc, ADMA_CH_LOWER_TRG_ADDR -
+						tdma->cdata->ch_tc_offset_diff);
 		ch_reg->ctrl = tdma_ch_read(tdc, ADMA_CH_CTRL);
-		ch_reg->fifo_ctrl = tdma_ch_read(tdc, ADMA_CH_FIFO_CTRL);
+
+		if (tdc->global_ch_config_offset)
+			ch_reg->global_config = tdma_read(tdc->tdma, tdc->global_ch_config_offset);
+
+		if (!tdc->tdma->cdata->global_ch_fifo_base)
+			ch_reg->fifo_ctrl = tdma_ch_read(tdc, ADMA_CH_FIFO_CTRL);
+		else if (tdc->global_ch_fifo_offset)
+			ch_reg->fifo_ctrl = tdma_read(tdc->tdma, tdc->global_ch_fifo_offset);
+
 		ch_reg->config = tdma_ch_read(tdc, ADMA_CH_CONFIG);
+
 	}
 
 clk_disable:
@@ -832,12 +908,23 @@ static int __maybe_unused tegra_adma_runtime_resume(struct device *dev)
 		/* skip if channel was not active earlier */
 		if (!ch_reg->cmd)
 			continue;
-		tdma_ch_write(tdc, ADMA_CH_TC, ch_reg->tc);
-		tdma_ch_write(tdc, ADMA_CH_LOWER_SRC_ADDR, ch_reg->src_addr);
-		tdma_ch_write(tdc, ADMA_CH_LOWER_TRG_ADDR, ch_reg->trg_addr);
+		tdma_ch_write(tdc, ADMA_CH_TC - tdma->cdata->ch_tc_offset_diff, ch_reg->tc);
+		tdma_ch_write(tdc, ADMA_CH_LOWER_SRC_ADDR - tdma->cdata->ch_tc_offset_diff,
+			      ch_reg->src_addr);
+		tdma_ch_write(tdc, ADMA_CH_LOWER_TRG_ADDR - tdma->cdata->ch_tc_offset_diff,
+			      ch_reg->trg_addr);
 		tdma_ch_write(tdc, ADMA_CH_CTRL, ch_reg->ctrl);
-		tdma_ch_write(tdc, ADMA_CH_FIFO_CTRL, ch_reg->fifo_ctrl);
+
+		if (!tdc->tdma->cdata->global_ch_fifo_base)
+			tdma_ch_write(tdc, ADMA_CH_FIFO_CTRL, ch_reg->fifo_ctrl);
+		else if (tdc->global_ch_fifo_offset)
+			tdma_write(tdc->tdma, tdc->global_ch_fifo_offset, ch_reg->fifo_ctrl);
+
+		if (tdc->global_ch_config_offset)
+			tdma_write(tdc->tdma, tdc->global_ch_config_offset, ch_reg->global_config);
+
 		tdma_ch_write(tdc, ADMA_CH_CONFIG, ch_reg->config);
+
 		tdma_ch_write(tdc, ADMA_CH_CMD, ch_reg->cmd);
 	}
 
@@ -848,17 +935,23 @@ static const struct tegra_adma_chip_data tegra210_chip_data = {
 	.adma_get_burst_config  = tegra210_adma_get_burst_config,
 	.global_reg_offset	= 0xc00,
 	.global_int_clear	= 0x20,
+	.global_ch_fifo_base	= 0,
+	.global_ch_config_base	= 0,
 	.ch_req_tx_shift	= 28,
 	.ch_req_rx_shift	= 24,
+	.ch_dir_shift		= 12,
+	.ch_mode_shift		= 8,
 	.ch_base_offset		= 0,
+	.ch_tc_offset_diff	= 0,
+	.ch_config		= ADMA_CH_CONFIG_WEIGHT_FOR_WRR(1),
 	.ch_req_mask		= 0xf,
+	.ch_dir_mask		= 0xf,
 	.ch_req_max		= 10,
 	.ch_reg_size		= 0x80,
 	.nr_channels		= 22,
 	.ch_fifo_size_mask	= 0xf,
 	.sreq_index_offset	= 2,
 	.max_page		= 0,
-	.has_outstanding_reqs	= false,
 	.set_global_pg_config	= NULL,
 };
 
@@ -866,23 +959,56 @@ static const struct tegra_adma_chip_data tegra186_chip_data = {
 	.adma_get_burst_config  = tegra186_adma_get_burst_config,
 	.global_reg_offset	= 0,
 	.global_int_clear	= 0x402c,
+	.global_ch_fifo_base	= 0,
+	.global_ch_config_base	= 0,
 	.ch_req_tx_shift	= 27,
 	.ch_req_rx_shift	= 22,
+	.ch_dir_shift		= 12,
+	.ch_mode_shift		= 8,
 	.ch_base_offset		= 0x10000,
+	.ch_tc_offset_diff	= 0,
+	.ch_config		= ADMA_CH_CONFIG_WEIGHT_FOR_WRR(1) |
+				  TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(8),
 	.ch_req_mask		= 0x1f,
+	.ch_dir_mask		= 0xf,
 	.ch_req_max		= 20,
 	.ch_reg_size		= 0x100,
 	.nr_channels		= 32,
 	.ch_fifo_size_mask	= 0x1f,
 	.sreq_index_offset	= 4,
 	.max_page		= 4,
-	.has_outstanding_reqs	= true,
 	.set_global_pg_config	= tegra186_adma_global_page_config,
 };
 
+static const struct tegra_adma_chip_data tegra264_chip_data = {
+	.adma_get_burst_config  = tegra186_adma_get_burst_config,
+	.global_reg_offset	= 0,
+	.global_int_clear	= 0x800c,
+	.global_ch_fifo_base	= ADMA_GLOBAL_CH_FIFO_CTRL,
+	.global_ch_config_base	= ADMA_GLOBAL_CH_CONFIG,
+	.ch_req_tx_shift	= 26,
+	.ch_req_rx_shift	= 20,
+	.ch_dir_shift		= 10,
+	.ch_mode_shift		= 7,
+	.ch_base_offset		= 0x10000,
+	.ch_tc_offset_diff	= 4,
+	.ch_config		= ADMA_GLOBAL_CH_CONFIG_WEIGHT_FOR_WRR(1) |
+				  ADMA_GLOBAL_CH_CONFIG_OUTSTANDING_REQS(8),
+	.ch_req_mask		= 0x3f,
+	.ch_dir_mask		= 7,
+	.ch_req_max		= 32,
+	.ch_reg_size		= 0x100,
+	.nr_channels		= 64,
+	.ch_fifo_size_mask	= 0x7f,
+	.sreq_index_offset	= 0,
+	.max_page		= 10,
+	.set_global_pg_config	= tegra264_adma_global_page_config,
+};
+
 static const struct of_device_id tegra_adma_of_match[] = {
 	{ .compatible = "nvidia,tegra210-adma", .data = &tegra210_chip_data },
 	{ .compatible = "nvidia,tegra186-adma", .data = &tegra186_chip_data },
+	{ .compatible = "nvidia,tegra264-adma", .data = &tegra264_chip_data },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, tegra_adma_of_match);
@@ -985,6 +1111,15 @@ static int tegra_adma_probe(struct platform_device *pdev)
 
 		tdc->chan_addr = tdma->ch_base_addr + (cdata->ch_reg_size * i);
 
+		if (tdma->base_addr) {
+			if (cdata->global_ch_fifo_base)
+				tdc->global_ch_fifo_offset = cdata->global_ch_fifo_base + (4 * i);
+
+			if (cdata->global_ch_config_base)
+				tdc->global_ch_config_offset =
+					cdata->global_ch_config_base + (4 * i);
+		}
+
 		tdc->irq = of_irq_get(pdev->dev.of_node, i);
 		if (tdc->irq <= 0) {
 			ret = tdc->irq ?: -ENXIO;
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index b6255c0601bb..aa2dc762140f 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -5624,7 +5624,8 @@ static int udma_probe(struct platform_device *pdev)
 		uc->config.dir = DMA_MEM_TO_MEM;
 		uc->name = devm_kasprintf(dev, GFP_KERNEL, "%s chan%d",
 					  dev_name(dev), i);
-
+		if (!uc->name)
+			return -ENOMEM;
 		vchan_init(&uc->vc, &ud->ddev);
 		/* Use custom vchan completion handling */
 		tasklet_setup(&uc->vc.task, udma_vchan_complete);
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 3ad44afd0e74..a34d8f0ceed8 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -2909,6 +2909,8 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 		return -EINVAL;
 	}
 
+	xdev->common.directions |= chan->direction;
+
 	/* Request the interrupt */
 	chan->irq = of_irq_get(node, chan->tdest);
 	if (chan->irq < 0)
@@ -3115,6 +3117,8 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 		}
 	}
 
+	dma_set_max_seg_size(xdev->dev, xdev->max_buffer_len);
+
 	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
 		xdev->has_axistream_connected =
 			of_property_read_bool(node, "xlnx,axistream-connected");
diff --git a/drivers/edac/mem_repair.c b/drivers/edac/mem_repair.c
index 3b1a845457b0..d1a8caa85369 100755
--- a/drivers/edac/mem_repair.c
+++ b/drivers/edac/mem_repair.c
@@ -45,6 +45,15 @@ struct edac_mem_repair_context {
 	struct attribute_group group;
 };
 
+const char * const edac_repair_type[] = {
+	[EDAC_REPAIR_PPR] = "ppr",
+	[EDAC_REPAIR_CACHELINE_SPARING] = "cacheline-sparing",
+	[EDAC_REPAIR_ROW_SPARING] = "row-sparing",
+	[EDAC_REPAIR_BANK_SPARING] = "bank-sparing",
+	[EDAC_REPAIR_RANK_SPARING] = "rank-sparing",
+};
+EXPORT_SYMBOL_GPL(edac_repair_type);
+
 #define TO_MR_DEV_ATTR(_dev_attr)      \
 	container_of(_dev_attr, struct edac_mem_repair_dev_attr, dev_attr)
 
diff --git a/drivers/firewire/Kconfig b/drivers/firewire/Kconfig
index 905c82e26ce7..a5f5e250223a 100644
--- a/drivers/firewire/Kconfig
+++ b/drivers/firewire/Kconfig
@@ -83,7 +83,7 @@ config FIREWIRE_KUNIT_SELF_ID_SEQUENCE_HELPER_TEST
 
 config FIREWIRE_OHCI
 	tristate "OHCI-1394 controllers"
-	depends on PCI && FIREWIRE && MMU
+	depends on PCI && FIREWIRE
 	help
 	  Enable this driver if you have a FireWire controller based
 	  on the OHCI specification.  For all practical purposes, this
diff --git a/drivers/firmware/smccc/kvm_guest.c b/drivers/firmware/smccc/kvm_guest.c
index a123c05cbc9e..49e1de83d2e8 100644
--- a/drivers/firmware/smccc/kvm_guest.c
+++ b/drivers/firmware/smccc/kvm_guest.c
@@ -17,17 +17,11 @@ static DECLARE_BITMAP(__kvm_arm_hyp_services, ARM_SMCCC_KVM_NUM_FUNCS) __ro_afte
 
 void __init kvm_init_hyp_services(void)
 {
+	uuid_t kvm_uuid = ARM_SMCCC_VENDOR_HYP_UID_KVM;
 	struct arm_smccc_res res;
 	u32 val[4];
 
-	if (arm_smccc_1_1_get_conduit() != SMCCC_CONDUIT_HVC)
-		return;
-
-	arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, &res);
-	if (res.a0 != ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 ||
-	    res.a1 != ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 ||
-	    res.a2 != ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 ||
-	    res.a3 != ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3)
+	if (!arm_smccc_hypervisor_has_uuid(&kvm_uuid))
 		return;
 
 	memset(&res, 0, sizeof(res));
diff --git a/drivers/firmware/smccc/smccc.c b/drivers/firmware/smccc/smccc.c
index a74600d9f2d7..cd65b434dc6e 100644
--- a/drivers/firmware/smccc/smccc.c
+++ b/drivers/firmware/smccc/smccc.c
@@ -67,6 +67,23 @@ s32 arm_smccc_get_soc_id_revision(void)
 }
 EXPORT_SYMBOL_GPL(arm_smccc_get_soc_id_revision);
 
+bool arm_smccc_hypervisor_has_uuid(const uuid_t *hyp_uuid)
+{
+	struct arm_smccc_res res = {};
+	uuid_t uuid;
+
+	if (arm_smccc_1_1_get_conduit() != SMCCC_CONDUIT_HVC)
+		return false;
+
+	arm_smccc_1_1_hvc(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, &res);
+	if (res.a0 == SMCCC_RET_NOT_SUPPORTED)
+		return false;
+
+	uuid = smccc_res_to_uuid(res.a0, res.a1, res.a2, res.a3);
+	return uuid_equal(&uuid, hyp_uuid);
+}
+EXPORT_SYMBOL_GPL(arm_smccc_hypervisor_has_uuid);
+
 static int __init smccc_devices_init(void)
 {
 	struct platform_device *pdev;
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index f094797f3b2b..f7ea8e895c0c 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -188,6 +188,7 @@ source "drivers/gpu/drm/display/Kconfig"
 config DRM_TTM
 	tristate
 	depends on DRM && MMU
+	select SHMEM
 	help
 	  GPU memory management subsystem for devices with multiple
 	  GPU memory types. Will be enabled automatically if a device driver
@@ -397,7 +398,7 @@ source "drivers/gpu/drm/imagination/Kconfig"
 
 config DRM_HYPERV
 	tristate "DRM Support for Hyper-V synthetic video device"
-	depends on DRM && PCI && MMU && HYPERV
+	depends on DRM && PCI && HYPERV
 	select DRM_CLIENT_SELECTION
 	select DRM_KMS_HELPER
 	select DRM_GEM_SHMEM_HELPER
diff --git a/drivers/gpu/drm/amd/amdgpu/Kconfig b/drivers/gpu/drm/amd/amdgpu/Kconfig
index 1a11cab741ac..058e3b3ad520 100644
--- a/drivers/gpu/drm/amd/amdgpu/Kconfig
+++ b/drivers/gpu/drm/amd/amdgpu/Kconfig
@@ -2,7 +2,7 @@
 
 config DRM_AMDGPU
 	tristate "AMD GPU"
-	depends on DRM && PCI && MMU
+	depends on DRM && PCI
 	depends on !UML
 	select FW_LOADER
 	select DRM_CLIENT
@@ -68,7 +68,6 @@ config DRM_AMDGPU_CIK
 config DRM_AMDGPU_USERPTR
 	bool "Always enable userptr write support"
 	depends on DRM_AMDGPU
-	depends on MMU
 	select HMM_MIRROR
 	select MMU_NOTIFIER
 	help
diff --git a/drivers/gpu/drm/ast/Kconfig b/drivers/gpu/drm/ast/Kconfig
index da0663542e8a..242fbccdf844 100644
--- a/drivers/gpu/drm/ast/Kconfig
+++ b/drivers/gpu/drm/ast/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config DRM_AST
 	tristate "AST server chips"
-	depends on DRM && PCI && MMU
+	depends on DRM && PCI
 	select DRM_CLIENT_SELECTION
 	select DRM_GEM_SHMEM_HELPER
 	select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/gma500/Kconfig b/drivers/gpu/drm/gma500/Kconfig
index aa2ea128aa2f..a2acaa699dd5 100644
--- a/drivers/gpu/drm/gma500/Kconfig
+++ b/drivers/gpu/drm/gma500/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config DRM_GMA500
 	tristate "Intel GMA500/600/3600/3650 KMS Framebuffer"
-	depends on DRM && PCI && X86 && MMU && HAS_IOPORT
+	depends on DRM && PCI && X86 && HAS_IOPORT
 	select DRM_CLIENT_SELECTION
 	select DRM_KMS_HELPER
 	select FB_IOMEM_HELPERS if DRM_FBDEV_EMULATION
diff --git a/drivers/gpu/drm/hisilicon/hibmc/Kconfig b/drivers/gpu/drm/hisilicon/hibmc/Kconfig
index 98d77d74999d..d1f3f5793f34 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/Kconfig
+++ b/drivers/gpu/drm/hisilicon/hibmc/Kconfig
@@ -2,7 +2,6 @@
 config DRM_HISI_HIBMC
 	tristate "DRM Support for Hisilicon Hibmc"
 	depends on DRM && PCI
-	depends on MMU
 	select DRM_CLIENT_SELECTION
 	select DRM_DISPLAY_HELPER
 	select DRM_DISPLAY_DP_HELPER
diff --git a/drivers/gpu/drm/i915/i915_reg_defs.h b/drivers/gpu/drm/i915/i915_reg_defs.h
index 94a8f902689e..bfe98cb9a038 100644
--- a/drivers/gpu/drm/i915/i915_reg_defs.h
+++ b/drivers/gpu/drm/i915/i915_reg_defs.h
@@ -9,76 +9,19 @@
 #include <linux/bitfield.h>
 #include <linux/bits.h>
 
-/**
- * REG_BIT() - Prepare a u32 bit value
- * @__n: 0-based bit number
- *
- * Local wrapper for BIT() to force u32, with compile time checks.
- *
- * @return: Value with bit @__n set.
- */
-#define REG_BIT(__n)							\
-	((u32)(BIT(__n) +						\
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__n) &&		\
-				 ((__n) < 0 || (__n) > 31))))
-
-/**
- * REG_BIT8() - Prepare a u8 bit value
- * @__n: 0-based bit number
- *
- * Local wrapper for BIT() to force u8, with compile time checks.
- *
- * @return: Value with bit @__n set.
- */
-#define REG_BIT8(__n)                                                   \
-	((u8)(BIT(__n) +                                                \
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__n) &&         \
-				 ((__n) < 0 || (__n) > 7))))
-
-/**
- * REG_GENMASK() - Prepare a continuous u32 bitmask
- * @__high: 0-based high bit
- * @__low: 0-based low bit
- *
- * Local wrapper for GENMASK() to force u32, with compile time checks.
- *
- * @return: Continuous bitmask from @__high to @__low, inclusive.
- */
-#define REG_GENMASK(__high, __low)					\
-	((u32)(GENMASK(__high, __low) +					\
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__high) &&	\
-				 __is_constexpr(__low) &&		\
-				 ((__low) < 0 || (__high) > 31 || (__low) > (__high)))))
-
-/**
- * REG_GENMASK64() - Prepare a continuous u64 bitmask
- * @__high: 0-based high bit
- * @__low: 0-based low bit
- *
- * Local wrapper for GENMASK_ULL() to force u64, with compile time checks.
- *
- * @return: Continuous bitmask from @__high to @__low, inclusive.
+/*
+ * Wrappers over the generic fixed width BIT_U*() and GENMASK_U*()
+ * implementations, for compatibility reasons with previous implementation.
  */
-#define REG_GENMASK64(__high, __low)					\
-	((u64)(GENMASK_ULL(__high, __low) +				\
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__high) &&		\
-				 __is_constexpr(__low) &&		\
-				 ((__low) < 0 || (__high) > 63 || (__low) > (__high)))))
+#define REG_GENMASK(high, low)		GENMASK_U32(high, low)
+#define REG_GENMASK64(high, low)	GENMASK_U64(high, low)
+#define REG_GENMASK16(high, low)	GENMASK_U16(high, low)
+#define REG_GENMASK8(high, low)		GENMASK_U8(high, low)
 
-/**
- * REG_GENMASK8() - Prepare a continuous u8 bitmask
- * @__high: 0-based high bit
- * @__low: 0-based low bit
- *
- * Local wrapper for GENMASK() to force u8, with compile time checks.
- *
- * @return: Continuous bitmask from @__high to @__low, inclusive.
- */
-#define REG_GENMASK8(__high, __low)                                     \
-	((u8)(GENMASK(__high, __low) +                                  \
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__high) &&      \
-				 __is_constexpr(__low) &&               \
-				 ((__low) < 0 || (__high) > 7 || (__low) > (__high)))))
+#define REG_BIT(n)			BIT_U32(n)
+#define REG_BIT64(n)			BIT_U64(n)
+#define REG_BIT16(n)			BIT_U16(n)
+#define REG_BIT8(n)			BIT_U8(n)
 
 /*
  * Local integer constant expression version of is_power_of_2().
@@ -143,35 +86,6 @@
  */
 #define REG_FIELD_GET64(__mask, __val)	((u64)FIELD_GET(__mask, __val))
 
-/**
- * REG_BIT16() - Prepare a u16 bit value
- * @__n: 0-based bit number
- *
- * Local wrapper for BIT() to force u16, with compile time
- * checks.
- *
- * @return: Value with bit @__n set.
- */
-#define REG_BIT16(__n)                                                   \
-	((u16)(BIT(__n) +                                                \
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__n) &&         \
-				 ((__n) < 0 || (__n) > 15))))
-
-/**
- * REG_GENMASK16() - Prepare a continuous u8 bitmask
- * @__high: 0-based high bit
- * @__low: 0-based low bit
- *
- * Local wrapper for GENMASK() to force u16, with compile time
- * checks.
- *
- * @return: Continuous bitmask from @__high to @__low, inclusive.
- */
-#define REG_GENMASK16(__high, __low)                                     \
-	((u16)(GENMASK(__high, __low) +                                  \
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__high) &&      \
-				 __is_constexpr(__low) &&               \
-				 ((__low) < 0 || (__high) > 15 || (__low) > (__high)))))
 
 /**
  * REG_FIELD_PREP16() - Prepare a u16 bitfield value
diff --git a/drivers/gpu/drm/loongson/Kconfig b/drivers/gpu/drm/loongson/Kconfig
index 552edfec7afb..d739d51cf54c 100644
--- a/drivers/gpu/drm/loongson/Kconfig
+++ b/drivers/gpu/drm/loongson/Kconfig
@@ -2,7 +2,7 @@
 
 config DRM_LOONGSON
 	tristate "DRM support for Loongson Graphics"
-	depends on DRM && PCI && MMU
+	depends on DRM && PCI
 	depends on LOONGARCH || MIPS || COMPILE_TEST
 	select DRM_CLIENT_SELECTION
 	select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/mgag200/Kconfig b/drivers/gpu/drm/mgag200/Kconfig
index 412dcbea0e2d..a962ae564a75 100644
--- a/drivers/gpu/drm/mgag200/Kconfig
+++ b/drivers/gpu/drm/mgag200/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config DRM_MGAG200
 	tristate "Matrox G200"
-	depends on DRM && PCI && MMU
+	depends on DRM && PCI
 	select DRM_CLIENT_SELECTION
 	select DRM_GEM_SHMEM_HELPER
 	select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index 7b3e979c51ec..d1587639ebb0 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config DRM_NOUVEAU
 	tristate "Nouveau (NVIDIA) cards"
-	depends on DRM && PCI && MMU
+	depends on DRM && PCI
 	select IOMMU_API
 	select FW_LOADER
 	select FW_CACHE if PM_SLEEP
@@ -94,7 +94,6 @@ config DRM_NOUVEAU_SVM
 	bool "(EXPERIMENTAL) Enable SVM (Shared Virtual Memory) support"
 	depends on DEVICE_PRIVATE
 	depends on DRM_NOUVEAU
-	depends on MMU
 	depends on STAGING
 	select HMM_MIRROR
 	select MMU_NOTIFIER
diff --git a/drivers/gpu/drm/qxl/Kconfig b/drivers/gpu/drm/qxl/Kconfig
index 69427eb8bed2..d8f24bcae34b 100644
--- a/drivers/gpu/drm/qxl/Kconfig
+++ b/drivers/gpu/drm/qxl/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config DRM_QXL
 	tristate "QXL virtual GPU"
-	depends on DRM && PCI && MMU && HAS_IOPORT
+	depends on DRM && PCI && HAS_IOPORT
 	select DRM_CLIENT_SELECTION
 	select DRM_KMS_HELPER
 	select DRM_TTM
diff --git a/drivers/gpu/drm/radeon/Kconfig b/drivers/gpu/drm/radeon/Kconfig
index f51bace9555d..c479f0c0dd5c 100644
--- a/drivers/gpu/drm/radeon/Kconfig
+++ b/drivers/gpu/drm/radeon/Kconfig
@@ -2,7 +2,7 @@
 
 config DRM_RADEON
 	tristate "ATI Radeon"
-	depends on DRM && PCI && MMU
+	depends on DRM && PCI
 	depends on AGP || !AGP
 	select FW_LOADER
 	select DRM_CLIENT_SELECTION
diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index 6d1b3e2cb3fb..06e54694a7f2 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -38,7 +38,7 @@ config DRM_BOCHS
 
 config DRM_CIRRUS_QEMU
 	tristate "Cirrus driver for QEMU emulated device"
-	depends on DRM && PCI && MMU
+	depends on DRM && PCI
 	select DRM_CLIENT_SELECTION
 	select DRM_KMS_HELPER
 	select DRM_GEM_SHMEM_HELPER
diff --git a/drivers/gpu/drm/vmwgfx/Kconfig b/drivers/gpu/drm/vmwgfx/Kconfig
index 6c3c2922ae8b..aab646b91ca9 100644
--- a/drivers/gpu/drm/vmwgfx/Kconfig
+++ b/drivers/gpu/drm/vmwgfx/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 config DRM_VMWGFX
 	tristate "DRM driver for VMware Virtual GPU"
-	depends on DRM && PCI && MMU
+	depends on DRM && PCI
 	depends on (X86 && HYPERVISOR_GUEST) || ARM64
 	select DRM_CLIENT_SELECTION
 	select DRM_TTM
diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig
index 9bce047901b2..2169bc969ea1 100644
--- a/drivers/gpu/drm/xe/Kconfig
+++ b/drivers/gpu/drm/xe/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config DRM_XE
 	tristate "Intel Xe Graphics"
-	depends on DRM && PCI && MMU && (m || (y && KUNIT=y))
+	depends on DRM && PCI && (m || (y && KUNIT=y))
 	select INTERVAL_TREE
 	# we need shmfs for the swappable backing store, and in particular
 	# the shmem_readpage() which depends upon tmpfs
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index a503252702b7..43859fc75747 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -151,6 +151,7 @@ config HID_APPLEIR
 config HID_APPLETB_BL
 	tristate "Apple Touch Bar Backlight"
 	depends on BACKLIGHT_CLASS_DEVICE
+	depends on X86 || COMPILE_TEST
 	help
 	  Say Y here if you want support for the backlight of Touch Bars on x86
 	  MacBook Pros.
@@ -163,6 +164,7 @@ config HID_APPLETB_KBD
 	depends on USB_HID
 	depends on BACKLIGHT_CLASS_DEVICE
 	depends on INPUT
+	depends on X86 || COMPILE_TEST
 	select INPUT_SPARSEKMAP
 	select HID_APPLETB_BL
 	help
diff --git a/drivers/hid/hid-appletb-kbd.c b/drivers/hid/hid-appletb-kbd.c
index 029ccbaa1d12..ef51b2c06872 100644
--- a/drivers/hid/hid-appletb-kbd.c
+++ b/drivers/hid/hid-appletb-kbd.c
@@ -172,7 +172,8 @@ static void appletb_inactivity_timer(struct timer_list *t)
 		if (!kbd->has_dimmed) {
 			backlight_device_set_brightness(kbd->backlight_dev, 1);
 			kbd->has_dimmed = true;
-			mod_timer(&kbd->inactivity_timer, jiffies + msecs_to_jiffies(appletb_tb_idle_timeout * 1000));
+			mod_timer(&kbd->inactivity_timer,
+				jiffies + secs_to_jiffies(appletb_tb_idle_timeout));
 		} else if (!kbd->has_turned_off) {
 			backlight_device_set_brightness(kbd->backlight_dev, 0);
 			kbd->has_turned_off = true;
@@ -188,7 +189,8 @@ static void reset_inactivity_timer(struct appletb_kbd *kbd)
 			kbd->has_dimmed = false;
 			kbd->has_turned_off = false;
 		}
-		mod_timer(&kbd->inactivity_timer, jiffies + msecs_to_jiffies(appletb_tb_dim_timeout * 1000));
+		mod_timer(&kbd->inactivity_timer,
+			jiffies + secs_to_jiffies(appletb_tb_dim_timeout));
 	}
 }
 
@@ -407,7 +409,8 @@ static int appletb_kbd_probe(struct hid_device *hdev, const struct hid_device_id
 	} else {
 		backlight_device_set_brightness(kbd->backlight_dev, 2);
 		timer_setup(&kbd->inactivity_timer, appletb_inactivity_timer, 0);
-		mod_timer(&kbd->inactivity_timer, jiffies + msecs_to_jiffies(appletb_tb_dim_timeout * 1000));
+		mod_timer(&kbd->inactivity_timer,
+			jiffies + secs_to_jiffies(appletb_tb_dim_timeout));
 	}
 
 	kbd->inp_handler.event = appletb_kbd_inp_event;
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 4741ff626771..b348d0464314 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -2396,6 +2396,9 @@ int hid_hw_open(struct hid_device *hdev)
 		ret = hdev->ll_driver->open(hdev);
 		if (ret)
 			hdev->ll_open_count--;
+
+		if (hdev->driver->on_hid_hw_open)
+			hdev->driver->on_hid_hw_open(hdev);
 	}
 
 	mutex_unlock(&hdev->ll_open_lock);
@@ -2415,8 +2418,12 @@ EXPORT_SYMBOL_GPL(hid_hw_open);
 void hid_hw_close(struct hid_device *hdev)
 {
 	mutex_lock(&hdev->ll_open_lock);
-	if (!--hdev->ll_open_count)
+	if (!--hdev->ll_open_count) {
 		hdev->ll_driver->close(hdev);
+
+		if (hdev->driver->on_hid_hw_close)
+			hdev->driver->on_hid_hw_close(hdev);
+	}
 	mutex_unlock(&hdev->ll_open_lock);
 }
 EXPORT_SYMBOL_GPL(hid_hw_close);
diff --git a/drivers/hid/hid-corsair-void.c b/drivers/hid/hid-corsair-void.c
index afbd67aa9719..fee134a7eba3 100644
--- a/drivers/hid/hid-corsair-void.c
+++ b/drivers/hid/hid-corsair-void.c
@@ -507,7 +507,7 @@ static void corsair_void_status_work_handler(struct work_struct *work)
 	struct delayed_work *delayed_work;
 	int battery_ret;
 
-	delayed_work = container_of(work, struct delayed_work, work);
+	delayed_work = to_delayed_work(work);
 	drvdata = container_of(delayed_work, struct corsair_void_drvdata,
 			       delayed_status_work);
 
@@ -525,7 +525,7 @@ static void corsair_void_firmware_work_handler(struct work_struct *work)
 	struct delayed_work *delayed_work;
 	int firmware_ret;
 
-	delayed_work = container_of(work, struct delayed_work, work);
+	delayed_work = to_delayed_work(work);
 	drvdata = container_of(delayed_work, struct corsair_void_drvdata,
 			       delayed_firmware_work);
 
diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c
index f4c8d981aa0a..234fa82eab07 100644
--- a/drivers/hid/hid-cp2112.c
+++ b/drivers/hid/hid-cp2112.c
@@ -17,11 +17,13 @@
  */
 
 #include <linux/bitops.h>
+#include <linux/cleanup.h>
 #include <linux/gpio/driver.h>
 #include <linux/hid.h>
 #include <linux/hidraw.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/nls.h>
 #include <linux/string_choices.h>
 #include <linux/usb/ch9.h>
@@ -185,7 +187,7 @@ static int cp2112_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 	u8 *buf = dev->in_out_buffer;
 	int ret;
 
-	mutex_lock(&dev->lock);
+	guard(mutex)(&dev->lock);
 
 	ret = hid_hw_raw_request(hdev, CP2112_GPIO_CONFIG, buf,
 				 CP2112_GPIO_CONFIG_LENGTH, HID_FEATURE_REPORT,
@@ -194,7 +196,7 @@ static int cp2112_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 		hid_err(hdev, "error requesting GPIO config: %d\n", ret);
 		if (ret >= 0)
 			ret = -EIO;
-		goto exit;
+		return ret;
 	}
 
 	buf[1] &= ~BIT(offset);
@@ -207,25 +209,19 @@ static int cp2112_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 		hid_err(hdev, "error setting GPIO config: %d\n", ret);
 		if (ret >= 0)
 			ret = -EIO;
-		goto exit;
+		return ret;
 	}
 
-	ret = 0;
-
-exit:
-	mutex_unlock(&dev->lock);
-	return ret;
+	return 0;
 }
 
-static void cp2112_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+static int cp2112_gpio_set_unlocked(struct cp2112_device *dev,
+				    unsigned int offset, int value)
 {
-	struct cp2112_device *dev = gpiochip_get_data(chip);
 	struct hid_device *hdev = dev->hdev;
 	u8 *buf = dev->in_out_buffer;
 	int ret;
 
-	mutex_lock(&dev->lock);
-
 	buf[0] = CP2112_GPIO_SET;
 	buf[1] = value ? CP2112_GPIO_ALL_GPIO_MASK : 0;
 	buf[2] = BIT(offset);
@@ -236,7 +232,17 @@ static void cp2112_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 	if (ret < 0)
 		hid_err(hdev, "error setting GPIO values: %d\n", ret);
 
-	mutex_unlock(&dev->lock);
+	return ret;
+}
+
+static int cp2112_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			   int value)
+{
+	struct cp2112_device *dev = gpiochip_get_data(chip);
+
+	guard(mutex)(&dev->lock);
+
+	return cp2112_gpio_set_unlocked(dev, offset, value);
 }
 
 static int cp2112_gpio_get_all(struct gpio_chip *chip)
@@ -246,23 +252,17 @@ static int cp2112_gpio_get_all(struct gpio_chip *chip)
 	u8 *buf = dev->in_out_buffer;
 	int ret;
 
-	mutex_lock(&dev->lock);
+	guard(mutex)(&dev->lock);
 
 	ret = hid_hw_raw_request(hdev, CP2112_GPIO_GET, buf,
 				 CP2112_GPIO_GET_LENGTH, HID_FEATURE_REPORT,
 				 HID_REQ_GET_REPORT);
 	if (ret != CP2112_GPIO_GET_LENGTH) {
 		hid_err(hdev, "error requesting GPIO values: %d\n", ret);
-		ret = ret < 0 ? ret : -EIO;
-		goto exit;
+		return ret < 0 ? ret : -EIO;
 	}
 
-	ret = buf[1];
-
-exit:
-	mutex_unlock(&dev->lock);
-
-	return ret;
+	return buf[1];
 }
 
 static int cp2112_gpio_get(struct gpio_chip *chip, unsigned int offset)
@@ -284,14 +284,14 @@ static int cp2112_gpio_direction_output(struct gpio_chip *chip,
 	u8 *buf = dev->in_out_buffer;
 	int ret;
 
-	mutex_lock(&dev->lock);
+	guard(mutex)(&dev->lock);
 
 	ret = hid_hw_raw_request(hdev, CP2112_GPIO_CONFIG, buf,
 				 CP2112_GPIO_CONFIG_LENGTH, HID_FEATURE_REPORT,
 				 HID_REQ_GET_REPORT);
 	if (ret != CP2112_GPIO_CONFIG_LENGTH) {
 		hid_err(hdev, "error requesting GPIO config: %d\n", ret);
-		goto fail;
+		return ret < 0 ? ret : -EIO;
 	}
 
 	buf[1] |= 1 << offset;
@@ -302,22 +302,16 @@ static int cp2112_gpio_direction_output(struct gpio_chip *chip,
 				 HID_REQ_SET_REPORT);
 	if (ret < 0) {
 		hid_err(hdev, "error setting GPIO config: %d\n", ret);
-		goto fail;
+		return ret;
 	}
 
-	mutex_unlock(&dev->lock);
-
 	/*
 	 * Set gpio value when output direction is already set,
 	 * as specified in AN495, Rev. 0.2, cpt. 4.4
 	 */
-	cp2112_gpio_set(chip, offset, value);
+	cp2112_gpio_set_unlocked(dev, offset, value);
 
 	return 0;
-
-fail:
-	mutex_unlock(&dev->lock);
-	return ret < 0 ? ret : -EIO;
 }
 
 static int cp2112_hid_get(struct hid_device *hdev, unsigned char report_number,
@@ -1205,7 +1199,11 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	if (!dev->in_out_buffer)
 		return -ENOMEM;
 
-	mutex_init(&dev->lock);
+	ret = devm_mutex_init(&hdev->dev, &dev->lock);
+	if (ret) {
+		hid_err(hdev, "mutex init failed\n");
+		return ret;
+	}
 
 	ret = hid_parse(hdev);
 	if (ret) {
@@ -1290,7 +1288,7 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	dev->gc.label			= "cp2112_gpio";
 	dev->gc.direction_input		= cp2112_gpio_direction_input;
 	dev->gc.direction_output	= cp2112_gpio_direction_output;
-	dev->gc.set			= cp2112_gpio_set;
+	dev->gc.set_rv			= cp2112_gpio_set;
 	dev->gc.get			= cp2112_gpio_get;
 	dev->gc.base			= -1;
 	dev->gc.ngpio			= CP2112_GPIO_MAX_GPIO;
diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c
index 0fb210e40a41..9eafff0b6ea4 100644
--- a/drivers/hid/hid-hyperv.c
+++ b/drivers/hid/hid-hyperv.c
@@ -192,7 +192,7 @@ static void mousevsc_on_receive_device_info(struct mousevsc_dev *input_device,
 		goto cleanup;
 
 	input_device->report_desc_size = le16_to_cpu(
-					desc->desc[0].wDescriptorLength);
+					desc->rpt_desc.wDescriptorLength);
 	if (input_device->report_desc_size == 0) {
 		input_device->dev_info_status = -EINVAL;
 		goto cleanup;
@@ -210,7 +210,7 @@ static void mousevsc_on_receive_device_info(struct mousevsc_dev *input_device,
 
 	memcpy(input_device->report_desc,
 	       ((unsigned char *)desc) + desc->bLength,
-	       le16_to_cpu(desc->desc[0].wDescriptorLength));
+	       le16_to_cpu(desc->rpt_desc.wDescriptorLength));
 
 	/* Send the ack */
 	memset(&ack, 0, sizeof(struct mousevsc_prt_msg));
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 1062731315a2..e3fb4e2fe911 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -96,6 +96,7 @@
 #define USB_DEVICE_ID_APPLE_MIGHTYMOUSE	0x0304
 #define USB_DEVICE_ID_APPLE_MAGICMOUSE	0x030d
 #define USB_DEVICE_ID_APPLE_MAGICMOUSE2	0x0269
+#define USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC	0x0323
 #define USB_DEVICE_ID_APPLE_MAGICTRACKPAD	0x030e
 #define USB_DEVICE_ID_APPLE_MAGICTRACKPAD2	0x0265
 #define USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC	0x0324
diff --git a/drivers/hid/hid-kysona.c b/drivers/hid/hid-kysona.c
index d4c0406b3323..09bfe30d02cb 100644
--- a/drivers/hid/hid-kysona.c
+++ b/drivers/hid/hid-kysona.c
@@ -14,6 +14,7 @@
 
 #define BATTERY_TIMEOUT_MS 5000
 
+#define ONLINE_REPORT_ID 3
 #define BATTERY_REPORT_ID 4
 
 struct kysona_drvdata {
@@ -80,11 +81,46 @@ static int kysona_battery_get_property(struct power_supply *psy,
 	return ret;
 }
 
+static const char kysona_online_request[] = {
+	0x08, ONLINE_REPORT_ID, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x4a
+};
+
 static const char kysona_battery_request[] = {
 	0x08, BATTERY_REPORT_ID, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x49
 };
 
+static int kysona_m600_fetch_online(struct hid_device *hdev)
+{
+	u8 *write_buf;
+	int ret;
+
+	/* Request online information */
+	write_buf = kmemdup(kysona_online_request, sizeof(kysona_online_request), GFP_KERNEL);
+	if (!write_buf)
+		return -ENOMEM;
+
+	ret = hid_hw_raw_request(hdev, kysona_online_request[0],
+				 write_buf, sizeof(kysona_online_request),
+				 HID_OUTPUT_REPORT, HID_REQ_SET_REPORT);
+	if (ret < (int)sizeof(kysona_online_request)) {
+		hid_err(hdev, "hid_hw_raw_request() failed with %d\n", ret);
+		ret = -ENODATA;
+	}
+	kfree(write_buf);
+	return ret;
+}
+
+static void kysona_fetch_online(struct hid_device *hdev)
+{
+	int ret = kysona_m600_fetch_online(hdev);
+
+	if (ret < 0)
+		hid_dbg(hdev,
+			"Online query failed (err: %d)\n", ret);
+}
+
 static int kysona_m600_fetch_battery(struct hid_device *hdev)
 {
 	u8 *write_buf;
@@ -121,6 +157,7 @@ static void kysona_battery_timer_tick(struct work_struct *work)
 		struct kysona_drvdata, battery_work.work);
 	struct hid_device *hdev = drv_data->hdev;
 
+	kysona_fetch_online(hdev);
 	kysona_fetch_battery(hdev);
 	schedule_delayed_work(&drv_data->battery_work,
 			      msecs_to_jiffies(BATTERY_TIMEOUT_MS));
@@ -160,6 +197,7 @@ static int kysona_battery_probe(struct hid_device *hdev)
 	power_supply_powers(drv_data->battery, &hdev->dev);
 
 	INIT_DELAYED_WORK(&drv_data->battery_work, kysona_battery_timer_tick);
+	kysona_fetch_online(hdev);
 	kysona_fetch_battery(hdev);
 	schedule_delayed_work(&drv_data->battery_work,
 			      msecs_to_jiffies(BATTERY_TIMEOUT_MS));
@@ -206,12 +244,16 @@ static int kysona_raw_event(struct hid_device *hdev,
 {
 	struct kysona_drvdata *drv_data = hid_get_drvdata(hdev);
 
-	if (drv_data->battery && size == sizeof(kysona_battery_request) &&
+	if (size == sizeof(kysona_online_request) &&
+	    data[0] == 8 && data[1] == ONLINE_REPORT_ID) {
+		drv_data->online = data[6];
+	}
+
+	if (size == sizeof(kysona_battery_request) &&
 	    data[0] == 8 && data[1] == BATTERY_REPORT_ID) {
 		drv_data->battery_capacity = data[6];
 		drv_data->battery_charging = data[7];
 		drv_data->battery_voltage = (data[8] << 8) | data[9];
-		drv_data->online = true;
 	}
 
 	return 0;
diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c
index c0a138f21ca4..445623dd1bd6 100644
--- a/drivers/hid/hid-lg4ff.c
+++ b/drivers/hid/hid-lg4ff.c
@@ -823,7 +823,7 @@ static ssize_t lg4ff_alternate_modes_show(struct device *dev, struct device_attr
 	for (i = 0; i < LG4FF_MODE_MAX_IDX; i++) {
 		if (entry->wdata.alternate_modes & BIT(i)) {
 			/* Print tag and full name */
-			count += scnprintf(buf + count, PAGE_SIZE - count, "%s: %s",
+			count += sysfs_emit_at(buf, count, "%s: %s",
 					   lg4ff_alternate_modes[i].tag,
 					   !lg4ff_alternate_modes[i].product_id ? entry->wdata.real_name : lg4ff_alternate_modes[i].name);
 			if (count >= PAGE_SIZE - 1)
@@ -832,9 +832,9 @@ static ssize_t lg4ff_alternate_modes_show(struct device *dev, struct device_attr
 			/* Mark the currently active mode with an asterisk */
 			if (lg4ff_alternate_modes[i].product_id == entry->wdata.product_id ||
 			    (lg4ff_alternate_modes[i].product_id == 0 && entry->wdata.product_id == entry->wdata.real_product_id))
-				count += scnprintf(buf + count, PAGE_SIZE - count, " *\n");
+				count += sysfs_emit_at(buf, count, " *\n");
 			else
-				count += scnprintf(buf + count, PAGE_SIZE - count, "\n");
+				count += sysfs_emit_at(buf, count, "\n");
 
 			if (count >= PAGE_SIZE - 1)
 				return count;
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index adfa329e917b..d4d91e49bbe8 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -218,7 +218,8 @@ static void magicmouse_emit_touch(struct magicmouse_sc *msc, int raw_id, u8 *tda
 	int pressure = 0;
 
 	if (input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE ||
-	    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2) {
+	    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 ||
+	    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC) {
 		id = (tdata[6] << 2 | tdata[5] >> 6) & 0xf;
 		x = (tdata[1] << 28 | tdata[0] << 20) >> 20;
 		y = -((tdata[2] << 24 | tdata[1] << 16) >> 20);
@@ -370,7 +371,8 @@ static void magicmouse_emit_touch(struct magicmouse_sc *msc, int raw_id, u8 *tda
 
 		if (report_undeciphered) {
 			if (input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE ||
-			    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2)
+			    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 ||
+			    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC)
 				input_event(input, EV_MSC, MSC_RAW, tdata[7]);
 			else if (input->id.product !=
 					 USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 &&
@@ -497,7 +499,8 @@ static int magicmouse_raw_event(struct hid_device *hdev,
 	}
 
 	if (input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE ||
-	    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2) {
+	    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 ||
+	    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC) {
 		magicmouse_emit_buttons(msc, clicks & 3);
 		input_report_rel(input, REL_X, x);
 		input_report_rel(input, REL_Y, y);
@@ -519,7 +522,8 @@ static int magicmouse_event(struct hid_device *hdev, struct hid_field *field,
 		struct hid_usage *usage, __s32 value)
 {
 	struct magicmouse_sc *msc = hid_get_drvdata(hdev);
-	if (msc->input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 &&
+	if ((msc->input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 ||
+	     msc->input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC) &&
 	    field->report->id == MOUSE2_REPORT_ID) {
 		/*
 		 * magic_mouse_raw_event has done all the work. Skip hidinput.
@@ -540,7 +544,8 @@ static int magicmouse_setup_input(struct input_dev *input, struct hid_device *hd
 	__set_bit(EV_KEY, input->evbit);
 
 	if (input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE ||
-	    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2) {
+	    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 ||
+	    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC) {
 		__set_bit(BTN_LEFT, input->keybit);
 		__set_bit(BTN_RIGHT, input->keybit);
 		if (emulate_3button)
@@ -625,7 +630,8 @@ static int magicmouse_setup_input(struct input_dev *input, struct hid_device *hd
 	 * inverse of the reported Y.
 	 */
 	if (input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE ||
-	    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2) {
+	    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 ||
+	    input->id.product == USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC) {
 		input_set_abs_params(input, ABS_MT_ORIENTATION, -31, 32, 1, 0);
 		input_set_abs_params(input, ABS_MT_POSITION_X,
 				     MOUSE_MIN_X, MOUSE_MAX_X, 4, 0);
@@ -741,19 +747,25 @@ static int magicmouse_enable_multitouch(struct hid_device *hdev)
 	int ret;
 	int feature_size;
 
-	if (hdev->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 ||
-	    hdev->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC) {
-		if (hdev->vendor == BT_VENDOR_ID_APPLE) {
+	switch (hdev->product) {
+	case USB_DEVICE_ID_APPLE_MAGICTRACKPAD2:
+	case USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC:
+		switch (hdev->vendor) {
+		case BT_VENDOR_ID_APPLE:
 			feature_size = sizeof(feature_mt_trackpad2_bt);
 			feature = feature_mt_trackpad2_bt;
-		} else { /* USB_VENDOR_ID_APPLE */
+			break;
+		default: /* USB_VENDOR_ID_APPLE */
 			feature_size = sizeof(feature_mt_trackpad2_usb);
 			feature = feature_mt_trackpad2_usb;
 		}
-	} else if (hdev->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2) {
+		break;
+	case USB_DEVICE_ID_APPLE_MAGICMOUSE2:
+	case USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC:
 		feature_size = sizeof(feature_mt_mouse2);
 		feature = feature_mt_mouse2;
-	} else {
+		break;
+	default:
 		feature_size = sizeof(feature_mt);
 		feature = feature_mt;
 	}
@@ -787,6 +799,7 @@ static int magicmouse_fetch_battery(struct hid_device *hdev)
 
 	if (!hdev->battery || hdev->vendor != USB_VENDOR_ID_APPLE ||
 	    (hdev->product != USB_DEVICE_ID_APPLE_MAGICMOUSE2 &&
+	     hdev->product != USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC &&
 	     hdev->product != USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 &&
 	     hdev->product != USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC))
 		return -1;
@@ -857,6 +870,7 @@ static int magicmouse_probe(struct hid_device *hdev,
 
 	if (id->vendor == USB_VENDOR_ID_APPLE &&
 	    (id->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 ||
+	     id->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC ||
 	     ((id->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 ||
 	       id->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC) &&
 	      hdev->type != HID_TYPE_USBMOUSE)))
@@ -868,21 +882,27 @@ static int magicmouse_probe(struct hid_device *hdev,
 		goto err_stop_hw;
 	}
 
-	if (id->product == USB_DEVICE_ID_APPLE_MAGICMOUSE)
-		report = hid_register_report(hdev, HID_INPUT_REPORT,
-			MOUSE_REPORT_ID, 0);
-	else if (id->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2)
-		report = hid_register_report(hdev, HID_INPUT_REPORT,
-			MOUSE2_REPORT_ID, 0);
-	else if (id->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 ||
-		 id->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC) {
-		if (id->vendor == BT_VENDOR_ID_APPLE)
+	switch (id->product) {
+	case USB_DEVICE_ID_APPLE_MAGICMOUSE:
+		report = hid_register_report(hdev, HID_INPUT_REPORT, MOUSE_REPORT_ID, 0);
+		break;
+	case USB_DEVICE_ID_APPLE_MAGICMOUSE2:
+	case USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC:
+		report = hid_register_report(hdev, HID_INPUT_REPORT, MOUSE2_REPORT_ID, 0);
+		break;
+	case USB_DEVICE_ID_APPLE_MAGICTRACKPAD2:
+	case USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC:
+		switch (id->vendor) {
+		case BT_VENDOR_ID_APPLE:
 			report = hid_register_report(hdev, HID_INPUT_REPORT,
 				TRACKPAD2_BT_REPORT_ID, 0);
-		else /* USB_VENDOR_ID_APPLE */
+			break;
+		default:
 			report = hid_register_report(hdev, HID_INPUT_REPORT,
 				TRACKPAD2_USB_REPORT_ID, 0);
-	} else { /* USB_DEVICE_ID_APPLE_MAGICTRACKPAD */
+		}
+		break;
+	default: /* USB_DEVICE_ID_APPLE_MAGICTRACKPAD */
 		report = hid_register_report(hdev, HID_INPUT_REPORT,
 			TRACKPAD_REPORT_ID, 0);
 		report = hid_register_report(hdev, HID_INPUT_REPORT,
@@ -909,7 +929,8 @@ static int magicmouse_probe(struct hid_device *hdev,
 		hid_err(hdev, "unable to request touch data (%d)\n", ret);
 		goto err_stop_hw;
 	}
-	if (ret == -EIO && id->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2) {
+	if (ret == -EIO && (id->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 ||
+			    id->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC)) {
 		schedule_delayed_work(&msc->work, msecs_to_jiffies(500));
 	}
 
@@ -945,6 +966,7 @@ static const __u8 *magicmouse_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	 */
 	if (hdev->vendor == USB_VENDOR_ID_APPLE &&
 	    (hdev->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 ||
+	     hdev->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC ||
 	     hdev->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2 ||
 	     hdev->product == USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC) &&
 	    *rsize == 83 && rdesc[46] == 0x84 && rdesc[58] == 0x85) {
@@ -971,6 +993,10 @@ static const struct hid_device_id magic_mice[] = {
 		USB_DEVICE_ID_APPLE_MAGICMOUSE2), .driver_data = 0 },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE,
 		USB_DEVICE_ID_APPLE_MAGICMOUSE2), .driver_data = 0 },
+	{ HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE,
+		USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC), .driver_data = 0 },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE,
+		USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC), .driver_data = 0 },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
 		USB_DEVICE_ID_APPLE_MAGICTRACKPAD), .driver_data = 0 },
 	{ HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE,
diff --git a/drivers/hid/hid-mcp2200.c b/drivers/hid/hid-mcp2200.c
index bf57f7f6caa0..e6ea0a2140eb 100644
--- a/drivers/hid/hid-mcp2200.c
+++ b/drivers/hid/hid-mcp2200.c
@@ -127,8 +127,8 @@ static int mcp_cmd_read_all(struct mcp2200 *mcp)
 	return mcp->status;
 }
 
-static void mcp_set_multiple(struct gpio_chip *gc, unsigned long *mask,
-			     unsigned long *bits)
+static int mcp_set_multiple(struct gpio_chip *gc, unsigned long *mask,
+			    unsigned long *bits)
 {
 	struct mcp2200 *mcp = gpiochip_get_data(gc);
 	u8 value;
@@ -150,16 +150,20 @@ static void mcp_set_multiple(struct gpio_chip *gc, unsigned long *mask,
 
 	if (status == sizeof(struct mcp_set_clear_outputs))
 		mcp->gpio_val = value;
+	else
+		status = -EIO;
 
 	mutex_unlock(&mcp->lock);
+
+	return status;
 }
 
-static void mcp_set(struct gpio_chip *gc, unsigned int gpio_nr, int value)
+static int mcp_set(struct gpio_chip *gc, unsigned int gpio_nr, int value)
 {
 	unsigned long mask = 1 << gpio_nr;
 	unsigned long bmap_value = value << gpio_nr;
 
-	mcp_set_multiple(gc, &mask, &bmap_value);
+	return mcp_set_multiple(gc, &mask, &bmap_value);
 }
 
 static int mcp_get_multiple(struct gpio_chip *gc, unsigned long *mask,
@@ -263,9 +267,10 @@ static int mcp_direction_output(struct gpio_chip *gc, unsigned int gpio_nr,
 	bmap_value = value << gpio_nr;
 
 	ret = mcp_set_direction(gc, gpio_nr, MCP2200_DIR_OUT);
-	if (!ret)
-		mcp_set_multiple(gc, &mask, &bmap_value);
-	return ret;
+	if (ret)
+		return ret;
+
+	return mcp_set_multiple(gc, &mask, &bmap_value);
 }
 
 static const struct gpio_chip template_chip = {
@@ -274,8 +279,8 @@ static const struct gpio_chip template_chip = {
 	.get_direction		= mcp_get_direction,
 	.direction_input	= mcp_direction_input,
 	.direction_output	= mcp_direction_output,
-	.set			= mcp_set,
-	.set_multiple		= mcp_set_multiple,
+	.set_rv			= mcp_set,
+	.set_multiple_rv	= mcp_set_multiple,
 	.get			= mcp_get,
 	.get_multiple		= mcp_get_multiple,
 	.base			= -1,
diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c
index 0f93c22a479f..6c0ac14f11a6 100644
--- a/drivers/hid/hid-mcp2221.c
+++ b/drivers/hid/hid-mcp2221.c
@@ -624,10 +624,10 @@ static int mcp_gpio_get(struct gpio_chip *gc,
 	return ret;
 }
 
-static void mcp_gpio_set(struct gpio_chip *gc,
-				unsigned int offset, int value)
+static int mcp_gpio_set(struct gpio_chip *gc, unsigned int offset, int value)
 {
 	struct mcp2221 *mcp = gpiochip_get_data(gc);
+	int ret;
 
 	memset(mcp->txbuf, 0, 18);
 	mcp->txbuf[0] = MCP2221_GPIO_SET;
@@ -638,8 +638,10 @@ static void mcp_gpio_set(struct gpio_chip *gc,
 	mcp->txbuf[mcp->gp_idx] = !!value;
 
 	mutex_lock(&mcp->lock);
-	mcp_send_data_req_status(mcp, mcp->txbuf, 18);
+	ret = mcp_send_data_req_status(mcp, mcp->txbuf, 18);
 	mutex_unlock(&mcp->lock);
+
+	return ret;
 }
 
 static int mcp_gpio_dir_set(struct mcp2221 *mcp,
@@ -1206,7 +1208,7 @@ static int mcp2221_probe(struct hid_device *hdev,
 	mcp->gc->direction_input = mcp_gpio_direction_input;
 	mcp->gc->direction_output = mcp_gpio_direction_output;
 	mcp->gc->get_direction = mcp_gpio_get_direction;
-	mcp->gc->set = mcp_gpio_set;
+	mcp->gc->set_rv = mcp_gpio_set;
 	mcp->gc->get = mcp_gpio_get;
 	mcp->gc->ngpio = MCP_NGPIO;
 	mcp->gc->base = -1;
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 7ac8e16e6158..ded0fef7d8c7 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -1887,6 +1887,16 @@ static void mt_remove(struct hid_device *hdev)
 	hid_hw_stop(hdev);
 }
 
+static void mt_on_hid_hw_open(struct hid_device *hdev)
+{
+	mt_set_modes(hdev, HID_LATENCY_NORMAL, TOUCHPAD_REPORT_ALL);
+}
+
+static void mt_on_hid_hw_close(struct hid_device *hdev)
+{
+	mt_set_modes(hdev, HID_LATENCY_HIGH, TOUCHPAD_REPORT_NONE);
+}
+
 /*
  * This list contains only:
  * - VID/PID of products not working with the default multitouch handling
@@ -2354,5 +2364,7 @@ static struct hid_driver mt_driver = {
 	.suspend = pm_ptr(mt_suspend),
 	.reset_resume = pm_ptr(mt_reset_resume),
 	.resume = pm_ptr(mt_resume),
+	.on_hid_hw_open = mt_on_hid_hw_open,
+	.on_hid_hw_close = mt_on_hid_hw_close,
 };
 module_hid_driver(mt_driver);
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 0731473cc9b1..7fefeb413ec3 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -1063,7 +1063,7 @@ bool hid_ignore(struct hid_device *hdev)
 	}
 
 	if (hdev->type == HID_TYPE_USBMOUSE &&
-	    hid_match_id(hdev, hid_mouse_ignore_list))
+	    hdev->quirks & HID_QUIRK_IGNORE_MOUSE)
 		return true;
 
 	return !!hid_match_id(hdev, hid_ignore_list);
@@ -1267,6 +1267,9 @@ static unsigned long hid_gets_squirk(const struct hid_device *hdev)
 	if (hid_match_id(hdev, hid_ignore_list))
 		quirks |= HID_QUIRK_IGNORE;
 
+	if (hid_match_id(hdev, hid_mouse_ignore_list))
+		quirks |= HID_QUIRK_IGNORE_MOUSE;
+
 	if (hid_match_id(hdev, hid_have_special_driver))
 		quirks |= HID_QUIRK_HAVE_SPECIAL_DRIVER;
 
diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
index fa51155ebe39..8a8c4a46f927 100644
--- a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
+++ b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
@@ -82,15 +82,10 @@ static int quicki2c_acpi_get_dsd_property(struct acpi_device *adev, acpi_string
 {
 	acpi_handle handle = acpi_device_handle(adev);
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-	union acpi_object obj = { .type = type };
-	struct acpi_object_list arg_list = {
-		.count = 1,
-		.pointer = &obj,
-	};
 	union acpi_object *ret_obj;
 	acpi_status status;
 
-	status = acpi_evaluate_object(handle, dsd_method_name, &arg_list, &buffer);
+	status = acpi_evaluate_object(handle, dsd_method_name, NULL, &buffer);
 	if (ACPI_FAILURE(status)) {
 		acpi_handle_err(handle,
 				"Can't evaluate %s method: %d\n", dsd_method_name, status);
diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c
index 4fc78b5a04b5..c105df7f6c87 100644
--- a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c
+++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c
@@ -1121,7 +1121,7 @@ EXPORT_SYMBOL_NS_GPL(thc_port_select, "INTEL_THC");
 
 static u8 thc_get_spi_freq_div_val(struct thc_device *dev, u32 spi_freq_val)
 {
-	int frequency[] = {
+	static const int frequency[] = {
 		THC_SPI_FREQUENCY_7M,
 		THC_SPI_FREQUENCY_15M,
 		THC_SPI_FREQUENCY_17M,
@@ -1130,7 +1130,7 @@ static u8 thc_get_spi_freq_div_val(struct thc_device *dev, u32 spi_freq_val)
 		THC_SPI_FREQUENCY_31M,
 		THC_SPI_FREQUENCY_41M,
 	};
-	u8 frequency_div[] = {
+	static const u8 frequency_div[] = {
 		THC_SPI_FRQ_DIV_2,
 		THC_SPI_FRQ_DIV_1,
 		THC_SPI_FRQ_DIV_7,
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 7d9297fad90e..d4cbecc668ec 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -984,12 +984,11 @@ static int usbhid_parse(struct hid_device *hid)
 	struct usb_host_interface *interface = intf->cur_altsetting;
 	struct usb_device *dev = interface_to_usbdev (intf);
 	struct hid_descriptor *hdesc;
+	struct hid_class_descriptor *hcdesc;
 	u32 quirks = 0;
 	unsigned int rsize = 0;
 	char *rdesc;
-	int ret, n;
-	int num_descriptors;
-	size_t offset = offsetof(struct hid_descriptor, desc);
+	int ret;
 
 	quirks = hid_lookup_quirk(hid);
 
@@ -1011,20 +1010,19 @@ static int usbhid_parse(struct hid_device *hid)
 		return -ENODEV;
 	}
 
-	if (hdesc->bLength < sizeof(struct hid_descriptor)) {
-		dbg_hid("hid descriptor is too short\n");
+	if (!hdesc->bNumDescriptors ||
+	    hdesc->bLength != sizeof(*hdesc) +
+			      (hdesc->bNumDescriptors - 1) * sizeof(*hcdesc)) {
+		dbg_hid("hid descriptor invalid, bLen=%hhu bNum=%hhu\n",
+			hdesc->bLength, hdesc->bNumDescriptors);
 		return -EINVAL;
 	}
 
 	hid->version = le16_to_cpu(hdesc->bcdHID);
 	hid->country = hdesc->bCountryCode;
 
-	num_descriptors = min_t(int, hdesc->bNumDescriptors,
-	       (hdesc->bLength - offset) / sizeof(struct hid_class_descriptor));
-
-	for (n = 0; n < num_descriptors; n++)
-		if (hdesc->desc[n].bDescriptorType == HID_DT_REPORT)
-			rsize = le16_to_cpu(hdesc->desc[n].wDescriptorLength);
+	if (hdesc->rpt_desc.bDescriptorType == HID_DT_REPORT)
+		rsize = le16_to_cpu(hdesc->rpt_desc.wDescriptorLength);
 
 	if (!rsize || rsize > HID_MAX_DESCRIPTOR_SIZE) {
 		dbg_hid("weird size of report descriptor (%u)\n", rsize);
@@ -1052,6 +1050,11 @@ static int usbhid_parse(struct hid_device *hid)
 		goto err;
 	}
 
+	if (hdesc->bNumDescriptors > 1)
+		hid_warn(intf,
+			"%u unsupported optional hid class descriptors\n",
+			(int)(hdesc->bNumDescriptors - 1));
+
 	hid->quirks |= quirks;
 
 	return 0;
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
index 6c1416167bd2..1cd188b73b74 100644
--- a/drivers/hv/Kconfig
+++ b/drivers/hv/Kconfig
@@ -5,17 +5,18 @@ menu "Microsoft Hyper-V guest support"
 config HYPERV
 	tristate "Microsoft Hyper-V client drivers"
 	depends on (X86 && X86_LOCAL_APIC && HYPERVISOR_GUEST) \
-		|| (ACPI && ARM64 && !CPU_BIG_ENDIAN)
+		|| (ARM64 && !CPU_BIG_ENDIAN)
 	select PARAVIRT
 	select X86_HV_CALLBACK_VECTOR if X86
 	select OF_EARLY_FLATTREE if OF
+	select SYSFB if !HYPERV_VTL_MODE
 	help
 	  Select this option to run Linux as a Hyper-V client operating
 	  system.
 
 config HYPERV_VTL_MODE
 	bool "Enable Linux to boot in VTL context"
-	depends on X86_64 && HYPERV
+	depends on (X86_64 || ARM64) && HYPERV
 	depends on SMP
 	default n
 	help
@@ -31,7 +32,7 @@ config HYPERV_VTL_MODE
 
 	  Select this option to build a Linux kernel to run at a VTL other than
 	  the normal VTL0, which currently is only VTL2.  This option
-	  initializes the x86 platform for VTL2, and adds the ability to boot
+	  initializes the kernel to run in VTL2, and adds the ability to boot
 	  secondary CPUs directly into 64-bit context as required for VTLs other
 	  than 0.  A kernel built with this option must run at VTL2, and will
 	  not run as a normal guest.
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 8351360bba16..be490c598785 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -207,10 +207,19 @@ int vmbus_connect(void)
 	mutex_init(&vmbus_connection.channel_mutex);
 
 	/*
+	 * The following Hyper-V interrupt and monitor pages can be used by
+	 * UIO for mapping to user-space, so they should always be allocated on
+	 * system page boundaries. The system page size must be >= the Hyper-V
+	 * page size.
+	 */
+	BUILD_BUG_ON(PAGE_SIZE < HV_HYP_PAGE_SIZE);
+
+	/*
 	 * Setup the vmbus event connection for channel interrupt
 	 * abstraction stuff
 	 */
-	vmbus_connection.int_page = hv_alloc_hyperv_zeroed_page();
+	vmbus_connection.int_page =
+		(void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 	if (vmbus_connection.int_page == NULL) {
 		ret = -ENOMEM;
 		goto cleanup;
@@ -225,8 +234,8 @@ int vmbus_connect(void)
 	 * Setup the monitor notification facility. The 1st page for
 	 * parent->child and the 2nd page for child->parent
 	 */
-	vmbus_connection.monitor_pages[0] = hv_alloc_hyperv_page();
-	vmbus_connection.monitor_pages[1] = hv_alloc_hyperv_page();
+	vmbus_connection.monitor_pages[0] = (void *)__get_free_page(GFP_KERNEL);
+	vmbus_connection.monitor_pages[1] = (void *)__get_free_page(GFP_KERNEL);
 	if ((vmbus_connection.monitor_pages[0] == NULL) ||
 	    (vmbus_connection.monitor_pages[1] == NULL)) {
 		ret = -ENOMEM;
@@ -342,21 +351,23 @@ void vmbus_disconnect(void)
 		destroy_workqueue(vmbus_connection.work_queue);
 
 	if (vmbus_connection.int_page) {
-		hv_free_hyperv_page(vmbus_connection.int_page);
+		free_page((unsigned long)vmbus_connection.int_page);
 		vmbus_connection.int_page = NULL;
 	}
 
 	if (vmbus_connection.monitor_pages[0]) {
 		if (!set_memory_encrypted(
 			(unsigned long)vmbus_connection.monitor_pages[0], 1))
-			hv_free_hyperv_page(vmbus_connection.monitor_pages[0]);
+			free_page((unsigned long)
+				vmbus_connection.monitor_pages[0]);
 		vmbus_connection.monitor_pages[0] = NULL;
 	}
 
 	if (vmbus_connection.monitor_pages[1]) {
 		if (!set_memory_encrypted(
 			(unsigned long)vmbus_connection.monitor_pages[1], 1))
-			hv_free_hyperv_page(vmbus_connection.monitor_pages[1]);
+			free_page((unsigned long)
+				vmbus_connection.monitor_pages[1]);
 		vmbus_connection.monitor_pages[1] = NULL;
 	}
 }
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index 59792e00cecf..49898d10faff 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -105,45 +105,6 @@ void __init hv_common_free(void)
 	hv_synic_eventring_tail = NULL;
 }
 
-/*
- * Functions for allocating and freeing memory with size and
- * alignment HV_HYP_PAGE_SIZE. These functions are needed because
- * the guest page size may not be the same as the Hyper-V page
- * size. We depend upon kmalloc() aligning power-of-two size
- * allocations to the allocation size boundary, so that the
- * allocated memory appears to Hyper-V as a page of the size
- * it expects.
- */
-
-void *hv_alloc_hyperv_page(void)
-{
-	BUILD_BUG_ON(PAGE_SIZE <  HV_HYP_PAGE_SIZE);
-
-	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
-		return (void *)__get_free_page(GFP_KERNEL);
-	else
-		return kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
-}
-EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page);
-
-void *hv_alloc_hyperv_zeroed_page(void)
-{
-	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
-		return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-	else
-		return kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
-}
-EXPORT_SYMBOL_GPL(hv_alloc_hyperv_zeroed_page);
-
-void hv_free_hyperv_page(void *addr)
-{
-	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
-		free_page((unsigned long)addr);
-	else
-		kfree(addr);
-}
-EXPORT_SYMBOL_GPL(hv_free_hyperv_page);
-
 static void *hv_panic_page;
 
 /*
@@ -272,7 +233,7 @@ static void hv_kmsg_dump_unregister(void)
 	atomic_notifier_chain_unregister(&panic_notifier_list,
 					 &hyperv_panic_report_block);
 
-	hv_free_hyperv_page(hv_panic_page);
+	kfree(hv_panic_page);
 	hv_panic_page = NULL;
 }
 
@@ -280,7 +241,7 @@ static void hv_kmsg_dump_register(void)
 {
 	int ret;
 
-	hv_panic_page = hv_alloc_hyperv_zeroed_page();
+	hv_panic_page = kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
 	if (!hv_panic_page) {
 		pr_err("Hyper-V: panic message page memory allocation failed\n");
 		return;
@@ -289,7 +250,7 @@ static void hv_kmsg_dump_register(void)
 	ret = kmsg_dump_register(&hv_kmsg_dumper);
 	if (ret) {
 		pr_err("Hyper-V: kmsg dump register error 0x%x\n", ret);
-		hv_free_hyperv_page(hv_panic_page);
+		kfree(hv_panic_page);
 		hv_panic_page = NULL;
 	}
 }
@@ -317,6 +278,37 @@ void __init hv_get_partition_id(void)
 		pr_err("Hyper-V: failed to get partition ID: %#x\n",
 		       hv_result(status));
 }
+#if IS_ENABLED(CONFIG_HYPERV_VTL_MODE)
+u8 __init get_vtl(void)
+{
+	u64 control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_REGISTERS;
+	struct hv_input_get_vp_registers *input;
+	struct hv_output_get_vp_registers *output;
+	unsigned long flags;
+	u64 ret;
+
+	local_irq_save(flags);
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+	memset(input, 0, struct_size(input, names, 1));
+	input->partition_id = HV_PARTITION_ID_SELF;
+	input->vp_index = HV_VP_INDEX_SELF;
+	input->input_vtl.as_uint8 = 0;
+	input->names[0] = HV_REGISTER_VSM_VP_STATUS;
+
+	ret = hv_do_hypercall(control, input, output);
+	if (hv_result_success(ret)) {
+		ret = output->values[0].reg8 & HV_VTL_MASK;
+	} else {
+		pr_err("Failed to get VTL(error: %lld) exiting...\n", ret);
+		BUG();
+	}
+
+	local_irq_restore(flags);
+	return ret;
+}
+#endif
 
 int __init hv_common_init(void)
 {
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index d74adb5bba44..33b524b4eb5e 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -45,7 +45,8 @@ struct vmbus_dynid {
 	struct hv_vmbus_device_id id;
 };
 
-static struct device  *hv_dev;
+/* VMBus Root Device */
+static struct device  *vmbus_root_device;
 
 static int hyperv_cpuhp_online;
 
@@ -80,9 +81,15 @@ static struct resource *fb_mmio;
 static struct resource *hyperv_mmio;
 static DEFINE_MUTEX(hyperv_mmio_lock);
 
+struct device *hv_get_vmbus_root_device(void)
+{
+	return vmbus_root_device;
+}
+EXPORT_SYMBOL_GPL(hv_get_vmbus_root_device);
+
 static int vmbus_exists(void)
 {
-	if (hv_dev == NULL)
+	if (vmbus_root_device == NULL)
 		return -ENODEV;
 
 	return 0;
@@ -707,7 +714,30 @@ static const struct hv_vmbus_device_id *hv_vmbus_get_id(const struct hv_driver *
 	return id;
 }
 
-/* vmbus_add_dynid - add a new device ID to this driver and re-probe devices */
+/* vmbus_add_dynid - add a new device ID to this driver and re-probe devices
+ *
+ * This function can race with vmbus_device_register(). This function is
+ * typically running on a user thread in response to writing to the "new_id"
+ * sysfs entry for a driver. vmbus_device_register() is running on a
+ * workqueue thread in response to the Hyper-V host offering a device to the
+ * guest. This function calls driver_attach(), which looks for an existing
+ * device matching the new id, and attaches the driver to which the new id
+ * has been assigned. vmbus_device_register() calls device_register(), which
+ * looks for a driver that matches the device being registered. If both
+ * operations are running simultaneously, the device driver probe function runs
+ * on whichever thread establishes the linkage between the driver and device.
+ *
+ * In most cases, it doesn't matter which thread runs the driver probe
+ * function. But if vmbus_device_register() does not find a matching driver,
+ * it proceeds to create the "channels" subdirectory and numbered per-channel
+ * subdirectory in sysfs. While that multi-step creation is in progress, this
+ * function could run the driver probe function. If the probe function checks
+ * for, or operates on, entries in the "channels" subdirectory, including by
+ * calling hv_create_ring_sysfs(), the operation may or may not succeed
+ * depending on the race. The race can't create a kernel failure in VMBus
+ * or device subsystem code, but probe functions in VMBus drivers doing such
+ * operations must be prepared for the failure case.
+ */
 static int vmbus_add_dynid(struct hv_driver *drv, guid_t *guid)
 {
 	struct vmbus_dynid *dynid;
@@ -861,7 +891,7 @@ static int vmbus_dma_configure(struct device *child_device)
 	 * On x86/x64 coherence is assumed and these calls have no effect.
 	 */
 	hv_setup_dma_ops(child_device,
-		device_get_dma_attr(hv_dev) == DEV_DMA_COHERENT);
+		device_get_dma_attr(vmbus_root_device) == DEV_DMA_COHERENT);
 	return 0;
 }
 
@@ -1921,7 +1951,8 @@ static const struct kobj_type vmbus_chan_ktype = {
  * ring for userspace to use.
  * Note: Race conditions can happen with userspace and it is not encouraged to create new
  * use-cases for this. This was added to maintain backward compatibility, while solving
- * one of the race conditions in uio_hv_generic while creating sysfs.
+ * one of the race conditions in uio_hv_generic while creating sysfs. See comments with
+ * vmbus_add_dynid() and vmbus_device_register().
  *
  * Returns 0 on success or error code on failure.
  */
@@ -2037,7 +2068,7 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 		     &child_device_obj->channel->offermsg.offer.if_instance);
 
 	child_device_obj->device.bus = &hv_bus;
-	child_device_obj->device.parent = hv_dev;
+	child_device_obj->device.parent = vmbus_root_device;
 	child_device_obj->device.release = vmbus_device_release;
 
 	child_device_obj->device.dma_parms = &child_device_obj->dma_parms;
@@ -2055,6 +2086,20 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 		return ret;
 	}
 
+	/*
+	 * If device_register() found a driver to assign to the device, the
+	 * driver's probe function has already run at this point. If that
+	 * probe function accesses or operates on the "channels" subdirectory
+	 * in sysfs, those operations will have failed because the "channels"
+	 * subdirectory doesn't exist until the code below runs. Or if the
+	 * probe function creates a /dev entry, a user space program could
+	 * find and open the /dev entry, and then create a race by accessing
+	 * the "channels" subdirectory while the creation steps are in progress
+	 * here. The race can't result in a kernel failure, but the user space
+	 * program may get an error in accessing "channels" or its
+	 * subdirectories. See also comments with vmbus_add_dynid() about a
+	 * related race condition.
+	 */
 	child_device_obj->channels_kset = kset_create_and_add("channels",
 							      NULL, kobj);
 	if (!child_device_obj->channels_kset) {
@@ -2412,7 +2457,7 @@ static int vmbus_acpi_add(struct platform_device *pdev)
 	struct acpi_device *ancestor;
 	struct acpi_device *device = ACPI_COMPANION(&pdev->dev);
 
-	hv_dev = &device->dev;
+	vmbus_root_device = &device->dev;
 
 	/*
 	 * Older versions of Hyper-V for ARM64 fail to include the _CCA
@@ -2465,6 +2510,31 @@ static int vmbus_acpi_add(struct platform_device *pdev)
 }
 #endif
 
+static int vmbus_set_irq(struct platform_device *pdev)
+{
+	struct irq_data *data;
+	int irq;
+	irq_hw_number_t hwirq;
+
+	irq = platform_get_irq(pdev, 0);
+	/* platform_get_irq() may not return 0. */
+	if (irq < 0)
+		return irq;
+
+	data = irq_get_irq_data(irq);
+	if (!data) {
+		pr_err("No interrupt data for VMBus virq %d\n", irq);
+		return -ENODEV;
+	}
+	hwirq = irqd_to_hwirq(data);
+
+	vmbus_irq = irq;
+	vmbus_interrupt = hwirq;
+	pr_debug("VMBus virq %d, hwirq %d\n", vmbus_irq, vmbus_interrupt);
+
+	return 0;
+}
+
 static int vmbus_device_add(struct platform_device *pdev)
 {
 	struct resource **cur_res = &hyperv_mmio;
@@ -2473,12 +2543,17 @@ static int vmbus_device_add(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	int ret;
 
-	hv_dev = &pdev->dev;
+	vmbus_root_device = &pdev->dev;
 
 	ret = of_range_parser_init(&parser, np);
 	if (ret)
 		return ret;
 
+	if (!__is_defined(HYPERVISOR_CALLBACK_VECTOR))
+		ret = vmbus_set_irq(pdev);
+	if (ret)
+		return ret;
+
 	for_each_of_range(&parser, &range) {
 		struct resource *res;
 
@@ -2786,7 +2861,7 @@ static int __init hv_acpi_init(void)
 	if (ret)
 		return ret;
 
-	if (!hv_dev) {
+	if (!vmbus_root_device) {
 		ret = -ENODEV;
 		goto cleanup;
 	}
@@ -2817,7 +2892,7 @@ static int __init hv_acpi_init(void)
 
 cleanup:
 	platform_driver_unregister(&vmbus_platform_driver);
-	hv_dev = NULL;
+	vmbus_root_device = NULL;
 	return ret;
 }
 
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 5fd93aad2d6d..1b1d64493909 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -335,6 +335,26 @@ config SENSORS_K10TEMP
 	  This driver can also be built as a module. If so, the module
 	  will be called k10temp.
 
+config SENSORS_KBATT
+	tristate "KEBA battery controller support"
+	depends on KEBA_CP500
+	help
+	  This driver supports the battery monitoring controller found in
+	  KEBA system FPGA devices.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called kbatt.
+
+config SENSORS_KFAN
+	tristate "KEBA fan controller support"
+	depends on KEBA_CP500
+	help
+	  This driver supports the fan controller found in KEBA system
+	  FPGA devices.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called kfan.
+
 config SENSORS_FAM15H_POWER
 	tristate "AMD Family 15h processor power"
 	depends on X86 && PCI && CPU_SUP_AMD
@@ -1308,6 +1328,15 @@ config SENSORS_MAX31790
 	  This driver can also be built as a module. If so, the module
 	  will be called max31790.
 
+config SENSORS_MAX77705
+	tristate "MAX77705 current and voltage sensor"
+	depends on MFD_MAX77705
+	help
+	  If you say yes here you get support for MAX77705 sensors connected with I2C.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called max77705-hwmon.
+
 config SENSORS_MC34VR500
 	tristate "NXP MC34VR500 hardware monitoring driver"
 	depends on I2C
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index e3468d024ff3..48e5866c0c9a 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -110,6 +110,8 @@ obj-$(CONFIG_SENSORS_IT87)	+= it87.o
 obj-$(CONFIG_SENSORS_JC42)	+= jc42.o
 obj-$(CONFIG_SENSORS_K8TEMP)	+= k8temp.o
 obj-$(CONFIG_SENSORS_K10TEMP)	+= k10temp.o
+obj-$(CONFIG_SENSORS_KBATT)	+= kbatt.o
+obj-$(CONFIG_SENSORS_KFAN)	+= kfan.o
 obj-$(CONFIG_SENSORS_LAN966X)	+= lan966x-hwmon.o
 obj-$(CONFIG_SENSORS_LENOVO_EC)	+= lenovo-ec-sensors.o
 obj-$(CONFIG_SENSORS_LINEAGE)	+= lineage-pem.o
@@ -161,6 +163,7 @@ obj-$(CONFIG_SENSORS_MAX6650)	+= max6650.o
 obj-$(CONFIG_SENSORS_MAX6697)	+= max6697.o
 obj-$(CONFIG_SENSORS_MAX31790)	+= max31790.o
 obj-$(CONFIG_MAX31827) += max31827.o
+obj-$(CONFIG_SENSORS_MAX77705) += max77705-hwmon.o
 obj-$(CONFIG_SENSORS_MC13783_ADC)+= mc13783-adc.o
 obj-$(CONFIG_SENSORS_MC34VR500)	+= mc34vr500.o
 obj-$(CONFIG_SENSORS_MCP3021)	+= mcp3021.o
diff --git a/drivers/hwmon/aht10.c b/drivers/hwmon/aht10.c
index 312ef3e98754..d1c55e2eb479 100644
--- a/drivers/hwmon/aht10.c
+++ b/drivers/hwmon/aht10.c
@@ -94,7 +94,7 @@ struct aht10_data {
 	unsigned int meas_size;
 };
 
-/**
+/*
  * aht10_init() - Initialize an AHT10/AHT20 chip
  * @data: the data associated with this AHT10/AHT20 chip
  * Return: 0 if successful, 1 if not
@@ -124,7 +124,7 @@ static int aht10_init(struct aht10_data *data)
 	return 0;
 }
 
-/**
+/*
  * aht10_polltime_expired() - check if the minimum poll interval has
  *                                  expired
  * @data: the data containing the time to compare
@@ -140,7 +140,7 @@ static int aht10_polltime_expired(struct aht10_data *data)
 
 DECLARE_CRC8_TABLE(crc8_table);
 
-/**
+/*
  * crc8_check() - check crc of the sensor's measurements
  * @raw_data: data frame received from sensor(including crc as the last byte)
  * @count: size of the data frame
@@ -155,7 +155,7 @@ static int crc8_check(u8 *raw_data, int count)
 	return crc8(crc8_table, raw_data, count, CRC8_INIT_VALUE);
 }
 
-/**
+/*
  * aht10_read_values() - read and parse the raw data from the AHT10/AHT20
  * @data: the struct aht10_data to use for the lock
  * Return: 0 if successful, 1 if not
@@ -214,7 +214,7 @@ static int aht10_read_values(struct aht10_data *data)
 	return 0;
 }
 
-/**
+/*
  * aht10_interval_write() - store the given minimum poll interval.
  * Return: 0 on success, -EINVAL if a value lower than the
  *         AHT10_MIN_POLL_INTERVAL is given
@@ -226,7 +226,7 @@ static ssize_t aht10_interval_write(struct aht10_data *data,
 	return 0;
 }
 
-/**
+/*
  * aht10_interval_read() - read the minimum poll interval
  *                            in milliseconds
  */
@@ -237,7 +237,7 @@ static ssize_t aht10_interval_read(struct aht10_data *data,
 	return 0;
 }
 
-/**
+/*
  * aht10_temperature1_read() - read the temperature in millidegrees
  */
 static int aht10_temperature1_read(struct aht10_data *data, long *val)
@@ -252,7 +252,7 @@ static int aht10_temperature1_read(struct aht10_data *data, long *val)
 	return 0;
 }
 
-/**
+/*
  * aht10_humidity1_read() - read the relative humidity in millipercent
  */
 static int aht10_humidity1_read(struct aht10_data *data, long *val)
diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c
index 1e3c6acd8974..13a789cc85d2 100644
--- a/drivers/hwmon/amc6821.c
+++ b/drivers/hwmon/amc6821.c
@@ -23,9 +23,12 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/of_platform.h>
+#include <linux/pwm.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
 
+#include <dt-bindings/pwm/pwm.h>
+
 /*
  * Addresses to scan.
  */
@@ -37,7 +40,7 @@ static const unsigned short normal_i2c[] = {0x18, 0x19, 0x1a, 0x2c, 0x2d, 0x2e,
  * Insmod parameters
  */
 
-static int pwminv;	/*Inverted PWM output. */
+static int pwminv = -1; /*Inverted PWM output. */
 module_param(pwminv, int, 0444);
 
 static int init = 1; /*Power-on initialization.*/
@@ -845,9 +848,43 @@ static int amc6821_detect(struct i2c_client *client, struct i2c_board_info *info
 	return 0;
 }
 
-static int amc6821_init_client(struct amc6821_data *data)
+static enum pwm_polarity amc6821_pwm_polarity(struct i2c_client *client)
+{
+	enum pwm_polarity polarity = PWM_POLARITY_NORMAL;
+	struct of_phandle_args args;
+	struct device_node *fan_np;
+
+	/*
+	 * For backward compatibility, the pwminv module parameter takes
+	 * always the precedence over any other device description
+	 */
+	if (pwminv == 0)
+		return PWM_POLARITY_NORMAL;
+	if (pwminv > 0)
+		return PWM_POLARITY_INVERSED;
+
+	fan_np = of_get_child_by_name(client->dev.of_node, "fan");
+	if (!fan_np)
+		return PWM_POLARITY_NORMAL;
+
+	if (of_parse_phandle_with_args(fan_np, "pwms", "#pwm-cells", 0, &args))
+		goto out;
+	of_node_put(args.np);
+
+	if (args.args_count != 2)
+		goto out;
+
+	if (args.args[1] & PWM_POLARITY_INVERTED)
+		polarity = PWM_POLARITY_INVERSED;
+out:
+	of_node_put(fan_np);
+	return polarity;
+}
+
+static int amc6821_init_client(struct i2c_client *client, struct amc6821_data *data)
 {
 	struct regmap *regmap = data->regmap;
+	u32 regval;
 	int err;
 
 	if (init) {
@@ -864,11 +901,14 @@ static int amc6821_init_client(struct amc6821_data *data)
 		if (err)
 			return err;
 
+		regval = AMC6821_CONF1_START;
+		if (amc6821_pwm_polarity(client) == PWM_POLARITY_INVERSED)
+			regval |= AMC6821_CONF1_PWMINV;
+
 		err = regmap_update_bits(regmap, AMC6821_REG_CONF1,
 					 AMC6821_CONF1_THERMOVIE | AMC6821_CONF1_FANIE |
 					 AMC6821_CONF1_START | AMC6821_CONF1_PWMINV,
-					 AMC6821_CONF1_START |
-					 (pwminv ? AMC6821_CONF1_PWMINV : 0));
+					 regval);
 		if (err)
 			return err;
 	}
@@ -916,7 +956,7 @@ static int amc6821_probe(struct i2c_client *client)
 				     "Failed to initialize regmap\n");
 	data->regmap = regmap;
 
-	err = amc6821_init_client(data);
+	err = amc6821_init_client(client, data);
 	if (err)
 		return err;
 
diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c
index 006ced5ab6e6..e0a95197c71b 100644
--- a/drivers/hwmon/asus-ec-sensors.c
+++ b/drivers/hwmon/asus-ec-sensors.c
@@ -169,7 +169,11 @@ enum board_family {
 	family_intel_600_series
 };
 
-/* All the known sensors for ASUS EC controllers */
+/*
+ * All the known sensors for ASUS EC controllers. These arrays have to be sorted
+ * by the full ((bank << 8) + index) register index (see asus_ec_block_read() as
+ * to why).
+ */
 static const struct ec_sensor_info sensors_family_amd_400[] = {
 	[ec_sensor_temp_chipset] =
 		EC_SENSOR("Chipset", hwmon_temp, 1, 0x00, 0x3a),
@@ -183,10 +187,10 @@ static const struct ec_sensor_info sensors_family_amd_400[] = {
 		EC_SENSOR("VRM", hwmon_temp, 1, 0x00, 0x3e),
 	[ec_sensor_in_cpu_core] =
 		EC_SENSOR("CPU Core", hwmon_in, 2, 0x00, 0xa2),
-	[ec_sensor_fan_cpu_opt] =
-		EC_SENSOR("CPU_Opt", hwmon_fan, 2, 0x00, 0xbc),
 	[ec_sensor_fan_vrm_hs] =
 		EC_SENSOR("VRM HS", hwmon_fan, 2, 0x00, 0xb2),
+	[ec_sensor_fan_cpu_opt] =
+		EC_SENSOR("CPU_Opt", hwmon_fan, 2, 0x00, 0xbc),
 	[ec_sensor_fan_chipset] =
 		/* no chipset fans in this generation */
 		EC_SENSOR("Chipset", hwmon_fan, 0, 0x00, 0x00),
@@ -194,10 +198,10 @@ static const struct ec_sensor_info sensors_family_amd_400[] = {
 		EC_SENSOR("Water_Flow", hwmon_fan, 2, 0x00, 0xb4),
 	[ec_sensor_curr_cpu] =
 		EC_SENSOR("CPU", hwmon_curr, 1, 0x00, 0xf4),
-	[ec_sensor_temp_water_in] =
-		EC_SENSOR("Water_In", hwmon_temp, 1, 0x01, 0x0d),
 	[ec_sensor_temp_water_out] =
 		EC_SENSOR("Water_Out", hwmon_temp, 1, 0x01, 0x0b),
+	[ec_sensor_temp_water_in] =
+		EC_SENSOR("Water_In", hwmon_temp, 1, 0x01, 0x0d),
 };
 
 static const struct ec_sensor_info sensors_family_amd_500[] = {
@@ -239,19 +243,20 @@ static const struct ec_sensor_info sensors_family_amd_500[] = {
 
 static const struct ec_sensor_info sensors_family_amd_600[] = {
 	[ec_sensor_temp_cpu] = EC_SENSOR("CPU", hwmon_temp, 1, 0x00, 0x30),
-	[ec_sensor_temp_cpu_package] = EC_SENSOR("CPU Package", hwmon_temp, 1, 0x00, 0x31),
+	[ec_sensor_temp_cpu_package] =
+		EC_SENSOR("CPU Package", hwmon_temp, 1, 0x00, 0x31),
 	[ec_sensor_temp_mb] =
 	EC_SENSOR("Motherboard", hwmon_temp, 1, 0x00, 0x32),
 	[ec_sensor_temp_vrm] =
 		EC_SENSOR("VRM", hwmon_temp, 1, 0x00, 0x33),
 	[ec_sensor_temp_t_sensor] =
 		EC_SENSOR("T_Sensor", hwmon_temp, 1, 0x00, 0x36),
+	[ec_sensor_fan_cpu_opt] =
+		EC_SENSOR("CPU_Opt", hwmon_fan, 2, 0x00, 0xb0),
 	[ec_sensor_temp_water_in] =
 		EC_SENSOR("Water_In", hwmon_temp, 1, 0x01, 0x00),
 	[ec_sensor_temp_water_out] =
 		EC_SENSOR("Water_Out", hwmon_temp, 1, 0x01, 0x01),
-	[ec_sensor_fan_cpu_opt] =
-		EC_SENSOR("CPU_Opt", hwmon_fan, 2, 0x00, 0xb0),
 };
 
 static const struct ec_sensor_info sensors_family_intel_300[] = {
@@ -278,6 +283,14 @@ static const struct ec_sensor_info sensors_family_intel_600[] = {
 	[ec_sensor_temp_t_sensor] =
 		EC_SENSOR("T_Sensor", hwmon_temp, 1, 0x00, 0x3d),
 	[ec_sensor_temp_vrm] = EC_SENSOR("VRM", hwmon_temp, 1, 0x00, 0x3e),
+	[ec_sensor_fan_water_flow] =
+		EC_SENSOR("Water_Flow", hwmon_fan, 2, 0x00, 0xbe),
+	[ec_sensor_temp_water_in] =
+		EC_SENSOR("Water_In", hwmon_temp, 1, 0x01, 0x00),
+	[ec_sensor_temp_water_out] =
+		EC_SENSOR("Water_Out", hwmon_temp, 1, 0x01, 0x01),
+	[ec_sensor_temp_water_block_in] =
+		EC_SENSOR("Water_Block_In", hwmon_temp, 1, 0x01, 0x02),
 };
 
 /* Shortcuts for common combinations */
@@ -300,6 +313,15 @@ struct ec_board_info {
 	enum board_family family;
 };
 
+static const struct ec_board_info board_info_maximus_vi_hero = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
+		SENSOR_TEMP_T_SENSOR |
+		SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER |
+		SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW,
+	.mutex_path = ACPI_GLOBAL_LOCK_PSEUDO_PATH,
+	.family = family_intel_300_series,
+};
+
 static const struct ec_board_info board_info_prime_x470_pro = {
 	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
 		SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
@@ -402,6 +424,13 @@ static const struct ec_board_info board_info_maximus_xi_hero = {
 	.family = family_intel_300_series,
 };
 
+static const struct ec_board_info board_info_maximus_z690_formula = {
+	.sensors = SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
+		SENSOR_SET_TEMP_WATER | SENSOR_FAN_WATER_FLOW,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_RMTW_ASMX,
+	.family = family_intel_600_series,
+};
+
 static const struct ec_board_info board_info_crosshair_viii_impact = {
 	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
 		SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
@@ -507,6 +536,8 @@ static const struct ec_board_info board_info_tuf_gaming_x670e_plus = {
 	}
 
 static const struct dmi_system_id dmi_table[] = {
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("MAXIMUS VI HERO",
+					&board_info_maximus_vi_hero),
 	DMI_EXACT_MATCH_ASUS_BOARD_NAME("PRIME X470-PRO",
 					&board_info_prime_x470_pro),
 	DMI_EXACT_MATCH_ASUS_BOARD_NAME("PRIME X570-PRO",
@@ -537,6 +568,8 @@ static const struct dmi_system_id dmi_table[] = {
 					&board_info_maximus_xi_hero),
 	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG MAXIMUS XI HERO (WI-FI)",
 					&board_info_maximus_xi_hero),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG MAXIMUS Z690 FORMULA",
+					&board_info_maximus_z690_formula),
 	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII IMPACT",
 					&board_info_crosshair_viii_impact),
 	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX B550-E GAMING",
@@ -933,6 +966,10 @@ static int asus_ec_hwmon_read_string(struct device *dev,
 {
 	struct ec_sensors_data *state = dev_get_drvdata(dev);
 	int sensor_index = find_ec_sensor_index(state, type, channel);
+
+	if (sensor_index < 0)
+		return sensor_index;
+
 	*str = get_sensor_info(state, sensor_index)->label;
 
 	return 0;
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index 79e5606e6d2f..1e2c8e284001 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -1274,6 +1274,13 @@ static const struct dmi_system_id i8k_dmi_table[] __initconst = {
 		},
 	},
 	{
+		.ident = "Dell OptiPlex 7050",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "OptiPlex 7050"),
+		},
+	},
+	{
 		.ident = "Dell Precision",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index b779240328d5..516c34bb61c9 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -20,6 +20,9 @@
 #include <linux/gpio/consumer.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/regulator/consumer.h>
 #include <linux/thermal.h>
 
 struct gpio_fan_speed {
@@ -42,6 +45,7 @@ struct gpio_fan_data {
 	bool			pwm_enable;
 	struct gpio_desc	*alarm_gpio;
 	struct work_struct	alarm_work;
+	struct regulator	*supply;
 };
 
 /*
@@ -125,13 +129,32 @@ static int __get_fan_ctrl(struct gpio_fan_data *fan_data)
 }
 
 /* Must be called with fan_data->lock held, except during initialization. */
-static void set_fan_speed(struct gpio_fan_data *fan_data, int speed_index)
+static int set_fan_speed(struct gpio_fan_data *fan_data, int speed_index)
 {
 	if (fan_data->speed_index == speed_index)
-		return;
+		return 0;
+
+	if (fan_data->speed_index == 0 && speed_index > 0) {
+		int ret;
+
+		ret = pm_runtime_resume_and_get(fan_data->dev);
+		if (ret < 0)
+			return ret;
+	}
 
 	__set_fan_ctrl(fan_data, fan_data->speed[speed_index].ctrl_val);
+
+	if (fan_data->speed_index > 0 && speed_index == 0) {
+		int ret;
+
+		ret = pm_runtime_put_sync(fan_data->dev);
+		if (ret < 0)
+			return ret;
+	}
+
 	fan_data->speed_index = speed_index;
+
+	return 0;
 }
 
 static int get_fan_speed_index(struct gpio_fan_data *fan_data)
@@ -176,7 +199,7 @@ static ssize_t pwm1_store(struct device *dev, struct device_attribute *attr,
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
 	unsigned long pwm;
 	int speed_index;
-	int ret = count;
+	int ret;
 
 	if (kstrtoul(buf, 10, &pwm) || pwm > 255)
 		return -EINVAL;
@@ -189,12 +212,12 @@ static ssize_t pwm1_store(struct device *dev, struct device_attribute *attr,
 	}
 
 	speed_index = DIV_ROUND_UP(pwm * (fan_data->num_speed - 1), 255);
-	set_fan_speed(fan_data, speed_index);
+	ret = set_fan_speed(fan_data, speed_index);
 
 exit_unlock:
 	mutex_unlock(&fan_data->lock);
 
-	return ret;
+	return ret ? ret : count;
 }
 
 static ssize_t pwm1_enable_show(struct device *dev,
@@ -211,6 +234,7 @@ static ssize_t pwm1_enable_store(struct device *dev,
 {
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
 	unsigned long val;
+	int ret = 0;
 
 	if (kstrtoul(buf, 10, &val) || val > 1)
 		return -EINVAL;
@@ -224,11 +248,11 @@ static ssize_t pwm1_enable_store(struct device *dev,
 
 	/* Disable manual control mode: set fan at full speed. */
 	if (val == 0)
-		set_fan_speed(fan_data, fan_data->num_speed - 1);
+		ret = set_fan_speed(fan_data, fan_data->num_speed - 1);
 
 	mutex_unlock(&fan_data->lock);
 
-	return count;
+	return ret ? ret : count;
 }
 
 static ssize_t pwm1_mode_show(struct device *dev,
@@ -279,7 +303,7 @@ static ssize_t set_rpm(struct device *dev, struct device_attribute *attr,
 		goto exit_unlock;
 	}
 
-	set_fan_speed(fan_data, rpm_to_speed_index(fan_data, rpm));
+	ret = set_fan_speed(fan_data, rpm_to_speed_index(fan_data, rpm));
 
 exit_unlock:
 	mutex_unlock(&fan_data->lock);
@@ -386,6 +410,7 @@ static int gpio_fan_set_cur_state(struct thermal_cooling_device *cdev,
 				  unsigned long state)
 {
 	struct gpio_fan_data *fan_data = cdev->devdata;
+	int ret;
 
 	if (!fan_data)
 		return -EINVAL;
@@ -395,11 +420,11 @@ static int gpio_fan_set_cur_state(struct thermal_cooling_device *cdev,
 
 	mutex_lock(&fan_data->lock);
 
-	set_fan_speed(fan_data, state);
+	ret = set_fan_speed(fan_data, state);
 
 	mutex_unlock(&fan_data->lock);
 
-	return 0;
+	return ret;
 }
 
 static const struct thermal_cooling_device_ops gpio_fan_cool_ops = {
@@ -499,6 +524,8 @@ static void gpio_fan_stop(void *data)
 	mutex_lock(&fan_data->lock);
 	set_fan_speed(data, 0);
 	mutex_unlock(&fan_data->lock);
+
+	pm_runtime_disable(fan_data->dev);
 }
 
 static int gpio_fan_probe(struct platform_device *pdev)
@@ -521,6 +548,11 @@ static int gpio_fan_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, fan_data);
 	mutex_init(&fan_data->lock);
 
+	fan_data->supply = devm_regulator_get(dev, "fan");
+	if (IS_ERR(fan_data->supply))
+		return dev_err_probe(dev, PTR_ERR(fan_data->supply),
+				     "Failed to get fan-supply");
+
 	/* Configure control GPIOs if available. */
 	if (fan_data->gpios && fan_data->num_gpios > 0) {
 		if (!fan_data->speed || fan_data->num_speed <= 1)
@@ -548,6 +580,17 @@ static int gpio_fan_probe(struct platform_device *pdev)
 			return err;
 	}
 
+	pm_runtime_set_suspended(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+	/* If current GPIO state is active, mark RPM as active as well */
+	if (fan_data->speed_index > 0) {
+		int ret;
+
+		ret = pm_runtime_resume_and_get(&pdev->dev);
+		if (ret)
+			return ret;
+	}
+
 	/* Optional cooling device register for Device tree platforms */
 	fan_data->cdev = devm_thermal_of_cooling_device_register(dev, np,
 				"gpio-fan", fan_data, &gpio_fan_cool_ops);
@@ -565,41 +608,69 @@ static void gpio_fan_shutdown(struct platform_device *pdev)
 		set_fan_speed(fan_data, 0);
 }
 
+static int gpio_fan_runtime_suspend(struct device *dev)
+{
+	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
+	int ret = 0;
+
+	if (fan_data->supply)
+		ret = regulator_disable(fan_data->supply);
+
+	return ret;
+}
+
+static int gpio_fan_runtime_resume(struct device *dev)
+{
+	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
+	int ret = 0;
+
+	if (fan_data->supply)
+		ret = regulator_enable(fan_data->supply);
+
+	return ret;
+}
+
 static int gpio_fan_suspend(struct device *dev)
 {
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
+	int ret = 0;
 
 	if (fan_data->gpios) {
 		fan_data->resume_speed = fan_data->speed_index;
 		mutex_lock(&fan_data->lock);
-		set_fan_speed(fan_data, 0);
+		ret = set_fan_speed(fan_data, 0);
 		mutex_unlock(&fan_data->lock);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int gpio_fan_resume(struct device *dev)
 {
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
+	int ret = 0;
 
 	if (fan_data->gpios) {
 		mutex_lock(&fan_data->lock);
-		set_fan_speed(fan_data, fan_data->resume_speed);
+		ret = set_fan_speed(fan_data, fan_data->resume_speed);
 		mutex_unlock(&fan_data->lock);
 	}
 
-	return 0;
+	return ret;
 }
 
-static DEFINE_SIMPLE_DEV_PM_OPS(gpio_fan_pm, gpio_fan_suspend, gpio_fan_resume);
+static const struct dev_pm_ops gpio_fan_pm = {
+	RUNTIME_PM_OPS(gpio_fan_runtime_suspend,
+		       gpio_fan_runtime_resume, NULL)
+	SYSTEM_SLEEP_PM_OPS(gpio_fan_suspend, gpio_fan_resume)
+};
 
 static struct platform_driver gpio_fan_driver = {
 	.probe		= gpio_fan_probe,
 	.shutdown	= gpio_fan_shutdown,
 	.driver	= {
 		.name	= "gpio-fan",
-		.pm	= pm_sleep_ptr(&gpio_fan_pm),
+		.pm	= pm_ptr(&gpio_fan_pm),
 		.of_match_table = of_gpio_fan_match,
 	},
 };
diff --git a/drivers/hwmon/ina238.c b/drivers/hwmon/ina238.c
index 2d9f12f68d50..a4a41742786b 100644
--- a/drivers/hwmon/ina238.c
+++ b/drivers/hwmon/ina238.c
@@ -21,11 +21,14 @@
 #define INA238_CONFIG			0x0
 #define INA238_ADC_CONFIG		0x1
 #define INA238_SHUNT_CALIBRATION	0x2
+#define SQ52206_SHUNT_TEMPCO		0x3
 #define INA238_SHUNT_VOLTAGE		0x4
 #define INA238_BUS_VOLTAGE		0x5
 #define INA238_DIE_TEMP			0x6
 #define INA238_CURRENT			0x7
 #define INA238_POWER			0x8
+#define SQ52206_ENERGY			0x9
+#define SQ52206_CHARGE			0xa
 #define INA238_DIAG_ALERT		0xb
 #define INA238_SHUNT_OVER_VOLTAGE	0xc
 #define INA238_SHUNT_UNDER_VOLTAGE	0xd
@@ -33,9 +36,12 @@
 #define INA238_BUS_UNDER_VOLTAGE	0xf
 #define INA238_TEMP_LIMIT		0x10
 #define INA238_POWER_LIMIT		0x11
+#define SQ52206_POWER_PEAK		0x20
 #define INA238_DEVICE_ID		0x3f /* not available on INA237 */
 
 #define INA238_CONFIG_ADCRANGE		BIT(4)
+#define SQ52206_CONFIG_ADCRANGE_HIGH	BIT(4)
+#define SQ52206_CONFIG_ADCRANGE_LOW		BIT(3)
 
 #define INA238_DIAG_ALERT_TMPOL		BIT(7)
 #define INA238_DIAG_ALERT_SHNTOL	BIT(6)
@@ -44,12 +50,13 @@
 #define INA238_DIAG_ALERT_BUSUL		BIT(3)
 #define INA238_DIAG_ALERT_POL		BIT(2)
 
-#define INA238_REGISTERS		0x11
+#define INA238_REGISTERS		0x20
 
 #define INA238_RSHUNT_DEFAULT		10000 /* uOhm */
 
 /* Default configuration of device on reset. */
 #define INA238_CONFIG_DEFAULT		0
+#define SQ52206_CONFIG_DEFAULT		0x0005
 /* 16 sample averaging, 1052us conversion time, continuous mode */
 #define INA238_ADC_CONFIG_DEFAULT	0xfb6a
 /* Configure alerts to be based on averaged value (SLOWALERT) */
@@ -87,14 +94,19 @@
  *  shunt = 0x4000 / (819.2 * 10^6) / 0.001 = 20000 uOhms (with 1mA/lsb)
  *
  *  Current (mA) = register value * 20000 / rshunt / 4 * gain
- *  Power (W) = 0.2 * register value * 20000 / rshunt / 4 * gain
+ *  Power (mW) = 0.2 * register value * 20000 / rshunt / 4 * gain
+ *  (Specific for SQ52206)
+ *  Power (mW) = 0.24 * register value * 20000 / rshunt / 4 * gain
+ *  Energy (mJ) = 16 * 0.24 * register value * 20000 / rshunt / 4 * gain
  */
 #define INA238_CALIBRATION_VALUE	16384
 #define INA238_FIXED_SHUNT		20000
 
 #define INA238_SHUNT_VOLTAGE_LSB	5 /* 5 uV/lsb */
 #define INA238_BUS_VOLTAGE_LSB		3125 /* 3.125 mV/lsb */
-#define INA238_DIE_TEMP_LSB		125 /* 125 mC/lsb */
+#define INA238_DIE_TEMP_LSB			1250000 /* 125.0000 mC/lsb */
+#define SQ52206_BUS_VOLTAGE_LSB		3750 /* 3.75 mV/lsb */
+#define SQ52206_DIE_TEMP_LSB		78125 /* 7.8125 mC/lsb */
 
 static const struct regmap_config ina238_regmap_config = {
 	.max_register = INA238_REGISTERS,
@@ -102,7 +114,20 @@ static const struct regmap_config ina238_regmap_config = {
 	.val_bits = 16,
 };
 
+enum ina238_ids { ina238, ina237, sq52206 };
+
+struct ina238_config {
+	bool has_power_highest;		/* chip detection power peak */
+	bool has_energy;			/* chip detection energy */
+	u8 temp_shift;				/* fixed parameters for temp calculate */
+	u32 power_calculate_factor;	/* fixed parameters for power calculate */
+	u16 config_default;			/* Power-on default state */
+	int bus_voltage_lsb;		/* use for temperature calculate, uV/lsb */
+	int temp_lsb;				/* use for temperature calculate */
+};
+
 struct ina238_data {
+	const struct ina238_config *config;
 	struct i2c_client *client;
 	struct mutex config_lock;
 	struct regmap *regmap;
@@ -110,6 +135,36 @@ struct ina238_data {
 	int gain;
 };
 
+static const struct ina238_config ina238_config[] = {
+	[ina238] = {
+		.has_energy = false,
+		.has_power_highest = false,
+		.temp_shift = 4,
+		.power_calculate_factor = 20,
+		.config_default = INA238_CONFIG_DEFAULT,
+		.bus_voltage_lsb = INA238_BUS_VOLTAGE_LSB,
+		.temp_lsb = INA238_DIE_TEMP_LSB,
+	},
+	[ina237] = {
+		.has_energy = false,
+		.has_power_highest = false,
+		.temp_shift = 4,
+		.power_calculate_factor = 20,
+		.config_default = INA238_CONFIG_DEFAULT,
+		.bus_voltage_lsb = INA238_BUS_VOLTAGE_LSB,
+		.temp_lsb = INA238_DIE_TEMP_LSB,
+	},
+	[sq52206] = {
+		.has_energy = true,
+		.has_power_highest = true,
+		.temp_shift = 0,
+		.power_calculate_factor = 24,
+		.config_default = SQ52206_CONFIG_DEFAULT,
+		.bus_voltage_lsb = SQ52206_BUS_VOLTAGE_LSB,
+		.temp_lsb = SQ52206_DIE_TEMP_LSB,
+	},
+};
+
 static int ina238_read_reg24(const struct i2c_client *client, u8 reg, u32 *val)
 {
 	u8 data[3];
@@ -126,6 +181,24 @@ static int ina238_read_reg24(const struct i2c_client *client, u8 reg, u32 *val)
 	return 0;
 }
 
+static int ina238_read_reg40(const struct i2c_client *client, u8 reg, u64 *val)
+{
+	u8 data[5];
+	u32 low;
+	int err;
+
+	/* 40-bit register read */
+	err = i2c_smbus_read_i2c_block_data(client, reg, 5, data);
+	if (err < 0)
+		return err;
+	if (err != 5)
+		return -EIO;
+	low = (data[1] << 24) | (data[2] << 16) | (data[3] << 8) | data[4];
+	*val = ((long long)data[0] << 32) | low;
+
+	return 0;
+}
+
 static int ina238_read_in(struct device *dev, u32 attr, int channel,
 			  long *val)
 {
@@ -197,10 +270,10 @@ static int ina238_read_in(struct device *dev, u32 attr, int channel,
 		regval = (s16)regval;
 		if (channel == 0)
 			/* gain of 1 -> LSB / 4 */
-			*val = (regval * INA238_SHUNT_VOLTAGE_LSB) /
-			       (1000 * (4 - data->gain + 1));
+			*val = (regval * INA238_SHUNT_VOLTAGE_LSB) *
+					data->gain / (1000 * 4);
 		else
-			*val = (regval * INA238_BUS_VOLTAGE_LSB) / 1000;
+			*val = (regval * data->config->bus_voltage_lsb) / 1000;
 		break;
 	case hwmon_in_max_alarm:
 	case hwmon_in_min_alarm:
@@ -225,8 +298,8 @@ static int ina238_write_in(struct device *dev, u32 attr, int channel,
 	case 0:
 		/* signed value, clamp to max range +/-163 mV */
 		regval = clamp_val(val, -163, 163);
-		regval = (regval * 1000 * (4 - data->gain + 1)) /
-			 INA238_SHUNT_VOLTAGE_LSB;
+		regval = (regval * 1000 * 4) /
+			 (INA238_SHUNT_VOLTAGE_LSB * data->gain);
 		regval = clamp_val(regval, S16_MIN, S16_MAX);
 
 		switch (attr) {
@@ -242,7 +315,7 @@ static int ina238_write_in(struct device *dev, u32 attr, int channel,
 	case 1:
 		/* signed value, positive values only. Clamp to max 102.396 V */
 		regval = clamp_val(val, 0, 102396);
-		regval = (regval * 1000) / INA238_BUS_VOLTAGE_LSB;
+		regval = (regval * 1000) / data->config->bus_voltage_lsb;
 		regval = clamp_val(regval, 0, S16_MAX);
 
 		switch (attr) {
@@ -297,8 +370,19 @@ static int ina238_read_power(struct device *dev, u32 attr, long *val)
 			return err;
 
 		/* Fixed 1mA lsb, scaled by 1000000 to have result in uW */
-		power = div_u64(regval * 1000ULL * INA238_FIXED_SHUNT *
-				data->gain, 20 * data->rshunt);
+		power = div_u64(regval * 1000ULL * INA238_FIXED_SHUNT *	data->gain *
+				data->config->power_calculate_factor, 4 * 100 * data->rshunt);
+		/* Clamp value to maximum value of long */
+		*val = clamp_val(power, 0, LONG_MAX);
+		break;
+	case hwmon_power_input_highest:
+		err = ina238_read_reg24(data->client, SQ52206_POWER_PEAK, &regval);
+		if (err)
+			return err;
+
+		/* Fixed 1mA lsb, scaled by 1000000 to have result in uW */
+		power = div_u64(regval * 1000ULL * INA238_FIXED_SHUNT *	data->gain *
+				data->config->power_calculate_factor, 4 * 100 * data->rshunt);
 		/* Clamp value to maximum value of long */
 		*val = clamp_val(power, 0, LONG_MAX);
 		break;
@@ -311,8 +395,8 @@ static int ina238_read_power(struct device *dev, u32 attr, long *val)
 		 * Truncated 24-bit compare register, lower 8-bits are
 		 * truncated. Same conversion to/from uW as POWER register.
 		 */
-		power = div_u64((regval << 8) * 1000ULL * INA238_FIXED_SHUNT *
-			       data->gain, 20 * data->rshunt);
+		power = div_u64((regval << 8) * 1000ULL * INA238_FIXED_SHUNT *	data->gain *
+				data->config->power_calculate_factor, 4 * 100 * data->rshunt);
 		/* Clamp value to maximum value of long */
 		*val = clamp_val(power, 0, LONG_MAX);
 		break;
@@ -344,8 +428,8 @@ static int ina238_write_power(struct device *dev, u32 attr, long val)
 	 * register.
 	 */
 	regval = clamp_val(val, 0, LONG_MAX);
-	regval = div_u64(val * 20ULL * data->rshunt,
-			 1000ULL * INA238_FIXED_SHUNT * data->gain);
+	regval = div_u64(val * 4 * 100 * data->rshunt, data->config->power_calculate_factor *
+			1000ULL * INA238_FIXED_SHUNT * data->gain);
 	regval = clamp_val(regval >> 8, 0, U16_MAX);
 
 	return regmap_write(data->regmap, INA238_POWER_LIMIT, regval);
@@ -362,17 +446,17 @@ static int ina238_read_temp(struct device *dev, u32 attr, long *val)
 		err = regmap_read(data->regmap, INA238_DIE_TEMP, &regval);
 		if (err)
 			return err;
-
-		/* Signed, bits 15-4 of register, result in mC */
-		*val = ((s16)regval >> 4) * INA238_DIE_TEMP_LSB;
+		/* Signed, result in mC */
+		*val = div_s64(((s64)((s16)regval) >> data->config->temp_shift) *
+						(s64)data->config->temp_lsb, 10000);
 		break;
 	case hwmon_temp_max:
 		err = regmap_read(data->regmap, INA238_TEMP_LIMIT, &regval);
 		if (err)
 			return err;
-
-		/* Signed, bits 15-4 of register, result in mC */
-		*val = ((s16)regval >> 4) * INA238_DIE_TEMP_LSB;
+		/* Signed, result in mC */
+		*val = div_s64(((s64)((s16)regval) >> data->config->temp_shift) *
+						(s64)data->config->temp_lsb, 10000);
 		break;
 	case hwmon_temp_max_alarm:
 		err = regmap_read(data->regmap, INA238_DIAG_ALERT, &regval);
@@ -396,13 +480,33 @@ static int ina238_write_temp(struct device *dev, u32 attr, long val)
 	if (attr != hwmon_temp_max)
 		return -EOPNOTSUPP;
 
-	/* Signed, bits 15-4 of register */
-	regval = (val / INA238_DIE_TEMP_LSB) << 4;
-	regval = clamp_val(regval, S16_MIN, S16_MAX) & 0xfff0;
+	/* Signed */
+	regval = clamp_val(val, -40000, 125000);
+	regval = div_s64(val * 10000, data->config->temp_lsb) << data->config->temp_shift;
+	regval = clamp_val(regval, S16_MIN, S16_MAX) & (0xffff << data->config->temp_shift);
 
 	return regmap_write(data->regmap, INA238_TEMP_LIMIT, regval);
 }
 
+static ssize_t energy1_input_show(struct device *dev,
+				  struct device_attribute *da, char *buf)
+{
+	struct ina238_data *data = dev_get_drvdata(dev);
+	int ret;
+	u64 regval;
+	u64 energy;
+
+	ret = ina238_read_reg40(data->client, SQ52206_ENERGY, &regval);
+	if (ret)
+		return ret;
+
+	/* result in mJ */
+	energy = div_u64(regval * INA238_FIXED_SHUNT *	data->gain * 16 *
+				data->config->power_calculate_factor, 4 * 100 * data->rshunt);
+
+	return sysfs_emit(buf, "%llu\n", energy);
+}
+
 static int ina238_read(struct device *dev, enum hwmon_sensor_types type,
 		       u32 attr, int channel, long *val)
 {
@@ -422,7 +526,7 @@ static int ina238_read(struct device *dev, enum hwmon_sensor_types type,
 }
 
 static int ina238_write(struct device *dev, enum hwmon_sensor_types type,
-		       u32 attr, int channel, long val)
+			u32 attr, int channel, long val)
 {
 	struct ina238_data *data = dev_get_drvdata(dev);
 	int err;
@@ -452,6 +556,9 @@ static umode_t ina238_is_visible(const void *drvdata,
 				 enum hwmon_sensor_types type,
 				 u32 attr, int channel)
 {
+	const struct ina238_data *data = drvdata;
+	bool has_power_highest = data->config->has_power_highest;
+
 	switch (type) {
 	case hwmon_in:
 		switch (attr) {
@@ -479,6 +586,10 @@ static umode_t ina238_is_visible(const void *drvdata,
 			return 0444;
 		case hwmon_power_max:
 			return 0644;
+		case hwmon_power_input_highest:
+			if (has_power_highest)
+				return 0444;
+			return 0;
 		default:
 			return 0;
 		}
@@ -512,7 +623,8 @@ static const struct hwmon_channel_info * const ina238_info[] = {
 			   HWMON_C_INPUT),
 	HWMON_CHANNEL_INFO(power,
 			   /* 0: power */
-			   HWMON_P_INPUT | HWMON_P_MAX | HWMON_P_MAX_ALARM),
+			   HWMON_P_INPUT | HWMON_P_MAX |
+			   HWMON_P_MAX_ALARM | HWMON_P_INPUT_HIGHEST),
 	HWMON_CHANNEL_INFO(temp,
 			   /* 0: die temperature */
 			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MAX_ALARM),
@@ -530,20 +642,35 @@ static const struct hwmon_chip_info ina238_chip_info = {
 	.info = ina238_info,
 };
 
+/* energy attributes are 5 bytes wide so we need u64 */
+static DEVICE_ATTR_RO(energy1_input);
+
+static struct attribute *ina238_attrs[] = {
+	&dev_attr_energy1_input.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(ina238);
+
 static int ina238_probe(struct i2c_client *client)
 {
 	struct ina2xx_platform_data *pdata = dev_get_platdata(&client->dev);
 	struct device *dev = &client->dev;
 	struct device *hwmon_dev;
 	struct ina238_data *data;
+	enum ina238_ids chip;
 	int config;
 	int ret;
 
+	chip = (uintptr_t)i2c_get_match_data(client);
+
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
 	data->client = client;
+	/* set the device type */
+	data->config = &ina238_config[chip];
+
 	mutex_init(&data->config_lock);
 
 	data->regmap = devm_regmap_init_i2c(client, &ina238_regmap_config);
@@ -564,15 +691,21 @@ static int ina238_probe(struct i2c_client *client)
 	/* load shunt gain value */
 	if (device_property_read_u32(dev, "ti,shunt-gain", &data->gain) < 0)
 		data->gain = 4; /* Default of ADCRANGE = 0 */
-	if (data->gain != 1 && data->gain != 4) {
+	if (data->gain != 1 && data->gain != 2 && data->gain != 4) {
 		dev_err(dev, "invalid shunt gain value %u\n", data->gain);
 		return -EINVAL;
 	}
 
 	/* Setup CONFIG register */
-	config = INA238_CONFIG_DEFAULT;
-	if (data->gain == 1)
+	config = data->config->config_default;
+	if (chip == sq52206) {
+		if (data->gain == 1)
+			config |= SQ52206_CONFIG_ADCRANGE_HIGH; /* ADCRANGE = 10/11 is /1 */
+		else if (data->gain == 2)
+			config |= SQ52206_CONFIG_ADCRANGE_LOW; /* ADCRANGE = 01 is /2 */
+	} else if (data->gain == 1) {
 		config |= INA238_CONFIG_ADCRANGE; /* ADCRANGE = 1 is /1 */
+	}
 	ret = regmap_write(data->regmap, INA238_CONFIG, config);
 	if (ret < 0) {
 		dev_err(dev, "error configuring the device: %d\n", ret);
@@ -605,7 +738,8 @@ static int ina238_probe(struct i2c_client *client)
 
 	hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name, data,
 							 &ina238_chip_info,
-							 NULL);
+							 data->config->has_energy ?
+								ina238_groups : NULL);
 	if (IS_ERR(hwmon_dev))
 		return PTR_ERR(hwmon_dev);
 
@@ -616,15 +750,27 @@ static int ina238_probe(struct i2c_client *client)
 }
 
 static const struct i2c_device_id ina238_id[] = {
-	{ "ina238" },
+	{ "ina237", ina237 },
+	{ "ina238", ina238 },
+	{ "sq52206", sq52206 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, ina238_id);
 
 static const struct of_device_id __maybe_unused ina238_of_match[] = {
-	{ .compatible = "ti,ina237" },
-	{ .compatible = "ti,ina238" },
-	{ },
+	{
+		.compatible = "ti,ina237",
+		.data = (void *)ina237
+	},
+	{
+		.compatible = "ti,ina238",
+		.data = (void *)ina238
+	},
+	{
+		.compatible = "silergy,sq52206",
+		.data = (void *)sq52206
+	},
+	{ }
 };
 MODULE_DEVICE_TABLE(of, ina238_of_match);
 
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index 345fe7db9de9..bc3c1f7314b3 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -959,8 +959,12 @@ static int ina2xx_probe(struct i2c_client *client)
 		return PTR_ERR(data->regmap);
 	}
 
-	ret = devm_regulator_get_enable(dev, "vs");
-	if (ret)
+	/*
+	 * Regulator core returns -ENODEV if the 'vs' is not available.
+	 * Hence the check for -ENODEV return code is necessary.
+	 */
+	ret = devm_regulator_get_enable_optional(dev, "vs");
+	if (ret < 0 && ret != -ENODEV)
 		return dev_err_probe(dev, ret, "failed to enable vs regulator\n");
 
 	ret = ina2xx_init(dev, data);
diff --git a/drivers/hwmon/isl28022.c b/drivers/hwmon/isl28022.c
index 1fb9864635db..c2e559dde63f 100644
--- a/drivers/hwmon/isl28022.c
+++ b/drivers/hwmon/isl28022.c
@@ -154,6 +154,7 @@ static int isl28022_read_current(struct device *dev, u32 attr, long *val)
 	struct isl28022_data *data = dev_get_drvdata(dev);
 	unsigned int regval;
 	int err;
+	u16 sign_bit;
 
 	switch (attr) {
 	case hwmon_curr_input:
@@ -161,8 +162,9 @@ static int isl28022_read_current(struct device *dev, u32 attr, long *val)
 				  ISL28022_REG_CURRENT, &regval);
 		if (err < 0)
 			return err;
-		*val = ((long)regval * 1250L * (long)data->gain) /
-			(long)data->shunt;
+		sign_bit = (regval >> 15) & 0x01;
+		*val = (((long)(((u16)regval) & 0x7FFF) - (sign_bit * 32768)) *
+			1250L * (long)data->gain) / (long)data->shunt;
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -301,7 +303,7 @@ static const struct regmap_config isl28022_regmap_config = {
 	.writeable_reg = isl28022_is_writeable_reg,
 	.volatile_reg = isl28022_is_volatile_reg,
 	.val_format_endian = REGMAP_ENDIAN_BIG,
-	.cache_type = REGCACHE_RBTREE,
+	.cache_type = REGCACHE_MAPLE,
 	.use_single_read = true,
 	.use_single_write = true,
 };
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 472bcf6092f6..babf2413d666 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -503,6 +503,13 @@ static int k10temp_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 			k10temp_get_ccd_support(data, 12);
 			break;
 		}
+	} else if (boot_cpu_data.x86 == 0x1a) {
+		switch (boot_cpu_data.x86_model) {
+		case 0x40 ... 0x4f:	/* Zen5 Ryzen Desktop */
+			data->ccd_offset = 0x308;
+			k10temp_get_ccd_support(data, 8);
+			break;
+		}
 	}
 
 	for (i = 0; i < ARRAY_SIZE(tctl_offset_table); i++) {
diff --git a/drivers/hwmon/kbatt.c b/drivers/hwmon/kbatt.c
new file mode 100644
index 000000000000..501b8f4ded33
--- /dev/null
+++ b/drivers/hwmon/kbatt.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 KEBA Industrial Automation GmbH
+ *
+ * Driver for KEBA battery monitoring controller FPGA IP core
+ */
+
+#include <linux/hwmon.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/auxiliary_bus.h>
+#include <linux/misc/keba.h>
+#include <linux/mutex.h>
+
+#define KBATT "kbatt"
+
+#define KBATT_CONTROL_REG		0x4
+#define   KBATT_CONTROL_BAT_TEST	0x01
+
+#define KBATT_STATUS_REG		0x8
+#define   KBATT_STATUS_BAT_OK		0x01
+
+#define KBATT_MAX_UPD_INTERVAL	(10 * HZ)
+#define KBATT_SETTLE_TIME_US	(100 * USEC_PER_MSEC)
+
+struct kbatt {
+	/* update lock */
+	struct mutex lock;
+	void __iomem *base;
+
+	unsigned long next_update; /* in jiffies */
+	bool alarm;
+};
+
+static bool kbatt_alarm(struct kbatt *kbatt)
+{
+	mutex_lock(&kbatt->lock);
+
+	if (!kbatt->next_update || time_after(jiffies, kbatt->next_update)) {
+		/* switch load on */
+		iowrite8(KBATT_CONTROL_BAT_TEST,
+			 kbatt->base + KBATT_CONTROL_REG);
+
+		/* wait some time to let things settle */
+		fsleep(KBATT_SETTLE_TIME_US);
+
+		/* check battery state */
+		if (ioread8(kbatt->base + KBATT_STATUS_REG) &
+		    KBATT_STATUS_BAT_OK)
+			kbatt->alarm = false;
+		else
+			kbatt->alarm = true;
+
+		/* switch load off */
+		iowrite8(0, kbatt->base + KBATT_CONTROL_REG);
+
+		kbatt->next_update = jiffies + KBATT_MAX_UPD_INTERVAL;
+	}
+
+	mutex_unlock(&kbatt->lock);
+
+	return kbatt->alarm;
+}
+
+static int kbatt_read(struct device *dev, enum hwmon_sensor_types type,
+		      u32 attr, int channel, long *val)
+{
+	struct kbatt *kbatt = dev_get_drvdata(dev);
+
+	*val = kbatt_alarm(kbatt) ? 1 : 0;
+
+	return 0;
+}
+
+static umode_t kbatt_is_visible(const void *data, enum hwmon_sensor_types type,
+				u32 attr, int channel)
+{
+	if (channel == 0 && attr == hwmon_in_min_alarm)
+		return 0444;
+
+	return 0;
+}
+
+static const struct hwmon_channel_info *kbatt_info[] = {
+	HWMON_CHANNEL_INFO(in,
+			   /* 0: input minimum alarm channel */
+			   HWMON_I_MIN_ALARM),
+	NULL
+};
+
+static const struct hwmon_ops kbatt_hwmon_ops = {
+	.is_visible = kbatt_is_visible,
+	.read = kbatt_read,
+};
+
+static const struct hwmon_chip_info kbatt_chip_info = {
+	.ops = &kbatt_hwmon_ops,
+	.info = kbatt_info,
+};
+
+static int kbatt_probe(struct auxiliary_device *auxdev,
+		       const struct auxiliary_device_id *id)
+{
+	struct keba_batt_auxdev *kbatt_auxdev =
+		container_of(auxdev, struct keba_batt_auxdev, auxdev);
+	struct device *dev = &auxdev->dev;
+	struct device *hwmon_dev;
+	struct kbatt *kbatt;
+	int retval;
+
+	kbatt = devm_kzalloc(dev, sizeof(*kbatt), GFP_KERNEL);
+	if (!kbatt)
+		return -ENOMEM;
+
+	retval = devm_mutex_init(dev, &kbatt->lock);
+	if (retval)
+		return retval;
+
+	kbatt->base = devm_ioremap_resource(dev, &kbatt_auxdev->io);
+	if (IS_ERR(kbatt->base))
+		return PTR_ERR(kbatt->base);
+
+	hwmon_dev = devm_hwmon_device_register_with_info(dev, KBATT, kbatt,
+							 &kbatt_chip_info,
+							 NULL);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct auxiliary_device_id kbatt_devtype_aux[] = {
+	{ .name = "keba.batt" },
+	{}
+};
+MODULE_DEVICE_TABLE(auxiliary, kbatt_devtype_aux);
+
+static struct auxiliary_driver kbatt_driver_aux = {
+	.name = KBATT,
+	.id_table = kbatt_devtype_aux,
+	.probe = kbatt_probe,
+};
+module_auxiliary_driver(kbatt_driver_aux);
+
+MODULE_AUTHOR("Petar Bojanic <boja@keba.com>");
+MODULE_AUTHOR("Gerhard Engleder <eg@keba.com>");
+MODULE_DESCRIPTION("KEBA battery monitoring controller driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/kfan.c b/drivers/hwmon/kfan.c
new file mode 100644
index 000000000000..f353acb66749
--- /dev/null
+++ b/drivers/hwmon/kfan.c
@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 KEBA Industrial Automation GmbH
+ *
+ * Driver for KEBA fan controller FPGA IP core
+ *
+ */
+
+#include <linux/hwmon.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/auxiliary_bus.h>
+#include <linux/misc/keba.h>
+
+#define KFAN "kfan"
+
+#define KFAN_CONTROL_REG	0x04
+
+#define KFAN_STATUS_REG		0x08
+#define   KFAN_STATUS_PRESENT	0x01
+#define   KFAN_STATUS_REGULABLE	0x02
+#define   KFAN_STATUS_TACHO	0x04
+#define   KFAN_STATUS_BLOCKED	0x08
+
+#define KFAN_TACHO_REG		0x0c
+
+#define KFAN_DEFAULT_DIV	2
+
+struct kfan {
+	void __iomem *base;
+	bool tacho;
+	bool regulable;
+
+	/* hwmon API configuration */
+	u32 fan_channel_config[2];
+	struct hwmon_channel_info fan_info;
+	u32 pwm_channel_config[2];
+	struct hwmon_channel_info pwm_info;
+	const struct hwmon_channel_info *info[3];
+	struct hwmon_chip_info chip;
+};
+
+static bool kfan_get_fault(struct kfan *kfan)
+{
+	u8 status = ioread8(kfan->base + KFAN_STATUS_REG);
+
+	if (!(status & KFAN_STATUS_PRESENT))
+		return true;
+
+	if (!kfan->tacho && (status & KFAN_STATUS_BLOCKED))
+		return true;
+
+	return false;
+}
+
+static unsigned int kfan_count_to_rpm(u16 count)
+{
+	if (count == 0 || count == 0xffff)
+		return 0;
+
+	return 5000000UL / (KFAN_DEFAULT_DIV * count);
+}
+
+static unsigned int kfan_get_rpm(struct kfan *kfan)
+{
+	unsigned int rpm;
+	u16 count;
+
+	count = ioread16(kfan->base + KFAN_TACHO_REG);
+	rpm = kfan_count_to_rpm(count);
+
+	return rpm;
+}
+
+static unsigned int kfan_get_pwm(struct kfan *kfan)
+{
+	return ioread8(kfan->base + KFAN_CONTROL_REG);
+}
+
+static int kfan_set_pwm(struct kfan *kfan, long val)
+{
+	if (val < 0 || val > 0xff)
+		return -EINVAL;
+
+	/* if none-regulable, then only 0 or 0xff can be written */
+	if (!kfan->regulable && val > 0)
+		val = 0xff;
+
+	iowrite8(val, kfan->base + KFAN_CONTROL_REG);
+
+	return 0;
+}
+
+static int kfan_write(struct device *dev, enum hwmon_sensor_types type,
+		      u32 attr, int channel, long val)
+{
+	struct kfan *kfan = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			return kfan_set_pwm(kfan, val);
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int kfan_read(struct device *dev, enum hwmon_sensor_types type,
+		     u32 attr, int channel, long *val)
+{
+	struct kfan *kfan = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_fan:
+		switch (attr) {
+		case hwmon_fan_fault:
+			*val = kfan_get_fault(kfan);
+			return 0;
+		case hwmon_fan_input:
+			*val = kfan_get_rpm(kfan);
+			return 0;
+		default:
+			break;
+		}
+		break;
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			*val = kfan_get_pwm(kfan);
+			return 0;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static umode_t kfan_is_visible(const void *data, enum hwmon_sensor_types type,
+			       u32 attr, int channel)
+{
+	switch (type) {
+	case hwmon_fan:
+		switch (attr) {
+		case hwmon_fan_input:
+			return 0444;
+		case hwmon_fan_fault:
+			return 0444;
+		default:
+			break;
+		}
+		break;
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			return 0644;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static const struct hwmon_ops kfan_hwmon_ops = {
+	.is_visible = kfan_is_visible,
+	.read = kfan_read,
+	.write = kfan_write,
+};
+
+static int kfan_probe(struct auxiliary_device *auxdev,
+		      const struct auxiliary_device_id *id)
+{
+	struct keba_fan_auxdev *kfan_auxdev =
+		container_of(auxdev, struct keba_fan_auxdev, auxdev);
+	struct device *dev = &auxdev->dev;
+	struct device *hwmon_dev;
+	struct kfan *kfan;
+	u8 status;
+
+	kfan = devm_kzalloc(dev, sizeof(*kfan), GFP_KERNEL);
+	if (!kfan)
+		return -ENOMEM;
+
+	kfan->base = devm_ioremap_resource(dev, &kfan_auxdev->io);
+	if (IS_ERR(kfan->base))
+		return PTR_ERR(kfan->base);
+
+	status = ioread8(kfan->base + KFAN_STATUS_REG);
+	if (status & KFAN_STATUS_REGULABLE)
+		kfan->regulable = true;
+	if (status & KFAN_STATUS_TACHO)
+		kfan->tacho = true;
+
+	/* fan */
+	kfan->fan_channel_config[0] = HWMON_F_FAULT;
+	if (kfan->tacho)
+		kfan->fan_channel_config[0] |= HWMON_F_INPUT;
+	kfan->fan_info.type = hwmon_fan;
+	kfan->fan_info.config = kfan->fan_channel_config;
+	kfan->info[0] = &kfan->fan_info;
+
+	/* PWM */
+	kfan->pwm_channel_config[0] = HWMON_PWM_INPUT;
+	kfan->pwm_info.type = hwmon_pwm;
+	kfan->pwm_info.config = kfan->pwm_channel_config;
+	kfan->info[1] = &kfan->pwm_info;
+
+	kfan->chip.ops = &kfan_hwmon_ops;
+	kfan->chip.info = kfan->info;
+	hwmon_dev = devm_hwmon_device_register_with_info(dev, KFAN, kfan,
+							 &kfan->chip, NULL);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct auxiliary_device_id kfan_devtype_aux[] = {
+	{ .name = "keba.fan" },
+	{}
+};
+MODULE_DEVICE_TABLE(auxiliary, kfan_devtype_aux);
+
+static struct auxiliary_driver kfan_driver_aux = {
+	.name = KFAN,
+	.id_table = kfan_devtype_aux,
+	.probe = kfan_probe,
+};
+module_auxiliary_driver(kfan_driver_aux);
+
+MODULE_AUTHOR("Petar Bojanic <boja@keba.com>");
+MODULE_AUTHOR("Gerhard Engleder <eg@keba.com>");
+MODULE_DESCRIPTION("KEBA fan controller driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c
index d95a3c6c245c..9b4875e2fd8d 100644
--- a/drivers/hwmon/lm75.c
+++ b/drivers/hwmon/lm75.c
@@ -622,7 +622,7 @@ static int lm75_i3c_reg_read(void *context, unsigned int reg, unsigned int *val)
 		{
 			.rnw = true,
 			.len = 2,
-			.data.out = data->val_buf,
+			.data.in = data->val_buf,
 		},
 	};
 	int ret;
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index 75f09553fd67..c1f528e292f3 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -1235,7 +1235,7 @@ static int lm90_update_alarms(struct lm90_data *data, bool force)
 
 static void lm90_alert_work(struct work_struct *__work)
 {
-	struct delayed_work *delayed_work = container_of(__work, struct delayed_work, work);
+	struct delayed_work *delayed_work = to_delayed_work(__work);
 	struct lm90_data *data = container_of(delayed_work, struct lm90_data, alert_work);
 
 	/* Nothing to do if alerts are enabled */
diff --git a/drivers/hwmon/ltc2992.c b/drivers/hwmon/ltc2992.c
index 541fa09dc6e7..a07e2eb93c71 100644
--- a/drivers/hwmon/ltc2992.c
+++ b/drivers/hwmon/ltc2992.c
@@ -256,33 +256,38 @@ static int ltc2992_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask
 	return 0;
 }
 
-static void ltc2992_gpio_set(struct gpio_chip *chip, unsigned int offset, int value)
+static int ltc2992_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			    int value)
 {
 	struct ltc2992_state *st = gpiochip_get_data(chip);
 	unsigned long gpio_ctrl;
-	int reg;
+	int reg, ret;
 
 	mutex_lock(&st->gpio_mutex);
 	reg = ltc2992_read_reg(st, ltc2992_gpio_addr_map[offset].ctrl, 1);
 	if (reg < 0) {
 		mutex_unlock(&st->gpio_mutex);
-		return;
+		return reg;
 	}
 
 	gpio_ctrl = reg;
 	assign_bit(ltc2992_gpio_addr_map[offset].ctrl_bit, &gpio_ctrl, value);
 
-	ltc2992_write_reg(st, ltc2992_gpio_addr_map[offset].ctrl, 1, gpio_ctrl);
+	ret = ltc2992_write_reg(st, ltc2992_gpio_addr_map[offset].ctrl, 1,
+				gpio_ctrl);
 	mutex_unlock(&st->gpio_mutex);
+
+	return ret;
 }
 
-static void ltc2992_gpio_set_multiple(struct gpio_chip *chip, unsigned long *mask,
-				      unsigned long *bits)
+static int ltc2992_gpio_set_multiple(struct gpio_chip *chip, unsigned long *mask,
+				     unsigned long *bits)
 {
 	struct ltc2992_state *st = gpiochip_get_data(chip);
 	unsigned long gpio_ctrl_io = 0;
 	unsigned long gpio_ctrl = 0;
 	unsigned int gpio_nr;
+	int ret;
 
 	for_each_set_bit(gpio_nr, mask, LTC2992_GPIO_NR) {
 		if (gpio_nr < 3)
@@ -293,9 +298,14 @@ static void ltc2992_gpio_set_multiple(struct gpio_chip *chip, unsigned long *mas
 	}
 
 	mutex_lock(&st->gpio_mutex);
-	ltc2992_write_reg(st, LTC2992_GPIO_IO_CTRL, 1, gpio_ctrl_io);
-	ltc2992_write_reg(st, LTC2992_GPIO_CTRL, 1, gpio_ctrl);
+	ret = ltc2992_write_reg(st, LTC2992_GPIO_IO_CTRL, 1, gpio_ctrl_io);
+	if (ret)
+		goto out;
+
+	ret = ltc2992_write_reg(st, LTC2992_GPIO_CTRL, 1, gpio_ctrl);
+out:
 	mutex_unlock(&st->gpio_mutex);
+	return ret;
 }
 
 static int ltc2992_config_gpio(struct ltc2992_state *st)
@@ -329,8 +339,8 @@ static int ltc2992_config_gpio(struct ltc2992_state *st)
 	st->gc.ngpio = ARRAY_SIZE(st->gpio_names);
 	st->gc.get = ltc2992_gpio_get;
 	st->gc.get_multiple = ltc2992_gpio_get_multiple;
-	st->gc.set = ltc2992_gpio_set;
-	st->gc.set_multiple = ltc2992_gpio_set_multiple;
+	st->gc.set_rv = ltc2992_gpio_set;
+	st->gc.set_multiple_rv = ltc2992_gpio_set_multiple;
 
 	ret = devm_gpiochip_add_data(&st->client->dev, &st->gc, st);
 	if (ret)
diff --git a/drivers/hwmon/max6639.c b/drivers/hwmon/max6639.c
index 32b4d54b2076..a06346496e1d 100644
--- a/drivers/hwmon/max6639.c
+++ b/drivers/hwmon/max6639.c
@@ -80,6 +80,7 @@ struct max6639_data {
 	/* Register values initialized only once */
 	u8 ppr[MAX6639_NUM_CHANNELS];	/* Pulses per rotation 0..3 for 1..4 ppr */
 	u8 rpm_range[MAX6639_NUM_CHANNELS]; /* Index in above rpm_ranges table */
+	u32 target_rpm[MAX6639_NUM_CHANNELS];
 
 	/* Optional regulator for FAN supply */
 	struct regulator *reg;
@@ -563,6 +564,10 @@ static int max6639_probe_child_from_dt(struct i2c_client *client,
 	if (!err)
 		data->rpm_range[i] = rpm_range_to_reg(val);
 
+	err = of_property_read_u32(child, "target-rpm", &val);
+	if (!err)
+		data->target_rpm[i] = val;
+
 	return 0;
 }
 
@@ -573,6 +578,7 @@ static int max6639_init_client(struct i2c_client *client,
 	const struct device_node *np = dev->of_node;
 	struct device_node *child;
 	int i, err;
+	u8 target_duty;
 
 	/* Reset chip to default values, see below for GCONFIG setup */
 	err = regmap_write(data->regmap, MAX6639_REG_GCONFIG, MAX6639_GCONFIG_POR);
@@ -586,6 +592,8 @@ static int max6639_init_client(struct i2c_client *client,
 	/* default: 4000 RPM */
 	data->rpm_range[0] = 1;
 	data->rpm_range[1] = 1;
+	data->target_rpm[0] = 4000;
+	data->target_rpm[1] = 4000;
 
 	for_each_child_of_node(np, child) {
 		if (strcmp(child->name, "fan"))
@@ -639,8 +647,12 @@ static int max6639_init_client(struct i2c_client *client,
 		if (err)
 			return err;
 
-		/* PWM 120/120 (i.e. 100%) */
-		err = regmap_write(data->regmap, MAX6639_REG_TARGTDUTY(i), 120);
+		/* Set PWM based on target RPM if specified */
+		if (data->target_rpm[i] >  rpm_ranges[data->rpm_range[i]])
+			data->target_rpm[i] = rpm_ranges[data->rpm_range[i]];
+
+		target_duty = 120 * data->target_rpm[i] / rpm_ranges[data->rpm_range[i]];
+		err = regmap_write(data->regmap, MAX6639_REG_TARGTDUTY(i), target_duty);
 		if (err)
 			return err;
 	}
diff --git a/drivers/hwmon/max77705-hwmon.c b/drivers/hwmon/max77705-hwmon.c
new file mode 100644
index 000000000000..990023e6474e
--- /dev/null
+++ b/drivers/hwmon/max77705-hwmon.c
@@ -0,0 +1,221 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  MAX77705 voltage and current hwmon driver.
+ *
+ *  Copyright (C) 2025 Dzmitry Sankouski <dsankouski@gmail.com>
+ */
+
+#include <linux/err.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/hwmon.h>
+#include <linux/kernel.h>
+#include <linux/mfd/max77705-private.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+struct channel_desc {
+	u8 reg;
+	u8 avg_reg;
+	const char *const label;
+	// register resolution. nano Volts for voltage, nano Amperes for current
+	u32 resolution;
+};
+
+static const struct channel_desc current_channel_desc[] = {
+	{
+		.reg = IIN_REG,
+		.label = "IIN_REG",
+		.resolution = 125000
+	},
+	{
+		.reg = ISYS_REG,
+		.avg_reg = AVGISYS_REG,
+		.label = "ISYS_REG",
+		.resolution = 312500
+	}
+};
+
+static const struct channel_desc voltage_channel_desc[] = {
+	{
+		.reg = VBYP_REG,
+		.label = "VBYP_REG",
+		.resolution = 427246
+	},
+	{
+		.reg = VSYS_REG,
+		.label = "VSYS_REG",
+		.resolution = 156250
+	}
+};
+
+static int max77705_read_and_convert(struct regmap *regmap, u8 reg, u32 res,
+				     bool is_signed, long *val)
+{
+	int ret;
+	u32 regval;
+
+	ret = regmap_read(regmap, reg, &regval);
+	if (ret < 0)
+		return ret;
+
+	if (is_signed)
+		*val = mult_frac((long)sign_extend32(regval, 15), res, 1000000);
+	else
+		*val = mult_frac((long)regval, res, 1000000);
+
+	return 0;
+}
+
+static umode_t max77705_is_visible(const void *data,
+				   enum hwmon_sensor_types type,
+				   u32 attr, int channel)
+{
+	switch (type) {
+	case hwmon_in:
+		switch (attr) {
+		case hwmon_in_input:
+		case hwmon_in_label:
+			return 0444;
+		default:
+			break;
+		}
+		break;
+	case hwmon_curr:
+		switch (attr) {
+		case hwmon_curr_input:
+		case hwmon_in_label:
+			return 0444;
+		case hwmon_curr_average:
+			if (current_channel_desc[channel].avg_reg)
+				return 0444;
+			break;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int max77705_read_string(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+				int channel, const char **buf)
+{
+	switch (type) {
+	case hwmon_curr:
+		switch (attr) {
+		case hwmon_in_label:
+			*buf = current_channel_desc[channel].label;
+			return 0;
+		default:
+			return -EOPNOTSUPP;
+		}
+
+	case hwmon_in:
+		switch (attr) {
+		case hwmon_in_label:
+			*buf = voltage_channel_desc[channel].label;
+			return 0;
+		default:
+			return -EOPNOTSUPP;
+		}
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int max77705_read(struct device *dev, enum hwmon_sensor_types type,
+			 u32 attr, int channel, long *val)
+{
+	struct regmap *regmap = dev_get_drvdata(dev);
+	u8 reg;
+	u32 res;
+
+	switch (type) {
+	case hwmon_curr:
+		switch (attr) {
+		case hwmon_curr_input:
+			reg = current_channel_desc[channel].reg;
+			res = current_channel_desc[channel].resolution;
+
+			return max77705_read_and_convert(regmap, reg, res, true, val);
+		case hwmon_curr_average:
+			reg = current_channel_desc[channel].avg_reg;
+			res = current_channel_desc[channel].resolution;
+
+			return max77705_read_and_convert(regmap, reg, res, true, val);
+		default:
+			return -EOPNOTSUPP;
+		}
+
+	case hwmon_in:
+		switch (attr) {
+		case hwmon_in_input:
+			reg = voltage_channel_desc[channel].reg;
+			res = voltage_channel_desc[channel].resolution;
+
+			return max77705_read_and_convert(regmap, reg, res, false, val);
+		default:
+			return -EOPNOTSUPP;
+		}
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static const struct hwmon_ops max77705_hwmon_ops = {
+	.is_visible = max77705_is_visible,
+	.read = max77705_read,
+	.read_string = max77705_read_string,
+};
+
+static const struct hwmon_channel_info *max77705_info[] = {
+	HWMON_CHANNEL_INFO(in,
+			   HWMON_I_INPUT | HWMON_I_LABEL,
+			   HWMON_I_INPUT | HWMON_I_LABEL
+			),
+	HWMON_CHANNEL_INFO(curr,
+			   HWMON_C_INPUT | HWMON_C_LABEL,
+			   HWMON_C_INPUT | HWMON_C_AVERAGE | HWMON_C_LABEL
+			),
+	NULL
+};
+
+static const struct hwmon_chip_info max77705_chip_info = {
+	.ops = &max77705_hwmon_ops,
+	.info = max77705_info,
+};
+
+static int max77705_hwmon_probe(struct platform_device *pdev)
+{
+	struct device *hwmon_dev;
+	struct regmap *regmap;
+
+	regmap = dev_get_regmap(pdev->dev.parent, NULL);
+	if (!regmap)
+		return -ENODEV;
+
+	hwmon_dev = devm_hwmon_device_register_with_info(&pdev->dev, "max77705", regmap,
+							 &max77705_chip_info, NULL);
+	if (IS_ERR(hwmon_dev))
+		return dev_err_probe(&pdev->dev, PTR_ERR(hwmon_dev),
+				"Unable to register hwmon device\n");
+
+	return 0;
+};
+
+static struct platform_driver max77705_hwmon_driver = {
+	.driver = {
+		.name = "max77705-hwmon",
+	},
+	.probe = max77705_hwmon_probe,
+};
+
+module_platform_driver(max77705_hwmon_driver);
+
+MODULE_AUTHOR("Dzmitry Sankouski <dsankouski@gmail.com>");
+MODULE_DESCRIPTION("MAX77705 monitor driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/nct7363.c b/drivers/hwmon/nct7363.c
index be7bf32f6e68..e13ab918b1ab 100644
--- a/drivers/hwmon/nct7363.c
+++ b/drivers/hwmon/nct7363.c
@@ -391,7 +391,7 @@ static const struct regmap_config nct7363_regmap_config = {
 	.val_bits = 8,
 	.use_single_read = true,
 	.use_single_write = true,
-	.cache_type = REGCACHE_RBTREE,
+	.cache_type = REGCACHE_MAPLE,
 	.volatile_reg = nct7363_regmap_is_volatile,
 };
 
diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig
index c9b3c3149982..441f984a859d 100644
--- a/drivers/hwmon/pmbus/Kconfig
+++ b/drivers/hwmon/pmbus/Kconfig
@@ -218,6 +218,24 @@ config SENSORS_LM25066_REGULATOR
 	  If you say yes here you get regulator support for National
 	  Semiconductor LM25066, LM5064, and LM5066.
 
+config SENSORS_LT3074
+	tristate "Analog Devices LT3074"
+	help
+	  If you say yes here you get hardware monitoring support for Analog
+	  Devices LT3074.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called lt3074.
+
+config SENSORS_LT3074_REGULATOR
+	tristate "Regulator support for LT3074"
+	depends on SENSORS_LT3074 && REGULATOR
+	help
+	  If you say yes here you get regulator support for Analog Devices
+	  LT3074. The LT3074 is a low voltage, ultralow noise, high PSRR,
+	  dropout linear regulator. The device supplies up to 3A with a
+	  typical dropout voltage of 45mV.
+
 config SENSORS_LT7182S
 	tristate "Analog Devices LT7182S"
 	help
diff --git a/drivers/hwmon/pmbus/Makefile b/drivers/hwmon/pmbus/Makefile
index 56f128c4653e..29cd8a3317d2 100644
--- a/drivers/hwmon/pmbus/Makefile
+++ b/drivers/hwmon/pmbus/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_SENSORS_IR38064)	+= ir38064.o
 obj-$(CONFIG_SENSORS_IRPS5401)	+= irps5401.o
 obj-$(CONFIG_SENSORS_ISL68137)	+= isl68137.o
 obj-$(CONFIG_SENSORS_LM25066)	+= lm25066.o
+obj-$(CONFIG_SENSORS_LT3074)	+= lt3074.o
 obj-$(CONFIG_SENSORS_LT7182S)	+= lt7182s.o
 obj-$(CONFIG_SENSORS_LTC2978)	+= ltc2978.o
 obj-$(CONFIG_SENSORS_LTC3815)	+= ltc3815.o
diff --git a/drivers/hwmon/pmbus/lm25066.c b/drivers/hwmon/pmbus/lm25066.c
index 40b0dda32ea6..dd7275a67a0a 100644
--- a/drivers/hwmon/pmbus/lm25066.c
+++ b/drivers/hwmon/pmbus/lm25066.c
@@ -437,7 +437,7 @@ static int lm25066_write_word_data(struct i2c_client *client, int page, int reg,
 
 #if IS_ENABLED(CONFIG_SENSORS_LM25066_REGULATOR)
 static const struct regulator_desc lm25066_reg_desc[] = {
-	PMBUS_REGULATOR_ONE("vout"),
+	PMBUS_REGULATOR_ONE_NODE("vout"),
 };
 #endif
 
diff --git a/drivers/hwmon/pmbus/lt3074.c b/drivers/hwmon/pmbus/lt3074.c
new file mode 100644
index 000000000000..3704dbe7b54a
--- /dev/null
+++ b/drivers/hwmon/pmbus/lt3074.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hardware monitoring driver for Analog Devices LT3074
+ *
+ * Copyright (C) 2025 Analog Devices, Inc.
+ */
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+
+#include "pmbus.h"
+
+#define LT3074_MFR_READ_VBIAS			0xc6
+#define LT3074_MFR_BIAS_OV_WARN_LIMIT		0xc7
+#define LT3074_MFR_BIAS_UV_WARN_LIMIT		0xc8
+#define LT3074_MFR_SPECIAL_ID			0xe7
+
+#define LT3074_SPECIAL_ID_VALUE			0x1c1d
+
+static const struct regulator_desc __maybe_unused lt3074_reg_desc[] = {
+	PMBUS_REGULATOR_ONE("regulator"),
+};
+
+static int lt3074_read_word_data(struct i2c_client *client, int page,
+				 int phase, int reg)
+{
+	switch (reg) {
+	case PMBUS_VIRT_READ_VMON:
+		return pmbus_read_word_data(client, page, phase,
+					   LT3074_MFR_READ_VBIAS);
+	case PMBUS_VIRT_VMON_UV_WARN_LIMIT:
+		return pmbus_read_word_data(client, page, phase,
+					   LT3074_MFR_BIAS_UV_WARN_LIMIT);
+	case PMBUS_VIRT_VMON_OV_WARN_LIMIT:
+		return pmbus_read_word_data(client, page, phase,
+					   LT3074_MFR_BIAS_OV_WARN_LIMIT);
+	default:
+		return -ENODATA;
+	}
+}
+
+static int lt3074_write_word_data(struct i2c_client *client, int page,
+				  int reg, u16 word)
+{
+	switch (reg) {
+	case PMBUS_VIRT_VMON_UV_WARN_LIMIT:
+		return pmbus_write_word_data(client, 0,
+					    LT3074_MFR_BIAS_UV_WARN_LIMIT,
+					    word);
+	case PMBUS_VIRT_VMON_OV_WARN_LIMIT:
+		return pmbus_write_word_data(client, 0,
+					    LT3074_MFR_BIAS_OV_WARN_LIMIT,
+					    word);
+	default:
+		return -ENODATA;
+	}
+}
+
+static struct pmbus_driver_info lt3074_info = {
+	.pages = 1,
+	.format[PSC_VOLTAGE_IN] = linear,
+	.format[PSC_VOLTAGE_OUT] = linear,
+	.format[PSC_CURRENT_OUT] = linear,
+	.format[PSC_TEMPERATURE] = linear,
+	.func[0] = PMBUS_HAVE_VIN | PMBUS_HAVE_VOUT | PMBUS_HAVE_IOUT |
+		   PMBUS_HAVE_TEMP | PMBUS_HAVE_VMON |
+		   PMBUS_HAVE_STATUS_VOUT | PMBUS_HAVE_STATUS_IOUT |
+		   PMBUS_HAVE_STATUS_INPUT | PMBUS_HAVE_STATUS_TEMP,
+	.read_word_data = lt3074_read_word_data,
+	.write_word_data = lt3074_write_word_data,
+#if IS_ENABLED(CONFIG_SENSORS_LT3074_REGULATOR)
+	.num_regulators = 1,
+	.reg_desc = lt3074_reg_desc,
+#endif
+};
+
+static int lt3074_probe(struct i2c_client *client)
+{
+	int ret;
+	struct device *dev = &client->dev;
+
+	if (!i2c_check_functionality(client->adapter,
+				     I2C_FUNC_SMBUS_READ_WORD_DATA))
+		return -ENODEV;
+
+	ret = i2c_smbus_read_word_data(client, LT3074_MFR_SPECIAL_ID);
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "Failed to read ID\n");
+
+	if (ret != LT3074_SPECIAL_ID_VALUE)
+		return dev_err_probe(dev, -ENODEV, "ID mismatch\n");
+
+	return pmbus_do_probe(client, &lt3074_info);
+}
+
+static const struct i2c_device_id lt3074_id[] = {
+	{ "lt3074", 0 },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, lt3074_id);
+
+static const struct of_device_id __maybe_unused lt3074_of_match[] = {
+	{ .compatible = "adi,lt3074" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, lt3074_of_match);
+
+static struct i2c_driver lt3074_driver = {
+	.driver = {
+		.name = "lt3074",
+		.of_match_table = of_match_ptr(lt3074_of_match),
+	},
+	.probe = lt3074_probe,
+	.id_table = lt3074_id,
+};
+module_i2c_driver(lt3074_driver);
+
+MODULE_AUTHOR("Cedric Encarnacion <cedricjustine.encarnacion@analog.com>");
+MODULE_DESCRIPTION("PMBus driver for Analog Devices LT3074");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("PMBUS");
diff --git a/drivers/hwmon/pmbus/max34440.c b/drivers/hwmon/pmbus/max34440.c
index c9dda33831ff..56834d26f8ef 100644
--- a/drivers/hwmon/pmbus/max34440.c
+++ b/drivers/hwmon/pmbus/max34440.c
@@ -12,9 +12,26 @@
 #include <linux/init.h>
 #include <linux/err.h>
 #include <linux/i2c.h>
+#include <linux/delay.h>
 #include "pmbus.h"
 
-enum chips { max34440, max34441, max34446, max34451, max34460, max34461 };
+enum chips {
+	adpm12160,
+	max34440,
+	max34441,
+	max34446,
+	max34451,
+	max34460,
+	max34461,
+};
+
+/*
+ * Firmware is sometimes not ready if we try and read the
+ * data from the page immediately after setting. Maxim
+ * recommends 50us delay due to the chip failing to clock
+ * stretch long enough here.
+ */
+#define MAX34440_PAGE_CHANGE_DELAY 50
 
 #define MAX34440_MFR_VOUT_PEAK		0xd4
 #define MAX34440_MFR_IOUT_PEAK		0xd5
@@ -34,16 +51,21 @@ enum chips { max34440, max34441, max34446, max34451, max34460, max34461 };
 /*
  * The whole max344* family have IOUT_OC_WARN_LIMIT and IOUT_OC_FAULT_LIMIT
  * swapped from the standard pmbus spec addresses.
+ * For max34451, version MAX34451ETNA6+ and later has this issue fixed.
  */
 #define MAX34440_IOUT_OC_WARN_LIMIT	0x46
 #define MAX34440_IOUT_OC_FAULT_LIMIT	0x4A
 
+#define MAX34451ETNA6_MFR_REV		0x0012
+
 #define MAX34451_MFR_CHANNEL_CONFIG	0xe4
 #define MAX34451_MFR_CHANNEL_CONFIG_SEL_MASK	0x3f
 
 struct max34440_data {
 	int id;
 	struct pmbus_driver_info info;
+	u8 iout_oc_warn_limit;
+	u8 iout_oc_fault_limit;
 };
 
 #define to_max34440_data(x)  container_of(x, struct max34440_data, info)
@@ -60,11 +82,11 @@ static int max34440_read_word_data(struct i2c_client *client, int page,
 	switch (reg) {
 	case PMBUS_IOUT_OC_FAULT_LIMIT:
 		ret = pmbus_read_word_data(client, page, phase,
-					   MAX34440_IOUT_OC_FAULT_LIMIT);
+					   data->iout_oc_fault_limit);
 		break;
 	case PMBUS_IOUT_OC_WARN_LIMIT:
 		ret = pmbus_read_word_data(client, page, phase,
-					   MAX34440_IOUT_OC_WARN_LIMIT);
+					   data->iout_oc_warn_limit);
 		break;
 	case PMBUS_VIRT_READ_VOUT_MIN:
 		ret = pmbus_read_word_data(client, page, phase,
@@ -75,7 +97,8 @@ static int max34440_read_word_data(struct i2c_client *client, int page,
 					   MAX34440_MFR_VOUT_PEAK);
 		break;
 	case PMBUS_VIRT_READ_IOUT_AVG:
-		if (data->id != max34446 && data->id != max34451)
+		if (data->id != max34446 && data->id != max34451 &&
+		    data->id != adpm12160)
 			return -ENXIO;
 		ret = pmbus_read_word_data(client, page, phase,
 					   MAX34446_MFR_IOUT_AVG);
@@ -133,11 +156,11 @@ static int max34440_write_word_data(struct i2c_client *client, int page,
 
 	switch (reg) {
 	case PMBUS_IOUT_OC_FAULT_LIMIT:
-		ret = pmbus_write_word_data(client, page, MAX34440_IOUT_OC_FAULT_LIMIT,
+		ret = pmbus_write_word_data(client, page, data->iout_oc_fault_limit,
 					    word);
 		break;
 	case PMBUS_IOUT_OC_WARN_LIMIT:
-		ret = pmbus_write_word_data(client, page, MAX34440_IOUT_OC_WARN_LIMIT,
+		ret = pmbus_write_word_data(client, page, data->iout_oc_warn_limit,
 					    word);
 		break;
 	case PMBUS_VIRT_RESET_POUT_HISTORY:
@@ -159,7 +182,8 @@ static int max34440_write_word_data(struct i2c_client *client, int page,
 	case PMBUS_VIRT_RESET_IOUT_HISTORY:
 		ret = pmbus_write_word_data(client, page,
 					    MAX34440_MFR_IOUT_PEAK, 0);
-		if (!ret && (data->id == max34446 || data->id == max34451))
+		if (!ret && (data->id == max34446 || data->id == max34451 ||
+			     data->id == adpm12160))
 			ret = pmbus_write_word_data(client, page,
 					MAX34446_MFR_IOUT_AVG, 0);
 
@@ -235,9 +259,29 @@ static int max34451_set_supported_funcs(struct i2c_client *client,
 	 */
 
 	int page, rv;
+	bool max34451_na6 = false;
+
+	rv = i2c_smbus_read_word_data(client, PMBUS_MFR_REVISION);
+	if (rv < 0)
+		return rv;
+
+	if (rv >= MAX34451ETNA6_MFR_REV) {
+		max34451_na6 = true;
+		data->info.format[PSC_VOLTAGE_IN] = direct;
+		data->info.format[PSC_CURRENT_IN] = direct;
+		data->info.m[PSC_VOLTAGE_IN] = 1;
+		data->info.b[PSC_VOLTAGE_IN] = 0;
+		data->info.R[PSC_VOLTAGE_IN] = 3;
+		data->info.m[PSC_CURRENT_IN] = 1;
+		data->info.b[PSC_CURRENT_IN] = 0;
+		data->info.R[PSC_CURRENT_IN] = 2;
+		data->iout_oc_fault_limit = PMBUS_IOUT_OC_FAULT_LIMIT;
+		data->iout_oc_warn_limit = PMBUS_IOUT_OC_WARN_LIMIT;
+	}
 
 	for (page = 0; page < 16; page++) {
 		rv = i2c_smbus_write_byte_data(client, PMBUS_PAGE, page);
+		fsleep(MAX34440_PAGE_CHANGE_DELAY);
 		if (rv < 0)
 			return rv;
 
@@ -251,16 +295,30 @@ static int max34451_set_supported_funcs(struct i2c_client *client,
 		case 0x20:
 			data->info.func[page] = PMBUS_HAVE_VOUT |
 				PMBUS_HAVE_STATUS_VOUT;
+
+			if (max34451_na6)
+				data->info.func[page] |= PMBUS_HAVE_VIN |
+					PMBUS_HAVE_STATUS_INPUT;
 			break;
 		case 0x21:
 			data->info.func[page] = PMBUS_HAVE_VOUT;
+
+			if (max34451_na6)
+				data->info.func[page] |= PMBUS_HAVE_VIN;
 			break;
 		case 0x22:
 			data->info.func[page] = PMBUS_HAVE_IOUT |
 				PMBUS_HAVE_STATUS_IOUT;
+
+			if (max34451_na6)
+				data->info.func[page] |= PMBUS_HAVE_IIN |
+					PMBUS_HAVE_STATUS_INPUT;
 			break;
 		case 0x23:
 			data->info.func[page] = PMBUS_HAVE_IOUT;
+
+			if (max34451_na6)
+				data->info.func[page] |= PMBUS_HAVE_IIN;
 			break;
 		default:
 			break;
@@ -271,6 +329,41 @@ static int max34451_set_supported_funcs(struct i2c_client *client,
 }
 
 static struct pmbus_driver_info max34440_info[] = {
+	[adpm12160] = {
+		.pages = 19,
+		.format[PSC_VOLTAGE_IN] = direct,
+		.format[PSC_VOLTAGE_OUT] = direct,
+		.format[PSC_CURRENT_IN] = direct,
+		.format[PSC_CURRENT_OUT] = direct,
+		.format[PSC_TEMPERATURE] = direct,
+		.m[PSC_VOLTAGE_IN] = 1,
+		.b[PSC_VOLTAGE_IN] = 0,
+		.R[PSC_VOLTAGE_IN] = 0,
+		.m[PSC_VOLTAGE_OUT] = 1,
+		.b[PSC_VOLTAGE_OUT] = 0,
+		.R[PSC_VOLTAGE_OUT] = 0,
+		.m[PSC_CURRENT_IN] = 1,
+		.b[PSC_CURRENT_IN] = 0,
+		.R[PSC_CURRENT_IN] = 2,
+		.m[PSC_CURRENT_OUT] = 1,
+		.b[PSC_CURRENT_OUT] = 0,
+		.R[PSC_CURRENT_OUT] = 2,
+		.m[PSC_TEMPERATURE] = 1,
+		.b[PSC_TEMPERATURE] = 0,
+		.R[PSC_TEMPERATURE] = 2,
+		/* absent func below [18] are not for monitoring */
+		.func[2] = PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT,
+		.func[4] = PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT,
+		.func[5] = PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT,
+		.func[6] = PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT,
+		.func[7] = PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT,
+		.func[8] = PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT,
+		.func[9] = PMBUS_HAVE_VIN | PMBUS_HAVE_STATUS_INPUT,
+		.func[10] = PMBUS_HAVE_IIN | PMBUS_HAVE_STATUS_INPUT,
+		.func[18] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.read_word_data = max34440_read_word_data,
+		.write_word_data = max34440_write_word_data,
+	},
 	[max34440] = {
 		.pages = 14,
 		.format[PSC_VOLTAGE_IN] = direct,
@@ -312,6 +405,7 @@ static struct pmbus_driver_info max34440_info[] = {
 		.read_byte_data = max34440_read_byte_data,
 		.read_word_data = max34440_read_word_data,
 		.write_word_data = max34440_write_word_data,
+		.page_change_delay = MAX34440_PAGE_CHANGE_DELAY,
 	},
 	[max34441] = {
 		.pages = 12,
@@ -355,6 +449,7 @@ static struct pmbus_driver_info max34440_info[] = {
 		.read_byte_data = max34440_read_byte_data,
 		.read_word_data = max34440_read_word_data,
 		.write_word_data = max34440_write_word_data,
+		.page_change_delay = MAX34440_PAGE_CHANGE_DELAY,
 	},
 	[max34446] = {
 		.pages = 7,
@@ -392,6 +487,7 @@ static struct pmbus_driver_info max34440_info[] = {
 		.read_byte_data = max34440_read_byte_data,
 		.read_word_data = max34440_read_word_data,
 		.write_word_data = max34440_write_word_data,
+		.page_change_delay = MAX34440_PAGE_CHANGE_DELAY,
 	},
 	[max34451] = {
 		.pages = 21,
@@ -415,6 +511,7 @@ static struct pmbus_driver_info max34440_info[] = {
 		.func[20] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
 		.read_word_data = max34440_read_word_data,
 		.write_word_data = max34440_write_word_data,
+		.page_change_delay = MAX34440_PAGE_CHANGE_DELAY,
 	},
 	[max34460] = {
 		.pages = 18,
@@ -445,6 +542,7 @@ static struct pmbus_driver_info max34440_info[] = {
 		.func[17] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
 		.read_word_data = max34440_read_word_data,
 		.write_word_data = max34440_write_word_data,
+		.page_change_delay = MAX34440_PAGE_CHANGE_DELAY,
 	},
 	[max34461] = {
 		.pages = 23,
@@ -480,6 +578,7 @@ static struct pmbus_driver_info max34440_info[] = {
 		.func[21] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
 		.read_word_data = max34440_read_word_data,
 		.write_word_data = max34440_write_word_data,
+		.page_change_delay = MAX34440_PAGE_CHANGE_DELAY,
 	},
 };
 
@@ -494,17 +593,23 @@ static int max34440_probe(struct i2c_client *client)
 		return -ENOMEM;
 	data->id = i2c_match_id(max34440_id, client)->driver_data;
 	data->info = max34440_info[data->id];
+	data->iout_oc_fault_limit = MAX34440_IOUT_OC_FAULT_LIMIT;
+	data->iout_oc_warn_limit = MAX34440_IOUT_OC_WARN_LIMIT;
 
 	if (data->id == max34451) {
 		rv = max34451_set_supported_funcs(client, data);
 		if (rv)
 			return rv;
+	} else if (data->id == adpm12160) {
+		data->iout_oc_fault_limit = PMBUS_IOUT_OC_FAULT_LIMIT;
+		data->iout_oc_warn_limit = PMBUS_IOUT_OC_WARN_LIMIT;
 	}
 
 	return pmbus_do_probe(client, &data->info);
 }
 
 static const struct i2c_device_id max34440_id[] = {
+	{"adpm12160", adpm12160},
 	{"max34440", max34440},
 	{"max34441", max34441},
 	{"max34446", max34446},
diff --git a/drivers/hwmon/pmbus/mpq7932.c b/drivers/hwmon/pmbus/mpq7932.c
index c1e2d0cb2fd0..8f10e37a7a76 100644
--- a/drivers/hwmon/pmbus/mpq7932.c
+++ b/drivers/hwmon/pmbus/mpq7932.c
@@ -51,8 +51,8 @@ static const struct regulator_desc mpq7932_regulators_desc[] = {
 };
 
 static const struct regulator_desc mpq7932_regulators_desc_one[] = {
-	PMBUS_REGULATOR_STEP_ONE("buck", MPQ7932_N_VOLTAGES,
-				 MPQ7932_UV_STEP, MPQ7932_BUCK_UV_MIN),
+	PMBUS_REGULATOR_STEP_ONE_NODE("buck", MPQ7932_N_VOLTAGES,
+				      MPQ7932_UV_STEP, MPQ7932_BUCK_UV_MIN),
 };
 #endif
 
diff --git a/drivers/hwmon/pmbus/mpq8785.c b/drivers/hwmon/pmbus/mpq8785.c
index 331c274ca892..1f56aaf4dde8 100644
--- a/drivers/hwmon/pmbus/mpq8785.c
+++ b/drivers/hwmon/pmbus/mpq8785.c
@@ -4,10 +4,23 @@
  */
 
 #include <linux/i2c.h>
+#include <linux/bitops.h>
 #include <linux/module.h>
+#include <linux/property.h>
 #include <linux/of_device.h>
 #include "pmbus.h"
 
+#define MPM82504_READ_TEMPERATURE_1_SIGN_POS	9
+
+enum chips { mpm3695, mpm3695_25, mpm82504, mpq8785 };
+
+static u16 voltage_scale_loop_max_val[] = {
+	[mpm3695] = GENMASK(9, 0),
+	[mpm3695_25] = GENMASK(11, 0),
+	[mpm82504] = GENMASK(9, 0),
+	[mpq8785] = GENMASK(10, 0),
+};
+
 static int mpq8785_identify(struct i2c_client *client,
 			    struct pmbus_driver_info *info)
 {
@@ -34,6 +47,20 @@ static int mpq8785_identify(struct i2c_client *client,
 	return 0;
 };
 
+static int mpm82504_read_word_data(struct i2c_client *client, int page,
+				   int phase, int reg)
+{
+	int ret;
+
+	ret = pmbus_read_word_data(client, page, phase, reg);
+
+	if (ret < 0 || reg != PMBUS_READ_TEMPERATURE_1)
+		return ret;
+
+	/* Fix PMBUS_READ_TEMPERATURE_1 signedness */
+	return sign_extend32(ret, MPM82504_READ_TEMPERATURE_1_SIGN_POS) & 0xffff;
+}
+
 static struct pmbus_driver_info mpq8785_info = {
 	.pages = 1,
 	.format[PSC_VOLTAGE_IN] = direct,
@@ -53,26 +80,74 @@ static struct pmbus_driver_info mpq8785_info = {
 		PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT |
 		PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT |
 		PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
-	.identify = mpq8785_identify,
-};
-
-static int mpq8785_probe(struct i2c_client *client)
-{
-	return pmbus_do_probe(client, &mpq8785_info);
 };
 
 static const struct i2c_device_id mpq8785_id[] = {
-	{ "mpq8785" },
+	{ "mpm3695", mpm3695 },
+	{ "mpm3695-25", mpm3695_25 },
+	{ "mpm82504", mpm82504 },
+	{ "mpq8785", mpq8785 },
 	{ },
 };
 MODULE_DEVICE_TABLE(i2c, mpq8785_id);
 
 static const struct of_device_id __maybe_unused mpq8785_of_match[] = {
-	{ .compatible = "mps,mpq8785" },
+	{ .compatible = "mps,mpm3695", .data = (void *)mpm3695 },
+	{ .compatible = "mps,mpm3695-25", .data = (void *)mpm3695_25 },
+	{ .compatible = "mps,mpm82504", .data = (void *)mpm82504 },
+	{ .compatible = "mps,mpq8785", .data = (void *)mpq8785 },
 	{}
 };
 MODULE_DEVICE_TABLE(of, mpq8785_of_match);
 
+static int mpq8785_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct pmbus_driver_info *info;
+	enum chips chip_id;
+	u32 voltage_scale;
+	int ret;
+
+	info = devm_kmemdup(dev, &mpq8785_info, sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	if (dev->of_node)
+		chip_id = (kernel_ulong_t)of_device_get_match_data(dev);
+	else
+		chip_id = (kernel_ulong_t)i2c_get_match_data(client);
+
+	switch (chip_id) {
+	case mpm3695:
+	case mpm3695_25:
+	case mpm82504:
+		info->format[PSC_VOLTAGE_OUT] = direct;
+		info->m[PSC_VOLTAGE_OUT] = 8;
+		info->b[PSC_VOLTAGE_OUT] = 0;
+		info->R[PSC_VOLTAGE_OUT] = 2;
+		info->read_word_data = mpm82504_read_word_data;
+		break;
+	case mpq8785:
+		info->identify = mpq8785_identify;
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	if (!device_property_read_u32(dev, "mps,vout-fb-divider-ratio-permille",
+				      &voltage_scale)) {
+		if (voltage_scale > voltage_scale_loop_max_val[chip_id])
+			return -EINVAL;
+
+		ret = i2c_smbus_write_word_data(client, PMBUS_VOUT_SCALE_LOOP,
+						voltage_scale);
+		if (ret)
+			return ret;
+	}
+
+	return pmbus_do_probe(client, info);
+};
+
 static struct i2c_driver mpq8785_driver = {
 	.driver = {
 		   .name = "mpq8785",
diff --git a/drivers/hwmon/pmbus/pmbus.h b/drivers/hwmon/pmbus/pmbus.h
index ddb19c9726d6..d2e9bfb5320f 100644
--- a/drivers/hwmon/pmbus/pmbus.h
+++ b/drivers/hwmon/pmbus/pmbus.h
@@ -482,6 +482,7 @@ struct pmbus_driver_info {
 	 */
 	int access_delay;		/* in microseconds */
 	int write_delay;		/* in microseconds */
+	int page_change_delay;		/* in microseconds */
 };
 
 /* Regulator ops */
@@ -508,11 +509,11 @@ int pmbus_regulator_init_cb(struct regulator_dev *rdev,
 
 #define PMBUS_REGULATOR(_name, _id)   PMBUS_REGULATOR_STEP(_name, _id, 0, 0, 0)
 
-#define PMBUS_REGULATOR_STEP_ONE(_name, _voltages, _step, _min_uV)  \
+#define __PMBUS_REGULATOR_STEP_ONE(_name, _node, _voltages, _step, _min_uV)  \
 	{							\
 		.name = (_name),				\
 		.of_match = of_match_ptr(_name),		\
-		.regulators_node = of_match_ptr("regulators"),	\
+		.regulators_node = of_match_ptr(_node),		\
 		.ops = &pmbus_regulator_ops,			\
 		.type = REGULATOR_VOLTAGE,			\
 		.owner = THIS_MODULE,				\
@@ -522,7 +523,19 @@ int pmbus_regulator_init_cb(struct regulator_dev *rdev,
 		.init_cb = pmbus_regulator_init_cb,		\
 	}
 
-#define PMBUS_REGULATOR_ONE(_name)   PMBUS_REGULATOR_STEP_ONE(_name, 0, 0, 0)
+/*
+ * _NODE macros are defined for historic reasons and MUST NOT be used in new
+ * drivers.
+ */
+#define PMBUS_REGULATOR_STEP_ONE_NODE(_name, _voltages, _step, _min_uV)  \
+	__PMBUS_REGULATOR_STEP_ONE(_name, "regulators", _voltages, _step, _min_uV)
+
+#define PMBUS_REGULATOR_ONE_NODE(_name)	PMBUS_REGULATOR_STEP_ONE_NODE(_name, 0, 0, 0)
+
+#define PMBUS_REGULATOR_STEP_ONE(_name, _voltages, _step, _min_uV)  \
+	__PMBUS_REGULATOR_STEP_ONE(_name, NULL, _voltages, _step, _min_uV)
+
+#define PMBUS_REGULATOR_ONE(_name)	PMBUS_REGULATOR_STEP_ONE(_name, 0, 0, 0)
 
 /* Function declarations */
 
diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
index cfeba2e4c5c3..be6d05def115 100644
--- a/drivers/hwmon/pmbus/pmbus_core.c
+++ b/drivers/hwmon/pmbus/pmbus_core.c
@@ -32,6 +32,13 @@
 #define PMBUS_ATTR_ALLOC_SIZE	32
 #define PMBUS_NAME_SIZE		24
 
+/*
+ * The type of operation used for picking the delay between
+ * successive pmbus operations.
+ */
+#define PMBUS_OP_WRITE		BIT(0)
+#define PMBUS_OP_PAGE_CHANGE	BIT(1)
+
 static int wp = -1;
 module_param(wp, int, 0444);
 
@@ -113,8 +120,8 @@ struct pmbus_data {
 
 	int vout_low[PMBUS_PAGES];	/* voltage low margin */
 	int vout_high[PMBUS_PAGES];	/* voltage high margin */
-	ktime_t write_time;		/* Last SMBUS write timestamp */
-	ktime_t access_time;		/* Last SMBUS access timestamp */
+
+	ktime_t next_access_backoff;	/* Wait until at least this time */
 };
 
 struct pmbus_debugfs_entry {
@@ -169,32 +176,26 @@ EXPORT_SYMBOL_NS_GPL(pmbus_set_update, "PMBUS");
 static void pmbus_wait(struct i2c_client *client)
 {
 	struct pmbus_data *data = i2c_get_clientdata(client);
-	const struct pmbus_driver_info *info = data->info;
-	s64 delta;
+	s64 delay = ktime_us_delta(data->next_access_backoff, ktime_get());
 
-	if (info->access_delay) {
-		delta = ktime_us_delta(ktime_get(), data->access_time);
-
-		if (delta < info->access_delay)
-			fsleep(info->access_delay - delta);
-	} else if (info->write_delay) {
-		delta = ktime_us_delta(ktime_get(), data->write_time);
-
-		if (delta < info->write_delay)
-			fsleep(info->write_delay - delta);
-	}
+	if (delay > 0)
+		fsleep(delay);
 }
 
-/* Sets the last accessed timestamp for pmbus_wait */
-static void pmbus_update_ts(struct i2c_client *client, bool write_op)
+/* Sets the last operation timestamp for pmbus_wait */
+static void pmbus_update_ts(struct i2c_client *client, int op)
 {
 	struct pmbus_data *data = i2c_get_clientdata(client);
 	const struct pmbus_driver_info *info = data->info;
+	int delay = info->access_delay;
+
+	if (op & PMBUS_OP_WRITE)
+		delay = max(delay, info->write_delay);
+	if (op & PMBUS_OP_PAGE_CHANGE)
+		delay = max(delay, info->page_change_delay);
 
-	if (info->access_delay)
-		data->access_time = ktime_get();
-	else if (info->write_delay && write_op)
-		data->write_time = ktime_get();
+	if (delay > 0)
+		data->next_access_backoff = ktime_add_us(ktime_get(), delay);
 }
 
 int pmbus_set_page(struct i2c_client *client, int page, int phase)
@@ -209,13 +210,13 @@ int pmbus_set_page(struct i2c_client *client, int page, int phase)
 	    data->info->pages > 1 && page != data->currpage) {
 		pmbus_wait(client);
 		rv = i2c_smbus_write_byte_data(client, PMBUS_PAGE, page);
-		pmbus_update_ts(client, true);
+		pmbus_update_ts(client, PMBUS_OP_WRITE | PMBUS_OP_PAGE_CHANGE);
 		if (rv < 0)
 			return rv;
 
 		pmbus_wait(client);
 		rv = i2c_smbus_read_byte_data(client, PMBUS_PAGE);
-		pmbus_update_ts(client, false);
+		pmbus_update_ts(client, 0);
 		if (rv < 0)
 			return rv;
 
@@ -229,7 +230,7 @@ int pmbus_set_page(struct i2c_client *client, int page, int phase)
 		pmbus_wait(client);
 		rv = i2c_smbus_write_byte_data(client, PMBUS_PHASE,
 					       phase);
-		pmbus_update_ts(client, true);
+		pmbus_update_ts(client, PMBUS_OP_WRITE);
 		if (rv)
 			return rv;
 	}
@@ -249,7 +250,7 @@ int pmbus_write_byte(struct i2c_client *client, int page, u8 value)
 
 	pmbus_wait(client);
 	rv = i2c_smbus_write_byte(client, value);
-	pmbus_update_ts(client, true);
+	pmbus_update_ts(client, PMBUS_OP_WRITE);
 
 	return rv;
 }
@@ -284,7 +285,7 @@ int pmbus_write_word_data(struct i2c_client *client, int page, u8 reg,
 
 	pmbus_wait(client);
 	rv = i2c_smbus_write_word_data(client, reg, word);
-	pmbus_update_ts(client, true);
+	pmbus_update_ts(client, PMBUS_OP_WRITE);
 
 	return rv;
 }
@@ -405,7 +406,7 @@ int pmbus_read_word_data(struct i2c_client *client, int page, int phase, u8 reg)
 
 	pmbus_wait(client);
 	rv = i2c_smbus_read_word_data(client, reg);
-	pmbus_update_ts(client, false);
+	pmbus_update_ts(client, 0);
 
 	return rv;
 }
@@ -468,7 +469,7 @@ int pmbus_read_byte_data(struct i2c_client *client, int page, u8 reg)
 
 	pmbus_wait(client);
 	rv = i2c_smbus_read_byte_data(client, reg);
-	pmbus_update_ts(client, false);
+	pmbus_update_ts(client, 0);
 
 	return rv;
 }
@@ -484,7 +485,7 @@ int pmbus_write_byte_data(struct i2c_client *client, int page, u8 reg, u8 value)
 
 	pmbus_wait(client);
 	rv = i2c_smbus_write_byte_data(client, reg, value);
-	pmbus_update_ts(client, true);
+	pmbus_update_ts(client, PMBUS_OP_WRITE);
 
 	return rv;
 }
@@ -520,7 +521,7 @@ static int pmbus_read_block_data(struct i2c_client *client, int page, u8 reg,
 
 	pmbus_wait(client);
 	rv = i2c_smbus_read_block_data(client, reg, data_buf);
-	pmbus_update_ts(client, false);
+	pmbus_update_ts(client, 0);
 
 	return rv;
 }
@@ -2524,7 +2525,7 @@ static int pmbus_read_coefficients(struct i2c_client *client,
 	rv = i2c_smbus_xfer(client->adapter, client->addr, client->flags,
 			    I2C_SMBUS_WRITE, PMBUS_COEFFICIENTS,
 			    I2C_SMBUS_BLOCK_PROC_CALL, &data);
-	pmbus_update_ts(client, true);
+	pmbus_update_ts(client, PMBUS_OP_WRITE);
 
 	if (rv < 0)
 		return rv;
@@ -2728,7 +2729,7 @@ static int pmbus_init_common(struct i2c_client *client, struct pmbus_data *data,
 	if (!(data->flags & PMBUS_NO_CAPABILITY)) {
 		pmbus_wait(client);
 		ret = i2c_smbus_read_byte_data(client, PMBUS_CAPABILITY);
-		pmbus_update_ts(client, false);
+		pmbus_update_ts(client, 0);
 
 		if (ret >= 0 && (ret & PB_CAPABILITY_ERROR_CHECK)) {
 			if (i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_PEC))
@@ -2744,13 +2745,13 @@ static int pmbus_init_common(struct i2c_client *client, struct pmbus_data *data,
 	data->read_status = pmbus_read_status_word;
 	pmbus_wait(client);
 	ret = i2c_smbus_read_word_data(client, PMBUS_STATUS_WORD);
-	pmbus_update_ts(client, false);
+	pmbus_update_ts(client, 0);
 
 	if (ret < 0 || ret == 0xffff) {
 		data->read_status = pmbus_read_status_byte;
 		pmbus_wait(client);
 		ret = i2c_smbus_read_byte_data(client, PMBUS_STATUS_BYTE);
-		pmbus_update_ts(client, false);
+		pmbus_update_ts(client, 0);
 
 		if (ret < 0 || ret == 0xff) {
 			dev_err(dev, "PMBus status register not found\n");
diff --git a/drivers/hwmon/pmbus/tda38640.c b/drivers/hwmon/pmbus/tda38640.c
index 07fe58c24485..d902d39f49f4 100644
--- a/drivers/hwmon/pmbus/tda38640.c
+++ b/drivers/hwmon/pmbus/tda38640.c
@@ -15,7 +15,7 @@
 #include "pmbus.h"
 
 static const struct regulator_desc __maybe_unused tda38640_reg_desc[] = {
-	PMBUS_REGULATOR_ONE("vout"),
+	PMBUS_REGULATOR_ONE_NODE("vout"),
 };
 
 struct tda38640_data {
diff --git a/drivers/hwmon/pmbus/tps25990.c b/drivers/hwmon/pmbus/tps25990.c
index 0d2655e69549..c13edd7e1abf 100644
--- a/drivers/hwmon/pmbus/tps25990.c
+++ b/drivers/hwmon/pmbus/tps25990.c
@@ -333,7 +333,7 @@ static int tps25990_write_byte_data(struct i2c_client *client,
 
 #if IS_ENABLED(CONFIG_SENSORS_TPS25990_REGULATOR)
 static const struct regulator_desc tps25990_reg_desc[] = {
-	PMBUS_REGULATOR_ONE("vout"),
+	PMBUS_REGULATOR_ONE_NODE("vout"),
 };
 #endif
 
diff --git a/drivers/hwmon/pmbus/ucd9000.c b/drivers/hwmon/pmbus/ucd9000.c
index 9b0eadc81a2e..2bc8cccb01fd 100644
--- a/drivers/hwmon/pmbus/ucd9000.c
+++ b/drivers/hwmon/pmbus/ucd9000.c
@@ -212,8 +212,8 @@ static int ucd9000_gpio_get(struct gpio_chip *gc, unsigned int offset)
 	return !!(ret & UCD9000_GPIO_CONFIG_STATUS);
 }
 
-static void ucd9000_gpio_set(struct gpio_chip *gc, unsigned int offset,
-			     int value)
+static int ucd9000_gpio_set(struct gpio_chip *gc, unsigned int offset,
+			    int value)
 {
 	struct i2c_client *client = gpiochip_get_data(gc);
 	int ret;
@@ -222,17 +222,17 @@ static void ucd9000_gpio_set(struct gpio_chip *gc, unsigned int offset,
 	if (ret < 0) {
 		dev_dbg(&client->dev, "failed to read GPIO %d config: %d\n",
 			offset, ret);
-		return;
+		return ret;
 	}
 
 	if (value) {
 		if (ret & UCD9000_GPIO_CONFIG_STATUS)
-			return;
+			return 0;
 
 		ret |= UCD9000_GPIO_CONFIG_STATUS;
 	} else {
 		if (!(ret & UCD9000_GPIO_CONFIG_STATUS))
-			return;
+			return 0;
 
 		ret &= ~UCD9000_GPIO_CONFIG_STATUS;
 	}
@@ -244,7 +244,7 @@ static void ucd9000_gpio_set(struct gpio_chip *gc, unsigned int offset,
 	if (ret < 0) {
 		dev_dbg(&client->dev, "Failed to write GPIO %d config: %d\n",
 			offset, ret);
-		return;
+		return ret;
 	}
 
 	ret &= ~UCD9000_GPIO_CONFIG_ENABLE;
@@ -253,6 +253,8 @@ static void ucd9000_gpio_set(struct gpio_chip *gc, unsigned int offset,
 	if (ret < 0)
 		dev_dbg(&client->dev, "Failed to write GPIO %d config: %d\n",
 			offset, ret);
+
+	return ret;
 }
 
 static int ucd9000_gpio_get_direction(struct gpio_chip *gc,
@@ -362,7 +364,7 @@ static void ucd9000_probe_gpio(struct i2c_client *client,
 	data->gpio.direction_input = ucd9000_gpio_direction_input;
 	data->gpio.direction_output = ucd9000_gpio_direction_output;
 	data->gpio.get = ucd9000_gpio_get;
-	data->gpio.set = ucd9000_gpio_set;
+	data->gpio.set_rv = ucd9000_gpio_set;
 	data->gpio.can_sleep = true;
 	data->gpio.base = -1;
 	data->gpio.parent = &client->dev;
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index d506a5e7e033..2df294793f6e 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -620,8 +620,8 @@ static int pwm_fan_probe(struct platform_device *pdev)
 		if (tach->irq == -EPROBE_DEFER)
 			return tach->irq;
 		if (tach->irq > 0) {
-			ret = devm_request_irq(dev, tach->irq, pulse_handler, 0,
-					       pdev->name, tach);
+			ret = devm_request_irq(dev, tach->irq, pulse_handler,
+					       IRQF_NO_THREAD, pdev->name, tach);
 			if (ret) {
 				dev_err(dev,
 					"Failed to request interrupt: %d\n",
diff --git a/drivers/hwmon/qnap-mcu-hwmon.c b/drivers/hwmon/qnap-mcu-hwmon.c
index 29057514739c..e86e64c4d391 100644
--- a/drivers/hwmon/qnap-mcu-hwmon.c
+++ b/drivers/hwmon/qnap-mcu-hwmon.c
@@ -6,7 +6,6 @@
  * Copyright (C) 2024 Heiko Stuebner <heiko@sntech.de>
  */
 
-#include <linux/fwnode.h>
 #include <linux/hwmon.h>
 #include <linux/mfd/qnap-mcu.h>
 #include <linux/module.h>
diff --git a/drivers/hwmon/spd5118.c b/drivers/hwmon/spd5118.c
index 358152868d96..5da44571b6a0 100644
--- a/drivers/hwmon/spd5118.c
+++ b/drivers/hwmon/spd5118.c
@@ -66,6 +66,9 @@ static const unsigned short normal_i2c[] = {
 #define SPD5118_EEPROM_BASE		0x80
 #define SPD5118_EEPROM_SIZE		(SPD5118_PAGE_SIZE * SPD5118_NUM_PAGES)
 
+#define PAGE_ADDR0(page)		(((page) & BIT(0)) << 6)
+#define PAGE_ADDR1_4(page)		(((page) & GENMASK(4, 1)) >> 1)
+
 /* Temperature unit in millicelsius */
 #define SPD5118_TEMP_UNIT		(MILLIDEGREE_PER_DEGREE / 4)
 /* Representable temperature range in millicelsius */
@@ -75,6 +78,7 @@ static const unsigned short normal_i2c[] = {
 struct spd5118_data {
 	struct regmap *regmap;
 	struct mutex nvmem_lock;
+	bool is_16bit;
 };
 
 /* hwmon */
@@ -305,51 +309,6 @@ static bool spd5118_vendor_valid(u8 bank, u8 id)
 	return id && id != 0x7f;
 }
 
-/* Return 0 if detection is successful, -ENODEV otherwise */
-static int spd5118_detect(struct i2c_client *client, struct i2c_board_info *info)
-{
-	struct i2c_adapter *adapter = client->adapter;
-	int regval;
-
-	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA |
-				     I2C_FUNC_SMBUS_WORD_DATA))
-		return -ENODEV;
-
-	regval = i2c_smbus_read_word_swapped(client, SPD5118_REG_TYPE);
-	if (regval != 0x5118)
-		return -ENODEV;
-
-	regval = i2c_smbus_read_word_data(client, SPD5118_REG_VENDOR);
-	if (regval < 0 || !spd5118_vendor_valid(regval & 0xff, regval >> 8))
-		return -ENODEV;
-
-	regval = i2c_smbus_read_byte_data(client, SPD5118_REG_CAPABILITY);
-	if (regval < 0)
-		return -ENODEV;
-	if (!(regval & SPD5118_CAP_TS_SUPPORT) || (regval & 0xfc))
-		return -ENODEV;
-
-	regval = i2c_smbus_read_byte_data(client, SPD5118_REG_TEMP_CLR);
-	if (regval)
-		return -ENODEV;
-	regval = i2c_smbus_read_byte_data(client, SPD5118_REG_ERROR_CLR);
-	if (regval)
-		return -ENODEV;
-
-	regval = i2c_smbus_read_byte_data(client, SPD5118_REG_REVISION);
-	if (regval < 0 || (regval & 0xc1))
-		return -ENODEV;
-
-	regval = i2c_smbus_read_byte_data(client, SPD5118_REG_TEMP_CONFIG);
-	if (regval < 0)
-		return -ENODEV;
-	if (regval & ~SPD5118_TS_DISABLE)
-		return -ENODEV;
-
-	strscpy(info->type, "spd5118", I2C_NAME_SIZE);
-	return 0;
-}
-
 static const struct hwmon_channel_info *spd5118_info[] = {
 	HWMON_CHANNEL_INFO(chip,
 			   HWMON_C_REGISTER_TZ),
@@ -376,11 +335,12 @@ static const struct hwmon_chip_info spd5118_chip_info = {
 
 /* nvmem */
 
-static ssize_t spd5118_nvmem_read_page(struct regmap *regmap, char *buf,
+static ssize_t spd5118_nvmem_read_page(struct spd5118_data *data, char *buf,
 				       unsigned int offset, size_t count)
 {
-	int addr = (offset >> SPD5118_PAGE_SHIFT) * 0x100 + SPD5118_EEPROM_BASE;
-	int err;
+	int page = offset >> SPD5118_PAGE_SHIFT;
+	struct regmap *regmap = data->regmap;
+	int err, addr;
 
 	offset &= SPD5118_PAGE_MASK;
 
@@ -388,6 +348,12 @@ static ssize_t spd5118_nvmem_read_page(struct regmap *regmap, char *buf,
 	if (offset + count > SPD5118_PAGE_SIZE)
 		count = SPD5118_PAGE_SIZE - offset;
 
+	if (data->is_16bit) {
+		addr = SPD5118_EEPROM_BASE | PAGE_ADDR0(page) |
+		  (PAGE_ADDR1_4(page) << 8);
+	} else {
+		addr = page * 0x100 + SPD5118_EEPROM_BASE;
+	}
 	err = regmap_bulk_read(regmap, addr + offset, buf, count);
 	if (err)
 		return err;
@@ -410,7 +376,7 @@ static int spd5118_nvmem_read(void *priv, unsigned int off, void *val, size_t co
 	mutex_lock(&data->nvmem_lock);
 
 	while (count) {
-		ret = spd5118_nvmem_read_page(data->regmap, buf, off, count);
+		ret = spd5118_nvmem_read_page(data, buf, off, count);
 		if (ret < 0) {
 			mutex_unlock(&data->nvmem_lock);
 			return ret;
@@ -483,7 +449,7 @@ static bool spd5118_volatile_reg(struct device *dev, unsigned int reg)
 	}
 }
 
-static const struct regmap_range_cfg spd5118_regmap_range_cfg[] = {
+static const struct regmap_range_cfg spd5118_i2c_regmap_range_cfg[] = {
 	{
 	.selector_reg   = SPD5118_REG_I2C_LEGACY_MODE,
 	.selector_mask  = SPD5118_LEGACY_PAGE_MASK,
@@ -495,7 +461,7 @@ static const struct regmap_range_cfg spd5118_regmap_range_cfg[] = {
 	},
 };
 
-static const struct regmap_config spd5118_regmap_config = {
+static const struct regmap_config spd5118_regmap8_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 	.max_register = 0x7ff,
@@ -503,89 +469,76 @@ static const struct regmap_config spd5118_regmap_config = {
 	.volatile_reg = spd5118_volatile_reg,
 	.cache_type = REGCACHE_MAPLE,
 
-	.ranges = spd5118_regmap_range_cfg,
-	.num_ranges = ARRAY_SIZE(spd5118_regmap_range_cfg),
+	.ranges = spd5118_i2c_regmap_range_cfg,
+	.num_ranges = ARRAY_SIZE(spd5118_i2c_regmap_range_cfg),
 };
 
-static int spd5118_init(struct i2c_client *client)
-{
-	struct i2c_adapter *adapter = client->adapter;
-	int err, regval, mode;
-
-	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA |
-				     I2C_FUNC_SMBUS_WORD_DATA))
-		return -ENODEV;
+static const struct regmap_config spd5118_regmap16_config = {
+	.reg_bits = 16,
+	.val_bits = 8,
+	.max_register = 0x7ff,
+	.writeable_reg = spd5118_writeable_reg,
+	.volatile_reg = spd5118_volatile_reg,
+	.cache_type = REGCACHE_MAPLE,
+};
 
-	regval = i2c_smbus_read_word_swapped(client, SPD5118_REG_TYPE);
-	if (regval < 0 || (regval && regval != 0x5118))
-		return -ENODEV;
+static int spd5118_suspend(struct device *dev)
+{
+	struct spd5118_data *data = dev_get_drvdata(dev);
+	struct regmap *regmap = data->regmap;
+	u32 regval;
+	int err;
 
 	/*
-	 * If the device type registers return 0, it is possible that the chip
-	 * has a non-zero page selected and takes the specification literally,
-	 * i.e. disables access to volatile registers besides the page register
-	 * if the page is not 0. Try to identify such chips.
+	 * Make sure the configuration register in the regmap cache is current
+	 * before bypassing it.
 	 */
-	if (!regval) {
-		/* Vendor ID registers must also be 0 */
-		regval = i2c_smbus_read_word_data(client, SPD5118_REG_VENDOR);
-		if (regval)
-			return -ENODEV;
-
-		/* The selected page in MR11 must not be 0 */
-		mode = i2c_smbus_read_byte_data(client, SPD5118_REG_I2C_LEGACY_MODE);
-		if (mode < 0 || (mode & ~SPD5118_LEGACY_MODE_MASK) ||
-		    !(mode & SPD5118_LEGACY_PAGE_MASK))
-			return -ENODEV;
+	err = regmap_read(regmap, SPD5118_REG_TEMP_CONFIG, &regval);
+	if (err < 0)
+		return err;
 
-		err = i2c_smbus_write_byte_data(client, SPD5118_REG_I2C_LEGACY_MODE,
-						mode & SPD5118_LEGACY_MODE_ADDR);
-		if (err)
-			return -ENODEV;
+	regcache_cache_bypass(regmap, true);
+	regmap_update_bits(regmap, SPD5118_REG_TEMP_CONFIG, SPD5118_TS_DISABLE,
+			   SPD5118_TS_DISABLE);
+	regcache_cache_bypass(regmap, false);
 
-		/*
-		 * If the device type registers are still bad after selecting
-		 * page 0, this is not a SPD5118 device. Restore original
-		 * legacy mode register value and abort.
-		 */
-		regval = i2c_smbus_read_word_swapped(client, SPD5118_REG_TYPE);
-		if (regval != 0x5118) {
-			i2c_smbus_write_byte_data(client, SPD5118_REG_I2C_LEGACY_MODE, mode);
-			return -ENODEV;
-		}
-	}
+	regcache_cache_only(regmap, true);
+	regcache_mark_dirty(regmap);
 
-	/* We are reasonably sure that this is really a SPD5118 hub controller */
 	return 0;
 }
 
-static int spd5118_probe(struct i2c_client *client)
+static int spd5118_resume(struct device *dev)
 {
-	struct device *dev = &client->dev;
-	unsigned int regval, revision, vendor, bank;
+	struct spd5118_data *data = dev_get_drvdata(dev);
+	struct regmap *regmap = data->regmap;
+
+	regcache_cache_only(regmap, false);
+	return regcache_sync(regmap);
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(spd5118_pm_ops, spd5118_suspend, spd5118_resume);
+
+static int spd5118_common_probe(struct device *dev, struct regmap *regmap,
+				bool is_16bit)
+{
+	unsigned int capability, revision, vendor, bank;
 	struct spd5118_data *data;
 	struct device *hwmon_dev;
-	struct regmap *regmap;
 	int err;
 
-	err = spd5118_init(client);
-	if (err)
-		return err;
-
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
-	regmap = devm_regmap_init_i2c(client, &spd5118_regmap_config);
-	if (IS_ERR(regmap))
-		return dev_err_probe(dev, PTR_ERR(regmap), "regmap init failed\n");
-
-	err = regmap_read(regmap, SPD5118_REG_CAPABILITY, &regval);
+	err = regmap_read(regmap, SPD5118_REG_CAPABILITY, &capability);
 	if (err)
 		return err;
-	if (!(regval & SPD5118_CAP_TS_SUPPORT))
+	if (!(capability & SPD5118_CAP_TS_SUPPORT))
 		return -ENODEV;
 
+	data->is_16bit = is_16bit;
+
 	err = regmap_read(regmap, SPD5118_REG_REVISION, &revision);
 	if (err)
 		return err;
@@ -627,48 +580,176 @@ static int spd5118_probe(struct i2c_client *client)
 	return 0;
 }
 
-static int spd5118_suspend(struct device *dev)
+/* I2C */
+
+/* Return 0 if detection is successful, -ENODEV otherwise */
+static int spd5118_detect(struct i2c_client *client, struct i2c_board_info *info)
 {
-	struct spd5118_data *data = dev_get_drvdata(dev);
-	struct regmap *regmap = data->regmap;
-	u32 regval;
-	int err;
+	struct i2c_adapter *adapter = client->adapter;
+	int regval;
+
+	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA |
+				     I2C_FUNC_SMBUS_WORD_DATA))
+		return -ENODEV;
+
+	regval = i2c_smbus_read_word_swapped(client, SPD5118_REG_TYPE);
+	if (regval != 0x5118)
+		return -ENODEV;
+
+	regval = i2c_smbus_read_word_data(client, SPD5118_REG_VENDOR);
+	if (regval < 0 || !spd5118_vendor_valid(regval & 0xff, regval >> 8))
+		return -ENODEV;
+
+	regval = i2c_smbus_read_byte_data(client, SPD5118_REG_CAPABILITY);
+	if (regval < 0)
+		return -ENODEV;
+	if (!(regval & SPD5118_CAP_TS_SUPPORT) || (regval & 0xfc))
+		return -ENODEV;
+
+	regval = i2c_smbus_read_byte_data(client, SPD5118_REG_TEMP_CLR);
+	if (regval)
+		return -ENODEV;
+	regval = i2c_smbus_read_byte_data(client, SPD5118_REG_ERROR_CLR);
+	if (regval)
+		return -ENODEV;
+
+	regval = i2c_smbus_read_byte_data(client, SPD5118_REG_REVISION);
+	if (regval < 0 || (regval & 0xc1))
+		return -ENODEV;
+
+	regval = i2c_smbus_read_byte_data(client, SPD5118_REG_TEMP_CONFIG);
+	if (regval < 0)
+		return -ENODEV;
+	if (regval & ~SPD5118_TS_DISABLE)
+		return -ENODEV;
+
+	strscpy(info->type, "spd5118", I2C_NAME_SIZE);
+	return 0;
+}
+
+static int spd5118_i2c_init(struct i2c_client *client)
+{
+	struct i2c_adapter *adapter = client->adapter;
+	int err, regval, mode;
+
+	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA |
+				     I2C_FUNC_SMBUS_WORD_DATA))
+		return -ENODEV;
+
+	regval = i2c_smbus_read_word_swapped(client, SPD5118_REG_TYPE);
+	if (regval < 0 || (regval && regval != 0x5118))
+		return -ENODEV;
 
 	/*
-	 * Make sure the configuration register in the regmap cache is current
-	 * before bypassing it.
+	 * If the device type registers return 0, it is possible that the chip
+	 * has a non-zero page selected and takes the specification literally,
+	 * i.e. disables access to volatile registers besides the page register
+	 * if the page is not 0. The Renesas/ITD SPD5118 Hub Controller is known
+	 * to show this behavior. Try to identify such chips.
 	 */
-	err = regmap_read(regmap, SPD5118_REG_TEMP_CONFIG, &regval);
-	if (err < 0)
-		return err;
+	if (!regval) {
+		/* Vendor ID registers must also be 0 */
+		regval = i2c_smbus_read_word_data(client, SPD5118_REG_VENDOR);
+		if (regval)
+			return -ENODEV;
 
-	regcache_cache_bypass(regmap, true);
-	regmap_update_bits(regmap, SPD5118_REG_TEMP_CONFIG, SPD5118_TS_DISABLE,
-			   SPD5118_TS_DISABLE);
-	regcache_cache_bypass(regmap, false);
+		/* The selected page in MR11 must not be 0 */
+		mode = i2c_smbus_read_byte_data(client, SPD5118_REG_I2C_LEGACY_MODE);
+		if (mode < 0 || (mode & ~SPD5118_LEGACY_MODE_MASK) ||
+		    !(mode & SPD5118_LEGACY_PAGE_MASK))
+			return -ENODEV;
 
-	regcache_cache_only(regmap, true);
-	regcache_mark_dirty(regmap);
+		err = i2c_smbus_write_byte_data(client, SPD5118_REG_I2C_LEGACY_MODE,
+						mode & SPD5118_LEGACY_MODE_ADDR);
+		if (err)
+			return -ENODEV;
 
+		/*
+		 * If the device type registers are still bad after selecting
+		 * page 0, this is not a SPD5118 device. Restore original
+		 * legacy mode register value and abort.
+		 */
+		regval = i2c_smbus_read_word_swapped(client, SPD5118_REG_TYPE);
+		if (regval != 0x5118) {
+			i2c_smbus_write_byte_data(client, SPD5118_REG_I2C_LEGACY_MODE, mode);
+			return -ENODEV;
+		}
+	}
+
+	/* We are reasonably sure that this is really a SPD5118 hub controller */
 	return 0;
 }
 
-static int spd5118_resume(struct device *dev)
+/*
+ * 16-bit addressing note:
+ *
+ * If I2C_FUNC_I2C is not supported by an I2C adapter driver, regmap uses
+ * SMBus operations as alternative. To simulate a read operation with a 16-bit
+ * address, it writes the address using i2c_smbus_write_byte_data(), followed
+ * by one or more calls to i2c_smbus_read_byte() to read the data.
+ * Per spd5118 standard, a read operation after writing the address must start
+ * with <Sr> (Repeat Start). However, a SMBus read byte operation starts with
+ * <S> (Start). This resets the register address in the spd5118 chip. As result,
+ * i2c_smbus_read_byte() always returns data from register address 0x00.
+ *
+ * A working alternative to access chips with 16-bit register addresses in the
+ * absence of I2C_FUNC_I2C support is not known.
+ *
+ * For this reason, 16-bit addressing can only be supported with I2C if the
+ * adapter supports I2C_FUNC_I2C.
+ *
+ * For I2C, the addressing mode selected by the BIOS must not be changed.
+ * Experiments show that at least some PC BIOS versions will not change the
+ * addressing mode on a soft reboot and end up in setup, claiming that some
+ * configuration change happened. This will happen again after a power cycle,
+ * which does reset the addressing mode. To prevent this from happening,
+ * detect if 16-bit addressing is enabled and always use the currently
+ * configured addressing mode.
+ */
+
+static int spd5118_i2c_probe(struct i2c_client *client)
 {
-	struct spd5118_data *data = dev_get_drvdata(dev);
-	struct regmap *regmap = data->regmap;
+	const struct regmap_config *config;
+	struct device *dev = &client->dev;
+	struct regmap *regmap;
+	int err, mode;
+	bool is_16bit;
 
-	regcache_cache_only(regmap, false);
-	return regcache_sync(regmap);
-}
+	err = spd5118_i2c_init(client);
+	if (err)
+		return err;
 
-static DEFINE_SIMPLE_DEV_PM_OPS(spd5118_pm_ops, spd5118_suspend, spd5118_resume);
+	mode = i2c_smbus_read_byte_data(client, SPD5118_REG_I2C_LEGACY_MODE);
+	if (mode < 0)
+		return mode;
+
+	is_16bit = mode & SPD5118_LEGACY_MODE_ADDR;
+	if (is_16bit) {
+		/*
+		 * See 16-bit addressing note above explaining why it is
+		 * necessary to check for I2C_FUNC_I2C support here.
+		 */
+		if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
+			dev_err(dev, "Adapter does not support 16-bit register addresses\n");
+			return -ENODEV;
+		}
+		config = &spd5118_regmap16_config;
+	} else {
+		config = &spd5118_regmap8_config;
+	}
+
+	regmap = devm_regmap_init_i2c(client, config);
+	if (IS_ERR(regmap))
+		return dev_err_probe(dev, PTR_ERR(regmap), "regmap init failed\n");
+
+	return spd5118_common_probe(dev, regmap, is_16bit);
+}
 
-static const struct i2c_device_id spd5118_id[] = {
+static const struct i2c_device_id spd5118_i2c_id[] = {
 	{ "spd5118" },
 	{ }
 };
-MODULE_DEVICE_TABLE(i2c, spd5118_id);
+MODULE_DEVICE_TABLE(i2c, spd5118_i2c_id);
 
 static const struct of_device_id spd5118_of_ids[] = {
 	{ .compatible = "jedec,spd5118", },
@@ -676,20 +757,20 @@ static const struct of_device_id spd5118_of_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, spd5118_of_ids);
 
-static struct i2c_driver spd5118_driver = {
+static struct i2c_driver spd5118_i2c_driver = {
 	.class		= I2C_CLASS_HWMON,
 	.driver = {
 		.name	= "spd5118",
 		.of_match_table = spd5118_of_ids,
 		.pm = pm_sleep_ptr(&spd5118_pm_ops),
 	},
-	.probe		= spd5118_probe,
-	.id_table	= spd5118_id,
+	.probe		= spd5118_i2c_probe,
+	.id_table	= spd5118_i2c_id,
 	.detect		= IS_ENABLED(CONFIG_SENSORS_SPD5118_DETECT) ? spd5118_detect : NULL,
 	.address_list	= IS_ENABLED(CONFIG_SENSORS_SPD5118_DETECT) ? normal_i2c : NULL,
 };
 
-module_i2c_driver(spd5118_driver);
+module_i2c_driver(spd5118_i2c_driver);
 
 MODULE_AUTHOR("René Rebe <rene@exactcode.de>");
 MODULE_AUTHOR("Guenter Roeck <linux@roeck-us.net>");
diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c
index 8af44a33055f..a02daa496c9c 100644
--- a/drivers/hwmon/tmp102.c
+++ b/drivers/hwmon/tmp102.c
@@ -16,6 +16,7 @@
 #include <linux/device.h>
 #include <linux/jiffies.h>
 #include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
 #include <linux/of.h>
 
 #define	DRIVER_NAME "tmp102"
@@ -204,6 +205,10 @@ static int tmp102_probe(struct i2c_client *client)
 		return -ENODEV;
 	}
 
+	err = devm_regulator_get_enable_optional(dev, "vcc");
+	if (err < 0 && err != -ENODEV)
+		return dev_err_probe(dev, err, "Failed to enable regulator\n");
+
 	tmp102 = devm_kzalloc(dev, sizeof(*tmp102), GFP_KERNEL);
 	if (!tmp102)
 		return -ENOMEM;
diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c
index 2cdbd5f107a2..11c5d80428cd 100644
--- a/drivers/hwmon/xgene-hwmon.c
+++ b/drivers/hwmon/xgene-hwmon.c
@@ -103,8 +103,6 @@ struct xgene_hwmon_dev {
 	struct device		*hwmon_dev;
 	bool			temp_critical_alarm;
 
-	phys_addr_t		comm_base_addr;
-	void			*pcc_comm_addr;
 	unsigned int		usecs_lat;
 };
 
@@ -125,7 +123,8 @@ static u16 xgene_word_tst_and_clr(u16 *addr, u16 mask)
 
 static int xgene_hwmon_pcc_rd(struct xgene_hwmon_dev *ctx, u32 *msg)
 {
-	struct acpi_pcct_shared_memory *generic_comm_base = ctx->pcc_comm_addr;
+	struct acpi_pcct_shared_memory __iomem *generic_comm_base =
+							ctx->pcc_chan->shmem;
 	u32 *ptr = (void *)(generic_comm_base + 1);
 	int rc, i;
 	u16 val;
@@ -523,7 +522,8 @@ static void xgene_hwmon_rx_cb(struct mbox_client *cl, void *msg)
 static void xgene_hwmon_pcc_rx_cb(struct mbox_client *cl, void *msg)
 {
 	struct xgene_hwmon_dev *ctx = to_xgene_hwmon_dev(cl);
-	struct acpi_pcct_shared_memory *generic_comm_base = ctx->pcc_comm_addr;
+	struct acpi_pcct_shared_memory __iomem *generic_comm_base =
+							ctx->pcc_chan->shmem;
 	struct slimpro_resp_msg amsg;
 
 	/*
@@ -649,7 +649,6 @@ static int xgene_hwmon_probe(struct platform_device *pdev)
 	} else {
 		struct pcc_mbox_chan *pcc_chan;
 		const struct acpi_device_id *acpi_id;
-		int version;
 
 		acpi_id = acpi_match_device(pdev->dev.driver->acpi_match_table,
 					    &pdev->dev);
@@ -658,8 +657,6 @@ static int xgene_hwmon_probe(struct platform_device *pdev)
 			goto out_mbox_free;
 		}
 
-		version = (int)acpi_id->driver_data;
-
 		if (device_property_read_u32(&pdev->dev, "pcc-channel",
 					     &ctx->mbox_idx)) {
 			dev_err(&pdev->dev, "no pcc-channel property\n");
@@ -686,34 +683,6 @@ static int xgene_hwmon_probe(struct platform_device *pdev)
 		}
 
 		/*
-		 * This is the shared communication region
-		 * for the OS and Platform to communicate over.
-		 */
-		ctx->comm_base_addr = pcc_chan->shmem_base_addr;
-		if (ctx->comm_base_addr) {
-			if (version == XGENE_HWMON_V2)
-				ctx->pcc_comm_addr = (void __force *)devm_ioremap(&pdev->dev,
-								  ctx->comm_base_addr,
-								  pcc_chan->shmem_size);
-			else
-				ctx->pcc_comm_addr = devm_memremap(&pdev->dev,
-								   ctx->comm_base_addr,
-								   pcc_chan->shmem_size,
-								   MEMREMAP_WB);
-		} else {
-			dev_err(&pdev->dev, "Failed to get PCC comm region\n");
-			rc = -ENODEV;
-			goto out;
-		}
-
-		if (IS_ERR_OR_NULL(ctx->pcc_comm_addr)) {
-			dev_err(&pdev->dev,
-				"Failed to ioremap PCC comm region\n");
-			rc = -ENOMEM;
-			goto out;
-		}
-
-		/*
 		 * pcc_chan->latency is just a Nominal value. In reality
 		 * the remote processor could be much slower to reply.
 		 * So add an arbitrary amount of wait on top of Nominal.
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index c06b62f87b9b..9c17dfa76703 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -2024,9 +2024,6 @@ static int __init iommu_init_pci(struct amd_iommu *iommu)
 	if (!iommu->dev)
 		return -ENODEV;
 
-	/* Prevent binding other PCI device drivers to IOMMU devices */
-	iommu->dev->match_driver = false;
-
 	/* ACPI _PRT won't have an IRQ for IOMMU */
 	iommu->dev->irq_managed = 1;
 
diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index 1c12e6ec1370..69b32c19e8ff 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -15,6 +15,7 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/irqchip.h>
+#include <linux/irqchip/irq-renesas-rzv2h.h>
 #include <linux/irqdomain.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
@@ -41,6 +42,8 @@
 #define ICU_TSCLR				0x24
 #define ICU_TITSR(k)				(0x28 + (k) * 4)
 #define ICU_TSSR(k)				(0x30 + (k) * 4)
+#define ICU_DMkSELy(k, y)			(0x420 + (k) * 0x20 + (y) * 4)
+#define ICU_DMACKSELk(k)			(0x500 + (k) * 4)
 
 /* NMI */
 #define ICU_NMI_EDGE_FALLING			0
@@ -103,6 +106,15 @@ struct rzv2h_hw_info {
 	u8		field_width;
 };
 
+/* DMAC */
+#define ICU_DMAC_DkRQ_SEL_MASK			GENMASK(9, 0)
+
+#define ICU_DMAC_DMAREQ_SHIFT(up)		((up) * 16)
+#define ICU_DMAC_DMAREQ_MASK(up)		(ICU_DMAC_DkRQ_SEL_MASK \
+						 << ICU_DMAC_DMAREQ_SHIFT(up))
+#define ICU_DMAC_PREP_DMAREQ(sel, up)		(FIELD_PREP(ICU_DMAC_DkRQ_SEL_MASK, (sel)) \
+						 << ICU_DMAC_DMAREQ_SHIFT(up))
+
 /**
  * struct rzv2h_icu_priv - Interrupt Control Unit controller private data structure.
  * @base:	Controller's base address
@@ -117,6 +129,27 @@ struct rzv2h_icu_priv {
 	const struct rzv2h_hw_info	*info;
 };
 
+void rzv2h_icu_register_dma_req(struct platform_device *icu_dev, u8 dmac_index, u8 dmac_channel,
+				u16 req_no)
+{
+	struct rzv2h_icu_priv *priv = platform_get_drvdata(icu_dev);
+	u32 icu_dmksely, dmareq, dmareq_mask;
+	u8 y, upper;
+
+	y = dmac_channel / 2;
+	upper = dmac_channel % 2;
+
+	dmareq = ICU_DMAC_PREP_DMAREQ(req_no, upper);
+	dmareq_mask = ICU_DMAC_DMAREQ_MASK(upper);
+
+	guard(raw_spinlock_irqsave)(&priv->lock);
+
+	icu_dmksely = readl(priv->base + ICU_DMkSELy(dmac_index, y));
+	icu_dmksely = (icu_dmksely & ~dmareq_mask) | dmareq;
+	writel(icu_dmksely, priv->base + ICU_DMkSELy(dmac_index, y));
+}
+EXPORT_SYMBOL_GPL(rzv2h_icu_register_dma_req);
+
 static inline struct rzv2h_icu_priv *irq_data_to_priv(struct irq_data *data)
 {
 	return data->domain->host_data;
@@ -491,6 +524,8 @@ static int rzv2h_icu_init_common(struct device_node *node, struct device_node *p
 	if (!rzv2h_icu_data)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, rzv2h_icu_data);
+
 	rzv2h_icu_data->base = devm_of_iomap(&pdev->dev, pdev->dev.of_node, 0, NULL);
 	if (IS_ERR(rzv2h_icu_data->base))
 		return PTR_ERR(rzv2h_icu_data->base);
diff --git a/drivers/leds/.kunitconfig b/drivers/leds/.kunitconfig
new file mode 100644
index 000000000000..5180f77910a1
--- /dev/null
+++ b/drivers/leds/.kunitconfig
@@ -0,0 +1,4 @@
+CONFIG_KUNIT=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_KUNIT_TEST=y
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index a104cbb0a001..6e3dce7e35a4 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -55,6 +55,13 @@ config LEDS_BRIGHTNESS_HW_CHANGED
 
 	  See Documentation/ABI/testing/sysfs-class-led for details.
 
+config LEDS_KUNIT_TEST
+	tristate "KUnit tests for LEDs"
+	depends on KUNIT && LEDS_CLASS
+	default KUNIT_ALL_TESTS
+	help
+	  Say Y here to enable KUnit testing for the LEDs framework.
+
 comment "LED drivers"
 
 config LEDS_88PM860X
@@ -735,7 +742,7 @@ config LEDS_NS2
 	tristate "LED support for Network Space v2 GPIO LEDs"
 	depends on LEDS_CLASS
 	depends on MACH_KIRKWOOD || MACH_ARMADA_370 || COMPILE_TEST
-	default y
+	default y if MACH_KIRKWOOD || MACH_ARMADA_370
 	help
 	  This option enables support for the dual-GPIO LEDs found on the
 	  following LaCie/Seagate boards:
@@ -750,7 +757,7 @@ config LEDS_NETXBIG
 	depends on LEDS_CLASS
 	depends on MACH_KIRKWOOD || COMPILE_TEST
 	depends on OF_GPIO
-	default y
+	default MACH_KIRKWOOD
 	help
 	  This option enables support for LEDs found on the LaCie 2Big
 	  and 5Big Network v2 boards. The LEDs are wired to a CPLD and are
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index 2f170d69dcbf..9a0333ec1a86 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_LEDS_CLASS)		+= led-class.o
 obj-$(CONFIG_LEDS_CLASS_FLASH)		+= led-class-flash.o
 obj-$(CONFIG_LEDS_CLASS_MULTICOLOR)	+= led-class-multicolor.o
 obj-$(CONFIG_LEDS_TRIGGERS)		+= led-triggers.o
+obj-$(CONFIG_LEDS_KUNIT_TEST)		+= led-test.o
 
 # LED Platform Drivers (keep this sorted, M-| sort)
 obj-$(CONFIG_LEDS_88PM860X)		+= leds-88pm860x.o
diff --git a/drivers/leds/blink/leds-lgm-sso.c b/drivers/leds/blink/leds-lgm-sso.c
index effaaaf302b5..c9027f9c4bb7 100644
--- a/drivers/leds/blink/leds-lgm-sso.c
+++ b/drivers/leds/blink/leds-lgm-sso.c
@@ -450,7 +450,7 @@ static int sso_gpio_get(struct gpio_chip *chip, unsigned int offset)
 	return !!(reg_val & BIT(offset));
 }
 
-static void sso_gpio_set(struct gpio_chip *chip, unsigned int offset, int value)
+static int sso_gpio_set(struct gpio_chip *chip, unsigned int offset, int value)
 {
 	struct sso_led_priv *priv = gpiochip_get_data(chip);
 
@@ -458,6 +458,8 @@ static void sso_gpio_set(struct gpio_chip *chip, unsigned int offset, int value)
 	if (!priv->gpio.freq)
 		regmap_update_bits(priv->mmap, SSO_CON0, SSO_CON0_SWU,
 				   SSO_CON0_SWU);
+
+	return 0;
 }
 
 static int sso_gpio_gc_init(struct device *dev, struct sso_led_priv *priv)
@@ -469,7 +471,7 @@ static int sso_gpio_gc_init(struct device *dev, struct sso_led_priv *priv)
 	gc->get_direction       = sso_gpio_get_dir;
 	gc->direction_output    = sso_gpio_dir_out;
 	gc->get                 = sso_gpio_get;
-	gc->set                 = sso_gpio_set;
+	gc->set_rv              = sso_gpio_set;
 
 	gc->label               = "lgm-sso";
 	gc->base                = -1;
diff --git a/drivers/leds/flash/Kconfig b/drivers/leds/flash/Kconfig
index f39f0bfe6eef..55ca663ca506 100644
--- a/drivers/leds/flash/Kconfig
+++ b/drivers/leds/flash/Kconfig
@@ -132,4 +132,15 @@ config LEDS_SY7802
 
 	  This driver can be built as a module, it will be called "leds-sy7802".
 
+config LEDS_TPS6131X
+	tristate "LED support for TI TPS6131x flash LED driver"
+	depends on I2C && OF
+	depends on GPIOLIB
+	select REGMAP_I2C
+	help
+	  This option enables support for Texas Instruments TPS61310/TPS61311
+	  flash LED driver.
+
+	  This driver can be built as a module, it will be called "leds-tps6131x".
+
 endif # LEDS_CLASS_FLASH
diff --git a/drivers/leds/flash/Makefile b/drivers/leds/flash/Makefile
index 48860eeced79..712fb737a428 100644
--- a/drivers/leds/flash/Makefile
+++ b/drivers/leds/flash/Makefile
@@ -12,3 +12,4 @@ obj-$(CONFIG_LEDS_RT4505)	+= leds-rt4505.o
 obj-$(CONFIG_LEDS_RT8515)	+= leds-rt8515.o
 obj-$(CONFIG_LEDS_SGM3140)	+= leds-sgm3140.o
 obj-$(CONFIG_LEDS_SY7802)	+= leds-sy7802.o
+obj-$(CONFIG_LEDS_TPS6131X)	+= leds-tps6131x.o
diff --git a/drivers/leds/flash/leds-tps6131x.c b/drivers/leds/flash/leds-tps6131x.c
new file mode 100644
index 000000000000..6f4d4fd55361
--- /dev/null
+++ b/drivers/leds/flash/leds-tps6131x.c
@@ -0,0 +1,815 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Texas Instruments TPS61310/TPS61311 flash LED driver with I2C interface
+ *
+ * Copyright 2025 Matthias Fend <matthias.fend@emfend.at>
+ */
+
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/led-class-flash.h>
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <media/v4l2-flash-led-class.h>
+
+#define TPS6131X_REG_0				0x00
+#define   TPS6131X_REG_0_RESET			BIT(7)
+#define   TPS6131X_REG_0_DCLC13			GENMASK(5, 3)
+#define   TPS6131X_REG_0_DCLC13_SHIFT		3
+#define   TPS6131X_REG_0_DCLC2			GENMASK(2, 0)
+#define   TPS6131X_REG_0_DCLC2_SHIFT		0
+
+#define TPS6131X_REG_1				0x01
+#define   TPS6131X_REG_1_MODE			GENMASK(7, 6)
+#define   TPS6131X_REG_1_MODE_SHIFT		6
+#define   TPS6131X_REG_1_FC2			GENMASK(5, 0)
+#define   TPS6131X_REG_1_FC2_SHIFT		0
+
+#define TPS6131X_REG_2				0x02
+#define   TPS6131X_REG_2_MODE			GENMASK(7, 6)
+#define   TPS6131X_REG_2_MODE_SHIFT		6
+#define   TPS6131X_REG_2_ENVM			BIT(5)
+#define   TPS6131X_REG_2_FC13			GENMASK(4, 0)
+#define   TPS6131X_REG_2_FC13_SHIFT		0
+
+#define TPS6131X_REG_3				0x03
+#define   TPS6131X_REG_3_STIM			GENMASK(7, 5)
+#define   TPS6131X_REG_3_STIM_SHIFT		5
+#define   TPS6131X_REG_3_HPFL			BIT(4)
+#define   TPS6131X_REG_3_SELSTIM_TO		BIT(3)
+#define   TPS6131X_REG_3_STT			BIT(2)
+#define   TPS6131X_REG_3_SFT			BIT(1)
+#define   TPS6131X_REG_3_TXMASK			BIT(0)
+
+#define TPS6131X_REG_4				0x04
+#define   TPS6131X_REG_4_PG			BIT(7)
+#define   TPS6131X_REG_4_HOTDIE_HI		BIT(6)
+#define   TPS6131X_REG_4_HOTDIE_LO		BIT(5)
+#define   TPS6131X_REG_4_ILIM			BIT(4)
+#define   TPS6131X_REG_4_INDC			GENMASK(3, 0)
+#define   TPS6131X_REG_4_INDC_SHIFT		0
+
+#define TPS6131X_REG_5				0x05
+#define   TPS6131X_REG_5_SELFCAL		BIT(7)
+#define   TPS6131X_REG_5_ENPSM			BIT(6)
+#define   TPS6131X_REG_5_STSTRB1_DIR		BIT(5)
+#define   TPS6131X_REG_5_GPIO			BIT(4)
+#define   TPS6131X_REG_5_GPIOTYPE		BIT(3)
+#define   TPS6131X_REG_5_ENLED3			BIT(2)
+#define   TPS6131X_REG_5_ENLED2			BIT(1)
+#define   TPS6131X_REG_5_ENLED1			BIT(0)
+
+#define TPS6131X_REG_6				0x06
+#define   TPS6131X_REG_6_ENTS			BIT(7)
+#define   TPS6131X_REG_6_LEDHOT			BIT(6)
+#define   TPS6131X_REG_6_LEDWARN		BIT(5)
+#define   TPS6131X_REG_6_LEDHDR			BIT(4)
+#define   TPS6131X_REG_6_OV			GENMASK(3, 0)
+#define   TPS6131X_REG_6_OV_SHIFT		0
+
+#define TPS6131X_REG_7				0x07
+#define   TPS6131X_REG_7_ENBATMON		BIT(7)
+#define   TPS6131X_REG_7_BATDROOP		GENMASK(6, 4)
+#define   TPS6131X_REG_7_BATDROOP_SHIFT		4
+#define   TPS6131X_REG_7_REVID			GENMASK(2, 0)
+#define   TPS6131X_REG_7_REVID_SHIFT		0
+
+#define TPS6131X_MAX_CHANNELS			3
+
+#define TPS6131X_FLASH_MAX_I_CHAN13_MA		400
+#define TPS6131X_FLASH_MAX_I_CHAN2_MA		800
+#define TPS6131X_FLASH_STEP_I_MA		25
+
+#define TPS6131X_TORCH_MAX_I_CHAN13_MA		175
+#define TPS6131X_TORCH_MAX_I_CHAN2_MA		175
+#define TPS6131X_TORCH_STEP_I_MA		25
+
+/* The torch watchdog timer must be refreshed within an interval of 13 seconds. */
+#define TPS6131X_TORCH_REFRESH_INTERVAL_JIFFIES msecs_to_jiffies(10000)
+
+#define UA_TO_MA(UA)				((UA) / 1000)
+
+enum tps6131x_mode {
+	TPS6131X_MODE_SHUTDOWN = 0x0,
+	TPS6131X_MODE_TORCH = 0x1,
+	TPS6131X_MODE_FLASH = 0x2,
+};
+
+struct tps6131x {
+	struct device *dev;
+	struct regmap *regmap;
+	struct gpio_desc *reset_gpio;
+	/*
+	 * Registers 0, 1, 2, and 3 control parts of the controller that are not completely
+	 * independent of each other. Since some operations require the registers to be written in
+	 * a specific order to avoid unwanted side effects, they are synchronized with a lock.
+	 */
+	struct mutex lock; /* Hardware access lock for register 0, 1, 2 and 3 */
+	struct delayed_work torch_refresh_work;
+	bool valley_current_limit;
+	bool chan1_en;
+	bool chan2_en;
+	bool chan3_en;
+	struct fwnode_handle *led_node;
+	u32 max_flash_current_ma;
+	u32 step_flash_current_ma;
+	u32 max_torch_current_ma;
+	u32 step_torch_current_ma;
+	u32 max_timeout_us;
+	struct led_classdev_flash fled_cdev;
+	struct v4l2_flash *v4l2_flash;
+};
+
+static struct tps6131x *fled_cdev_to_tps6131x(struct led_classdev_flash *fled_cdev)
+{
+	return container_of(fled_cdev, struct tps6131x, fled_cdev);
+}
+
+/*
+ * Register contents after a power on/reset. These values cannot be changed.
+ */
+
+#define TPS6131X_DCLC2_50MA	     2
+#define TPS6131X_DCLC13_25MA	     1
+#define TPS6131X_FC2_400MA	     16
+#define TPS6131X_FC13_200MA	     8
+#define TPS6131X_STIM_0_579MS_1_37MS 6
+#define TPS6131X_SELSTIM_RANGE0	     0
+#define TPS6131X_INDC_OFF	     0
+#define TPS6131X_OV_4950MV	     9
+#define TPS6131X_BATDROOP_150MV	     4
+
+static const struct reg_default tps6131x_regmap_defaults[] = {
+	{ TPS6131X_REG_0, (TPS6131X_DCLC13_25MA << TPS6131X_REG_0_DCLC13_SHIFT) |
+				  (TPS6131X_DCLC2_50MA << TPS6131X_REG_0_DCLC2_SHIFT) },
+	{ TPS6131X_REG_1, (TPS6131X_MODE_SHUTDOWN << TPS6131X_REG_1_MODE_SHIFT) |
+				  (TPS6131X_FC2_400MA << TPS6131X_REG_1_FC2_SHIFT) },
+	{ TPS6131X_REG_2, (TPS6131X_MODE_SHUTDOWN << TPS6131X_REG_2_MODE_SHIFT) |
+				  (TPS6131X_FC13_200MA << TPS6131X_REG_2_FC13_SHIFT) },
+	{ TPS6131X_REG_3, (TPS6131X_STIM_0_579MS_1_37MS << TPS6131X_REG_3_STIM_SHIFT) |
+				  (TPS6131X_SELSTIM_RANGE0 << TPS6131X_REG_3_SELSTIM_TO) |
+				  TPS6131X_REG_3_TXMASK },
+	{ TPS6131X_REG_4, (TPS6131X_INDC_OFF << TPS6131X_REG_4_INDC_SHIFT) },
+	{ TPS6131X_REG_5, TPS6131X_REG_5_ENPSM | TPS6131X_REG_5_STSTRB1_DIR |
+				  TPS6131X_REG_5_GPIOTYPE | TPS6131X_REG_5_ENLED2 },
+	{ TPS6131X_REG_6, (TPS6131X_OV_4950MV << TPS6131X_REG_6_OV_SHIFT) },
+	{ TPS6131X_REG_7, (TPS6131X_BATDROOP_150MV << TPS6131X_REG_7_BATDROOP_SHIFT) },
+};
+
+/*
+ * These registers contain flags that are reset when read.
+ */
+static bool tps6131x_regmap_precious(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case TPS6131X_REG_3:
+	case TPS6131X_REG_4:
+	case TPS6131X_REG_6:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const struct regmap_config tps6131x_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = TPS6131X_REG_7,
+	.reg_defaults = tps6131x_regmap_defaults,
+	.num_reg_defaults = ARRAY_SIZE(tps6131x_regmap_defaults),
+	.cache_type = REGCACHE_FLAT,
+	.precious_reg = &tps6131x_regmap_precious,
+};
+
+struct tps6131x_timer_config {
+	u8 val;
+	u8 range;
+	u32 time_us;
+};
+
+static const struct tps6131x_timer_config tps6131x_timer_configs[] = {
+	{ .val = 0, .range = 1, .time_us = 5300 },
+	{ .val = 1, .range = 1, .time_us = 10700 },
+	{ .val = 2, .range = 1, .time_us = 16000 },
+	{ .val = 3, .range = 1, .time_us = 21300 },
+	{ .val = 4, .range = 1, .time_us = 26600 },
+	{ .val = 5, .range = 1, .time_us = 32000 },
+	{ .val = 6, .range = 1, .time_us = 37300 },
+	{ .val = 0, .range = 0, .time_us = 68200 },
+	{ .val = 7, .range = 1, .time_us = 71500 },
+	{ .val = 1, .range = 0, .time_us = 102200 },
+	{ .val = 2, .range = 0, .time_us = 136300 },
+	{ .val = 3, .range = 0, .time_us = 170400 },
+	{ .val = 4, .range = 0, .time_us = 204500 },
+	{ .val = 5, .range = 0, .time_us = 340800 },
+	{ .val = 6, .range = 0, .time_us = 579300 },
+	{ .val = 7, .range = 0, .time_us = 852000 },
+};
+
+static const struct tps6131x_timer_config *tps6131x_find_closest_timer_config(u32 timeout_us)
+{
+	const struct tps6131x_timer_config *timer_config = &tps6131x_timer_configs[0];
+	u32 diff, min_diff = U32_MAX;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tps6131x_timer_configs); i++) {
+		diff = abs(tps6131x_timer_configs[i].time_us - timeout_us);
+		if (diff < min_diff) {
+			timer_config = &tps6131x_timer_configs[i];
+			min_diff = diff;
+			if (!min_diff)
+				break;
+		}
+	}
+
+	return timer_config;
+}
+
+static int tps6131x_reset_chip(struct tps6131x *tps6131x)
+{
+	int ret;
+
+	if (tps6131x->reset_gpio) {
+		gpiod_set_value_cansleep(tps6131x->reset_gpio, 1);
+		fsleep(10);
+		gpiod_set_value_cansleep(tps6131x->reset_gpio, 0);
+		fsleep(100);
+	} else {
+		ret = regmap_update_bits(tps6131x->regmap, TPS6131X_REG_0, TPS6131X_REG_0_RESET,
+					 TPS6131X_REG_0_RESET);
+		if (ret)
+			return ret;
+
+		fsleep(100);
+
+		ret = regmap_update_bits(tps6131x->regmap, TPS6131X_REG_0, TPS6131X_REG_0_RESET, 0);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int tps6131x_init_chip(struct tps6131x *tps6131x)
+{
+	u32 val;
+	int ret;
+
+	val = tps6131x->valley_current_limit ? TPS6131X_REG_4_ILIM : 0;
+
+	ret = regmap_write(tps6131x->regmap, TPS6131X_REG_4, val);
+	if (ret)
+		return ret;
+
+	val = TPS6131X_REG_5_ENPSM | TPS6131X_REG_5_STSTRB1_DIR | TPS6131X_REG_5_GPIOTYPE;
+
+	if (tps6131x->chan1_en)
+		val |= TPS6131X_REG_5_ENLED1;
+
+	if (tps6131x->chan2_en)
+		val |= TPS6131X_REG_5_ENLED2;
+
+	if (tps6131x->chan3_en)
+		val |= TPS6131X_REG_5_ENLED3;
+
+	ret = regmap_write(tps6131x->regmap, TPS6131X_REG_5, val);
+	if (ret)
+		return ret;
+
+	val = TPS6131X_REG_6_ENTS;
+
+	ret = regmap_write(tps6131x->regmap, TPS6131X_REG_6, val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int tps6131x_set_mode(struct tps6131x *tps6131x, enum tps6131x_mode mode, bool force)
+{
+	u8 val = mode << TPS6131X_REG_1_MODE_SHIFT;
+
+	return regmap_update_bits_base(tps6131x->regmap, TPS6131X_REG_1, TPS6131X_REG_1_MODE, val,
+				       NULL, false, force);
+}
+
+static void tps6131x_torch_refresh_handler(struct work_struct *work)
+{
+	struct tps6131x *tps6131x = container_of(work, struct tps6131x, torch_refresh_work.work);
+	int ret;
+
+	guard(mutex)(&tps6131x->lock);
+
+	ret = tps6131x_set_mode(tps6131x, TPS6131X_MODE_TORCH, true);
+	if (ret < 0) {
+		dev_err(tps6131x->dev, "Failed to refresh torch watchdog timer\n");
+		return;
+	}
+
+	schedule_delayed_work(&tps6131x->torch_refresh_work,
+			      TPS6131X_TORCH_REFRESH_INTERVAL_JIFFIES);
+}
+
+static int tps6131x_brightness_set(struct led_classdev *cdev, enum led_brightness brightness)
+{
+	struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(cdev);
+	struct tps6131x *tps6131x = fled_cdev_to_tps6131x(fled_cdev);
+	u32 num_chans, steps_chan13, steps_chan2, steps_remaining;
+	u8 reg0;
+	int ret;
+
+	cancel_delayed_work_sync(&tps6131x->torch_refresh_work);
+
+	/*
+	 * The brightness parameter uses the number of current steps as the unit (not the current
+	 * value itself). Since the reported step size can vary depending on the configuration,
+	 * this value must be converted into actual register steps.
+	 */
+	steps_remaining = (brightness * tps6131x->step_torch_current_ma) / TPS6131X_TORCH_STEP_I_MA;
+
+	num_chans = tps6131x->chan1_en + tps6131x->chan2_en + tps6131x->chan3_en;
+
+	/*
+	 * The currents are distributed as evenly as possible across the activated channels.
+	 * Since channels 1 and 3 share the same register setting, they always use the same current
+	 * value. Channel 2 supports higher currents and thus takes over the remaining additional
+	 * portion that cannot be covered by the other channels.
+	 */
+	steps_chan13 = min_t(u32, steps_remaining / num_chans,
+			     TPS6131X_TORCH_MAX_I_CHAN13_MA / TPS6131X_TORCH_STEP_I_MA);
+	if (tps6131x->chan1_en)
+		steps_remaining -= steps_chan13;
+	if (tps6131x->chan3_en)
+		steps_remaining -= steps_chan13;
+
+	steps_chan2 = min_t(u32, steps_remaining,
+			    TPS6131X_TORCH_MAX_I_CHAN2_MA / TPS6131X_TORCH_STEP_I_MA);
+
+	guard(mutex)(&tps6131x->lock);
+
+	reg0 = (steps_chan13 << TPS6131X_REG_0_DCLC13_SHIFT) |
+	       (steps_chan2 << TPS6131X_REG_0_DCLC2_SHIFT);
+	ret = regmap_update_bits(tps6131x->regmap, TPS6131X_REG_0,
+				 TPS6131X_REG_0_DCLC13 | TPS6131X_REG_0_DCLC2, reg0);
+	if (ret < 0)
+		return ret;
+
+	ret = tps6131x_set_mode(tps6131x, brightness ? TPS6131X_MODE_TORCH : TPS6131X_MODE_SHUTDOWN,
+				true);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * In order to use both the flash and the video light functions purely via the I2C
+	 * interface, STRB1 must be low. If STRB1 is low, then the video light watchdog timer
+	 * is also active, which puts the device into the shutdown state after around 13 seconds.
+	 * To prevent this, the mode must be refreshed within the watchdog timeout.
+	 */
+	if (brightness)
+		schedule_delayed_work(&tps6131x->torch_refresh_work,
+				      TPS6131X_TORCH_REFRESH_INTERVAL_JIFFIES);
+
+	return 0;
+}
+
+static int tps6131x_strobe_set(struct led_classdev_flash *fled_cdev, bool state)
+{
+	struct tps6131x *tps6131x = fled_cdev_to_tps6131x(fled_cdev);
+	int ret;
+
+	guard(mutex)(&tps6131x->lock);
+
+	ret = tps6131x_set_mode(tps6131x, state ? TPS6131X_MODE_FLASH : TPS6131X_MODE_SHUTDOWN,
+				true);
+	if (ret < 0)
+		return ret;
+
+	if (state) {
+		ret = regmap_update_bits_base(tps6131x->regmap, TPS6131X_REG_3, TPS6131X_REG_3_SFT,
+					      TPS6131X_REG_3_SFT, NULL, false, true);
+		if (ret)
+			return ret;
+	}
+
+	ret = regmap_update_bits_base(tps6131x->regmap, TPS6131X_REG_3, TPS6131X_REG_3_SFT, 0, NULL,
+				      false, true);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int tps6131x_flash_brightness_set(struct led_classdev_flash *fled_cdev, u32 brightness)
+{
+	struct tps6131x *tps6131x = fled_cdev_to_tps6131x(fled_cdev);
+	u32 num_chans;
+	u32 steps_chan13, steps_chan2;
+	u32 steps_remaining;
+	int ret;
+
+	steps_remaining = brightness / TPS6131X_FLASH_STEP_I_MA;
+	num_chans = tps6131x->chan1_en + tps6131x->chan2_en + tps6131x->chan3_en;
+	steps_chan13 = min_t(u32, steps_remaining / num_chans,
+			     TPS6131X_FLASH_MAX_I_CHAN13_MA / TPS6131X_FLASH_STEP_I_MA);
+	if (tps6131x->chan1_en)
+		steps_remaining -= steps_chan13;
+	if (tps6131x->chan3_en)
+		steps_remaining -= steps_chan13;
+	steps_chan2 = min_t(u32, steps_remaining,
+			    TPS6131X_FLASH_MAX_I_CHAN2_MA / TPS6131X_FLASH_STEP_I_MA);
+
+	guard(mutex)(&tps6131x->lock);
+
+	ret = regmap_update_bits(tps6131x->regmap, TPS6131X_REG_2, TPS6131X_REG_2_FC13,
+				 steps_chan13 << TPS6131X_REG_2_FC13_SHIFT);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_update_bits(tps6131x->regmap, TPS6131X_REG_1, TPS6131X_REG_1_FC2,
+				 steps_chan2 << TPS6131X_REG_1_FC2_SHIFT);
+	if (ret < 0)
+		return ret;
+
+	fled_cdev->brightness.val = brightness;
+
+	return 0;
+}
+
+static int tps6131x_flash_timeout_set(struct led_classdev_flash *fled_cdev, u32 timeout_us)
+{
+	const struct tps6131x_timer_config *timer_config;
+	struct tps6131x *tps6131x = fled_cdev_to_tps6131x(fled_cdev);
+	u8 reg3;
+	int ret;
+
+	guard(mutex)(&tps6131x->lock);
+
+	timer_config = tps6131x_find_closest_timer_config(timeout_us);
+
+	reg3 = timer_config->val << TPS6131X_REG_3_STIM_SHIFT;
+	if (timer_config->range)
+		reg3 |= TPS6131X_REG_3_SELSTIM_TO;
+
+	ret = regmap_update_bits(tps6131x->regmap, TPS6131X_REG_3,
+				 TPS6131X_REG_3_STIM | TPS6131X_REG_3_SELSTIM_TO, reg3);
+	if (ret < 0)
+		return ret;
+
+	fled_cdev->timeout.val = timer_config->time_us;
+
+	return 0;
+}
+
+static int tps6131x_strobe_get(struct led_classdev_flash *fled_cdev, bool *state)
+{
+	struct tps6131x *tps6131x = fled_cdev_to_tps6131x(fled_cdev);
+	unsigned int reg3;
+	int ret;
+
+	ret = regmap_read_bypassed(tps6131x->regmap, TPS6131X_REG_3, &reg3);
+	if (ret)
+		return ret;
+
+	*state = !!(reg3 & TPS6131X_REG_3_SFT);
+
+	return 0;
+}
+
+static int tps6131x_flash_fault_get(struct led_classdev_flash *fled_cdev, u32 *fault)
+{
+	struct tps6131x *tps6131x = fled_cdev_to_tps6131x(fled_cdev);
+	unsigned int reg3, reg4, reg6;
+	int ret;
+
+	*fault = 0;
+
+	ret = regmap_read_bypassed(tps6131x->regmap, TPS6131X_REG_3, &reg3);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_read_bypassed(tps6131x->regmap, TPS6131X_REG_4, &reg4);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_read_bypassed(tps6131x->regmap, TPS6131X_REG_6, &reg6);
+	if (ret < 0)
+		return ret;
+
+	if (reg3 & TPS6131X_REG_3_HPFL)
+		*fault |= LED_FAULT_SHORT_CIRCUIT;
+
+	if (reg3 & TPS6131X_REG_3_SELSTIM_TO)
+		*fault |= LED_FAULT_TIMEOUT;
+
+	if (reg4 & TPS6131X_REG_4_HOTDIE_HI)
+		*fault |= LED_FAULT_OVER_TEMPERATURE;
+
+	if (reg6 & (TPS6131X_REG_6_LEDHOT | TPS6131X_REG_6_LEDWARN))
+		*fault |= LED_FAULT_LED_OVER_TEMPERATURE;
+
+	if (!(reg6 & TPS6131X_REG_6_LEDHDR))
+		*fault |= LED_FAULT_UNDER_VOLTAGE;
+
+	if (reg6 & TPS6131X_REG_6_LEDHOT) {
+		ret = regmap_update_bits_base(tps6131x->regmap, TPS6131X_REG_6,
+					      TPS6131X_REG_6_LEDHOT, 0, NULL, false, true);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static const struct led_flash_ops flash_ops = {
+	.flash_brightness_set = tps6131x_flash_brightness_set,
+	.strobe_set = tps6131x_strobe_set,
+	.strobe_get = tps6131x_strobe_get,
+	.timeout_set = tps6131x_flash_timeout_set,
+	.fault_get = tps6131x_flash_fault_get,
+};
+
+static int tps6131x_parse_node(struct tps6131x *tps6131x)
+{
+	const struct tps6131x_timer_config *timer_config;
+	struct device *dev = tps6131x->dev;
+	u32 channels[TPS6131X_MAX_CHANNELS];
+	u32 current_step_multiplier;
+	u32 current_ua;
+	u32 max_current_flash_ma, max_current_torch_ma;
+	u32 timeout_us;
+	int num_channels;
+	int i;
+	int ret;
+
+	tps6131x->valley_current_limit = device_property_read_bool(dev, "ti,valley-current-limit");
+
+	tps6131x->led_node = fwnode_get_next_available_child_node(dev->fwnode, NULL);
+	if (!tps6131x->led_node) {
+		dev_err(dev, "Missing LED node\n");
+		return -EINVAL;
+	}
+
+	num_channels = fwnode_property_count_u32(tps6131x->led_node, "led-sources");
+	if (num_channels <= 0) {
+		dev_err(dev, "Failed to read led-sources property\n");
+		return -EINVAL;
+	}
+
+	if (num_channels > TPS6131X_MAX_CHANNELS) {
+		dev_err(dev, "led-sources count %u exceeds maximum channel count %u\n",
+			num_channels, TPS6131X_MAX_CHANNELS);
+		return -EINVAL;
+	}
+
+	ret = fwnode_property_read_u32_array(tps6131x->led_node, "led-sources", channels,
+					     num_channels);
+	if (ret < 0) {
+		dev_err(dev, "Failed to read led-sources property\n");
+		return ret;
+	}
+
+	max_current_flash_ma = 0;
+	max_current_torch_ma = 0;
+	for (i = 0; i < num_channels; i++) {
+		switch (channels[i]) {
+		case 1:
+			tps6131x->chan1_en = true;
+			max_current_flash_ma += TPS6131X_FLASH_MAX_I_CHAN13_MA;
+			max_current_torch_ma += TPS6131X_TORCH_MAX_I_CHAN13_MA;
+			break;
+		case 2:
+			tps6131x->chan2_en = true;
+			max_current_flash_ma += TPS6131X_FLASH_MAX_I_CHAN2_MA;
+			max_current_torch_ma += TPS6131X_TORCH_MAX_I_CHAN2_MA;
+			break;
+		case 3:
+			tps6131x->chan3_en = true;
+			max_current_flash_ma += TPS6131X_FLASH_MAX_I_CHAN13_MA;
+			max_current_torch_ma += TPS6131X_TORCH_MAX_I_CHAN13_MA;
+			break;
+		default:
+			dev_err(dev, "led-source out of range [1-3]\n");
+			return -EINVAL;
+		}
+	}
+
+	/*
+	 * If only channels 1 and 3 are used, the step size is doubled because the two channels
+	 * share the same current control register.
+	 */
+	current_step_multiplier =
+		(tps6131x->chan1_en && tps6131x->chan3_en && !tps6131x->chan2_en) ? 2 : 1;
+	tps6131x->step_flash_current_ma = current_step_multiplier * TPS6131X_FLASH_STEP_I_MA;
+	tps6131x->step_torch_current_ma = current_step_multiplier * TPS6131X_TORCH_STEP_I_MA;
+
+	ret = fwnode_property_read_u32(tps6131x->led_node, "led-max-microamp", &current_ua);
+	if (ret < 0) {
+		dev_err(dev, "Failed to read led-max-microamp property\n");
+		return ret;
+	}
+
+	tps6131x->max_torch_current_ma = UA_TO_MA(current_ua);
+
+	if (!tps6131x->max_torch_current_ma ||
+	    tps6131x->max_torch_current_ma > max_current_torch_ma ||
+	    (tps6131x->max_torch_current_ma % tps6131x->step_torch_current_ma)) {
+		dev_err(dev, "led-max-microamp out of range or not a multiple of %u\n",
+			tps6131x->step_torch_current_ma);
+		return -EINVAL;
+	}
+
+	ret = fwnode_property_read_u32(tps6131x->led_node, "flash-max-microamp", &current_ua);
+	if (ret < 0) {
+		dev_err(dev, "Failed to read flash-max-microamp property\n");
+		return ret;
+	}
+
+	tps6131x->max_flash_current_ma = UA_TO_MA(current_ua);
+
+	if (!tps6131x->max_flash_current_ma ||
+	    tps6131x->max_flash_current_ma > max_current_flash_ma ||
+	    (tps6131x->max_flash_current_ma % tps6131x->step_flash_current_ma)) {
+		dev_err(dev, "flash-max-microamp out of range or not a multiple of %u\n",
+			tps6131x->step_flash_current_ma);
+		return -EINVAL;
+	}
+
+	ret = fwnode_property_read_u32(tps6131x->led_node, "flash-max-timeout-us", &timeout_us);
+	if (ret < 0) {
+		dev_err(dev, "Failed to read flash-max-timeout-us property\n");
+		return ret;
+	}
+
+	timer_config = tps6131x_find_closest_timer_config(timeout_us);
+	tps6131x->max_timeout_us = timer_config->time_us;
+
+	if (tps6131x->max_timeout_us != timeout_us)
+		dev_warn(dev, "flash-max-timeout-us %u not supported (using %u)\n", timeout_us,
+			 tps6131x->max_timeout_us);
+
+	return 0;
+}
+
+static int tps6131x_led_class_setup(struct tps6131x *tps6131x)
+{
+	const struct tps6131x_timer_config *timer_config;
+	struct led_classdev *led_cdev;
+	struct led_flash_setting *setting;
+	struct led_init_data init_data = {};
+	int ret;
+
+	tps6131x->fled_cdev.ops = &flash_ops;
+
+	setting = &tps6131x->fled_cdev.timeout;
+	timer_config = tps6131x_find_closest_timer_config(0);
+	setting->min = timer_config->time_us;
+	setting->max = tps6131x->max_timeout_us;
+	setting->step = 1; /* Only some specific time periods are supported. No fixed step size. */
+	setting->val = setting->min;
+
+	setting = &tps6131x->fled_cdev.brightness;
+	setting->min = tps6131x->step_flash_current_ma;
+	setting->max = tps6131x->max_flash_current_ma;
+	setting->step = tps6131x->step_flash_current_ma;
+	setting->val = setting->min;
+
+	led_cdev = &tps6131x->fled_cdev.led_cdev;
+	led_cdev->brightness_set_blocking = tps6131x_brightness_set;
+	led_cdev->max_brightness = tps6131x->max_torch_current_ma;
+	led_cdev->flags |= LED_DEV_CAP_FLASH;
+
+	init_data.fwnode = tps6131x->led_node;
+	init_data.devicename = NULL;
+	init_data.default_label = NULL;
+	init_data.devname_mandatory = false;
+
+	ret = devm_led_classdev_flash_register_ext(tps6131x->dev, &tps6131x->fled_cdev,
+						   &init_data);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int tps6131x_flash_external_strobe_set(struct v4l2_flash *v4l2_flash, bool enable)
+{
+	struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev;
+	struct tps6131x *tps6131x = fled_cdev_to_tps6131x(fled_cdev);
+
+	guard(mutex)(&tps6131x->lock);
+
+	return tps6131x_set_mode(tps6131x, enable ? TPS6131X_MODE_FLASH : TPS6131X_MODE_SHUTDOWN,
+				 false);
+}
+
+static const struct v4l2_flash_ops tps6131x_v4l2_flash_ops = {
+	.external_strobe_set = tps6131x_flash_external_strobe_set,
+};
+
+static int tps6131x_v4l2_setup(struct tps6131x *tps6131x)
+{
+	struct v4l2_flash_config v4l2_cfg = { 0 };
+	struct led_flash_setting *intensity = &v4l2_cfg.intensity;
+
+	intensity->min = tps6131x->step_torch_current_ma;
+	intensity->max = tps6131x->max_torch_current_ma;
+	intensity->step = tps6131x->step_torch_current_ma;
+	intensity->val = intensity->min;
+
+	strscpy(v4l2_cfg.dev_name, tps6131x->fled_cdev.led_cdev.dev->kobj.name,
+		sizeof(v4l2_cfg.dev_name));
+
+	v4l2_cfg.has_external_strobe = true;
+	v4l2_cfg.flash_faults = LED_FAULT_TIMEOUT | LED_FAULT_OVER_TEMPERATURE |
+				LED_FAULT_SHORT_CIRCUIT | LED_FAULT_UNDER_VOLTAGE |
+				LED_FAULT_LED_OVER_TEMPERATURE;
+
+	tps6131x->v4l2_flash = v4l2_flash_init(tps6131x->dev, tps6131x->led_node,
+					       &tps6131x->fled_cdev, &tps6131x_v4l2_flash_ops,
+					       &v4l2_cfg);
+	if (IS_ERR(tps6131x->v4l2_flash)) {
+		dev_err(tps6131x->dev, "Failed to initialize v4l2 flash LED\n");
+		return PTR_ERR(tps6131x->v4l2_flash);
+	}
+
+	return 0;
+}
+
+static int tps6131x_probe(struct i2c_client *client)
+{
+	struct tps6131x *tps6131x;
+	int ret;
+
+	tps6131x = devm_kzalloc(&client->dev, sizeof(*tps6131x), GFP_KERNEL);
+	if (!tps6131x)
+		return -ENOMEM;
+
+	tps6131x->dev = &client->dev;
+	i2c_set_clientdata(client, tps6131x);
+	mutex_init(&tps6131x->lock);
+	INIT_DELAYED_WORK(&tps6131x->torch_refresh_work, tps6131x_torch_refresh_handler);
+
+	ret = tps6131x_parse_node(tps6131x);
+	if (ret)
+		return ret;
+
+	tps6131x->regmap = devm_regmap_init_i2c(client, &tps6131x_regmap);
+	if (IS_ERR(tps6131x->regmap)) {
+		ret = PTR_ERR(tps6131x->regmap);
+		return dev_err_probe(&client->dev, ret, "Failed to allocate register map\n");
+	}
+
+	tps6131x->reset_gpio = devm_gpiod_get_optional(&client->dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(tps6131x->reset_gpio)) {
+		ret = PTR_ERR(tps6131x->reset_gpio);
+		return dev_err_probe(&client->dev, ret, "Failed to get reset GPIO\n");
+	}
+
+	ret = tps6131x_reset_chip(tps6131x);
+	if (ret)
+		return dev_err_probe(&client->dev, ret, "Failed to reset LED controller\n");
+
+	ret = tps6131x_init_chip(tps6131x);
+	if (ret)
+		return dev_err_probe(&client->dev, ret, "Failed to initialize LED controller\n");
+
+	ret = tps6131x_led_class_setup(tps6131x);
+	if (ret)
+		return dev_err_probe(&client->dev, ret, "Failed to setup LED class\n");
+
+	ret = tps6131x_v4l2_setup(tps6131x);
+	if (ret)
+		return dev_err_probe(&client->dev, ret, "Failed to setup v4l2 flash\n");
+
+	return 0;
+}
+
+static void tps6131x_remove(struct i2c_client *client)
+{
+	struct tps6131x *tps6131x = i2c_get_clientdata(client);
+
+	v4l2_flash_release(tps6131x->v4l2_flash);
+
+	cancel_delayed_work_sync(&tps6131x->torch_refresh_work);
+}
+
+static const struct of_device_id of_tps6131x_leds_match[] = {
+	{ .compatible = "ti,tps61310" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, of_tps6131x_leds_match);
+
+static struct i2c_driver tps6131x_i2c_driver = {
+	.driver = {
+		.name = "tps6131x",
+		.of_match_table = of_tps6131x_leds_match,
+	},
+	.probe = tps6131x_probe,
+	.remove = tps6131x_remove,
+};
+module_i2c_driver(tps6131x_i2c_driver);
+
+MODULE_DESCRIPTION("Texas Instruments TPS6131X flash LED driver");
+MODULE_AUTHOR("Matthias Fend <matthias.fend@emfend.at>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/leds/led-class-flash.c b/drivers/leds/led-class-flash.c
index f4e26ce84862..165035a8826c 100644
--- a/drivers/leds/led-class-flash.c
+++ b/drivers/leds/led-class-flash.c
@@ -440,6 +440,21 @@ int led_update_flash_brightness(struct led_classdev_flash *fled_cdev)
 }
 EXPORT_SYMBOL_GPL(led_update_flash_brightness);
 
+int led_set_flash_duration(struct led_classdev_flash *fled_cdev, u32 duration)
+{
+	struct led_classdev *led_cdev = &fled_cdev->led_cdev;
+	struct led_flash_setting *s = &fled_cdev->duration;
+
+	s->val = duration;
+	led_clamp_align(s);
+
+	if (!(led_cdev->flags & LED_SUSPENDED))
+		return call_flash_op(fled_cdev, duration_set, s->val);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(led_set_flash_duration);
+
 MODULE_AUTHOR("Jacek Anaszewski <j.anaszewski@samsung.com>");
 MODULE_DESCRIPTION("LED Flash class interface");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/led-class-multicolor.c b/drivers/leds/led-class-multicolor.c
index b2a87c994816..fd66d2bdeace 100644
--- a/drivers/leds/led-class-multicolor.c
+++ b/drivers/leds/led-class-multicolor.c
@@ -59,7 +59,8 @@ static ssize_t multi_intensity_store(struct device *dev,
 	for (i = 0; i < mcled_cdev->num_colors; i++)
 		mcled_cdev->subled_info[i].intensity = intensity_value[i];
 
-	led_set_brightness(led_cdev, led_cdev->brightness);
+	if (!test_bit(LED_BLINK_SW, &led_cdev->work_flags))
+		led_set_brightness(led_cdev, led_cdev->brightness);
 	ret = size;
 err_out:
 	mutex_unlock(&led_cdev->led_access);
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index 907fc703e0c5..1a59a4f38479 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -529,6 +529,7 @@ int led_compose_name(struct device *dev, struct led_init_data *init_data,
 	struct led_properties props = {};
 	struct fwnode_handle *fwnode = init_data->fwnode;
 	const char *devicename = init_data->devicename;
+	int n;
 
 	if (!led_classdev_name)
 		return -EINVAL;
@@ -542,45 +543,49 @@ int led_compose_name(struct device *dev, struct led_init_data *init_data,
 		 * Otherwise the label is prepended with devicename to compose
 		 * the final LED class device name.
 		 */
-		if (!devicename) {
-			strscpy(led_classdev_name, props.label,
-				LED_MAX_NAME_SIZE);
+		if (devicename) {
+			n = snprintf(led_classdev_name, LED_MAX_NAME_SIZE, "%s:%s",
+				     devicename, props.label);
 		} else {
-			snprintf(led_classdev_name, LED_MAX_NAME_SIZE, "%s:%s",
-				 devicename, props.label);
+			n = snprintf(led_classdev_name, LED_MAX_NAME_SIZE, "%s", props.label);
 		}
 	} else if (props.function || props.color_present) {
 		char tmp_buf[LED_MAX_NAME_SIZE];
 
 		if (props.func_enum_present) {
-			snprintf(tmp_buf, LED_MAX_NAME_SIZE, "%s:%s-%d",
-				 props.color_present ? led_colors[props.color] : "",
-				 props.function ?: "", props.func_enum);
+			n = snprintf(tmp_buf, LED_MAX_NAME_SIZE, "%s:%s-%d",
+				     props.color_present ? led_colors[props.color] : "",
+				     props.function ?: "", props.func_enum);
 		} else {
-			snprintf(tmp_buf, LED_MAX_NAME_SIZE, "%s:%s",
-				 props.color_present ? led_colors[props.color] : "",
-				 props.function ?: "");
+			n = snprintf(tmp_buf, LED_MAX_NAME_SIZE, "%s:%s",
+				     props.color_present ? led_colors[props.color] : "",
+				     props.function ?: "");
 		}
+		if (n >= LED_MAX_NAME_SIZE)
+			return -E2BIG;
+
 		if (init_data->devname_mandatory) {
-			snprintf(led_classdev_name, LED_MAX_NAME_SIZE, "%s:%s",
-				 devicename, tmp_buf);
+			n = snprintf(led_classdev_name, LED_MAX_NAME_SIZE, "%s:%s",
+				     devicename, tmp_buf);
 		} else {
-			strscpy(led_classdev_name, tmp_buf, LED_MAX_NAME_SIZE);
-
+			n = snprintf(led_classdev_name, LED_MAX_NAME_SIZE, "%s", tmp_buf);
 		}
 	} else if (init_data->default_label) {
 		if (!devicename) {
 			dev_err(dev, "Legacy LED naming requires devicename segment");
 			return -EINVAL;
 		}
-		snprintf(led_classdev_name, LED_MAX_NAME_SIZE, "%s:%s",
-			 devicename, init_data->default_label);
+		n = snprintf(led_classdev_name, LED_MAX_NAME_SIZE, "%s:%s",
+			     devicename, init_data->default_label);
 	} else if (is_of_node(fwnode)) {
-		strscpy(led_classdev_name, to_of_node(fwnode)->name,
-			LED_MAX_NAME_SIZE);
+		n = snprintf(led_classdev_name, LED_MAX_NAME_SIZE, "%s",
+			     to_of_node(fwnode)->name);
 	} else
 		return -EINVAL;
 
+	if (n >= LED_MAX_NAME_SIZE)
+		return -E2BIG;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(led_compose_name);
diff --git a/drivers/leds/led-test.c b/drivers/leds/led-test.c
new file mode 100644
index 000000000000..ddf9aa967a6a
--- /dev/null
+++ b/drivers/leds/led-test.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Google LLC
+ *
+ * Author: Lee Jones <lee@kernel.org>
+ */
+
+#include <kunit/device.h>
+#include <kunit/test.h>
+#include <linux/device.h>
+#include <linux/leds.h>
+
+#define LED_TEST_POST_REG_BRIGHTNESS 10
+
+struct led_test_ddata {
+	struct led_classdev cdev;
+	struct device *dev;
+};
+
+static enum led_brightness led_test_brightness_get(struct led_classdev *cdev)
+{
+	return LED_TEST_POST_REG_BRIGHTNESS;
+}
+
+static void led_test_class_register(struct kunit *test)
+{
+	struct led_test_ddata *ddata = test->priv;
+	struct led_classdev *cdev_clash, *cdev = &ddata->cdev;
+	struct device *dev = ddata->dev;
+	int ret;
+
+	/* Register a LED class device */
+	cdev->name = "led-test";
+	cdev->brightness_get = led_test_brightness_get;
+	cdev->brightness = 0;
+
+	ret = devm_led_classdev_register(dev, cdev);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
+	KUNIT_EXPECT_EQ(test, cdev->max_brightness, LED_FULL);
+	KUNIT_EXPECT_EQ(test, cdev->brightness, LED_TEST_POST_REG_BRIGHTNESS);
+	KUNIT_EXPECT_STREQ(test, cdev->dev->kobj.name, "led-test");
+
+	/* Register again with the same name - expect it to pass with the LED renamed */
+	cdev_clash = devm_kmemdup(dev, cdev, sizeof(*cdev), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cdev_clash);
+
+	ret = devm_led_classdev_register(dev, cdev_clash);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
+	KUNIT_EXPECT_STREQ(test, cdev_clash->dev->kobj.name, "led-test_1");
+	KUNIT_EXPECT_STREQ(test, cdev_clash->name, "led-test");
+
+	/* Enable name conflict rejection and register with the same name again - expect failure */
+	cdev_clash->flags |= LED_REJECT_NAME_CONFLICT;
+	ret = devm_led_classdev_register(dev, cdev_clash);
+	KUNIT_EXPECT_EQ(test, ret, -EEXIST);
+}
+
+static void led_test_class_add_lookup_and_get(struct kunit *test)
+{
+	struct led_test_ddata *ddata = test->priv;
+	struct led_classdev *cdev = &ddata->cdev, *cdev_get;
+	struct device *dev = ddata->dev;
+	struct led_lookup_data lookup;
+	int ret;
+
+	/* First, register a LED class device */
+	cdev->name = "led-test";
+	ret = devm_led_classdev_register(dev, cdev);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
+	/* Then make the LED available for lookup */
+	lookup.provider = cdev->name;
+	lookup.dev_id = dev_name(dev);
+	lookup.con_id = "led-test-1";
+	led_add_lookup(&lookup);
+
+	/* Finally, attempt to look it up via the API - imagine this was an orthogonal driver */
+	cdev_get = devm_led_get(dev, "led-test-1");
+	KUNIT_ASSERT_FALSE(test, IS_ERR(cdev_get));
+
+	KUNIT_EXPECT_STREQ(test, cdev_get->name, cdev->name);
+
+	led_remove_lookup(&lookup);
+}
+
+static struct kunit_case led_test_cases[] = {
+	KUNIT_CASE(led_test_class_register),
+	KUNIT_CASE(led_test_class_add_lookup_and_get),
+	{ }
+};
+
+static int led_test_init(struct kunit *test)
+{
+	struct led_test_ddata *ddata;
+	struct device *dev;
+
+	ddata = kunit_kzalloc(test, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
+		return -ENOMEM;
+
+	test->priv = ddata;
+
+	dev = kunit_device_register(test, "led_test");
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
+
+	ddata->dev = get_device(dev);
+
+	return 0;
+}
+
+static void led_test_exit(struct kunit *test)
+{
+	struct led_test_ddata *ddata = test->priv;
+
+	if (ddata && ddata->dev)
+		put_device(ddata->dev);
+}
+
+static struct kunit_suite led_test_suite = {
+	.name = "led",
+	.init = led_test_init,
+	.exit = led_test_exit,
+	.test_cases = led_test_cases,
+};
+kunit_test_suite(led_test_suite);
+
+MODULE_AUTHOR("Lee Jones <lee@kernel.org>");
+MODULE_DESCRIPTION("KUnit tests for the LED framework");
+MODULE_LICENSE("GPL");
diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index b2d40f87a5ff..3799dcc1cf07 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -54,6 +54,11 @@ ssize_t led_trigger_write(struct file *filp, struct kobject *kobj,
 		goto unlock;
 	}
 
+	if (sysfs_streq(buf, "default")) {
+		led_trigger_set_default(led_cdev);
+		goto unlock;
+	}
+
 	down_read(&triggers_list_lock);
 	list_for_each_entry(trig, &trigger_list, next_trig) {
 		if (sysfs_streq(buf, trig->name) && trigger_relevant(led_cdev, trig)) {
@@ -98,6 +103,9 @@ static int led_trigger_format(char *buf, size_t size,
 	int len = led_trigger_snprintf(buf, size, "%s",
 				       led_cdev->trigger ? "none" : "[none]");
 
+	if (led_cdev->default_trigger)
+		len += led_trigger_snprintf(buf + len, size - len, " default");
+
 	list_for_each_entry(trig, &trigger_list, next_trig) {
 		bool hit;
 
@@ -281,6 +289,11 @@ void led_trigger_set_default(struct led_classdev *led_cdev)
 	if (!led_cdev->default_trigger)
 		return;
 
+	if (!strcmp(led_cdev->default_trigger, "none")) {
+		led_trigger_remove(led_cdev);
+		return;
+	}
+
 	down_read(&triggers_list_lock);
 	down_write(&led_cdev->trigger_lock);
 	list_for_each_entry(trig, &trigger_list, next_trig) {
diff --git a/drivers/leds/leds-cros_ec.c b/drivers/leds/leds-cros_ec.c
index 275522b81ea5..377cf04e202a 100644
--- a/drivers/leds/leds-cros_ec.c
+++ b/drivers/leds/leds-cros_ec.c
@@ -60,31 +60,18 @@ static inline struct cros_ec_led_priv *cros_ec_led_cdev_to_priv(struct led_class
 union cros_ec_led_cmd_data {
 	struct ec_params_led_control req;
 	struct ec_response_led_control resp;
-} __packed;
+};
 
 static int cros_ec_led_send_cmd(struct cros_ec_device *cros_ec,
 				union cros_ec_led_cmd_data *arg)
 {
 	int ret;
-	struct {
-		struct cros_ec_command msg;
-		union cros_ec_led_cmd_data data;
-	} __packed buf = {
-		.msg = {
-			.version = 1,
-			.command = EC_CMD_LED_CONTROL,
-			.insize  = sizeof(arg->resp),
-			.outsize = sizeof(arg->req),
-		},
-		.data.req = arg->req
-	};
-
-	ret = cros_ec_cmd_xfer_status(cros_ec, &buf.msg);
+
+	ret = cros_ec_cmd(cros_ec, 1, EC_CMD_LED_CONTROL, &arg->req,
+			  sizeof(arg->req), &arg->resp, sizeof(arg->resp));
 	if (ret < 0)
 		return ret;
 
-	arg->resp = buf.data.resp;
-
 	return 0;
 }
 
diff --git a/drivers/leds/leds-lp8860.c b/drivers/leds/leds-lp8860.c
index 995f2adf8569..52b97c9f2a03 100644
--- a/drivers/leds/leds-lp8860.c
+++ b/drivers/leds/leds-lp8860.c
@@ -90,8 +90,6 @@
  * @led_dev: led class device pointer
  * @regmap: Devices register map
  * @eeprom_regmap: EEPROM register map
- * @enable_gpio: VDDIO/EN gpio to enable communication interface
- * @regulator: LED supply regulator pointer
  */
 struct lp8860_led {
 	struct mutex lock;
@@ -99,16 +97,9 @@ struct lp8860_led {
 	struct led_classdev led_dev;
 	struct regmap *regmap;
 	struct regmap *eeprom_regmap;
-	struct gpio_desc *enable_gpio;
-	struct regulator *regulator;
-};
-
-struct lp8860_eeprom_reg {
-	uint8_t reg;
-	uint8_t value;
 };
 
-static struct lp8860_eeprom_reg lp8860_eeprom_disp_regs[] = {
+static const struct reg_sequence lp8860_eeprom_disp_regs[] = {
 	{ LP8860_EEPROM_REG_0, 0xed },
 	{ LP8860_EEPROM_REG_1, 0xdf },
 	{ LP8860_EEPROM_REG_2, 0xdc },
@@ -136,43 +127,29 @@ static struct lp8860_eeprom_reg lp8860_eeprom_disp_regs[] = {
 	{ LP8860_EEPROM_REG_24, 0x3E },
 };
 
-static int lp8860_unlock_eeprom(struct lp8860_led *led, int lock)
+static int lp8860_unlock_eeprom(struct lp8860_led *led)
 {
 	int ret;
 
-	mutex_lock(&led->lock);
-
-	if (lock == LP8860_UNLOCK_EEPROM) {
-		ret = regmap_write(led->regmap,
-			LP8860_EEPROM_UNLOCK,
-			LP8860_EEPROM_CODE_1);
-		if (ret) {
-			dev_err(&led->client->dev, "EEPROM Unlock failed\n");
-			goto out;
-		}
-
-		ret = regmap_write(led->regmap,
-			LP8860_EEPROM_UNLOCK,
-			LP8860_EEPROM_CODE_2);
-		if (ret) {
-			dev_err(&led->client->dev, "EEPROM Unlock failed\n");
-			goto out;
-		}
-		ret = regmap_write(led->regmap,
-			LP8860_EEPROM_UNLOCK,
-			LP8860_EEPROM_CODE_3);
-		if (ret) {
-			dev_err(&led->client->dev, "EEPROM Unlock failed\n");
-			goto out;
-		}
-	} else {
-		ret = regmap_write(led->regmap,
-			LP8860_EEPROM_UNLOCK,
-			LP8860_LOCK_EEPROM);
+	guard(mutex)(&led->lock);
+
+	ret = regmap_write(led->regmap, LP8860_EEPROM_UNLOCK, LP8860_EEPROM_CODE_1);
+	if (ret) {
+		dev_err(&led->client->dev, "EEPROM Unlock failed\n");
+		return ret;
+	}
+
+	ret = regmap_write(led->regmap, LP8860_EEPROM_UNLOCK, LP8860_EEPROM_CODE_2);
+	if (ret) {
+		dev_err(&led->client->dev, "EEPROM Unlock failed\n");
+		return ret;
+	}
+	ret = regmap_write(led->regmap, LP8860_EEPROM_UNLOCK, LP8860_EEPROM_CODE_3);
+	if (ret) {
+		dev_err(&led->client->dev, "EEPROM Unlock failed\n");
+		return ret;
 	}
 
-out:
-	mutex_unlock(&led->lock);
 	return ret;
 }
 
@@ -209,47 +186,35 @@ static int lp8860_brightness_set(struct led_classdev *led_cdev,
 	int disp_brightness = brt_val * 255;
 	int ret;
 
-	mutex_lock(&led->lock);
+	guard(mutex)(&led->lock);
 
 	ret = lp8860_fault_check(led);
 	if (ret) {
 		dev_err(&led->client->dev, "Cannot read/clear faults\n");
-		goto out;
+		return ret;
 	}
 
 	ret = regmap_write(led->regmap, LP8860_DISP_CL1_BRT_MSB,
 			(disp_brightness & 0xff00) >> 8);
 	if (ret) {
 		dev_err(&led->client->dev, "Cannot write CL1 MSB\n");
-		goto out;
+		return ret;
 	}
 
 	ret = regmap_write(led->regmap, LP8860_DISP_CL1_BRT_LSB,
 			disp_brightness & 0xff);
 	if (ret) {
 		dev_err(&led->client->dev, "Cannot write CL1 LSB\n");
-		goto out;
+		return ret;
 	}
-out:
-	mutex_unlock(&led->lock);
-	return ret;
+
+	return 0;
 }
 
 static int lp8860_init(struct lp8860_led *led)
 {
 	unsigned int read_buf;
-	int ret, i, reg_count;
-
-	if (led->regulator) {
-		ret = regulator_enable(led->regulator);
-		if (ret) {
-			dev_err(&led->client->dev,
-				"Failed to enable regulator\n");
-			return ret;
-		}
-	}
-
-	gpiod_direction_output(led->enable_gpio, 1);
+	int ret, reg_count;
 
 	ret = lp8860_fault_check(led);
 	if (ret)
@@ -259,24 +224,20 @@ static int lp8860_init(struct lp8860_led *led)
 	if (ret)
 		goto out;
 
-	ret = lp8860_unlock_eeprom(led, LP8860_UNLOCK_EEPROM);
+	ret = lp8860_unlock_eeprom(led);
 	if (ret) {
 		dev_err(&led->client->dev, "Failed unlocking EEPROM\n");
 		goto out;
 	}
 
 	reg_count = ARRAY_SIZE(lp8860_eeprom_disp_regs);
-	for (i = 0; i < reg_count; i++) {
-		ret = regmap_write(led->eeprom_regmap,
-				lp8860_eeprom_disp_regs[i].reg,
-				lp8860_eeprom_disp_regs[i].value);
-		if (ret) {
-			dev_err(&led->client->dev, "Failed writing EEPROM\n");
-			goto out;
-		}
+	ret = regmap_multi_reg_write(led->eeprom_regmap, lp8860_eeprom_disp_regs, reg_count);
+	if (ret) {
+		dev_err(&led->client->dev, "Failed writing EEPROM\n");
+		goto out;
 	}
 
-	ret = lp8860_unlock_eeprom(led, LP8860_LOCK_EEPROM);
+	ret = regmap_write(led->regmap, LP8860_EEPROM_UNLOCK, LP8860_LOCK_EEPROM);
 	if (ret)
 		goto out;
 
@@ -291,74 +252,14 @@ static int lp8860_init(struct lp8860_led *led)
 	return ret;
 
 out:
-	if (ret)
-		gpiod_direction_output(led->enable_gpio, 0);
-
-	if (led->regulator) {
-		ret = regulator_disable(led->regulator);
-		if (ret)
-			dev_err(&led->client->dev,
-				"Failed to disable regulator\n");
-	}
-
 	return ret;
 }
 
-static const struct reg_default lp8860_reg_defs[] = {
-	{ LP8860_DISP_CL1_BRT_MSB, 0x00},
-	{ LP8860_DISP_CL1_BRT_LSB, 0x00},
-	{ LP8860_DISP_CL1_CURR_MSB, 0x00},
-	{ LP8860_DISP_CL1_CURR_LSB, 0x00},
-	{ LP8860_CL2_BRT_MSB, 0x00},
-	{ LP8860_CL2_BRT_LSB, 0x00},
-	{ LP8860_CL2_CURRENT, 0x00},
-	{ LP8860_CL3_BRT_MSB, 0x00},
-	{ LP8860_CL3_BRT_LSB, 0x00},
-	{ LP8860_CL3_CURRENT, 0x00},
-	{ LP8860_CL4_BRT_MSB, 0x00},
-	{ LP8860_CL4_BRT_LSB, 0x00},
-	{ LP8860_CL4_CURRENT, 0x00},
-	{ LP8860_CONFIG, 0x00},
-	{ LP8860_FAULT_CLEAR, 0x00},
-	{ LP8860_EEPROM_CNTRL, 0x80},
-	{ LP8860_EEPROM_UNLOCK, 0x00},
-};
-
 static const struct regmap_config lp8860_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 
 	.max_register = LP8860_EEPROM_UNLOCK,
-	.reg_defaults = lp8860_reg_defs,
-	.num_reg_defaults = ARRAY_SIZE(lp8860_reg_defs),
-};
-
-static const struct reg_default lp8860_eeprom_defs[] = {
-	{ LP8860_EEPROM_REG_0, 0x00 },
-	{ LP8860_EEPROM_REG_1, 0x00 },
-	{ LP8860_EEPROM_REG_2, 0x00 },
-	{ LP8860_EEPROM_REG_3, 0x00 },
-	{ LP8860_EEPROM_REG_4, 0x00 },
-	{ LP8860_EEPROM_REG_5, 0x00 },
-	{ LP8860_EEPROM_REG_6, 0x00 },
-	{ LP8860_EEPROM_REG_7, 0x00 },
-	{ LP8860_EEPROM_REG_8, 0x00 },
-	{ LP8860_EEPROM_REG_9, 0x00 },
-	{ LP8860_EEPROM_REG_10, 0x00 },
-	{ LP8860_EEPROM_REG_11, 0x00 },
-	{ LP8860_EEPROM_REG_12, 0x00 },
-	{ LP8860_EEPROM_REG_13, 0x00 },
-	{ LP8860_EEPROM_REG_14, 0x00 },
-	{ LP8860_EEPROM_REG_15, 0x00 },
-	{ LP8860_EEPROM_REG_16, 0x00 },
-	{ LP8860_EEPROM_REG_17, 0x00 },
-	{ LP8860_EEPROM_REG_18, 0x00 },
-	{ LP8860_EEPROM_REG_19, 0x00 },
-	{ LP8860_EEPROM_REG_20, 0x00 },
-	{ LP8860_EEPROM_REG_21, 0x00 },
-	{ LP8860_EEPROM_REG_22, 0x00 },
-	{ LP8860_EEPROM_REG_23, 0x00 },
-	{ LP8860_EEPROM_REG_24, 0x00 },
 };
 
 static const struct regmap_config lp8860_eeprom_regmap_config = {
@@ -366,10 +267,15 @@ static const struct regmap_config lp8860_eeprom_regmap_config = {
 	.val_bits = 8,
 
 	.max_register = LP8860_EEPROM_REG_24,
-	.reg_defaults = lp8860_eeprom_defs,
-	.num_reg_defaults = ARRAY_SIZE(lp8860_eeprom_defs),
 };
 
+static void lp8860_disable_gpio(void *data)
+{
+	struct gpio_desc *gpio = data;
+
+	gpiod_set_value(gpio, 0);
+}
+
 static int lp8860_probe(struct i2c_client *client)
 {
 	int ret;
@@ -377,6 +283,7 @@ static int lp8860_probe(struct i2c_client *client)
 	struct device_node *np = dev_of_node(&client->dev);
 	struct device_node *child_node;
 	struct led_init_data init_data = {};
+	struct gpio_desc *enable_gpio;
 
 	led = devm_kzalloc(&client->dev, sizeof(*led), GFP_KERNEL);
 	if (!led)
@@ -386,24 +293,21 @@ static int lp8860_probe(struct i2c_client *client)
 	if (!child_node)
 		return -EINVAL;
 
-	led->enable_gpio = devm_gpiod_get_optional(&client->dev,
-						   "enable", GPIOD_OUT_LOW);
-	if (IS_ERR(led->enable_gpio)) {
-		ret = PTR_ERR(led->enable_gpio);
-		dev_err(&client->dev, "Failed to get enable gpio: %d\n", ret);
-		return ret;
-	}
+	enable_gpio = devm_gpiod_get_optional(&client->dev, "enable", GPIOD_OUT_LOW);
+	if (IS_ERR(enable_gpio))
+		return dev_err_probe(&client->dev, PTR_ERR(enable_gpio),
+				     "Failed to get enable GPIO\n");
+	devm_add_action_or_reset(&client->dev, lp8860_disable_gpio, enable_gpio);
 
-	led->regulator = devm_regulator_get(&client->dev, "vled");
-	if (IS_ERR(led->regulator))
-		led->regulator = NULL;
+	ret = devm_regulator_get_enable_optional(&client->dev, "vled");
+	if (ret && ret != -ENODEV)
+		return dev_err_probe(&client->dev, ret,
+				     "Failed to enable vled regulator\n");
 
 	led->client = client;
 	led->led_dev.brightness_set_blocking = lp8860_brightness_set;
 
-	mutex_init(&led->lock);
-
-	i2c_set_clientdata(client, led);
+	devm_mutex_init(&client->dev, &led->lock);
 
 	led->regmap = devm_regmap_init_i2c(client, &lp8860_regmap_config);
 	if (IS_ERR(led->regmap)) {
@@ -439,23 +343,6 @@ static int lp8860_probe(struct i2c_client *client)
 	return 0;
 }
 
-static void lp8860_remove(struct i2c_client *client)
-{
-	struct lp8860_led *led = i2c_get_clientdata(client);
-	int ret;
-
-	gpiod_direction_output(led->enable_gpio, 0);
-
-	if (led->regulator) {
-		ret = regulator_disable(led->regulator);
-		if (ret)
-			dev_err(&led->client->dev,
-				"Failed to disable regulator\n");
-	}
-
-	mutex_destroy(&led->lock);
-}
-
 static const struct i2c_device_id lp8860_id[] = {
 	{ "lp8860" },
 	{ }
@@ -474,7 +361,6 @@ static struct i2c_driver lp8860_driver = {
 		.of_match_table = of_lp8860_leds_match,
 	},
 	.probe		= lp8860_probe,
-	.remove		= lp8860_remove,
 	.id_table	= lp8860_id,
 };
 module_i2c_driver(lp8860_driver);
diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c
index 1b47acf54720..7d4c071a6cd0 100644
--- a/drivers/leds/leds-pca9532.c
+++ b/drivers/leds/leds-pca9532.c
@@ -318,7 +318,8 @@ static int pca9532_gpio_request_pin(struct gpio_chip *gc, unsigned offset)
 	return -EBUSY;
 }
 
-static void pca9532_gpio_set_value(struct gpio_chip *gc, unsigned offset, int val)
+static int pca9532_gpio_set_value(struct gpio_chip *gc, unsigned int offset,
+				  int val)
 {
 	struct pca9532_data *data = gpiochip_get_data(gc);
 	struct pca9532_led *led = &data->leds[offset];
@@ -329,6 +330,8 @@ static void pca9532_gpio_set_value(struct gpio_chip *gc, unsigned offset, int va
 		led->state = PCA9532_OFF;
 
 	pca9532_setled(led);
+
+	return 0;
 }
 
 static int pca9532_gpio_get_value(struct gpio_chip *gc, unsigned offset)
@@ -351,9 +354,7 @@ static int pca9532_gpio_direction_input(struct gpio_chip *gc, unsigned offset)
 
 static int pca9532_gpio_direction_output(struct gpio_chip *gc, unsigned offset, int val)
 {
-	pca9532_gpio_set_value(gc, offset, val);
-
-	return 0;
+	return pca9532_gpio_set_value(gc, offset, val);
 }
 #endif /* CONFIG_LEDS_PCA9532_GPIO */
 
@@ -472,7 +473,7 @@ static int pca9532_configure(struct i2c_client *client,
 		data->gpio.label = "gpio-pca9532";
 		data->gpio.direction_input = pca9532_gpio_direction_input;
 		data->gpio.direction_output = pca9532_gpio_direction_output;
-		data->gpio.set = pca9532_gpio_set_value;
+		data->gpio.set_rv = pca9532_gpio_set_value;
 		data->gpio.get = pca9532_gpio_get_value;
 		data->gpio.request = pca9532_gpio_request_pin;
 		data->gpio.can_sleep = 1;
diff --git a/drivers/leds/leds-pca955x.c b/drivers/leds/leds-pca955x.c
index e9cfde9fe4b1..42fe056b1c74 100644
--- a/drivers/leds/leds-pca955x.c
+++ b/drivers/leds/leds-pca955x.c
@@ -73,7 +73,7 @@ enum pca955x_type {
 };
 
 struct pca955x_chipdef {
-	int			bits;
+	u8			bits;
 	u8			slv_addr;	/* 7-bit slave address mask */
 	int			slv_addr_shift;	/* Number of bits to ignore */
 	int			blink_div;	/* PSC divider */
@@ -142,13 +142,13 @@ struct pca955x_platform_data {
 };
 
 /* 8 bits per input register */
-static inline int pca955x_num_input_regs(int bits)
+static inline u8 pca955x_num_input_regs(u8 bits)
 {
 	return (bits + 7) / 8;
 }
 
 /* 4 bits per LED selector register */
-static inline int pca955x_num_led_regs(int bits)
+static inline u8 pca955x_num_led_regs(u8 bits)
 {
 	return (bits + 3)  / 4;
 }
@@ -495,10 +495,10 @@ static int pca955x_set_value(struct gpio_chip *gc, unsigned int offset,
 	return pca955x_led_set(&led->led_cdev, PCA955X_GPIO_LOW);
 }
 
-static void pca955x_gpio_set_value(struct gpio_chip *gc, unsigned int offset,
-				   int val)
+static int pca955x_gpio_set_value(struct gpio_chip *gc, unsigned int offset,
+				  int val)
 {
-	pca955x_set_value(gc, offset, val);
+	return pca955x_set_value(gc, offset, val);
 }
 
 static int pca955x_gpio_get_value(struct gpio_chip *gc, unsigned int offset)
@@ -581,14 +581,14 @@ static int pca955x_probe(struct i2c_client *client)
 	struct led_classdev *led;
 	struct led_init_data init_data;
 	struct i2c_adapter *adapter;
-	int i, bit, err, nls, reg;
+	u8 i, nls, psc0;
 	u8 ls1[4];
 	u8 ls2[4];
 	struct pca955x_platform_data *pdata;
-	u8 psc0;
 	bool keep_psc0 = false;
 	bool set_default_label = false;
 	char default_label[8];
+	int bit, err, reg;
 
 	chip = i2c_get_match_data(client);
 	if (!chip)
@@ -610,16 +610,15 @@ static int pca955x_probe(struct i2c_client *client)
 		return -ENODEV;
 	}
 
-	dev_info(&client->dev, "leds-pca955x: Using %s %d-bit LED driver at "
-		 "slave address 0x%02x\n", client->name, chip->bits,
-		 client->addr);
+	dev_info(&client->dev, "Using %s %u-bit LED driver at slave address 0x%02x\n",
+		 client->name, chip->bits, client->addr);
 
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA))
 		return -EIO;
 
 	if (pdata->num_leds != chip->bits) {
 		dev_err(&client->dev,
-			"board info claims %d LEDs on a %d-bit chip\n",
+			"board info claims %d LEDs on a %u-bit chip\n",
 			pdata->num_leds, chip->bits);
 		return -ENODEV;
 	}
@@ -694,8 +693,7 @@ static int pca955x_probe(struct i2c_client *client)
 			}
 
 			if (set_default_label) {
-				snprintf(default_label, sizeof(default_label),
-					 "%d", i);
+				snprintf(default_label, sizeof(default_label), "%u", i);
 				init_data.default_label = default_label;
 			} else {
 				init_data.default_label = NULL;
@@ -739,7 +737,7 @@ static int pca955x_probe(struct i2c_client *client)
 	pca955x->gpio.label = "gpio-pca955x";
 	pca955x->gpio.direction_input = pca955x_gpio_direction_input;
 	pca955x->gpio.direction_output = pca955x_gpio_direction_output;
-	pca955x->gpio.set = pca955x_gpio_set_value;
+	pca955x->gpio.set_rv = pca955x_gpio_set_value;
 	pca955x->gpio.get = pca955x_gpio_get_value;
 	pca955x->gpio.request = pca955x_gpio_request_pin;
 	pca955x->gpio.free = pca955x_gpio_free_pin;
diff --git a/drivers/leds/leds-pca995x.c b/drivers/leds/leds-pca995x.c
index 11c7bb69573e..6ad06ce2bf64 100644
--- a/drivers/leds/leds-pca995x.c
+++ b/drivers/leds/leds-pca995x.c
@@ -197,7 +197,7 @@ MODULE_DEVICE_TABLE(i2c, pca995x_id);
 
 static const struct of_device_id pca995x_of_match[] = {
 	{ .compatible = "nxp,pca9952", .data = &pca9952_chipdef },
-	{ .compatible = "nxp,pca9955b", . data = &pca9955b_chipdef },
+	{ .compatible = "nxp,pca9955b", .data = &pca9955b_chipdef },
 	{ .compatible = "nxp,pca9956b", .data = &pca9956b_chipdef },
 	{},
 };
diff --git a/drivers/leds/leds-tca6507.c b/drivers/leds/leds-tca6507.c
index acbd8169723c..89c165c8ee9c 100644
--- a/drivers/leds/leds-tca6507.c
+++ b/drivers/leds/leds-tca6507.c
@@ -588,8 +588,8 @@ static int tca6507_blink_set(struct led_classdev *led_cdev,
 }
 
 #ifdef CONFIG_GPIOLIB
-static void tca6507_gpio_set_value(struct gpio_chip *gc,
-				   unsigned offset, int val)
+static int tca6507_gpio_set_value(struct gpio_chip *gc, unsigned int offset,
+				  int val)
 {
 	struct tca6507_chip *tca = gpiochip_get_data(gc);
 	unsigned long flags;
@@ -604,13 +604,14 @@ static void tca6507_gpio_set_value(struct gpio_chip *gc,
 	spin_unlock_irqrestore(&tca->lock, flags);
 	if (tca->reg_set)
 		schedule_work(&tca->work);
+
+	return 0;
 }
 
 static int tca6507_gpio_direction_output(struct gpio_chip *gc,
 					  unsigned offset, int val)
 {
-	tca6507_gpio_set_value(gc, offset, val);
-	return 0;
+	return tca6507_gpio_set_value(gc, offset, val);
 }
 
 static int tca6507_probe_gpios(struct device *dev,
@@ -636,7 +637,7 @@ static int tca6507_probe_gpios(struct device *dev,
 	tca->gpio.base = -1;
 	tca->gpio.owner = THIS_MODULE;
 	tca->gpio.direction_output = tca6507_gpio_direction_output;
-	tca->gpio.set = tca6507_gpio_set_value;
+	tca->gpio.set_rv = tca6507_gpio_set_value;
 	tca->gpio.parent = dev;
 	err = devm_gpiochip_add_data(dev, &tca->gpio, tca);
 	if (err) {
diff --git a/drivers/leds/leds-turris-omnia.c b/drivers/leds/leds-turris-omnia.c
index 4fe1a9c0bc1b..25ee5c1eb820 100644
--- a/drivers/leds/leds-turris-omnia.c
+++ b/drivers/leds/leds-turris-omnia.c
@@ -361,7 +361,7 @@ static DEVICE_ATTR_RW(gamma_correction);
 static struct attribute *omnia_led_controller_attrs[] = {
 	&dev_attr_brightness.attr,
 	&dev_attr_gamma_correction.attr,
-	NULL,
+	NULL
 };
 ATTRIBUTE_GROUPS(omnia_led_controller);
 
@@ -527,7 +527,7 @@ static void omnia_leds_remove(struct i2c_client *client)
 
 static const struct of_device_id of_omnia_leds_match[] = {
 	{ .compatible = "cznic,turris-omnia-leds", },
-	{},
+	{ }
 };
 MODULE_DEVICE_TABLE(of, of_omnia_leds_match);
 
diff --git a/drivers/leds/rgb/leds-mt6370-rgb.c b/drivers/leds/rgb/leds-mt6370-rgb.c
index ebd3ba878dd5..c5927d0eb830 100644
--- a/drivers/leds/rgb/leds-mt6370-rgb.c
+++ b/drivers/leds/rgb/leds-mt6370-rgb.c
@@ -199,17 +199,17 @@ static const struct reg_field mt6372_reg_fields[F_MAX_FIELDS] = {
 
 /* Current unit: microamp, time unit: millisecond */
 static const struct linear_range common_led_ranges[R_MAX_RANGES] = {
-	[R_LED123_CURR]	= { 4000, 1, 6, 4000 },
-	[R_LED4_CURR]	= { 2000, 1, 3, 2000 },
-	[R_LED_TRFON]	= { 125, 0, 15, 200 },
-	[R_LED_TOFF]	= { 250, 0, 15, 400 },
+	[R_LED123_CURR]	= LINEAR_RANGE(4000, 1, 6, 4000),
+	[R_LED4_CURR]	= LINEAR_RANGE(2000, 1, 3, 2000),
+	[R_LED_TRFON]	= LINEAR_RANGE(125, 0, 15, 200),
+	[R_LED_TOFF]	= LINEAR_RANGE(250, 0, 15, 400),
 };
 
 static const struct linear_range mt6372_led_ranges[R_MAX_RANGES] = {
-	[R_LED123_CURR]	= { 2000, 1, 14, 2000 },
-	[R_LED4_CURR]	= { 2000, 1, 14, 2000 },
-	[R_LED_TRFON]	= { 125, 0, 15, 250 },
-	[R_LED_TOFF]	= { 250, 0, 15, 500 },
+	[R_LED123_CURR]	= LINEAR_RANGE(2000, 1, 14, 2000),
+	[R_LED4_CURR]	= LINEAR_RANGE(2000, 1, 14, 2000),
+	[R_LED_TRFON]	= LINEAR_RANGE(125, 0, 15, 250),
+	[R_LED_TOFF]	= LINEAR_RANGE(250, 0, 15, 500),
 };
 
 static const unsigned int common_tfreqs[] = {
diff --git a/drivers/leds/rgb/leds-ncp5623.c b/drivers/leds/rgb/leds-ncp5623.c
index f18156683375..7c7d44623a9e 100644
--- a/drivers/leds/rgb/leds-ncp5623.c
+++ b/drivers/leds/rgb/leds-ncp5623.c
@@ -155,9 +155,9 @@ static int ncp5623_probe(struct i2c_client *client)
 	struct device *dev = &client->dev;
 	struct fwnode_handle *mc_node, *led_node;
 	struct led_init_data init_data = { };
-	int num_subleds = 0;
 	struct ncp5623 *ncp;
 	struct mc_subled *subled_info;
+	unsigned int num_subleds;
 	u32 color_index;
 	u32 reg;
 	int ret;
@@ -172,8 +172,7 @@ static int ncp5623_probe(struct i2c_client *client)
 	if (!mc_node)
 		return -EINVAL;
 
-	fwnode_for_each_child_node(mc_node, led_node)
-		num_subleds++;
+	num_subleds = fwnode_get_child_node_count(mc_node);
 
 	subled_info = devm_kcalloc(dev, num_subleds, sizeof(*subled_info), GFP_KERNEL);
 	if (!subled_info) {
diff --git a/drivers/leds/rgb/leds-pwm-multicolor.c b/drivers/leds/rgb/leds-pwm-multicolor.c
index 1c7705bafdfc..e0d7d3c9215c 100644
--- a/drivers/leds/rgb/leds-pwm-multicolor.c
+++ b/drivers/leds/rgb/leds-pwm-multicolor.c
@@ -107,12 +107,12 @@ release_fwnode:
 
 static int led_pwm_mc_probe(struct platform_device *pdev)
 {
-	struct fwnode_handle *mcnode, *fwnode;
+	struct fwnode_handle *mcnode;
 	struct led_init_data init_data = {};
 	struct led_classdev *cdev;
 	struct mc_subled *subled;
 	struct pwm_mc_led *priv;
-	int count = 0;
+	unsigned int count;
 	int ret = 0;
 
 	mcnode = device_get_named_child_node(&pdev->dev, "multi-led");
@@ -121,8 +121,7 @@ static int led_pwm_mc_probe(struct platform_device *pdev)
 				     "expected multi-led node\n");
 
 	/* count the nodes inside the multi-led node */
-	fwnode_for_each_child_node(mcnode, fwnode)
-		count++;
+	count = fwnode_get_child_node_count(mcnode);
 
 	priv = devm_kzalloc(&pdev->dev, struct_size(priv, leds, count),
 			    GFP_KERNEL);
diff --git a/drivers/leds/trigger/ledtrig-backlight.c b/drivers/leds/trigger/ledtrig-backlight.c
index 487577d22cfc..c1f0f5becaee 100644
--- a/drivers/leds/trigger/ledtrig-backlight.c
+++ b/drivers/leds/trigger/ledtrig-backlight.c
@@ -10,7 +10,6 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/init.h>
-#include <linux/fb.h>
 #include <linux/leds.h>
 #include "../leds.h"
 
@@ -21,29 +20,20 @@ struct bl_trig_notifier {
 	struct led_classdev *led;
 	int brightness;
 	int old_status;
-	struct notifier_block notifier;
 	unsigned invert;
+
+	struct list_head entry;
 };
 
-static int fb_notifier_callback(struct notifier_block *p,
-				unsigned long event, void *data)
+static DEFINE_MUTEX(ledtrig_backlight_list_mutex);
+static LIST_HEAD(ledtrig_backlight_list);
+
+static void ledtrig_backlight_notify_blank(struct bl_trig_notifier *n, int new_status)
 {
-	struct bl_trig_notifier *n = container_of(p,
-					struct bl_trig_notifier, notifier);
 	struct led_classdev *led = n->led;
-	struct fb_event *fb_event = data;
-	int *blank;
-	int new_status;
-
-	/* If we aren't interested in this event, skip it immediately ... */
-	if (event != FB_EVENT_BLANK)
-		return 0;
-
-	blank = fb_event->data;
-	new_status = *blank ? BLANK : UNBLANK;
 
 	if (new_status == n->old_status)
-		return 0;
+		return;
 
 	if ((n->old_status == UNBLANK) ^ n->invert) {
 		n->brightness = led->brightness;
@@ -53,9 +43,19 @@ static int fb_notifier_callback(struct notifier_block *p,
 	}
 
 	n->old_status = new_status;
+}
 
-	return 0;
+void ledtrig_backlight_blank(bool blank)
+{
+	struct bl_trig_notifier *n;
+	int new_status = blank ? BLANK : UNBLANK;
+
+	guard(mutex)(&ledtrig_backlight_list_mutex);
+
+	list_for_each_entry(n, &ledtrig_backlight_list, entry)
+		ledtrig_backlight_notify_blank(n, new_status);
 }
+EXPORT_SYMBOL(ledtrig_backlight_blank);
 
 static ssize_t bl_trig_invert_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -100,8 +100,6 @@ ATTRIBUTE_GROUPS(bl_trig);
 
 static int bl_trig_activate(struct led_classdev *led)
 {
-	int ret;
-
 	struct bl_trig_notifier *n;
 
 	n = kzalloc(sizeof(struct bl_trig_notifier), GFP_KERNEL);
@@ -112,11 +110,9 @@ static int bl_trig_activate(struct led_classdev *led)
 	n->led = led;
 	n->brightness = led->brightness;
 	n->old_status = UNBLANK;
-	n->notifier.notifier_call = fb_notifier_callback;
 
-	ret = fb_register_client(&n->notifier);
-	if (ret)
-		dev_err(led->dev, "unable to register backlight trigger\n");
+	guard(mutex)(&ledtrig_backlight_list_mutex);
+	list_add(&n->entry, &ledtrig_backlight_list);
 
 	return 0;
 }
@@ -125,7 +121,9 @@ static void bl_trig_deactivate(struct led_classdev *led)
 {
 	struct bl_trig_notifier *n = led_get_trigger_data(led);
 
-	fb_unregister_client(&n->notifier);
+	guard(mutex)(&ledtrig_backlight_list_mutex);
+	list_del(&n->entry);
+
 	kfree(n);
 }
 
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index d098e75e3461..ec84ba5e93e5 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -41,16 +41,6 @@
 #define DM_BUFIO_LOW_WATERMARK_RATIO	16
 
 /*
- * Check buffer ages in this interval (seconds)
- */
-#define DM_BUFIO_WORK_TIMER_SECS	30
-
-/*
- * Free buffers when they are older than this (seconds)
- */
-#define DM_BUFIO_DEFAULT_AGE_SECS	300
-
-/*
  * The nr of bytes of cached data to keep around.
  */
 #define DM_BUFIO_DEFAULT_RETAIN_BYTES   (256 * 1024)
@@ -1057,10 +1047,8 @@ static unsigned long dm_bufio_cache_size_latch;
 
 static DEFINE_SPINLOCK(global_spinlock);
 
-/*
- * Buffers are freed after this timeout
- */
-static unsigned int dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS;
+static unsigned int dm_bufio_max_age; /* No longer does anything */
+
 static unsigned long dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES;
 
 static unsigned long dm_bufio_peak_allocated;
@@ -1088,7 +1076,6 @@ static LIST_HEAD(dm_bufio_all_clients);
 static DEFINE_MUTEX(dm_bufio_clients_lock);
 
 static struct workqueue_struct *dm_bufio_wq;
-static struct delayed_work dm_bufio_cleanup_old_work;
 static struct work_struct dm_bufio_replacement_work;
 
 
@@ -2680,130 +2667,6 @@ EXPORT_SYMBOL_GPL(dm_bufio_set_sector_offset);
 
 /*--------------------------------------------------------------*/
 
-static unsigned int get_max_age_hz(void)
-{
-	unsigned int max_age = READ_ONCE(dm_bufio_max_age);
-
-	if (max_age > UINT_MAX / HZ)
-		max_age = UINT_MAX / HZ;
-
-	return max_age * HZ;
-}
-
-static bool older_than(struct dm_buffer *b, unsigned long age_hz)
-{
-	return time_after_eq(jiffies, READ_ONCE(b->last_accessed) + age_hz);
-}
-
-struct evict_params {
-	gfp_t gfp;
-	unsigned long age_hz;
-
-	/*
-	 * This gets updated with the largest last_accessed (ie. most
-	 * recently used) of the evicted buffers.  It will not be reinitialised
-	 * by __evict_many(), so you can use it across multiple invocations.
-	 */
-	unsigned long last_accessed;
-};
-
-/*
- * We may not be able to evict this buffer if IO pending or the client
- * is still using it.
- *
- * And if GFP_NOFS is used, we must not do any I/O because we hold
- * dm_bufio_clients_lock and we would risk deadlock if the I/O gets
- * rerouted to different bufio client.
- */
-static enum evict_result select_for_evict(struct dm_buffer *b, void *context)
-{
-	struct evict_params *params = context;
-
-	if (!(params->gfp & __GFP_FS) ||
-	    (static_branch_unlikely(&no_sleep_enabled) && b->c->no_sleep)) {
-		if (test_bit_acquire(B_READING, &b->state) ||
-		    test_bit(B_WRITING, &b->state) ||
-		    test_bit(B_DIRTY, &b->state))
-			return ER_DONT_EVICT;
-	}
-
-	return older_than(b, params->age_hz) ? ER_EVICT : ER_STOP;
-}
-
-static unsigned long __evict_many(struct dm_bufio_client *c,
-				  struct evict_params *params,
-				  int list_mode, unsigned long max_count)
-{
-	unsigned long count;
-	unsigned long last_accessed;
-	struct dm_buffer *b;
-
-	for (count = 0; count < max_count; count++) {
-		b = cache_evict(&c->cache, list_mode, select_for_evict, params);
-		if (!b)
-			break;
-
-		last_accessed = READ_ONCE(b->last_accessed);
-		if (time_after_eq(params->last_accessed, last_accessed))
-			params->last_accessed = last_accessed;
-
-		__make_buffer_clean(b);
-		__free_buffer_wake(b);
-
-		cond_resched();
-	}
-
-	return count;
-}
-
-static void evict_old_buffers(struct dm_bufio_client *c, unsigned long age_hz)
-{
-	struct evict_params params = {.gfp = 0, .age_hz = age_hz, .last_accessed = 0};
-	unsigned long retain = get_retain_buffers(c);
-	unsigned long count;
-	LIST_HEAD(write_list);
-
-	dm_bufio_lock(c);
-
-	__check_watermark(c, &write_list);
-	if (unlikely(!list_empty(&write_list))) {
-		dm_bufio_unlock(c);
-		__flush_write_list(&write_list);
-		dm_bufio_lock(c);
-	}
-
-	count = cache_total(&c->cache);
-	if (count > retain)
-		__evict_many(c, &params, LIST_CLEAN, count - retain);
-
-	dm_bufio_unlock(c);
-}
-
-static void cleanup_old_buffers(void)
-{
-	unsigned long max_age_hz = get_max_age_hz();
-	struct dm_bufio_client *c;
-
-	mutex_lock(&dm_bufio_clients_lock);
-
-	__cache_size_refresh();
-
-	list_for_each_entry(c, &dm_bufio_all_clients, client_list)
-		evict_old_buffers(c, max_age_hz);
-
-	mutex_unlock(&dm_bufio_clients_lock);
-}
-
-static void work_fn(struct work_struct *w)
-{
-	cleanup_old_buffers();
-
-	queue_delayed_work(dm_bufio_wq, &dm_bufio_cleanup_old_work,
-			   DM_BUFIO_WORK_TIMER_SECS * HZ);
-}
-
-/*--------------------------------------------------------------*/
-
 /*
  * Global cleanup tries to evict the oldest buffers from across _all_
  * the clients.  It does this by repeatedly evicting a few buffers from
@@ -2841,27 +2704,51 @@ static void __insert_client(struct dm_bufio_client *new_client)
 	list_add_tail(&new_client->client_list, h);
 }
 
+static enum evict_result select_for_evict(struct dm_buffer *b, void *context)
+{
+	/* In no-sleep mode, we cannot wait on IO. */
+	if (static_branch_unlikely(&no_sleep_enabled) && b->c->no_sleep) {
+		if (test_bit_acquire(B_READING, &b->state) ||
+		    test_bit(B_WRITING, &b->state) ||
+		    test_bit(B_DIRTY, &b->state))
+			return ER_DONT_EVICT;
+	}
+	return ER_EVICT;
+}
+
 static unsigned long __evict_a_few(unsigned long nr_buffers)
 {
-	unsigned long count;
 	struct dm_bufio_client *c;
-	struct evict_params params = {
-		.gfp = GFP_KERNEL,
-		.age_hz = 0,
-		/* set to jiffies in case there are no buffers in this client */
-		.last_accessed = jiffies
-	};
+	unsigned long oldest_buffer = jiffies;
+	unsigned long last_accessed;
+	unsigned long count;
+	struct dm_buffer *b;
 
 	c = __pop_client();
 	if (!c)
 		return 0;
 
 	dm_bufio_lock(c);
-	count = __evict_many(c, &params, LIST_CLEAN, nr_buffers);
+
+	for (count = 0; count < nr_buffers; count++) {
+		b = cache_evict(&c->cache, LIST_CLEAN, select_for_evict, NULL);
+		if (!b)
+			break;
+
+		last_accessed = READ_ONCE(b->last_accessed);
+		if (time_after_eq(oldest_buffer, last_accessed))
+			oldest_buffer = last_accessed;
+
+		__make_buffer_clean(b);
+		__free_buffer_wake(b);
+
+		cond_resched();
+	}
+
 	dm_bufio_unlock(c);
 
 	if (count)
-		c->oldest_buffer = params.last_accessed;
+		c->oldest_buffer = oldest_buffer;
 	__insert_client(c);
 
 	return count;
@@ -2944,10 +2831,7 @@ static int __init dm_bufio_init(void)
 	if (!dm_bufio_wq)
 		return -ENOMEM;
 
-	INIT_DELAYED_WORK(&dm_bufio_cleanup_old_work, work_fn);
 	INIT_WORK(&dm_bufio_replacement_work, do_global_cleanup);
-	queue_delayed_work(dm_bufio_wq, &dm_bufio_cleanup_old_work,
-			   DM_BUFIO_WORK_TIMER_SECS * HZ);
 
 	return 0;
 }
@@ -2959,7 +2843,6 @@ static void __exit dm_bufio_exit(void)
 {
 	int bug = 0;
 
-	cancel_delayed_work_sync(&dm_bufio_cleanup_old_work);
 	destroy_workqueue(dm_bufio_wq);
 
 	if (dm_bufio_client_count) {
@@ -2996,7 +2879,7 @@ module_param_named(max_cache_size_bytes, dm_bufio_cache_size, ulong, 0644);
 MODULE_PARM_DESC(max_cache_size_bytes, "Size of metadata cache");
 
 module_param_named(max_age_seconds, dm_bufio_max_age, uint, 0644);
-MODULE_PARM_DESC(max_age_seconds, "Max age of a buffer in seconds");
+MODULE_PARM_DESC(max_age_seconds, "No longer does anything");
 
 module_param_named(retain_bytes, dm_bufio_retain_bytes, ulong, 0644);
 MODULE_PARM_DESC(retain_bytes, "Try to keep at least this many bytes cached in memory");
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 3637761f3585..c889332e533b 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -141,6 +141,7 @@ struct mapped_device {
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int nr_zones;
 	void *zone_revalidate_map;
+	struct task_struct *revalidate_map_task;
 #endif
 
 #ifdef CONFIG_IMA
@@ -162,9 +163,6 @@ struct mapped_device {
 #define DMF_POST_SUSPENDING 8
 #define DMF_EMULATE_ZONE_APPEND 9
 
-void disable_discard(struct mapped_device *md);
-void disable_write_zeroes(struct mapped_device *md);
-
 static inline sector_t dm_get_size(struct mapped_device *md)
 {
 	return get_capacity(md->disk);
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index d4cf0ac2a7aa..16d3d454fb0a 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -14,11 +14,14 @@
 #include <linux/bio.h>
 #include <linux/slab.h>
 #include <linux/kthread.h>
+#include <linux/delay.h>
 
 #include <linux/device-mapper.h>
 
 #define DM_MSG_PREFIX "delay"
 
+#define SLEEP_SHIFT 3
+
 struct delay_class {
 	struct dm_dev *dev;
 	sector_t start;
@@ -34,6 +37,7 @@ struct delay_c {
 	struct work_struct flush_expired_bios;
 	struct list_head delayed_bios;
 	struct task_struct *worker;
+	unsigned int worker_sleep_us;
 	bool may_delay;
 
 	struct delay_class read;
@@ -136,6 +140,7 @@ static int flush_worker_fn(void *data)
 			schedule();
 		} else {
 			spin_unlock(&dc->delayed_bios_lock);
+			fsleep(dc->worker_sleep_us);
 			cond_resched();
 		}
 	}
@@ -212,7 +217,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	struct delay_c *dc;
 	int ret;
-	unsigned int max_delay;
+	unsigned int max_delay, min_delay;
 
 	if (argc != 3 && argc != 6 && argc != 9) {
 		ti->error = "Requires exactly 3, 6 or 9 arguments";
@@ -235,7 +240,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	ret = delay_class_ctr(ti, &dc->read, argv);
 	if (ret)
 		goto bad;
-	max_delay = dc->read.delay;
+	min_delay = max_delay = dc->read.delay;
 
 	if (argc == 3) {
 		ret = delay_class_ctr(ti, &dc->write, argv);
@@ -251,6 +256,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (ret)
 		goto bad;
 	max_delay = max(max_delay, dc->write.delay);
+	min_delay = min_not_zero(min_delay, dc->write.delay);
 
 	if (argc == 6) {
 		ret = delay_class_ctr(ti, &dc->flush, argv + 3);
@@ -263,9 +269,14 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (ret)
 		goto bad;
 	max_delay = max(max_delay, dc->flush.delay);
+	min_delay = min_not_zero(min_delay, dc->flush.delay);
 
 out:
 	if (max_delay < 50) {
+		if (min_delay >> SLEEP_SHIFT)
+			dc->worker_sleep_us = 1000;
+		else
+			dc->worker_sleep_us = (min_delay * 1000) >> SLEEP_SHIFT;
 		/*
 		 * In case of small requested delays, use kthread instead of
 		 * timers and workqueue to achieve better latency.
@@ -438,7 +449,7 @@ out:
 
 static struct target_type delay_target = {
 	.name	     = "delay",
-	.version     = {1, 4, 0},
+	.version     = {1, 5, 0},
 	.features    = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM,
 	.module      = THIS_MODULE,
 	.ctr	     = delay_ctr,
diff --git a/drivers/md/dm-dust.c b/drivers/md/dm-dust.c
index 1a33820c9f46..e75310232bbf 100644
--- a/drivers/md/dm-dust.c
+++ b/drivers/md/dm-dust.c
@@ -534,7 +534,9 @@ static void dust_status(struct dm_target *ti, status_type_t type,
 	}
 }
 
-static int dust_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
+static int dust_prepare_ioctl(struct dm_target *ti, struct block_device **bdev,
+			      unsigned int cmd, unsigned long arg,
+			      bool *forward)
 {
 	struct dust_device *dd = ti->private;
 	struct dm_dev *dev = dd->dev;
diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c
index b19b0142a690..6abb31ca9662 100644
--- a/drivers/md/dm-ebs-target.c
+++ b/drivers/md/dm-ebs-target.c
@@ -415,7 +415,8 @@ static void ebs_status(struct dm_target *ti, status_type_t type,
 	}
 }
 
-static int ebs_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
+static int ebs_prepare_ioctl(struct dm_target *ti, struct block_device **bdev,
+			     unsigned int cmd, unsigned long arg, bool *forward)
 {
 	struct ebs_c *ec = ti->private;
 	struct dm_dev *dev = ec->dev;
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index b690905ab89f..c711db6f8f5c 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -47,14 +47,15 @@ enum feature_flag_bits {
 };
 
 struct per_bio_data {
-	bool bio_submitted;
+	bool bio_can_corrupt;
+	struct bvec_iter saved_iter;
 };
 
 static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 			  struct dm_target *ti)
 {
-	int r;
-	unsigned int argc;
+	int r = 0;
+	unsigned int argc = 0;
 	const char *arg_name;
 
 	static const struct dm_arg _args[] = {
@@ -65,14 +66,13 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 		{0, PROBABILITY_BASE, "Invalid random corrupt argument"},
 	};
 
-	/* No feature arguments supplied. */
-	if (!as->argc)
-		return 0;
-
-	r = dm_read_arg_group(_args, as, &argc, &ti->error);
-	if (r)
+	if (as->argc && (r = dm_read_arg_group(_args, as, &argc, &ti->error)))
 		return r;
 
+	/* No feature arguments supplied. */
+	if (!argc)
+		goto error_all_io;
+
 	while (argc) {
 		arg_name = dm_shift_arg(as);
 		argc--;
@@ -128,8 +128,11 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 		 * corrupt_bio_byte <Nth_byte> <direction> <value> <bio_flags>
 		 */
 		if (!strcasecmp(arg_name, "corrupt_bio_byte")) {
-			if (!argc) {
-				ti->error = "Feature corrupt_bio_byte requires parameters";
+			if (fc->corrupt_bio_byte) {
+				ti->error = "Feature corrupt_bio_byte duplicated";
+				return -EINVAL;
+			} else if (argc < 4) {
+				ti->error = "Feature corrupt_bio_byte requires 4 parameters";
 				return -EINVAL;
 			}
 
@@ -176,7 +179,10 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 		}
 
 		if (!strcasecmp(arg_name, "random_read_corrupt")) {
-			if (!argc) {
+			if (fc->random_read_corrupt) {
+				ti->error = "Feature random_read_corrupt duplicated";
+				return -EINVAL;
+			} else if (!argc) {
 				ti->error = "Feature random_read_corrupt requires a parameter";
 				return -EINVAL;
 			}
@@ -189,7 +195,10 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 		}
 
 		if (!strcasecmp(arg_name, "random_write_corrupt")) {
-			if (!argc) {
+			if (fc->random_write_corrupt) {
+				ti->error = "Feature random_write_corrupt duplicated";
+				return -EINVAL;
+			} else if (!argc) {
 				ti->error = "Feature random_write_corrupt requires a parameter";
 				return -EINVAL;
 			}
@@ -205,18 +214,25 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 		return -EINVAL;
 	}
 
-	if (test_bit(DROP_WRITES, &fc->flags) && (fc->corrupt_bio_rw == WRITE)) {
-		ti->error = "drop_writes is incompatible with corrupt_bio_byte with the WRITE flag set";
+	if (test_bit(DROP_WRITES, &fc->flags) &&
+	    (fc->corrupt_bio_rw == WRITE || fc->random_write_corrupt)) {
+		ti->error = "drop_writes is incompatible with random_write_corrupt or corrupt_bio_byte with the WRITE flag set";
 		return -EINVAL;
 
-	} else if (test_bit(ERROR_WRITES, &fc->flags) && (fc->corrupt_bio_rw == WRITE)) {
-		ti->error = "error_writes is incompatible with corrupt_bio_byte with the WRITE flag set";
+	} else if (test_bit(ERROR_WRITES, &fc->flags) &&
+		   (fc->corrupt_bio_rw == WRITE || fc->random_write_corrupt)) {
+		ti->error = "error_writes is incompatible with random_write_corrupt or corrupt_bio_byte with the WRITE flag set";
+		return -EINVAL;
+	} else if (test_bit(ERROR_READS, &fc->flags) &&
+		   (fc->corrupt_bio_rw == READ || fc->random_read_corrupt)) {
+		ti->error = "error_reads is incompatible with random_read_corrupt or corrupt_bio_byte with the READ flag set";
 		return -EINVAL;
 	}
 
 	if (!fc->corrupt_bio_byte && !test_bit(ERROR_READS, &fc->flags) &&
 	    !test_bit(DROP_WRITES, &fc->flags) && !test_bit(ERROR_WRITES, &fc->flags) &&
 	    !fc->random_read_corrupt && !fc->random_write_corrupt) {
+error_all_io:
 		set_bit(ERROR_WRITES, &fc->flags);
 		set_bit(ERROR_READS, &fc->flags);
 	}
@@ -278,7 +294,7 @@ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (r)
 		goto bad;
 
-	r = dm_read_arg(_args, &as, &fc->down_interval, &ti->error);
+	r = dm_read_arg(_args + 1, &as, &fc->down_interval, &ti->error);
 	if (r)
 		goto bad;
 
@@ -339,7 +355,8 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio)
 }
 
 static void corrupt_bio_common(struct bio *bio, unsigned int corrupt_bio_byte,
-			       unsigned char corrupt_bio_value)
+			       unsigned char corrupt_bio_value,
+			       struct bvec_iter start)
 {
 	struct bvec_iter iter;
 	struct bio_vec bvec;
@@ -348,7 +365,7 @@ static void corrupt_bio_common(struct bio *bio, unsigned int corrupt_bio_byte,
 	 * Overwrite the Nth byte of the bio's data, on whichever page
 	 * it falls.
 	 */
-	bio_for_each_segment(bvec, bio, iter) {
+	__bio_for_each_segment(bvec, bio, iter, start) {
 		if (bio_iter_len(bio, iter) > corrupt_bio_byte) {
 			unsigned char *segment = bvec_kmap_local(&bvec);
 			segment[corrupt_bio_byte] = corrupt_bio_value;
@@ -357,36 +374,31 @@ static void corrupt_bio_common(struct bio *bio, unsigned int corrupt_bio_byte,
 				"(rw=%c bi_opf=%u bi_sector=%llu size=%u)\n",
 				bio, corrupt_bio_value, corrupt_bio_byte,
 				(bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_opf,
-				(unsigned long long)bio->bi_iter.bi_sector,
-				bio->bi_iter.bi_size);
+				(unsigned long long)start.bi_sector,
+				start.bi_size);
 			break;
 		}
 		corrupt_bio_byte -= bio_iter_len(bio, iter);
 	}
 }
 
-static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)
+static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc,
+			     struct bvec_iter start)
 {
 	unsigned int corrupt_bio_byte = fc->corrupt_bio_byte - 1;
 
-	if (!bio_has_data(bio))
-		return;
-
-	corrupt_bio_common(bio, corrupt_bio_byte, fc->corrupt_bio_value);
+	corrupt_bio_common(bio, corrupt_bio_byte, fc->corrupt_bio_value, start);
 }
 
-static void corrupt_bio_random(struct bio *bio)
+static void corrupt_bio_random(struct bio *bio, struct bvec_iter start)
 {
 	unsigned int corrupt_byte;
 	unsigned char corrupt_value;
 
-	if (!bio_has_data(bio))
-		return;
-
-	corrupt_byte = get_random_u32() % bio->bi_iter.bi_size;
+	corrupt_byte = get_random_u32() % start.bi_size;
 	corrupt_value = get_random_u8();
 
-	corrupt_bio_common(bio, corrupt_byte, corrupt_value);
+	corrupt_bio_common(bio, corrupt_byte, corrupt_value, start);
 }
 
 static void clone_free(struct bio *clone)
@@ -481,7 +493,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 	unsigned int elapsed;
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 
-	pb->bio_submitted = false;
+	pb->bio_can_corrupt = false;
 
 	if (op_is_zone_mgmt(bio_op(bio)))
 		goto map_bio;
@@ -490,14 +502,15 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 	elapsed = (jiffies - fc->start_time) / HZ;
 	if (elapsed % (fc->up_interval + fc->down_interval) >= fc->up_interval) {
 		bool corrupt_fixed, corrupt_random;
-		/*
-		 * Flag this bio as submitted while down.
-		 */
-		pb->bio_submitted = true;
+
+		if (bio_has_data(bio)) {
+			pb->bio_can_corrupt = true;
+			pb->saved_iter = bio->bi_iter;
+		}
 
 		/*
-		 * Error reads if neither corrupt_bio_byte or drop_writes or error_writes are set.
-		 * Otherwise, flakey_end_io() will decide if the reads should be modified.
+		 * If ERROR_READS isn't set flakey_end_io() will decide if the
+		 * reads should be modified.
 		 */
 		if (bio_data_dir(bio) == READ) {
 			if (test_bit(ERROR_READS, &fc->flags))
@@ -516,6 +529,8 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 			return DM_MAPIO_SUBMITTED;
 		}
 
+		if (!pb->bio_can_corrupt)
+			goto map_bio;
 		/*
 		 * Corrupt matching writes.
 		 */
@@ -535,9 +550,11 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 			struct bio *clone = clone_bio(ti, fc, bio);
 			if (clone) {
 				if (corrupt_fixed)
-					corrupt_bio_data(clone, fc);
+					corrupt_bio_data(clone, fc,
+							 clone->bi_iter);
 				if (corrupt_random)
-					corrupt_bio_random(clone);
+					corrupt_bio_random(clone,
+							   clone->bi_iter);
 				submit_bio(clone);
 				return DM_MAPIO_SUBMITTED;
 			}
@@ -559,28 +576,21 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio,
 	if (op_is_zone_mgmt(bio_op(bio)))
 		return DM_ENDIO_DONE;
 
-	if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
+	if (!*error && pb->bio_can_corrupt && (bio_data_dir(bio) == READ)) {
 		if (fc->corrupt_bio_byte) {
 			if ((fc->corrupt_bio_rw == READ) &&
 			    all_corrupt_bio_flags_match(bio, fc)) {
 				/*
 				 * Corrupt successful matching READs while in down state.
 				 */
-				corrupt_bio_data(bio, fc);
+				corrupt_bio_data(bio, fc, pb->saved_iter);
 			}
 		}
 		if (fc->random_read_corrupt) {
 			u64 rnd = get_random_u64();
 			u32 rem = do_div(rnd, PROBABILITY_BASE);
 			if (rem < fc->random_read_corrupt)
-				corrupt_bio_random(bio);
-		}
-		if (test_bit(ERROR_READS, &fc->flags)) {
-			/*
-			 * Error read during the down_interval if drop_writes
-			 * and error_writes were not configured.
-			 */
-			*error = BLK_STS_IOERR;
+				corrupt_bio_random(bio, pb->saved_iter);
 		}
 	}
 
@@ -638,7 +648,9 @@ static void flakey_status(struct dm_target *ti, status_type_t type,
 	}
 }
 
-static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
+static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev,
+				unsigned int cmd, unsigned long arg,
+				bool *forward)
 {
 	struct flakey_c *fc = ti->private;
 
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index d42eac944eb5..4165fef4c170 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1885,6 +1885,7 @@ static ioctl_fn lookup_ioctl(unsigned int cmd, int *ioctl_flags)
 		{DM_DEV_SET_GEOMETRY_CMD, 0, dev_set_geometry},
 		{DM_DEV_ARM_POLL_CMD, IOCTL_FLAGS_NO_PARAMS, dev_arm_poll},
 		{DM_GET_TARGET_VERSION_CMD, 0, get_target_version},
+		{DM_MPATH_PROBE_PATHS_CMD, 0, NULL}, /* block device ioctl */
 	};
 
 	if (unlikely(cmd >= ARRAY_SIZE(_ioctls)))
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 66318aba4bdb..15538ec58f8e 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -119,7 +119,9 @@ static void linear_status(struct dm_target *ti, status_type_t type,
 	}
 }
 
-static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
+static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev,
+				unsigned int cmd, unsigned long arg,
+				bool *forward)
 {
 	struct linear_c *lc = ti->private;
 	struct dm_dev *dev = lc->dev;
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 8d7df8303d0a..d484e8e1d48a 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -818,7 +818,9 @@ static void log_writes_status(struct dm_target *ti, status_type_t type,
 }
 
 static int log_writes_prepare_ioctl(struct dm_target *ti,
-				    struct block_device **bdev)
+				    struct block_device **bdev,
+				    unsigned int cmd, unsigned long arg,
+				    bool *forward)
 {
 	struct log_writes_c *lc = ti->private;
 	struct dm_dev *dev = lc->dev;
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 6c98f4ae5ea9..81fec2e1e0ef 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -79,6 +79,7 @@ struct multipath {
 	struct pgpath *current_pgpath;
 	struct priority_group *current_pg;
 	struct priority_group *next_pg;	/* Switch to this PG if set */
+	struct priority_group *last_probed_pg;
 
 	atomic_t nr_valid_paths;	/* Total number of usable paths */
 	unsigned int nr_priority_groups;
@@ -87,6 +88,7 @@ struct multipath {
 	const char *hw_handler_name;
 	char *hw_handler_params;
 	wait_queue_head_t pg_init_wait;	/* Wait for pg_init completion */
+	wait_queue_head_t probe_wait;   /* Wait for probing paths */
 	unsigned int pg_init_retries;	/* Number of times to retry pg_init */
 	unsigned int pg_init_delay_msecs;	/* Number of msecs before pg_init retry */
 	atomic_t pg_init_in_progress;	/* Only one pg_init allowed at once */
@@ -100,6 +102,7 @@ struct multipath {
 	struct bio_list queued_bios;
 
 	struct timer_list nopath_timer;	/* Timeout for queue_if_no_path */
+	bool is_suspending;
 };
 
 /*
@@ -132,6 +135,8 @@ static void queue_if_no_path_timeout_work(struct timer_list *t);
 #define MPATHF_PG_INIT_DISABLED 4		/* pg_init is not currently allowed */
 #define MPATHF_PG_INIT_REQUIRED 5		/* pg_init needs calling? */
 #define MPATHF_PG_INIT_DELAY_RETRY 6		/* Delay pg_init retry? */
+#define MPATHF_DELAY_PG_SWITCH 7		/* Delay switching pg if it still has paths */
+#define MPATHF_NEED_PG_SWITCH 8			/* Need to switch pgs after the delay has ended */
 
 static bool mpath_double_check_test_bit(int MPATHF_bit, struct multipath *m)
 {
@@ -254,6 +259,7 @@ static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m)
 	atomic_set(&m->pg_init_count, 0);
 	m->pg_init_delay_msecs = DM_PG_INIT_DELAY_DEFAULT;
 	init_waitqueue_head(&m->pg_init_wait);
+	init_waitqueue_head(&m->probe_wait);
 
 	return 0;
 }
@@ -413,13 +419,21 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
 		goto failed;
 	}
 
+	/* Don't change PG until it has no remaining paths */
+	pg = READ_ONCE(m->current_pg);
+	if (pg) {
+		pgpath = choose_path_in_pg(m, pg, nr_bytes);
+		if (!IS_ERR_OR_NULL(pgpath))
+			return pgpath;
+	}
+
 	/* Were we instructed to switch PG? */
 	if (READ_ONCE(m->next_pg)) {
 		spin_lock_irqsave(&m->lock, flags);
 		pg = m->next_pg;
 		if (!pg) {
 			spin_unlock_irqrestore(&m->lock, flags);
-			goto check_current_pg;
+			goto check_all_pgs;
 		}
 		m->next_pg = NULL;
 		spin_unlock_irqrestore(&m->lock, flags);
@@ -427,16 +441,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
 		if (!IS_ERR_OR_NULL(pgpath))
 			return pgpath;
 	}
-
-	/* Don't change PG until it has no remaining paths */
-check_current_pg:
-	pg = READ_ONCE(m->current_pg);
-	if (pg) {
-		pgpath = choose_path_in_pg(m, pg, nr_bytes);
-		if (!IS_ERR_OR_NULL(pgpath))
-			return pgpath;
-	}
-
+check_all_pgs:
 	/*
 	 * Loop through priority groups until we find a valid path.
 	 * First time we skip PGs marked 'bypassed'.
@@ -612,7 +617,6 @@ static void multipath_queue_bio(struct multipath *m, struct bio *bio)
 static struct pgpath *__map_bio(struct multipath *m, struct bio *bio)
 {
 	struct pgpath *pgpath;
-	unsigned long flags;
 
 	/* Do we need to select a new pgpath? */
 	pgpath = READ_ONCE(m->current_pgpath);
@@ -620,12 +624,12 @@ static struct pgpath *__map_bio(struct multipath *m, struct bio *bio)
 		pgpath = choose_pgpath(m, bio->bi_iter.bi_size);
 
 	if (!pgpath) {
-		spin_lock_irqsave(&m->lock, flags);
+		spin_lock_irq(&m->lock);
 		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
 			__multipath_queue_bio(m, bio);
 			pgpath = ERR_PTR(-EAGAIN);
 		}
-		spin_unlock_irqrestore(&m->lock, flags);
+		spin_unlock_irq(&m->lock);
 
 	} else if (mpath_double_check_test_bit(MPATHF_QUEUE_IO, m) ||
 		   mpath_double_check_test_bit(MPATHF_PG_INIT_REQUIRED, m)) {
@@ -688,7 +692,6 @@ static void process_queued_io_list(struct multipath *m)
 static void process_queued_bios(struct work_struct *work)
 {
 	int r;
-	unsigned long flags;
 	struct bio *bio;
 	struct bio_list bios;
 	struct blk_plug plug;
@@ -697,16 +700,16 @@ static void process_queued_bios(struct work_struct *work)
 
 	bio_list_init(&bios);
 
-	spin_lock_irqsave(&m->lock, flags);
+	spin_lock_irq(&m->lock);
 
 	if (bio_list_empty(&m->queued_bios)) {
-		spin_unlock_irqrestore(&m->lock, flags);
+		spin_unlock_irq(&m->lock);
 		return;
 	}
 
 	bio_list_merge_init(&bios, &m->queued_bios);
 
-	spin_unlock_irqrestore(&m->lock, flags);
+	spin_unlock_irq(&m->lock);
 
 	blk_start_plug(&plug);
 	while ((bio = bio_list_pop(&bios))) {
@@ -1190,7 +1193,6 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	struct dm_arg_set as;
 	unsigned int pg_count = 0;
 	unsigned int next_pg_num;
-	unsigned long flags;
 
 	as.argc = argc;
 	as.argv = argv;
@@ -1255,9 +1257,9 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad;
 	}
 
-	spin_lock_irqsave(&m->lock, flags);
+	spin_lock_irq(&m->lock);
 	enable_nopath_timeout(m);
-	spin_unlock_irqrestore(&m->lock, flags);
+	spin_unlock_irq(&m->lock);
 
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
@@ -1292,23 +1294,21 @@ static void multipath_wait_for_pg_init_completion(struct multipath *m)
 static void flush_multipath_work(struct multipath *m)
 {
 	if (m->hw_handler_name) {
-		unsigned long flags;
-
 		if (!atomic_read(&m->pg_init_in_progress))
 			goto skip;
 
-		spin_lock_irqsave(&m->lock, flags);
+		spin_lock_irq(&m->lock);
 		if (atomic_read(&m->pg_init_in_progress) &&
 		    !test_and_set_bit(MPATHF_PG_INIT_DISABLED, &m->flags)) {
-			spin_unlock_irqrestore(&m->lock, flags);
+			spin_unlock_irq(&m->lock);
 
 			flush_workqueue(kmpath_handlerd);
 			multipath_wait_for_pg_init_completion(m);
 
-			spin_lock_irqsave(&m->lock, flags);
+			spin_lock_irq(&m->lock);
 			clear_bit(MPATHF_PG_INIT_DISABLED, &m->flags);
 		}
-		spin_unlock_irqrestore(&m->lock, flags);
+		spin_unlock_irq(&m->lock);
 	}
 skip:
 	if (m->queue_mode == DM_TYPE_BIO_BASED)
@@ -1370,11 +1370,10 @@ out:
 static int reinstate_path(struct pgpath *pgpath)
 {
 	int r = 0, run_queue = 0;
-	unsigned long flags;
 	struct multipath *m = pgpath->pg->m;
 	unsigned int nr_valid_paths;
 
-	spin_lock_irqsave(&m->lock, flags);
+	spin_lock_irq(&m->lock);
 
 	if (pgpath->is_active)
 		goto out;
@@ -1404,7 +1403,7 @@ static int reinstate_path(struct pgpath *pgpath)
 	schedule_work(&m->trigger_event);
 
 out:
-	spin_unlock_irqrestore(&m->lock, flags);
+	spin_unlock_irq(&m->lock);
 	if (run_queue) {
 		dm_table_run_md_queue_async(m->ti->table);
 		process_queued_io_list(m);
@@ -1439,15 +1438,19 @@ static int action_dev(struct multipath *m, dev_t dev, action_fn action)
  * Temporarily try to avoid having to use the specified PG
  */
 static void bypass_pg(struct multipath *m, struct priority_group *pg,
-		      bool bypassed)
+		      bool bypassed, bool can_be_delayed)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&m->lock, flags);
 
 	pg->bypassed = bypassed;
-	m->current_pgpath = NULL;
-	m->current_pg = NULL;
+	if (can_be_delayed && test_bit(MPATHF_DELAY_PG_SWITCH, &m->flags))
+		set_bit(MPATHF_NEED_PG_SWITCH, &m->flags);
+	else {
+		m->current_pgpath = NULL;
+		m->current_pg = NULL;
+	}
 
 	spin_unlock_irqrestore(&m->lock, flags);
 
@@ -1461,7 +1464,6 @@ static int switch_pg_num(struct multipath *m, const char *pgstr)
 {
 	struct priority_group *pg;
 	unsigned int pgnum;
-	unsigned long flags;
 	char dummy;
 
 	if (!pgstr || (sscanf(pgstr, "%u%c", &pgnum, &dummy) != 1) || !pgnum ||
@@ -1470,17 +1472,21 @@ static int switch_pg_num(struct multipath *m, const char *pgstr)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&m->lock, flags);
+	spin_lock_irq(&m->lock);
 	list_for_each_entry(pg, &m->priority_groups, list) {
 		pg->bypassed = false;
 		if (--pgnum)
 			continue;
 
-		m->current_pgpath = NULL;
-		m->current_pg = NULL;
+		if (test_bit(MPATHF_DELAY_PG_SWITCH, &m->flags))
+			set_bit(MPATHF_NEED_PG_SWITCH, &m->flags);
+		else {
+			m->current_pgpath = NULL;
+			m->current_pg = NULL;
+		}
 		m->next_pg = pg;
 	}
-	spin_unlock_irqrestore(&m->lock, flags);
+	spin_unlock_irq(&m->lock);
 
 	schedule_work(&m->trigger_event);
 	return 0;
@@ -1507,7 +1513,7 @@ static int bypass_pg_num(struct multipath *m, const char *pgstr, bool bypassed)
 			break;
 	}
 
-	bypass_pg(m, pg, bypassed);
+	bypass_pg(m, pg, bypassed, true);
 	return 0;
 }
 
@@ -1561,7 +1567,7 @@ static void pg_init_done(void *data, int errors)
 		 * Probably doing something like FW upgrade on the
 		 * controller so try the other pg.
 		 */
-		bypass_pg(m, pg, true);
+		bypass_pg(m, pg, true, false);
 		break;
 	case SCSI_DH_RETRY:
 		/* Wait before retrying. */
@@ -1742,6 +1748,9 @@ static void multipath_presuspend(struct dm_target *ti)
 {
 	struct multipath *m = ti->private;
 
+	spin_lock_irq(&m->lock);
+	m->is_suspending = true;
+	spin_unlock_irq(&m->lock);
 	/* FIXME: bio-based shouldn't need to always disable queue_if_no_path */
 	if (m->queue_mode == DM_TYPE_BIO_BASED || !dm_noflush_suspending(m->ti))
 		queue_if_no_path(m, false, true, __func__);
@@ -1762,9 +1771,9 @@ static void multipath_postsuspend(struct dm_target *ti)
 static void multipath_resume(struct dm_target *ti)
 {
 	struct multipath *m = ti->private;
-	unsigned long flags;
 
-	spin_lock_irqsave(&m->lock, flags);
+	spin_lock_irq(&m->lock);
+	m->is_suspending = false;
 	if (test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags)) {
 		set_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags);
 		clear_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags);
@@ -1775,7 +1784,7 @@ static void multipath_resume(struct dm_target *ti)
 		test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags),
 		test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags));
 
-	spin_unlock_irqrestore(&m->lock, flags);
+	spin_unlock_irq(&m->lock);
 }
 
 /*
@@ -1798,14 +1807,13 @@ static void multipath_status(struct dm_target *ti, status_type_t type,
 			     unsigned int status_flags, char *result, unsigned int maxlen)
 {
 	int sz = 0, pg_counter, pgpath_counter;
-	unsigned long flags;
 	struct multipath *m = ti->private;
 	struct priority_group *pg;
 	struct pgpath *p;
 	unsigned int pg_num;
 	char state;
 
-	spin_lock_irqsave(&m->lock, flags);
+	spin_lock_irq(&m->lock);
 
 	/* Features */
 	if (type == STATUSTYPE_INFO)
@@ -1845,10 +1853,10 @@ static void multipath_status(struct dm_target *ti, status_type_t type,
 
 	DMEMIT("%u ", m->nr_priority_groups);
 
-	if (m->next_pg)
-		pg_num = m->next_pg->pg_num;
-	else if (m->current_pg)
+	if (m->current_pg)
 		pg_num = m->current_pg->pg_num;
+	else if (m->next_pg)
+		pg_num = m->next_pg->pg_num;
 	else
 		pg_num = (m->nr_priority_groups ? 1 : 0);
 
@@ -1951,7 +1959,7 @@ static void multipath_status(struct dm_target *ti, status_type_t type,
 		break;
 	}
 
-	spin_unlock_irqrestore(&m->lock, flags);
+	spin_unlock_irq(&m->lock);
 }
 
 static int multipath_message(struct dm_target *ti, unsigned int argc, char **argv,
@@ -1961,7 +1969,6 @@ static int multipath_message(struct dm_target *ti, unsigned int argc, char **arg
 	dev_t dev;
 	struct multipath *m = ti->private;
 	action_fn action;
-	unsigned long flags;
 
 	mutex_lock(&m->work_mutex);
 
@@ -1973,9 +1980,9 @@ static int multipath_message(struct dm_target *ti, unsigned int argc, char **arg
 	if (argc == 1) {
 		if (!strcasecmp(argv[0], "queue_if_no_path")) {
 			r = queue_if_no_path(m, true, false, __func__);
-			spin_lock_irqsave(&m->lock, flags);
+			spin_lock_irq(&m->lock);
 			enable_nopath_timeout(m);
-			spin_unlock_irqrestore(&m->lock, flags);
+			spin_unlock_irq(&m->lock);
 			goto out;
 		} else if (!strcasecmp(argv[0], "fail_if_no_path")) {
 			r = queue_if_no_path(m, false, false, __func__);
@@ -2021,14 +2028,132 @@ out:
 	return r;
 }
 
+/*
+ * Perform a minimal read from the given path to find out whether the
+ * path still works.  If a path error occurs, fail it.
+ */
+static int probe_path(struct pgpath *pgpath)
+{
+	struct block_device *bdev = pgpath->path.dev->bdev;
+	unsigned int read_size = bdev_logical_block_size(bdev);
+	struct page *page;
+	struct bio *bio;
+	blk_status_t status;
+	int r = 0;
+
+	if (WARN_ON_ONCE(read_size > PAGE_SIZE))
+		return -EINVAL;
+
+	page = alloc_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	/* Perform a minimal read: Sector 0, length read_size */
+	bio = bio_alloc(bdev, 1, REQ_OP_READ, GFP_KERNEL);
+	if (!bio) {
+		r = -ENOMEM;
+		goto out;
+	}
+
+	bio->bi_iter.bi_sector = 0;
+	__bio_add_page(bio, page, read_size, 0);
+	submit_bio_wait(bio);
+	status = bio->bi_status;
+	bio_put(bio);
+
+	if (status && blk_path_error(status))
+		fail_path(pgpath);
+
+out:
+	__free_page(page);
+	return r;
+}
+
+/*
+ * Probe all active paths in current_pg to find out whether they still work.
+ * Fail all paths that do not work.
+ *
+ * Return -ENOTCONN if no valid path is left (even outside of current_pg). We
+ * cannot probe paths in other pgs without switching current_pg, so if valid
+ * paths are only in different pgs, they may or may not work. Additionally
+ * we should not probe paths in a pathgroup that is in the process of
+ * Initializing. Userspace can submit a request and we'll switch and wait
+ * for the pathgroup to be initialized. If the request fails, it may need to
+ * probe again.
+ */
+static int probe_active_paths(struct multipath *m)
+{
+	struct pgpath *pgpath;
+	struct priority_group *pg = NULL;
+	int r = 0;
+
+	spin_lock_irq(&m->lock);
+	if (test_bit(MPATHF_DELAY_PG_SWITCH, &m->flags)) {
+		wait_event_lock_irq(m->probe_wait,
+				    !test_bit(MPATHF_DELAY_PG_SWITCH, &m->flags),
+				    m->lock);
+		/*
+		 * if we waited because a probe was already in progress,
+		 * and it probed the current active pathgroup, don't
+		 * reprobe. Just return the number of valid paths
+		 */
+		if (m->current_pg == m->last_probed_pg)
+			goto skip_probe;
+	}
+	if (!m->current_pg || m->is_suspending ||
+	    test_bit(MPATHF_QUEUE_IO, &m->flags))
+		goto skip_probe;
+	set_bit(MPATHF_DELAY_PG_SWITCH, &m->flags);
+	pg = m->last_probed_pg = m->current_pg;
+	spin_unlock_irq(&m->lock);
+
+	list_for_each_entry(pgpath, &pg->pgpaths, list) {
+		if (pg != READ_ONCE(m->current_pg) ||
+		    READ_ONCE(m->is_suspending))
+			goto out;
+		if (!pgpath->is_active)
+			continue;
+
+		r = probe_path(pgpath);
+		if (r < 0)
+			goto out;
+	}
+
+out:
+	spin_lock_irq(&m->lock);
+	clear_bit(MPATHF_DELAY_PG_SWITCH, &m->flags);
+	if (test_and_clear_bit(MPATHF_NEED_PG_SWITCH, &m->flags)) {
+		m->current_pgpath = NULL;
+		m->current_pg = NULL;
+	}
+skip_probe:
+	if (r == 0 && !atomic_read(&m->nr_valid_paths))
+		r = -ENOTCONN;
+	spin_unlock_irq(&m->lock);
+	if (pg)
+		wake_up(&m->probe_wait);
+	return r;
+}
+
 static int multipath_prepare_ioctl(struct dm_target *ti,
-				   struct block_device **bdev)
+				   struct block_device **bdev,
+				   unsigned int cmd, unsigned long arg,
+				   bool *forward)
 {
 	struct multipath *m = ti->private;
 	struct pgpath *pgpath;
-	unsigned long flags;
 	int r;
 
+	if (_IOC_TYPE(cmd) == DM_IOCTL) {
+		*forward = false;
+		switch (cmd) {
+		case DM_MPATH_PROBE_PATHS:
+			return probe_active_paths(m);
+		default:
+			return -ENOTTY;
+		}
+	}
+
 	pgpath = READ_ONCE(m->current_pgpath);
 	if (!pgpath || !mpath_double_check_test_bit(MPATHF_QUEUE_IO, m))
 		pgpath = choose_pgpath(m, 0);
@@ -2044,10 +2169,10 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
 	} else {
 		/* No path is available */
 		r = -EIO;
-		spin_lock_irqsave(&m->lock, flags);
+		spin_lock_irq(&m->lock);
 		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
 			r = -ENOTCONN;
-		spin_unlock_irqrestore(&m->lock, flags);
+		spin_unlock_irq(&m->lock);
 	}
 
 	if (r == -ENOTCONN) {
@@ -2055,10 +2180,10 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
 			/* Path status changed, redo selection */
 			(void) choose_pgpath(m, 0);
 		}
-		spin_lock_irqsave(&m->lock, flags);
+		spin_lock_irq(&m->lock);
 		if (test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags))
 			(void) __pg_init_all_paths(m);
-		spin_unlock_irqrestore(&m->lock, flags);
+		spin_unlock_irq(&m->lock);
 		dm_table_run_md_queue_async(m->ti->table);
 		process_queued_io_list(m);
 	}
@@ -2180,7 +2305,7 @@ static int multipath_busy(struct dm_target *ti)
  */
 static struct target_type multipath_target = {
 	.name = "multipath",
-	.version = {1, 14, 0},
+	.version = {1, 15, 0},
 	.features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE |
 		    DM_TARGET_PASSES_INTEGRITY,
 	.module = THIS_MODULE,
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 9e615b4f1f5e..785af4816584 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -133,10 +133,9 @@ static void queue_bio(struct mirror_set *ms, struct bio *bio, int rw)
 	spin_lock_irqsave(&ms->lock, flags);
 	should_wake = !(bl->head);
 	bio_list_add(bl, bio);
-	spin_unlock_irqrestore(&ms->lock, flags);
-
 	if (should_wake)
 		wakeup_mirrord(ms);
+	spin_unlock_irqrestore(&ms->lock, flags);
 }
 
 static void dispatch_bios(void *context, struct bio_list *bio_list)
@@ -646,9 +645,9 @@ static void write_callback(unsigned long error, void *context)
 	if (!ms->failures.head)
 		should_wake = 1;
 	bio_list_add(&ms->failures, bio);
-	spin_unlock_irqrestore(&ms->lock, flags);
 	if (should_wake)
 		wakeup_mirrord(ms);
+	spin_unlock_irqrestore(&ms->lock, flags);
 }
 
 static void do_write(struct mirror_set *ms, struct bio *bio)
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index e23076f7ece2..a6ca92049c10 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -217,10 +217,10 @@ static void dm_done(struct request *clone, blk_status_t error, bool mapped)
 	if (unlikely(error == BLK_STS_TARGET)) {
 		if (req_op(clone) == REQ_OP_DISCARD &&
 		    !clone->q->limits.max_discard_sectors)
-			disable_discard(tio->md);
+			blk_queue_disable_discard(tio->md->queue);
 		else if (req_op(clone) == REQ_OP_WRITE_ZEROES &&
 			 !clone->q->limits.max_write_zeroes_sectors)
-			disable_write_zeroes(tio->md);
+			blk_queue_disable_write_zeroes(tio->md->queue);
 	}
 
 	switch (r) {
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index a1b7535c508a..a7dc04bd55e5 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -405,7 +405,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio,
 		blk_status_t *error)
 {
 	unsigned int i;
-	char major_minor[16];
+	char major_minor[22];
 	struct stripe_c *sc = ti->private;
 
 	if (!*error)
@@ -417,8 +417,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio,
 	if (*error == BLK_STS_NOTSUPP)
 		return DM_ENDIO_DONE;
 
-	memset(major_minor, 0, sizeof(major_minor));
-	sprintf(major_minor, "%d:%d", MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)));
+	format_dev_t(major_minor, bio_dev(bio));
 
 	/*
 	 * Test to see which stripe drive triggered the event
diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c
index dfd9fb52a6f3..bb1a70b5a215 100644
--- a/drivers/md/dm-switch.c
+++ b/drivers/md/dm-switch.c
@@ -517,7 +517,9 @@ static void switch_status(struct dm_target *ti, status_type_t type,
  *
  * Passthrough all ioctls to the path for sector 0
  */
-static int switch_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
+static int switch_prepare_ioctl(struct dm_target *ti, struct block_device **bdev,
+				unsigned int cmd, unsigned long arg,
+				bool *forward)
 {
 	struct switch_ctx *sctx = ti->private;
 	unsigned int path_nr;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 6b23e777e10e..24a857ff6d0b 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -117,7 +117,6 @@ static int alloc_targets(struct dm_table *t, unsigned int num)
 	n_targets = (struct dm_target *) (n_highs + num);
 
 	memset(n_highs, -1, sizeof(*n_highs) * num);
-	kvfree(t->highs);
 
 	t->num_allocated = num;
 	t->highs = n_highs;
@@ -257,7 +256,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
 	if (bdev_is_zoned(bdev)) {
 		unsigned int zone_sectors = bdev_zone_sectors(bdev);
 
-		if (start & (zone_sectors - 1)) {
+		if (!bdev_is_zone_aligned(bdev, start)) {
 			DMERR("%s: start=%llu not aligned to h/w zone size %u of %pg",
 			      dm_device_name(ti->table->md),
 			      (unsigned long long)start,
@@ -274,7 +273,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
 		 * devices do not end up with a smaller zone in the middle of
 		 * the sector range.
 		 */
-		if (len & (zone_sectors - 1)) {
+		if (!bdev_is_zone_aligned(bdev, len)) {
 			DMERR("%s: len=%llu not aligned to h/w zone size %u of %pg",
 			      dm_device_name(ti->table->md),
 			      (unsigned long long)len,
@@ -431,6 +430,13 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 		return 0;
 	}
 
+	mutex_lock(&q->limits_lock);
+	/*
+	 * BLK_FEAT_ATOMIC_WRITES is not inherited from the bottom device in
+	 * blk_stack_limits(), so do it manually.
+	 */
+	limits->features |= (q->limits.features & BLK_FEAT_ATOMIC_WRITES);
+
 	if (blk_stack_limits(limits, &q->limits,
 			get_start_sect(bdev) + start) < 0)
 		DMWARN("%s: adding target device %pg caused an alignment inconsistency: "
@@ -448,6 +454,7 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 	 */
 	if (!dm_target_has_integrity(ti->type))
 		queue_limits_stack_integrity_bdev(limits, bdev);
+	mutex_unlock(&q->limits_lock);
 	return 0;
 }
 
@@ -1189,6 +1196,176 @@ put_live_table:
 	return 0;
 }
 
+enum dm_wrappedkey_op {
+	DERIVE_SW_SECRET,
+	IMPORT_KEY,
+	GENERATE_KEY,
+	PREPARE_KEY,
+};
+
+struct dm_wrappedkey_op_args {
+	enum dm_wrappedkey_op op;
+	int err;
+	union {
+		struct {
+			const u8 *eph_key;
+			size_t eph_key_size;
+			u8 *sw_secret;
+		} derive_sw_secret;
+		struct {
+			const u8 *raw_key;
+			size_t raw_key_size;
+			u8 *lt_key;
+		} import_key;
+		struct {
+			u8 *lt_key;
+		} generate_key;
+		struct {
+			const u8 *lt_key;
+			size_t lt_key_size;
+			u8 *eph_key;
+		} prepare_key;
+	};
+};
+
+static int dm_wrappedkey_op_callback(struct dm_target *ti, struct dm_dev *dev,
+				     sector_t start, sector_t len, void *data)
+{
+	struct dm_wrappedkey_op_args *args = data;
+	struct block_device *bdev = dev->bdev;
+	struct blk_crypto_profile *profile =
+		bdev_get_queue(bdev)->crypto_profile;
+	int err = -EOPNOTSUPP;
+
+	if (!args->err)
+		return 0;
+
+	switch (args->op) {
+	case DERIVE_SW_SECRET:
+		err = blk_crypto_derive_sw_secret(
+					bdev,
+					args->derive_sw_secret.eph_key,
+					args->derive_sw_secret.eph_key_size,
+					args->derive_sw_secret.sw_secret);
+		break;
+	case IMPORT_KEY:
+		err = blk_crypto_import_key(profile,
+					    args->import_key.raw_key,
+					    args->import_key.raw_key_size,
+					    args->import_key.lt_key);
+		break;
+	case GENERATE_KEY:
+		err = blk_crypto_generate_key(profile,
+					      args->generate_key.lt_key);
+		break;
+	case PREPARE_KEY:
+		err = blk_crypto_prepare_key(profile,
+					     args->prepare_key.lt_key,
+					     args->prepare_key.lt_key_size,
+					     args->prepare_key.eph_key);
+		break;
+	}
+	args->err = err;
+
+	/* Try another device in case this fails. */
+	return 0;
+}
+
+static int dm_exec_wrappedkey_op(struct blk_crypto_profile *profile,
+				 struct dm_wrappedkey_op_args *args)
+{
+	struct mapped_device *md =
+		container_of(profile, struct dm_crypto_profile, profile)->md;
+	struct dm_target *ti;
+	struct dm_table *t;
+	int srcu_idx;
+	int i;
+
+	args->err = -EOPNOTSUPP;
+
+	t = dm_get_live_table(md, &srcu_idx);
+	if (!t)
+		goto out;
+
+	/*
+	 * blk-crypto currently has no support for multiple incompatible
+	 * implementations of wrapped inline crypto keys on a single system.
+	 * It was already checked earlier that support for wrapped keys was
+	 * declared on all underlying devices.  Thus, all the underlying devices
+	 * should support all wrapped key operations and they should behave
+	 * identically, i.e. work with the same keys.  So, just executing the
+	 * operation on the first device on which it works suffices for now.
+	 */
+	for (i = 0; i < t->num_targets; i++) {
+		ti = dm_table_get_target(t, i);
+		if (!ti->type->iterate_devices)
+			continue;
+		ti->type->iterate_devices(ti, dm_wrappedkey_op_callback, args);
+		if (!args->err)
+			break;
+	}
+out:
+	dm_put_live_table(md, srcu_idx);
+	return args->err;
+}
+
+static int dm_derive_sw_secret(struct blk_crypto_profile *profile,
+			       const u8 *eph_key, size_t eph_key_size,
+			       u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE])
+{
+	struct dm_wrappedkey_op_args args = {
+		.op = DERIVE_SW_SECRET,
+		.derive_sw_secret = {
+			.eph_key = eph_key,
+			.eph_key_size = eph_key_size,
+			.sw_secret = sw_secret,
+		},
+	};
+	return dm_exec_wrappedkey_op(profile, &args);
+}
+
+static int dm_import_key(struct blk_crypto_profile *profile,
+			 const u8 *raw_key, size_t raw_key_size,
+			 u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE])
+{
+	struct dm_wrappedkey_op_args args = {
+		.op = IMPORT_KEY,
+		.import_key = {
+			.raw_key = raw_key,
+			.raw_key_size = raw_key_size,
+			.lt_key = lt_key,
+		},
+	};
+	return dm_exec_wrappedkey_op(profile, &args);
+}
+
+static int dm_generate_key(struct blk_crypto_profile *profile,
+			   u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE])
+{
+	struct dm_wrappedkey_op_args args = {
+		.op = GENERATE_KEY,
+		.generate_key = {
+			.lt_key = lt_key,
+		},
+	};
+	return dm_exec_wrappedkey_op(profile, &args);
+}
+
+static int dm_prepare_key(struct blk_crypto_profile *profile,
+			  const u8 *lt_key, size_t lt_key_size,
+			  u8 eph_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE])
+{
+	struct dm_wrappedkey_op_args args = {
+		.op = PREPARE_KEY,
+		.prepare_key = {
+			.lt_key = lt_key,
+			.lt_key_size = lt_key_size,
+			.eph_key = eph_key,
+		},
+	};
+	return dm_exec_wrappedkey_op(profile, &args);
+}
+
 static int
 device_intersect_crypto_capabilities(struct dm_target *ti, struct dm_dev *dev,
 				     sector_t start, sector_t len, void *data)
@@ -1263,6 +1440,13 @@ static int dm_table_construct_crypto_profile(struct dm_table *t)
 					  profile);
 	}
 
+	if (profile->key_types_supported & BLK_CRYPTO_KEY_TYPE_HW_WRAPPED) {
+		profile->ll_ops.derive_sw_secret = dm_derive_sw_secret;
+		profile->ll_ops.import_key = dm_import_key;
+		profile->ll_ops.generate_key = dm_generate_key;
+		profile->ll_ops.prepare_key = dm_prepare_key;
+	}
+
 	if (t->md->queue &&
 	    !blk_crypto_has_capabilities(profile,
 					 t->md->queue->crypto_profile)) {
@@ -1490,6 +1674,18 @@ bool dm_table_has_no_data_devices(struct dm_table *t)
 	return true;
 }
 
+bool dm_table_is_wildcard(struct dm_table *t)
+{
+	for (unsigned int i = 0; i < t->num_targets; i++) {
+		struct dm_target *ti = dm_table_get_target(t, i);
+
+		if (!dm_target_is_wildcard(ti->type))
+			return false;
+	}
+
+	return true;
+}
+
 static int device_not_zoned(struct dm_target *ti, struct dm_dev *dev,
 			    sector_t start, sector_t len, void *data)
 {
@@ -1721,8 +1917,12 @@ static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *
 					   sector_t start, sector_t len, void *data)
 {
 	struct request_queue *q = bdev_get_queue(dev->bdev);
+	int b;
 
-	return !q->limits.max_write_zeroes_sectors;
+	mutex_lock(&q->limits_lock);
+	b = !q->limits.max_write_zeroes_sectors;
+	mutex_unlock(&q->limits_lock);
+	return b;
 }
 
 static bool dm_table_supports_write_zeroes(struct dm_table *t)
@@ -1830,10 +2030,24 @@ static bool dm_table_supports_atomic_writes(struct dm_table *t)
 	return true;
 }
 
+bool dm_table_supports_size_change(struct dm_table *t, sector_t old_size,
+				   sector_t new_size)
+{
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && dm_has_zone_plugs(t->md) &&
+	    old_size != new_size) {
+		DMWARN("%s: device has zone write plug resources. "
+		       "Cannot change size",
+		       dm_device_name(t->md));
+		return false;
+	}
+	return true;
+}
+
 int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			      struct queue_limits *limits)
 {
 	int r;
+	struct queue_limits old_limits;
 
 	if (!dm_table_supports_nowait(t))
 		limits->features &= ~BLK_FEAT_NOWAIT;
@@ -1860,28 +2074,30 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	if (dm_table_supports_flush(t))
 		limits->features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA;
 
-	if (dm_table_supports_dax(t, device_not_dax_capable)) {
+	if (dm_table_supports_dax(t, device_not_dax_capable))
 		limits->features |= BLK_FEAT_DAX;
-		if (dm_table_supports_dax(t, device_not_dax_synchronous_capable))
-			set_dax_synchronous(t->md->dax_dev);
-	} else
+	else
 		limits->features &= ~BLK_FEAT_DAX;
 
-	if (dm_table_any_dev_attr(t, device_dax_write_cache_enabled, NULL))
-		dax_write_cache(t->md->dax_dev, true);
-
 	/* For a zoned table, setup the zone related queue attributes. */
-	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
-	    (limits->features & BLK_FEAT_ZONED)) {
-		r = dm_set_zones_restrictions(t, q, limits);
-		if (r)
-			return r;
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
+		if (limits->features & BLK_FEAT_ZONED) {
+			r = dm_set_zones_restrictions(t, q, limits);
+			if (r)
+				return r;
+		} else if (dm_has_zone_plugs(t->md)) {
+			DMWARN("%s: device has zone write plug resources. "
+			       "Cannot switch to non-zoned table.",
+			       dm_device_name(t->md));
+			return -EINVAL;
+		}
 	}
 
 	if (dm_table_supports_atomic_writes(t))
 		limits->features |= BLK_FEAT_ATOMIC_WRITES;
 
-	r = queue_limits_set(q, limits);
+	old_limits = queue_limits_start_update(q);
+	r = queue_limits_commit_update(q, limits);
 	if (r)
 		return r;
 
@@ -1892,10 +2108,21 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
 	    (limits->features & BLK_FEAT_ZONED)) {
 		r = dm_revalidate_zones(t, q);
-		if (r)
+		if (r) {
+			queue_limits_set(q, &old_limits);
 			return r;
+		}
 	}
 
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
+		dm_finalize_zone_settings(t, limits);
+
+	if (dm_table_supports_dax(t, device_not_dax_synchronous_capable))
+		set_dax_synchronous(t->md->dax_dev);
+
+	if (dm_table_any_dev_attr(t, device_dax_write_cache_enabled, NULL))
+		dax_write_cache(t->md->dax_dev, true);
+
 	dm_update_crypto_profile(q, t);
 	return 0;
 }
diff --git a/drivers/md/dm-vdo/indexer/volume.c b/drivers/md/dm-vdo/indexer/volume.c
index 655453bb276b..425b3a74f4db 100644
--- a/drivers/md/dm-vdo/indexer/volume.c
+++ b/drivers/md/dm-vdo/indexer/volume.c
@@ -754,10 +754,11 @@ static int get_volume_page_protected(struct volume *volume, struct uds_request *
 				     u32 physical_page, struct cached_page **page_ptr)
 {
 	struct cached_page *page;
+	unsigned int zone_number = request->zone_number;
 
 	get_page_from_cache(&volume->page_cache, physical_page, &page);
 	if (page != NULL) {
-		if (request->zone_number == 0) {
+		if (zone_number == 0) {
 			/* Only one zone is allowed to update the LRU. */
 			make_page_most_recent(&volume->page_cache, page);
 		}
@@ -767,7 +768,7 @@ static int get_volume_page_protected(struct volume *volume, struct uds_request *
 	}
 
 	/* Prepare to enqueue a read for the page. */
-	end_pending_search(&volume->page_cache, request->zone_number);
+	end_pending_search(&volume->page_cache, zone_number);
 	mutex_lock(&volume->read_threads_mutex);
 
 	/*
@@ -787,8 +788,7 @@ static int get_volume_page_protected(struct volume *volume, struct uds_request *
 		 * the order does not matter for correctness as it does below.
 		 */
 		mutex_unlock(&volume->read_threads_mutex);
-		begin_pending_search(&volume->page_cache, physical_page,
-				     request->zone_number);
+		begin_pending_search(&volume->page_cache, physical_page, zone_number);
 		return UDS_QUEUED;
 	}
 
@@ -797,7 +797,7 @@ static int get_volume_page_protected(struct volume *volume, struct uds_request *
 	 * "search pending" state in careful order so no other thread can mess with the data before
 	 * the caller gets to look at it.
 	 */
-	begin_pending_search(&volume->page_cache, physical_page, request->zone_number);
+	begin_pending_search(&volume->page_cache, physical_page, zone_number);
 	mutex_unlock(&volume->read_threads_mutex);
 	*page_ptr = page;
 	return UDS_SUCCESS;
@@ -849,6 +849,7 @@ static int search_cached_index_page(struct volume *volume, struct uds_request *r
 {
 	int result;
 	struct cached_page *page = NULL;
+	unsigned int zone_number = request->zone_number;
 	u32 physical_page = map_to_physical_page(volume->geometry, chapter,
 						 index_page_number);
 
@@ -858,18 +859,18 @@ static int search_cached_index_page(struct volume *volume, struct uds_request *r
 	 * invalidation by the reader thread, before the reader thread has noticed that the
 	 * invalidate_counter has been incremented.
 	 */
-	begin_pending_search(&volume->page_cache, physical_page, request->zone_number);
+	begin_pending_search(&volume->page_cache, physical_page, zone_number);
 
 	result = get_volume_page_protected(volume, request, physical_page, &page);
 	if (result != UDS_SUCCESS) {
-		end_pending_search(&volume->page_cache, request->zone_number);
+		end_pending_search(&volume->page_cache, zone_number);
 		return result;
 	}
 
 	result = uds_search_chapter_index_page(&page->index_page, volume->geometry,
 					       &request->record_name,
 					       record_page_number);
-	end_pending_search(&volume->page_cache, request->zone_number);
+	end_pending_search(&volume->page_cache, zone_number);
 	return result;
 }
 
@@ -882,6 +883,7 @@ int uds_search_cached_record_page(struct volume *volume, struct uds_request *req
 {
 	struct cached_page *record_page;
 	struct index_geometry *geometry = volume->geometry;
+	unsigned int zone_number = request->zone_number;
 	int result;
 	u32 physical_page, page_number;
 
@@ -905,11 +907,11 @@ int uds_search_cached_record_page(struct volume *volume, struct uds_request *req
 	 * invalidation by the reader thread, before the reader thread has noticed that the
 	 * invalidate_counter has been incremented.
 	 */
-	begin_pending_search(&volume->page_cache, physical_page, request->zone_number);
+	begin_pending_search(&volume->page_cache, physical_page, zone_number);
 
 	result = get_volume_page_protected(volume, request, physical_page, &record_page);
 	if (result != UDS_SUCCESS) {
-		end_pending_search(&volume->page_cache, request->zone_number);
+		end_pending_search(&volume->page_cache, zone_number);
 		return result;
 	}
 
@@ -917,7 +919,7 @@ int uds_search_cached_record_page(struct volume *volume, struct uds_request *req
 			       &request->record_name, geometry, &request->old_metadata))
 		*found = true;
 
-	end_pending_search(&volume->page_cache, request->zone_number);
+	end_pending_search(&volume->page_cache, zone_number);
 	return UDS_SUCCESS;
 }
 
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 0c41949db784..631a887b487c 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -593,6 +593,10 @@ int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v,
 	(*argc)--;
 
 	if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) {
+		if (v->fec->dev) {
+			ti->error = "FEC device already specified";
+			return -EINVAL;
+		}
 		r = dm_get_device(ti, arg_value, BLK_OPEN_READ, &v->fec->dev);
 		if (r) {
 			ti->error = "FEC device lookup failed";
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 3c427f18a04b..81186bded1ce 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -682,7 +682,8 @@ static void verity_bh_work(struct work_struct *w)
 static inline bool verity_use_bh(unsigned int bytes, unsigned short ioprio)
 {
 	return ioprio <= IOPRIO_CLASS_IDLE &&
-		bytes <= READ_ONCE(dm_verity_use_bh_bytes[ioprio]);
+		bytes <= READ_ONCE(dm_verity_use_bh_bytes[ioprio]) &&
+		!need_resched();
 }
 
 static void verity_end_io(struct bio *bio)
@@ -993,7 +994,9 @@ static void verity_status(struct dm_target *ti, status_type_t type,
 	}
 }
 
-static int verity_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
+static int verity_prepare_ioctl(struct dm_target *ti, struct block_device **bdev,
+				unsigned int cmd, unsigned long arg,
+				bool *forward)
 {
 	struct dm_verity *v = ti->private;
 
@@ -1120,6 +1123,9 @@ static int verity_alloc_most_once(struct dm_verity *v)
 {
 	struct dm_target *ti = v->ti;
 
+	if (v->validated_blocks)
+		return 0;
+
 	/* the bitset can only handle INT_MAX blocks */
 	if (v->data_blocks > INT_MAX) {
 		ti->error = "device too large to use check_at_most_once";
@@ -1143,6 +1149,9 @@ static int verity_alloc_zero_digest(struct dm_verity *v)
 	struct dm_verity_io *io;
 	u8 *zero_data;
 
+	if (v->zero_digest)
+		return 0;
+
 	v->zero_digest = kmalloc(v->digest_size, GFP_KERNEL);
 
 	if (!v->zero_digest)
@@ -1577,7 +1586,7 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 			goto bad;
 	}
 
-	/* Root hash signature is  a optional parameter*/
+	/* Root hash signature is an optional parameter */
 	r = verity_verify_root_hash(root_hash_digest_to_validate,
 				    strlen(root_hash_digest_to_validate),
 				    verify_args.sig,
diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c
index a9e2c6c0a33c..d5261a0e4232 100644
--- a/drivers/md/dm-verity-verify-sig.c
+++ b/drivers/md/dm-verity-verify-sig.c
@@ -71,9 +71,14 @@ int verity_verify_sig_parse_opt_args(struct dm_arg_set *as,
 				     const char *arg_name)
 {
 	struct dm_target *ti = v->ti;
-	int ret = 0;
+	int ret;
 	const char *sig_key = NULL;
 
+	if (v->signature_key_desc) {
+		ti->error = DM_VERITY_VERIFY_ERR("root_hash_sig_key_desc already specified");
+		return -EINVAL;
+	}
+
 	if (!*argc) {
 		ti->error = DM_VERITY_VERIFY_ERR("Signature key not specified");
 		return -EINVAL;
@@ -83,14 +88,18 @@ int verity_verify_sig_parse_opt_args(struct dm_arg_set *as,
 	(*argc)--;
 
 	ret = verity_verify_get_sig_from_key(sig_key, sig_opts);
-	if (ret < 0)
+	if (ret < 0) {
 		ti->error = DM_VERITY_VERIFY_ERR("Invalid key specified");
+		return ret;
+	}
 
 	v->signature_key_desc = kstrdup(sig_key, GFP_KERNEL);
-	if (!v->signature_key_desc)
+	if (!v->signature_key_desc) {
+		ti->error = DM_VERITY_VERIFY_ERR("Could not allocate memory for signature key");
 		return -ENOMEM;
+	}
 
-	return ret;
+	return 0;
 }
 
 /*
diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c
index 20edd3fabbab..3d31b82e0730 100644
--- a/drivers/md/dm-zone.c
+++ b/drivers/md/dm-zone.c
@@ -56,24 +56,31 @@ int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 {
 	struct mapped_device *md = disk->private_data;
 	struct dm_table *map;
-	int srcu_idx, ret;
+	struct dm_table *zone_revalidate_map = md->zone_revalidate_map;
+	int srcu_idx, ret = -EIO;
+	bool put_table = false;
 
-	if (!md->zone_revalidate_map) {
-		/* Regular user context */
+	if (!zone_revalidate_map || md->revalidate_map_task != current) {
+		/*
+		 * Regular user context or
+		 * Zone revalidation during __bind() is in progress, but this
+		 * call is from a different process
+		 */
 		if (dm_suspended_md(md))
 			return -EAGAIN;
 
 		map = dm_get_live_table(md, &srcu_idx);
-		if (!map)
-			return -EIO;
+		put_table = true;
 	} else {
 		/* Zone revalidation during __bind() */
-		map = md->zone_revalidate_map;
+		map = zone_revalidate_map;
 	}
 
-	ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb, data);
+	if (map)
+		ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb,
+					     data);
 
-	if (!md->zone_revalidate_map)
+	if (put_table)
 		dm_put_live_table(md, srcu_idx);
 
 	return ret;
@@ -153,33 +160,36 @@ int dm_revalidate_zones(struct dm_table *t, struct request_queue *q)
 {
 	struct mapped_device *md = t->md;
 	struct gendisk *disk = md->disk;
+	unsigned int nr_zones = disk->nr_zones;
 	int ret;
 
 	if (!get_capacity(disk))
 		return 0;
 
-	/* Revalidate only if something changed. */
-	if (!disk->nr_zones || disk->nr_zones != md->nr_zones) {
-		DMINFO("%s using %s zone append",
-		       disk->disk_name,
-		       queue_emulates_zone_append(q) ? "emulated" : "native");
-		md->nr_zones = 0;
-	}
-
-	if (md->nr_zones)
+	/*
+	 * Do not revalidate if zone write plug resources have already
+	 * been allocated.
+	 */
+	if (dm_has_zone_plugs(md))
 		return 0;
 
+	DMINFO("%s using %s zone append", disk->disk_name,
+	       queue_emulates_zone_append(q) ? "emulated" : "native");
+
 	/*
 	 * Our table is not live yet. So the call to dm_get_live_table()
 	 * in dm_blk_report_zones() will fail. Set a temporary pointer to
 	 * our table for dm_blk_report_zones() to use directly.
 	 */
 	md->zone_revalidate_map = t;
+	md->revalidate_map_task = current;
 	ret = blk_revalidate_disk_zones(disk);
+	md->revalidate_map_task = NULL;
 	md->zone_revalidate_map = NULL;
 
 	if (ret) {
 		DMERR("Revalidate zones failed %d", ret);
+		disk->nr_zones = nr_zones;
 		return ret;
 	}
 
@@ -337,15 +347,15 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
 
 	/*
 	 * Check if zone append is natively supported, and if not, set the
-	 * mapped device queue as needing zone append emulation.
+	 * mapped device queue as needing zone append emulation. If zone
+	 * append is natively supported, make sure that
+	 * max_hw_zone_append_sectors is not set to 0.
 	 */
 	WARN_ON_ONCE(queue_is_mq(q));
-	if (dm_table_supports_zone_append(t)) {
-		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
-	} else {
-		set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
+	if (!dm_table_supports_zone_append(t))
 		lim->max_hw_zone_append_sectors = 0;
-	}
+	else if (lim->max_hw_zone_append_sectors == 0)
+		lim->max_hw_zone_append_sectors = lim->max_zone_append_sectors;
 
 	/*
 	 * Determine the max open and max active zone limits for the mapped
@@ -380,15 +390,28 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
 		lim->max_open_zones = 0;
 		lim->max_active_zones = 0;
 		lim->max_hw_zone_append_sectors = 0;
+		lim->max_zone_append_sectors = 0;
 		lim->zone_write_granularity = 0;
 		lim->chunk_sectors = 0;
 		lim->features &= ~BLK_FEAT_ZONED;
-		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
-		md->nr_zones = 0;
-		disk->nr_zones = 0;
 		return 0;
 	}
 
+	if (get_capacity(disk) && dm_has_zone_plugs(t->md)) {
+		if (q->limits.chunk_sectors != lim->chunk_sectors) {
+			DMWARN("%s: device has zone write plug resources. "
+			       "Cannot change zone size",
+			       disk->disk_name);
+			return -EINVAL;
+		}
+		if (lim->max_hw_zone_append_sectors != 0 &&
+		    !dm_table_is_wildcard(t)) {
+			DMWARN("%s: device has zone write plug resources. "
+			       "New table must emulate zone append",
+			       disk->disk_name);
+			return -EINVAL;
+		}
+	}
 	/*
 	 * Warn once (when the capacity is not yet set) if the mapped device is
 	 * partially using zone resources of the target devices as that leads to
@@ -408,6 +431,23 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
 	return 0;
 }
 
+void dm_finalize_zone_settings(struct dm_table *t, struct queue_limits *lim)
+{
+	struct mapped_device *md = t->md;
+
+	if (lim->features & BLK_FEAT_ZONED) {
+		if (dm_table_supports_zone_append(t))
+			clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
+		else
+			set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
+	} else {
+		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
+		md->nr_zones = 0;
+		md->disk->nr_zones = 0;
+	}
+}
+
+
 /*
  * IO completion callback called from clone_endio().
  */
@@ -423,9 +463,9 @@ void dm_zone_endio(struct dm_io *io, struct bio *clone)
 	 */
 	if (clone->bi_status == BLK_STS_OK &&
 	    bio_op(clone) == REQ_OP_ZONE_APPEND) {
-		sector_t mask = bdev_zone_sectors(disk->part0) - 1;
-
-		orig_bio->bi_iter.bi_sector += clone->bi_iter.bi_sector & mask;
+		orig_bio->bi_iter.bi_sector +=
+			bdev_offset_from_zone_start(disk->part0,
+						    clone->bi_iter.bi_sector);
 	}
 
 	return;
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 6141fc25d842..5da3db06da10 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -1015,7 +1015,8 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits)
 /*
  * Pass on ioctl to the backend device.
  */
-static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
+static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev,
+			     unsigned int cmd, unsigned long arg, bool *forward)
 {
 	struct dmz_target *dmz = ti->private;
 	struct dmz_dev *dev = &dmz->dev[0];
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5ab7574c0c76..1726f0f828cc 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -411,7 +411,8 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 }
 
 static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx,
-			    struct block_device **bdev)
+			    struct block_device **bdev, unsigned int cmd,
+			    unsigned long arg, bool *forward)
 {
 	struct dm_target *ti;
 	struct dm_table *map;
@@ -434,8 +435,8 @@ retry:
 	if (dm_suspended_md(md))
 		return -EAGAIN;
 
-	r = ti->type->prepare_ioctl(ti, bdev);
-	if (r == -ENOTCONN && !fatal_signal_pending(current)) {
+	r = ti->type->prepare_ioctl(ti, bdev, cmd, arg, forward);
+	if (r == -ENOTCONN && *forward && !fatal_signal_pending(current)) {
 		dm_put_live_table(md, *srcu_idx);
 		fsleep(10000);
 		goto retry;
@@ -454,9 +455,10 @@ static int dm_blk_ioctl(struct block_device *bdev, blk_mode_t mode,
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	int r, srcu_idx;
+	bool forward = true;
 
-	r = dm_prepare_ioctl(md, &srcu_idx, &bdev);
-	if (r < 0)
+	r = dm_prepare_ioctl(md, &srcu_idx, &bdev, cmd, arg, &forward);
+	if (!forward || r < 0)
 		goto out;
 
 	if (r > 0) {
@@ -1082,22 +1084,6 @@ static inline struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
 	return &md->queue->limits;
 }
 
-void disable_discard(struct mapped_device *md)
-{
-	struct queue_limits *limits = dm_get_queue_limits(md);
-
-	/* device doesn't really support DISCARD, disable it */
-	limits->max_hw_discard_sectors = 0;
-}
-
-void disable_write_zeroes(struct mapped_device *md)
-{
-	struct queue_limits *limits = dm_get_queue_limits(md);
-
-	/* device doesn't really support WRITE ZEROES, disable it */
-	limits->max_write_zeroes_sectors = 0;
-}
-
 static bool swap_bios_limit(struct dm_target *ti, struct bio *bio)
 {
 	return unlikely((bio->bi_opf & REQ_SWAP) != 0) && unlikely(ti->limit_swap_bios);
@@ -1115,10 +1101,10 @@ static void clone_endio(struct bio *bio)
 	if (unlikely(error == BLK_STS_TARGET)) {
 		if (bio_op(bio) == REQ_OP_DISCARD &&
 		    !bdev_max_discard_sectors(bio->bi_bdev))
-			disable_discard(md);
+			blk_queue_disable_discard(md->queue);
 		else if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
 			 !bdev_write_zeroes_sectors(bio->bi_bdev))
-			disable_write_zeroes(md);
+			blk_queue_disable_write_zeroes(md->queue);
 	}
 
 	if (static_branch_unlikely(&zoned_enabled) &&
@@ -2421,21 +2407,35 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 			       struct queue_limits *limits)
 {
 	struct dm_table *old_map;
-	sector_t size;
+	sector_t size, old_size;
 	int ret;
 
 	lockdep_assert_held(&md->suspend_lock);
 
 	size = dm_table_get_size(t);
 
+	old_size = dm_get_size(md);
+
+	if (!dm_table_supports_size_change(t, old_size, size)) {
+		old_map = ERR_PTR(-EINVAL);
+		goto out;
+	}
+
+	set_capacity(md->disk, size);
+
+	ret = dm_table_set_restrictions(t, md->queue, limits);
+	if (ret) {
+		set_capacity(md->disk, old_size);
+		old_map = ERR_PTR(ret);
+		goto out;
+	}
+
 	/*
 	 * Wipe any geometry if the size of the table changed.
 	 */
-	if (size != dm_get_size(md))
+	if (size != old_size)
 		memset(&md->geometry, 0, sizeof(md->geometry));
 
-	set_capacity(md->disk, size);
-
 	dm_table_event_callback(t, event_callback, md);
 
 	if (dm_table_request_based(t)) {
@@ -2453,10 +2453,10 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 		 * requests in the queue may refer to bio from the old bioset,
 		 * so you must walk through the queue to unprep.
 		 */
-		if (!md->mempools) {
+		if (!md->mempools)
 			md->mempools = t->mempools;
-			t->mempools = NULL;
-		}
+		else
+			dm_free_md_mempools(t->mempools);
 	} else {
 		/*
 		 * The md may already have mempools that need changing.
@@ -2465,14 +2465,8 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 		 */
 		dm_free_md_mempools(md->mempools);
 		md->mempools = t->mempools;
-		t->mempools = NULL;
-	}
-
-	ret = dm_table_set_restrictions(t, md->queue, limits);
-	if (ret) {
-		old_map = ERR_PTR(ret);
-		goto out;
 	}
+	t->mempools = NULL;
 
 	old_map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
 	rcu_assign_pointer(md->map, (void *)t);
@@ -3638,10 +3632,13 @@ static int dm_pr_clear(struct block_device *bdev, u64 key)
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	const struct pr_ops *ops;
 	int r, srcu_idx;
+	bool forward = true;
 
-	r = dm_prepare_ioctl(md, &srcu_idx, &bdev);
+	/* Not a real ioctl, but targets must not interpret non-DM ioctls */
+	r = dm_prepare_ioctl(md, &srcu_idx, &bdev, 0, 0, &forward);
 	if (r < 0)
 		goto out;
+	WARN_ON_ONCE(!forward);
 
 	ops = bdev->bd_disk->fops->pr_ops;
 	if (ops && ops->pr_clear)
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index a0a8ff119815..245f52b59215 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -58,6 +58,7 @@ void dm_table_event_callback(struct dm_table *t,
 			     void (*fn)(void *), void *context);
 struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector);
 bool dm_table_has_no_data_devices(struct dm_table *table);
+bool dm_table_is_wildcard(struct dm_table *t);
 int dm_calculate_queue_limits(struct dm_table *table,
 			      struct queue_limits *limits);
 int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
@@ -72,6 +73,8 @@ struct target_type *dm_table_get_immutable_target_type(struct dm_table *t);
 struct dm_target *dm_table_get_immutable_target(struct dm_table *t);
 struct dm_target *dm_table_get_wildcard_target(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
+bool dm_table_supports_size_change(struct dm_table *t, sector_t old_size,
+				   sector_t new_size);
 
 void dm_lock_md_type(struct mapped_device *md);
 void dm_unlock_md_type(struct mapped_device *md);
@@ -102,6 +105,7 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
 int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
 		struct queue_limits *lim);
 int dm_revalidate_zones(struct dm_table *t, struct request_queue *q);
+void dm_finalize_zone_settings(struct dm_table *t, struct queue_limits *lim);
 void dm_zone_endio(struct dm_io *io, struct bio *clone);
 #ifdef CONFIG_BLK_DEV_ZONED
 int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
@@ -110,12 +114,14 @@ bool dm_is_zone_write(struct mapped_device *md, struct bio *bio);
 int dm_zone_get_reset_bitmap(struct mapped_device *md, struct dm_table *t,
 			     sector_t sector, unsigned int nr_zones,
 			     unsigned long *need_reset);
+#define dm_has_zone_plugs(md) ((md)->disk->zone_wplugs_hash != NULL)
 #else
 #define dm_blk_report_zones	NULL
 static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
 {
 	return false;
 }
+#define dm_has_zone_plugs(md) false
 #endif
 
 /*
diff --git a/drivers/mfd/88pm886.c b/drivers/mfd/88pm886.c
index 891fdce5d8c1..39dd9a818b0f 100644
--- a/drivers/mfd/88pm886.c
+++ b/drivers/mfd/88pm886.c
@@ -16,11 +16,11 @@ static const struct regmap_config pm886_regmap_config = {
 	.max_register = PM886_REG_RTC_SPARE6,
 };
 
-static struct regmap_irq pm886_regmap_irqs[] = {
+static const struct regmap_irq pm886_regmap_irqs[] = {
 	REGMAP_IRQ_REG(PM886_IRQ_ONKEY, 0, PM886_INT_ENA1_ONKEY),
 };
 
-static struct regmap_irq_chip pm886_regmap_irq_chip = {
+static const struct regmap_irq_chip pm886_regmap_irq_chip = {
 	.name = "88pm886",
 	.irqs = pm886_regmap_irqs,
 	.num_irqs = ARRAY_SIZE(pm886_regmap_irqs),
@@ -30,11 +30,11 @@ static struct regmap_irq_chip pm886_regmap_irq_chip = {
 	.unmask_base = PM886_REG_INT_ENA_1,
 };
 
-static struct resource pm886_onkey_resources[] = {
+static const struct resource pm886_onkey_resources[] = {
 	DEFINE_RES_IRQ_NAMED(PM886_IRQ_ONKEY, "88pm886-onkey"),
 };
 
-static struct mfd_cell pm886_devs[] = {
+static const struct mfd_cell pm886_devs[] = {
 	MFD_CELL_RES("88pm886-onkey", pm886_onkey_resources),
 	MFD_CELL_NAME("88pm886-regulator"),
 	MFD_CELL_NAME("88pm886-rtc"),
@@ -124,7 +124,11 @@ static int pm886_probe(struct i2c_client *client)
 	if (err)
 		return dev_err_probe(dev, err, "Failed to register power off handler\n");
 
-	device_init_wakeup(dev, device_property_read_bool(dev, "wakeup-source"));
+	if (device_property_read_bool(dev, "wakeup-source")) {
+		err = devm_device_init_wakeup(dev);
+		if (err)
+			return dev_err_probe(dev, err, "Failed to init wakeup\n");
+	}
 
 	return 0;
 }
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 96992af22565..6fb3768e3d71 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1312,21 +1312,42 @@ config MFD_RN5T618
 	  functionality of the device.
 
 config MFD_SEC_CORE
-	tristate "Samsung Electronics PMIC Series Support"
+	tristate
+	select MFD_CORE
+	select REGMAP_IRQ
+
+config MFD_SEC_ACPM
+	tristate "Samsung Electronics S2MPG1x PMICs"
+	depends on EXYNOS_ACPM_PROTOCOL
+	depends on OF
+	select MFD_SEC_CORE
+	help
+	  Support for the Samsung Electronics PMICs with ACPM interface.
+	  This is a Power Management IC for mobile applications with buck
+	  converters, various LDOs, power meters, RTC, clock outputs, and
+	  additional GPIOs interfaces.
+	  This driver provides common support for accessing the device;
+	  additional drivers must be enabled in order to use the functionality
+	  of the device.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called sec-acpm.
+
+config MFD_SEC_I2C
+	tristate "Samsung Electronics S2MPA/S2MPS1X/S2MPU/S5M series PMICs"
 	depends on I2C=y
 	depends on OF
-	select MFD_CORE
+	select MFD_SEC_CORE
 	select REGMAP_I2C
-	select REGMAP_IRQ
 	help
-	  Support for the Samsung Electronics PMIC devices coming
-	  usually along with Samsung Exynos SoC chipset.
+	  Support for the Samsung Electronics PMIC devices with I2C interface
+	  coming usually along with Samsung Exynos SoC chipset.
 	  This driver provides common support for accessing the device,
 	  additional drivers must be enabled in order to use the functionality
-	  of the device
+	  of the device.
 
 	  To compile this driver as a module, choose M here: the
-	  module will be called sec-core.
+	  module will be called sec-i2c.
 	  Have in mind that important core drivers (like regulators) depend
 	  on this driver so building this as a module might require proper
 	  initial ramdisk or might not boot up as well in certain scenarios.
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 5e5cc279af60..79495f9f3457 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -229,7 +229,10 @@ obj-$(CONFIG_MFD_RK8XX)		+= rk8xx-core.o
 obj-$(CONFIG_MFD_RK8XX_I2C)	+= rk8xx-i2c.o
 obj-$(CONFIG_MFD_RK8XX_SPI)	+= rk8xx-spi.o
 obj-$(CONFIG_MFD_RN5T618)	+= rn5t618.o
-obj-$(CONFIG_MFD_SEC_CORE)	+= sec-core.o sec-irq.o
+sec-core-objs			:= sec-common.o sec-irq.o
+obj-$(CONFIG_MFD_SEC_CORE)	+= sec-core.o
+obj-$(CONFIG_MFD_SEC_ACPM)	+= sec-acpm.o
+obj-$(CONFIG_MFD_SEC_I2C)	+= sec-i2c.o
 obj-$(CONFIG_MFD_SYSCON)	+= syscon.o
 obj-$(CONFIG_MFD_LM3533)	+= lm3533-core.o lm3533-ctrlbank.o
 obj-$(CONFIG_MFD_VEXPRESS_SYSREG)	+= vexpress-sysreg.o
diff --git a/drivers/mfd/aat2870-core.c b/drivers/mfd/aat2870-core.c
index 8ef510e84688..34d66ba9646a 100644
--- a/drivers/mfd/aat2870-core.c
+++ b/drivers/mfd/aat2870-core.c
@@ -320,9 +320,7 @@ static const struct file_operations aat2870_reg_fops = {
 
 static void aat2870_init_debugfs(struct aat2870_data *aat2870)
 {
-	aat2870->dentry_root = debugfs_create_dir("aat2870", NULL);
-
-	debugfs_create_file("regs", 0644, aat2870->dentry_root, aat2870,
+	debugfs_create_file("regs", 0644, aat2870->client->debugfs, aat2870,
 			    &aat2870_reg_fops);
 }
 
diff --git a/drivers/mfd/as3722.c b/drivers/mfd/as3722.c
index 6c0d89b0c7e3..7ab6fcc9c27c 100644
--- a/drivers/mfd/as3722.c
+++ b/drivers/mfd/as3722.c
@@ -394,7 +394,9 @@ static int as3722_i2c_probe(struct i2c_client *i2c)
 		return ret;
 	}
 
-	device_init_wakeup(as3722->dev, true);
+	ret = devm_device_init_wakeup(as3722->dev);
+	if (ret)
+		return dev_err_probe(as3722->dev, ret, "Failed to init wakeup\n");
 
 	dev_dbg(as3722->dev, "AS3722 core driver initialized successfully\n");
 	return 0;
diff --git a/drivers/mfd/bcm590xx.c b/drivers/mfd/bcm590xx.c
index 8b56786d85d0..5a8456bbd63f 100644
--- a/drivers/mfd/bcm590xx.c
+++ b/drivers/mfd/bcm590xx.c
@@ -17,6 +17,15 @@
 #include <linux/regmap.h>
 #include <linux/slab.h>
 
+/* Under primary I2C address: */
+#define BCM590XX_REG_PMUID		0x1e
+
+#define BCM590XX_REG_PMUREV		0x1f
+#define BCM590XX_PMUREV_DIG_MASK	0xF
+#define BCM590XX_PMUREV_DIG_SHIFT	0
+#define BCM590XX_PMUREV_ANA_MASK	0xF0
+#define BCM590XX_PMUREV_ANA_SHIFT	4
+
 static const struct mfd_cell bcm590xx_devs[] = {
 	{
 		.name = "bcm590xx-vregs",
@@ -37,6 +46,47 @@ static const struct regmap_config bcm590xx_regmap_config_sec = {
 	.cache_type	= REGCACHE_MAPLE,
 };
 
+/* Map PMU ID value to model name string */
+static const char * const bcm590xx_names[] = {
+	[BCM590XX_PMUID_BCM59054] = "BCM59054",
+	[BCM590XX_PMUID_BCM59056] = "BCM59056",
+};
+
+static int bcm590xx_parse_version(struct bcm590xx *bcm590xx)
+{
+	unsigned int id, rev;
+	int ret;
+
+	/* Get PMU ID and verify that it matches compatible */
+	ret = regmap_read(bcm590xx->regmap_pri, BCM590XX_REG_PMUID, &id);
+	if (ret) {
+		dev_err(bcm590xx->dev, "failed to read PMU ID: %d\n", ret);
+		return ret;
+	}
+
+	if (id != bcm590xx->pmu_id) {
+		dev_err(bcm590xx->dev, "Incorrect ID for %s: expected %x, got %x.\n",
+			bcm590xx_names[bcm590xx->pmu_id], bcm590xx->pmu_id, id);
+		return -ENODEV;
+	}
+
+	/* Get PMU revision and store it in the info struct */
+	ret = regmap_read(bcm590xx->regmap_pri, BCM590XX_REG_PMUREV, &rev);
+	if (ret) {
+		dev_err(bcm590xx->dev, "failed to read PMU revision: %d\n", ret);
+		return ret;
+	}
+
+	bcm590xx->rev_digital = (rev & BCM590XX_PMUREV_DIG_MASK) >> BCM590XX_PMUREV_DIG_SHIFT;
+
+	bcm590xx->rev_analog = (rev & BCM590XX_PMUREV_ANA_MASK) >> BCM590XX_PMUREV_ANA_SHIFT;
+
+	dev_dbg(bcm590xx->dev, "PMU ID 0x%x (%s), revision: digital %d, analog %d",
+		 id, bcm590xx_names[id], bcm590xx->rev_digital, bcm590xx->rev_analog);
+
+	return 0;
+}
+
 static int bcm590xx_i2c_probe(struct i2c_client *i2c_pri)
 {
 	struct bcm590xx *bcm590xx;
@@ -50,6 +100,8 @@ static int bcm590xx_i2c_probe(struct i2c_client *i2c_pri)
 	bcm590xx->dev = &i2c_pri->dev;
 	bcm590xx->i2c_pri = i2c_pri;
 
+	bcm590xx->pmu_id = (uintptr_t) of_device_get_match_data(bcm590xx->dev);
+
 	bcm590xx->regmap_pri = devm_regmap_init_i2c(i2c_pri,
 						 &bcm590xx_regmap_config_pri);
 	if (IS_ERR(bcm590xx->regmap_pri)) {
@@ -76,6 +128,10 @@ static int bcm590xx_i2c_probe(struct i2c_client *i2c_pri)
 		goto err;
 	}
 
+	ret = bcm590xx_parse_version(bcm590xx);
+	if (ret)
+		goto err;
+
 	ret = devm_mfd_add_devices(&i2c_pri->dev, -1, bcm590xx_devs,
 				   ARRAY_SIZE(bcm590xx_devs), NULL, 0, NULL);
 	if (ret < 0) {
@@ -91,12 +147,20 @@ err:
 }
 
 static const struct of_device_id bcm590xx_of_match[] = {
-	{ .compatible = "brcm,bcm59056" },
+	{
+		.compatible = "brcm,bcm59054",
+		.data = (void *)BCM590XX_PMUID_BCM59054,
+	},
+	{
+		.compatible = "brcm,bcm59056",
+		.data = (void *)BCM590XX_PMUID_BCM59056,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, bcm590xx_of_match);
 
 static const struct i2c_device_id bcm590xx_i2c_id[] = {
+	{ "bcm59054" },
 	{ "bcm59056" },
 	{ }
 };
diff --git a/drivers/mfd/exynos-lpass.c b/drivers/mfd/exynos-lpass.c
index 6a585173230b..44797001a432 100644
--- a/drivers/mfd/exynos-lpass.c
+++ b/drivers/mfd/exynos-lpass.c
@@ -104,11 +104,22 @@ static const struct regmap_config exynos_lpass_reg_conf = {
 	.fast_io	= true,
 };
 
+static void exynos_lpass_disable_lpass(void *data)
+{
+	struct platform_device *pdev = data;
+	struct exynos_lpass *lpass = platform_get_drvdata(pdev);
+
+	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		exynos_lpass_disable(lpass);
+}
+
 static int exynos_lpass_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct exynos_lpass *lpass;
 	void __iomem *base_top;
+	int ret;
 
 	lpass = devm_kzalloc(dev, sizeof(*lpass), GFP_KERNEL);
 	if (!lpass)
@@ -122,8 +133,8 @@ static int exynos_lpass_probe(struct platform_device *pdev)
 	if (IS_ERR(lpass->sfr0_clk))
 		return PTR_ERR(lpass->sfr0_clk);
 
-	lpass->top = regmap_init_mmio(dev, base_top,
-					&exynos_lpass_reg_conf);
+	lpass->top = devm_regmap_init_mmio(dev, base_top,
+					   &exynos_lpass_reg_conf);
 	if (IS_ERR(lpass->top)) {
 		dev_err(dev, "LPASS top regmap initialization failed\n");
 		return PTR_ERR(lpass->top);
@@ -134,18 +145,11 @@ static int exynos_lpass_probe(struct platform_device *pdev)
 	pm_runtime_enable(dev);
 	exynos_lpass_enable(lpass);
 
-	return devm_of_platform_populate(dev);
-}
-
-static void exynos_lpass_remove(struct platform_device *pdev)
-{
-	struct exynos_lpass *lpass = platform_get_drvdata(pdev);
+	ret = devm_add_action_or_reset(dev, exynos_lpass_disable_lpass, pdev);
+	if (ret)
+		return ret;
 
-	exynos_lpass_disable(lpass);
-	pm_runtime_disable(&pdev->dev);
-	if (!pm_runtime_status_suspended(&pdev->dev))
-		exynos_lpass_disable(lpass);
-	regmap_exit(lpass->top);
+	return devm_of_platform_populate(dev);
 }
 
 static int __maybe_unused exynos_lpass_suspend(struct device *dev)
@@ -185,7 +189,6 @@ static struct platform_driver exynos_lpass_driver = {
 		.of_match_table	= exynos_lpass_of_match,
 	},
 	.probe	= exynos_lpass_probe,
-	.remove	= exynos_lpass_remove,
 };
 module_platform_driver(exynos_lpass_driver);
 
diff --git a/drivers/mfd/max14577.c b/drivers/mfd/max14577.c
index 6fce79ec2dc6..7e7e8af9af22 100644
--- a/drivers/mfd/max14577.c
+++ b/drivers/mfd/max14577.c
@@ -456,6 +456,7 @@ static void max14577_i2c_remove(struct i2c_client *i2c)
 {
 	struct max14577 *max14577 = i2c_get_clientdata(i2c);
 
+	device_init_wakeup(max14577->dev, false);
 	mfd_remove_devices(max14577->dev);
 	regmap_del_irq_chip(max14577->irq, max14577->irq_data);
 	if (max14577->dev_type == MAXIM_DEVICE_TYPE_MAX77836)
diff --git a/drivers/mfd/max77541.c b/drivers/mfd/max77541.c
index d77c31c86e43..f91b4f5373ce 100644
--- a/drivers/mfd/max77541.c
+++ b/drivers/mfd/max77541.c
@@ -152,7 +152,7 @@ static int max77541_pmic_setup(struct device *dev)
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to initialize IRQ\n");
 
-	ret = device_init_wakeup(dev, true);
+	ret = devm_device_init_wakeup(dev);
 	if (ret)
 		return dev_err_probe(dev, ret, "Unable to init wakeup\n");
 
diff --git a/drivers/mfd/max77705.c b/drivers/mfd/max77705.c
index 60c457c21d95..6b263bacb8c2 100644
--- a/drivers/mfd/max77705.c
+++ b/drivers/mfd/max77705.c
@@ -131,7 +131,9 @@ static int max77705_i2c_probe(struct i2c_client *i2c)
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to register child devices\n");
 
-	device_init_wakeup(dev, true);
+	ret = devm_device_init_wakeup(dev);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to init wakeup\n");
 
 	return 0;
 }
diff --git a/drivers/mfd/max8925-i2c.c b/drivers/mfd/max8925-i2c.c
index 556aea7ec0a0..ab19ff0c7867 100644
--- a/drivers/mfd/max8925-i2c.c
+++ b/drivers/mfd/max8925-i2c.c
@@ -201,6 +201,7 @@ static void max8925_remove(struct i2c_client *client)
 	struct max8925_chip *chip = i2c_get_clientdata(client);
 
 	max8925_device_exit(chip);
+	device_init_wakeup(&client->dev, false);
 	i2c_unregister_device(chip->adc);
 	i2c_unregister_device(chip->rtc);
 }
diff --git a/drivers/mfd/rohm-bd96801.c b/drivers/mfd/rohm-bd96801.c
index 60ec8db790a7..66fa017ad568 100644
--- a/drivers/mfd/rohm-bd96801.c
+++ b/drivers/mfd/rohm-bd96801.c
@@ -38,108 +38,172 @@
 #include <linux/types.h>
 
 #include <linux/mfd/rohm-bd96801.h>
+#include <linux/mfd/rohm-bd96802.h>
 #include <linux/mfd/rohm-generic.h>
 
-static const struct resource regulator_errb_irqs[] = {
-	DEFINE_RES_IRQ_NAMED(BD96801_OTP_ERR_STAT, "bd96801-otp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_DBIST_ERR_STAT, "bd96801-dbist-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_EEP_ERR_STAT, "bd96801-eep-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_ABIST_ERR_STAT, "bd96801-abist-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_PRSTB_ERR_STAT, "bd96801-prstb-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_DRMOS1_ERR_STAT, "bd96801-drmoserr1"),
-	DEFINE_RES_IRQ_NAMED(BD96801_DRMOS2_ERR_STAT, "bd96801-drmoserr2"),
-	DEFINE_RES_IRQ_NAMED(BD96801_SLAVE_ERR_STAT, "bd96801-slave-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_VREF_ERR_STAT, "bd96801-vref-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_TSD_ERR_STAT, "bd96801-tsd"),
-	DEFINE_RES_IRQ_NAMED(BD96801_UVLO_ERR_STAT, "bd96801-uvlo-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_OVLO_ERR_STAT, "bd96801-ovlo-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_OSC_ERR_STAT, "bd96801-osc-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_PON_ERR_STAT, "bd96801-pon-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_POFF_ERR_STAT, "bd96801-poff-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_CMD_SHDN_ERR_STAT, "bd96801-cmd-shdn-err"),
+struct bd968xx {
+	const struct resource *errb_irqs;
+	const struct resource *intb_irqs;
+	int num_errb_irqs;
+	int num_intb_irqs;
+	const struct regmap_irq_chip *errb_irq_chip;
+	const struct regmap_irq_chip *intb_irq_chip;
+	const struct regmap_config *regmap_config;
+	struct mfd_cell *cells;
+	int num_cells;
+	int unlock_reg;
+	int unlock_val;
+};
+
+static const struct resource bd96801_reg_errb_irqs[] = {
+	DEFINE_RES_IRQ_NAMED(BD96801_OTP_ERR_STAT, "otp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_DBIST_ERR_STAT, "dbist-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_EEP_ERR_STAT, "eep-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_ABIST_ERR_STAT, "abist-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_PRSTB_ERR_STAT, "prstb-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_DRMOS1_ERR_STAT, "drmoserr1"),
+	DEFINE_RES_IRQ_NAMED(BD96801_DRMOS2_ERR_STAT, "drmoserr2"),
+	DEFINE_RES_IRQ_NAMED(BD96801_SLAVE_ERR_STAT, "slave-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_VREF_ERR_STAT, "vref-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_TSD_ERR_STAT, "tsd"),
+	DEFINE_RES_IRQ_NAMED(BD96801_UVLO_ERR_STAT, "uvlo-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_OVLO_ERR_STAT, "ovlo-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_OSC_ERR_STAT, "osc-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_PON_ERR_STAT, "pon-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_POFF_ERR_STAT, "poff-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_CMD_SHDN_ERR_STAT, "cmd-shdn-err"),
 
 	DEFINE_RES_IRQ_NAMED(BD96801_INT_PRSTB_WDT_ERR, "bd96801-prstb-wdt-err"),
 	DEFINE_RES_IRQ_NAMED(BD96801_INT_CHIP_IF_ERR, "bd96801-chip-if-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_INT_SHDN_ERR_STAT, "bd96801-int-shdn-err"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_PVIN_ERR_STAT, "bd96801-buck1-pvin-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_OVP_ERR_STAT, "bd96801-buck1-ovp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_UVP_ERR_STAT, "bd96801-buck1-uvp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_SHDN_ERR_STAT, "bd96801-buck1-shdn-err"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_PVIN_ERR_STAT, "bd96801-buck2-pvin-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_OVP_ERR_STAT, "bd96801-buck2-ovp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_UVP_ERR_STAT, "bd96801-buck2-uvp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_SHDN_ERR_STAT, "bd96801-buck2-shdn-err"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_PVIN_ERR_STAT, "bd96801-buck3-pvin-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_OVP_ERR_STAT, "bd96801-buck3-ovp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_UVP_ERR_STAT, "bd96801-buck3-uvp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_SHDN_ERR_STAT, "bd96801-buck3-shdn-err"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_PVIN_ERR_STAT, "bd96801-buck4-pvin-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_OVP_ERR_STAT, "bd96801-buck4-ovp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_UVP_ERR_STAT, "bd96801-buck4-uvp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_SHDN_ERR_STAT, "bd96801-buck4-shdn-err"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_PVIN_ERR_STAT, "bd96801-ldo5-pvin-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_OVP_ERR_STAT, "bd96801-ldo5-ovp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_UVP_ERR_STAT, "bd96801-ldo5-uvp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_SHDN_ERR_STAT, "bd96801-ldo5-shdn-err"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_PVIN_ERR_STAT, "bd96801-ldo6-pvin-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_OVP_ERR_STAT, "bd96801-ldo6-ovp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_UVP_ERR_STAT, "bd96801-ldo6-uvp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_SHDN_ERR_STAT, "bd96801-ldo6-shdn-err"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_PVIN_ERR_STAT, "bd96801-ldo7-pvin-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_OVP_ERR_STAT, "bd96801-ldo7-ovp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_UVP_ERR_STAT, "bd96801-ldo7-uvp-err"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_SHDN_ERR_STAT, "bd96801-ldo7-shdn-err"),
-};
-
-static const struct resource regulator_intb_irqs[] = {
-	DEFINE_RES_IRQ_NAMED(BD96801_TW_STAT, "bd96801-core-thermal"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_OCPH_STAT, "bd96801-buck1-overcurr-h"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_OCPL_STAT, "bd96801-buck1-overcurr-l"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_OCPN_STAT, "bd96801-buck1-overcurr-n"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_OVD_STAT, "bd96801-buck1-overvolt"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_UVD_STAT, "bd96801-buck1-undervolt"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_TW_CH_STAT, "bd96801-buck1-thermal"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_OCPH_STAT, "bd96801-buck2-overcurr-h"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_OCPL_STAT, "bd96801-buck2-overcurr-l"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_OCPN_STAT, "bd96801-buck2-overcurr-n"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_OVD_STAT, "bd96801-buck2-overvolt"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_UVD_STAT, "bd96801-buck2-undervolt"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_TW_CH_STAT, "bd96801-buck2-thermal"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_OCPH_STAT, "bd96801-buck3-overcurr-h"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_OCPL_STAT, "bd96801-buck3-overcurr-l"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_OCPN_STAT, "bd96801-buck3-overcurr-n"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_OVD_STAT, "bd96801-buck3-overvolt"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_UVD_STAT, "bd96801-buck3-undervolt"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_TW_CH_STAT, "bd96801-buck3-thermal"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_OCPH_STAT, "bd96801-buck4-overcurr-h"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_OCPL_STAT, "bd96801-buck4-overcurr-l"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_OCPN_STAT, "bd96801-buck4-overcurr-n"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_OVD_STAT, "bd96801-buck4-overvolt"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_UVD_STAT, "bd96801-buck4-undervolt"),
-	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_TW_CH_STAT, "bd96801-buck4-thermal"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_OCPH_STAT, "bd96801-ldo5-overcurr"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_OVD_STAT, "bd96801-ldo5-overvolt"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_UVD_STAT, "bd96801-ldo5-undervolt"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_OCPH_STAT, "bd96801-ldo6-overcurr"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_OVD_STAT, "bd96801-ldo6-overvolt"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_UVD_STAT, "bd96801-ldo6-undervolt"),
-
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_OCPH_STAT, "bd96801-ldo7-overcurr"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_OVD_STAT, "bd96801-ldo7-overvolt"),
-	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_UVD_STAT, "bd96801-ldo7-undervolt"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_INT_SHDN_ERR_STAT, "int-shdn-err"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_PVIN_ERR_STAT, "buck1-pvin-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_OVP_ERR_STAT, "buck1-ovp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_UVP_ERR_STAT, "buck1-uvp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_SHDN_ERR_STAT, "buck1-shdn-err"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_PVIN_ERR_STAT, "buck2-pvin-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_OVP_ERR_STAT, "buck2-ovp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_UVP_ERR_STAT, "buck2-uvp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_SHDN_ERR_STAT, "buck2-shdn-err"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_PVIN_ERR_STAT, "buck3-pvin-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_OVP_ERR_STAT, "buck3-ovp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_UVP_ERR_STAT, "buck3-uvp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_SHDN_ERR_STAT, "buck3-shdn-err"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_PVIN_ERR_STAT, "buck4-pvin-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_OVP_ERR_STAT, "buck4-ovp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_UVP_ERR_STAT, "buck4-uvp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_SHDN_ERR_STAT, "buck4-shdn-err"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_PVIN_ERR_STAT, "ldo5-pvin-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_OVP_ERR_STAT, "ldo5-ovp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_UVP_ERR_STAT, "ldo5-uvp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_SHDN_ERR_STAT, "ldo5-shdn-err"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_PVIN_ERR_STAT, "ldo6-pvin-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_OVP_ERR_STAT, "ldo6-ovp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_UVP_ERR_STAT, "ldo6-uvp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_SHDN_ERR_STAT, "ldo6-shdn-err"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_PVIN_ERR_STAT, "ldo7-pvin-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_OVP_ERR_STAT, "ldo7-ovp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_UVP_ERR_STAT, "ldo7-uvp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_SHDN_ERR_STAT, "ldo7-shdn-err"),
+};
+
+static const struct resource bd96802_reg_errb_irqs[] = {
+	DEFINE_RES_IRQ_NAMED(BD96802_OTP_ERR_STAT, "otp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_DBIST_ERR_STAT, "dbist-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_EEP_ERR_STAT, "eep-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_ABIST_ERR_STAT, "abist-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_PRSTB_ERR_STAT, "prstb-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_DRMOS1_ERR_STAT, "drmoserr1"),
+	DEFINE_RES_IRQ_NAMED(BD96802_DRMOS1_ERR_STAT, "drmoserr2"),
+	DEFINE_RES_IRQ_NAMED(BD96802_SLAVE_ERR_STAT, "slave-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_VREF_ERR_STAT, "vref-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_TSD_ERR_STAT, "tsd"),
+	DEFINE_RES_IRQ_NAMED(BD96802_UVLO_ERR_STAT, "uvlo-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_OVLO_ERR_STAT, "ovlo-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_OSC_ERR_STAT, "osc-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_PON_ERR_STAT, "pon-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_POFF_ERR_STAT, "poff-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_CMD_SHDN_ERR_STAT, "cmd-shdn-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_INT_SHDN_ERR_STAT, "int-shdn-err"),
+
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK1_PVIN_ERR_STAT, "buck1-pvin-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK1_OVP_ERR_STAT, "buck1-ovp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK1_UVP_ERR_STAT, "buck1-uvp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK1_SHDN_ERR_STAT, "buck1-shdn-err"),
+
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK2_PVIN_ERR_STAT, "buck2-pvin-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK2_OVP_ERR_STAT, "buck2-ovp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK2_UVP_ERR_STAT, "buck2-uvp-err"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK2_SHDN_ERR_STAT, "buck2-shdn-err"),
+};
+
+static const struct resource bd96801_reg_intb_irqs[] = {
+	DEFINE_RES_IRQ_NAMED(BD96801_TW_STAT, "core-thermal"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_OCPH_STAT, "buck1-overcurr-h"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_OCPL_STAT, "buck1-overcurr-l"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_OCPN_STAT, "buck1-overcurr-n"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_OVD_STAT, "buck1-overvolt"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_UVD_STAT, "buck1-undervolt"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK1_TW_CH_STAT, "buck1-thermal"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_OCPH_STAT, "buck2-overcurr-h"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_OCPL_STAT, "buck2-overcurr-l"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_OCPN_STAT, "buck2-overcurr-n"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_OVD_STAT, "buck2-overvolt"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_UVD_STAT, "buck2-undervolt"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK2_TW_CH_STAT, "buck2-thermal"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_OCPH_STAT, "buck3-overcurr-h"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_OCPL_STAT, "buck3-overcurr-l"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_OCPN_STAT, "buck3-overcurr-n"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_OVD_STAT, "buck3-overvolt"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_UVD_STAT, "buck3-undervolt"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK3_TW_CH_STAT, "buck3-thermal"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_OCPH_STAT, "buck4-overcurr-h"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_OCPL_STAT, "buck4-overcurr-l"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_OCPN_STAT, "buck4-overcurr-n"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_OVD_STAT, "buck4-overvolt"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_UVD_STAT, "buck4-undervolt"),
+	DEFINE_RES_IRQ_NAMED(BD96801_BUCK4_TW_CH_STAT, "buck4-thermal"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_OCPH_STAT, "ldo5-overcurr"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_OVD_STAT, "ldo5-overvolt"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO5_UVD_STAT, "ldo5-undervolt"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_OCPH_STAT, "ldo6-overcurr"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_OVD_STAT, "ldo6-overvolt"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO6_UVD_STAT, "ldo6-undervolt"),
+
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_OCPH_STAT, "ldo7-overcurr"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_OVD_STAT, "ldo7-overvolt"),
+	DEFINE_RES_IRQ_NAMED(BD96801_LDO7_UVD_STAT, "ldo7-undervolt"),
+};
+
+static const struct resource bd96802_reg_intb_irqs[] = {
+	DEFINE_RES_IRQ_NAMED(BD96802_TW_STAT, "core-thermal"),
+
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK1_OCPH_STAT, "buck1-overcurr-h"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK1_OCPL_STAT, "buck1-overcurr-l"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK1_OCPN_STAT, "buck1-overcurr-n"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK1_OVD_STAT, "buck1-overvolt"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK1_UVD_STAT, "buck1-undervolt"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK1_TW_CH_STAT, "buck1-thermal"),
+
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK2_OCPH_STAT, "buck2-overcurr-h"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK2_OCPL_STAT, "buck2-overcurr-l"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK2_OCPN_STAT, "buck2-overcurr-n"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK2_OVD_STAT, "buck2-overvolt"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK2_UVD_STAT, "buck2-undervolt"),
+	DEFINE_RES_IRQ_NAMED(BD96802_BUCK2_TW_CH_STAT, "buck2-thermal"),
 };
 
 enum {
@@ -152,6 +216,20 @@ static struct mfd_cell bd96801_cells[] = {
 	[REGULATOR_CELL] = { .name = "bd96801-regulator", },
 };
 
+static struct mfd_cell bd96802_cells[] = {
+	[WDG_CELL] = { .name = "bd96801-wdt", },
+	[REGULATOR_CELL] = { .name = "bd96802-regulator", },
+};
+static struct mfd_cell bd96805_cells[] = {
+	[WDG_CELL] = { .name = "bd96801-wdt", },
+	[REGULATOR_CELL] = { .name = "bd96805-regulator", },
+};
+
+static struct mfd_cell bd96806_cells[] = {
+	[WDG_CELL] = { .name = "bd96806-wdt", },
+	[REGULATOR_CELL] = { .name = "bd96806-regulator", },
+};
+
 static const struct regmap_range bd96801_volatile_ranges[] = {
 	/* Status registers */
 	regmap_reg_range(BD96801_REG_WD_FEED, BD96801_REG_WD_FAILCOUNT),
@@ -169,11 +247,28 @@ static const struct regmap_range bd96801_volatile_ranges[] = {
 	regmap_reg_range(BD96801_LDO5_VOL_LVL_REG, BD96801_LDO7_VOL_LVL_REG),
 };
 
-static const struct regmap_access_table volatile_regs = {
+static const struct regmap_range bd96802_volatile_ranges[] = {
+	/* Status regs */
+	regmap_reg_range(BD96801_REG_WD_FEED, BD96801_REG_WD_FAILCOUNT),
+	regmap_reg_range(BD96801_REG_WD_ASK, BD96801_REG_WD_ASK),
+	regmap_reg_range(BD96801_REG_WD_STATUS, BD96801_REG_WD_STATUS),
+	regmap_reg_range(BD96801_REG_PMIC_STATE, BD96801_REG_INT_BUCK2_ERRB),
+	regmap_reg_range(BD96801_REG_INT_SYS_INTB, BD96801_REG_INT_BUCK2_INTB),
+	/* Registers which do not update value unless PMIC is in STBY */
+	regmap_reg_range(BD96801_REG_SSCG_CTRL, BD96801_REG_SHD_INTB),
+	regmap_reg_range(BD96801_REG_BUCK_OVP, BD96801_REG_BOOT_OVERTIME),
+};
+
+static const struct regmap_access_table bd96801_volatile_regs = {
 	.yes_ranges = bd96801_volatile_ranges,
 	.n_yes_ranges = ARRAY_SIZE(bd96801_volatile_ranges),
 };
 
+static const struct regmap_access_table bd96802_volatile_regs = {
+	.yes_ranges = bd96802_volatile_ranges,
+	.n_yes_ranges = ARRAY_SIZE(bd96802_volatile_ranges),
+};
+
 /*
  * For ERRB we need main register bit mapping as bit(0) indicates active IRQ
  * in one of the first 3 sub IRQ registers, For INTB we can use default 1 to 1
@@ -188,7 +283,7 @@ static unsigned int bit5_offsets[] = {7};	/* LDO 5 stat */
 static unsigned int bit6_offsets[] = {8};	/* LDO 6 stat */
 static unsigned int bit7_offsets[] = {9};	/* LDO 7 stat */
 
-static const struct regmap_irq_sub_irq_map errb_sub_irq_offsets[] = {
+static const struct regmap_irq_sub_irq_map bd96801_errb_sub_irq_offsets[] = {
 	REGMAP_IRQ_MAIN_REG_OFFSET(bit0_offsets),
 	REGMAP_IRQ_MAIN_REG_OFFSET(bit1_offsets),
 	REGMAP_IRQ_MAIN_REG_OFFSET(bit2_offsets),
@@ -199,6 +294,12 @@ static const struct regmap_irq_sub_irq_map errb_sub_irq_offsets[] = {
 	REGMAP_IRQ_MAIN_REG_OFFSET(bit7_offsets),
 };
 
+static const struct regmap_irq_sub_irq_map bd96802_errb_sub_irq_offsets[] = {
+	REGMAP_IRQ_MAIN_REG_OFFSET(bit0_offsets),
+	REGMAP_IRQ_MAIN_REG_OFFSET(bit1_offsets),
+	REGMAP_IRQ_MAIN_REG_OFFSET(bit2_offsets),
+};
+
 static const struct regmap_irq bd96801_errb_irqs[] = {
 	/* Reg 0x52 Fatal ERRB1 */
 	REGMAP_IRQ_REG(BD96801_OTP_ERR_STAT, 0, BD96801_OTP_ERR_MASK),
@@ -259,6 +360,39 @@ static const struct regmap_irq bd96801_errb_irqs[] = {
 	REGMAP_IRQ_REG(BD96801_LDO7_SHDN_ERR_STAT, 9, BD96801_OUT_SHDN_ERR_MASK),
 };
 
+static const struct regmap_irq bd96802_errb_irqs[] = {
+	/* Reg 0x52 Fatal ERRB1 */
+	REGMAP_IRQ_REG(BD96802_OTP_ERR_STAT, 0, BD96801_OTP_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_DBIST_ERR_STAT, 0, BD96801_DBIST_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_EEP_ERR_STAT, 0, BD96801_EEP_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_ABIST_ERR_STAT, 0, BD96801_ABIST_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_PRSTB_ERR_STAT, 0, BD96801_PRSTB_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_DRMOS1_ERR_STAT, 0, BD96801_DRMOS1_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_DRMOS2_ERR_STAT, 0, BD96801_DRMOS2_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_SLAVE_ERR_STAT, 0, BD96801_SLAVE_ERR_MASK),
+	/* 0x53 Fatal ERRB2 */
+	REGMAP_IRQ_REG(BD96802_VREF_ERR_STAT, 1, BD96801_VREF_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_TSD_ERR_STAT, 1, BD96801_TSD_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_UVLO_ERR_STAT, 1, BD96801_UVLO_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_OVLO_ERR_STAT, 1, BD96801_OVLO_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_OSC_ERR_STAT, 1, BD96801_OSC_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_PON_ERR_STAT, 1, BD96801_PON_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_POFF_ERR_STAT, 1, BD96801_POFF_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_CMD_SHDN_ERR_STAT, 1, BD96801_CMD_SHDN_ERR_MASK),
+	/* 0x54 Fatal INTB shadowed to ERRB */
+	REGMAP_IRQ_REG(BD96802_INT_SHDN_ERR_STAT, 2, BD96801_INT_SHDN_ERR_MASK),
+	/* Reg 0x55 BUCK1 ERR IRQs */
+	REGMAP_IRQ_REG(BD96802_BUCK1_PVIN_ERR_STAT, 3, BD96801_OUT_PVIN_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK1_OVP_ERR_STAT, 3, BD96801_OUT_OVP_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK1_UVP_ERR_STAT, 3, BD96801_OUT_UVP_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK1_SHDN_ERR_STAT, 3, BD96801_OUT_SHDN_ERR_MASK),
+	/* Reg 0x56 BUCK2 ERR IRQs */
+	REGMAP_IRQ_REG(BD96802_BUCK2_PVIN_ERR_STAT, 4, BD96801_OUT_PVIN_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK2_OVP_ERR_STAT, 4, BD96801_OUT_OVP_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK2_UVP_ERR_STAT, 4, BD96801_OUT_UVP_ERR_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK2_SHDN_ERR_STAT, 4, BD96801_OUT_SHDN_ERR_MASK),
+};
+
 static const struct regmap_irq bd96801_intb_irqs[] = {
 	/* STATUS SYSTEM INTB */
 	REGMAP_IRQ_REG(BD96801_TW_STAT, 0, BD96801_TW_STAT_MASK),
@@ -307,6 +441,69 @@ static const struct regmap_irq bd96801_intb_irqs[] = {
 	REGMAP_IRQ_REG(BD96801_LDO7_UVD_STAT, 7, BD96801_LDO_UVD_STAT_MASK),
 };
 
+static const struct regmap_irq bd96802_intb_irqs[] = {
+	/* STATUS SYSTEM INTB */
+	REGMAP_IRQ_REG(BD96802_TW_STAT, 0, BD96801_TW_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_WDT_ERR_STAT, 0, BD96801_WDT_ERR_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_I2C_ERR_STAT, 0, BD96801_I2C_ERR_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_CHIP_IF_ERR_STAT, 0, BD96801_CHIP_IF_ERR_STAT_MASK),
+	/* STATUS BUCK1 INTB */
+	REGMAP_IRQ_REG(BD96802_BUCK1_OCPH_STAT, 1, BD96801_BUCK_OCPH_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK1_OCPL_STAT, 1, BD96801_BUCK_OCPL_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK1_OCPN_STAT, 1, BD96801_BUCK_OCPN_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK1_OVD_STAT, 1, BD96801_BUCK_OVD_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK1_UVD_STAT, 1, BD96801_BUCK_UVD_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK1_TW_CH_STAT, 1, BD96801_BUCK_TW_CH_STAT_MASK),
+	/* BUCK 2 INTB */
+	REGMAP_IRQ_REG(BD96802_BUCK2_OCPH_STAT, 2, BD96801_BUCK_OCPH_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK2_OCPL_STAT, 2, BD96801_BUCK_OCPL_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK2_OCPN_STAT, 2, BD96801_BUCK_OCPN_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK2_OVD_STAT, 2, BD96801_BUCK_OVD_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK2_UVD_STAT, 2, BD96801_BUCK_UVD_STAT_MASK),
+	REGMAP_IRQ_REG(BD96802_BUCK2_TW_CH_STAT, 2, BD96801_BUCK_TW_CH_STAT_MASK),
+};
+
+/*
+ * The IRQ stuff is a bit hairy. The BD96801 / BD96802 provide two physical
+ * IRQ lines called INTB and ERRB. They share the same main status register.
+ *
+ * For ERRB, mapping from main status to sub-status is such that the
+ * 'global' faults are mapped to first 3 sub-status registers - and indicated
+ * by the first bit[0] in main status reg.
+ *
+ * Rest of the status registers are for indicating stuff for individual
+ * regulators, 1 sub register / regulator and 1 main status register bit /
+ * regulator, starting from bit[1].
+ *
+ * Eg, regulator specific stuff has 1 to 1 mapping from main-status to sub
+ * registers but 'global' ERRB IRQs require mapping from main status bit[0] to
+ * 3 status registers.
+ *
+ * Furthermore, the BD96801 has 7 regulators where the BD96802 has only 2.
+ *
+ * INTB has only 1 sub status register for 'global' events and then own sub
+ * status register for each of the regulators. So, for INTB we have direct
+ * 1 to 1 mapping - BD96801 just having 5 register and 5 main status bits
+ * more than the BD96802.
+ *
+ * Sharing the main status bits could be a problem if we had both INTB and
+ * ERRB IRQs asserted but for different sub-status offsets. This might lead
+ * IRQ controller code to go read a sub status register which indicates no
+ * active IRQs. I assume this occurring repeteadly might lead the IRQ to be
+ * disabled by core as a result of repeteadly returned IRQ_NONEs.
+ *
+ * I don't consider this as a fatal problem for now because:
+ *	a) Having ERRB asserted leads to PMIC fault state which will kill
+ *	   the SoC powered by the PMIC. (So, relevant only for potential
+ *	   case of not powering the processor with this PMIC).
+ *	b) Having ERRB set without having respective INTB is unlikely
+ *	   (haven't actually verified this).
+ *
+ * So, let's proceed with main status enabled for both INTB and ERRB. We can
+ * later disable main-status usage on systems where this ever proves to be
+ * a problem.
+ */
+
 static const struct regmap_irq_chip bd96801_irq_chip_errb = {
 	.name = "bd96801-irq-errb",
 	.domain_suffix = "errb",
@@ -320,7 +517,23 @@ static const struct regmap_irq_chip bd96801_irq_chip_errb = {
 	.init_ack_masked = true,
 	.num_regs = 10,
 	.irq_reg_stride = 1,
-	.sub_reg_offsets = &errb_sub_irq_offsets[0],
+	.sub_reg_offsets = &bd96801_errb_sub_irq_offsets[0],
+};
+
+static const struct regmap_irq_chip bd96802_irq_chip_errb = {
+	.name = "bd96802-irq-errb",
+	.domain_suffix = "errb",
+	.main_status = BD96801_REG_INT_MAIN,
+	.num_main_regs = 1,
+	.irqs = &bd96802_errb_irqs[0],
+	.num_irqs = ARRAY_SIZE(bd96802_errb_irqs),
+	.status_base = BD96801_REG_INT_SYS_ERRB1,
+	.mask_base = BD96801_REG_MASK_SYS_ERRB,
+	.ack_base = BD96801_REG_INT_SYS_ERRB1,
+	.init_ack_masked = true,
+	.num_regs = 5,
+	.irq_reg_stride = 1,
+	.sub_reg_offsets = &bd96802_errb_sub_irq_offsets[0],
 };
 
 static const struct regmap_irq_chip bd96801_irq_chip_intb = {
@@ -338,25 +551,124 @@ static const struct regmap_irq_chip bd96801_irq_chip_intb = {
 	.irq_reg_stride = 1,
 };
 
+static const struct regmap_irq_chip bd96802_irq_chip_intb = {
+	.name = "bd96802-irq-intb",
+	.domain_suffix = "intb",
+	.main_status = BD96801_REG_INT_MAIN,
+	.num_main_regs = 1,
+	.irqs = &bd96802_intb_irqs[0],
+	.num_irqs = ARRAY_SIZE(bd96802_intb_irqs),
+	.status_base = BD96801_REG_INT_SYS_INTB,
+	.mask_base = BD96801_REG_MASK_SYS_INTB,
+	.ack_base = BD96801_REG_INT_SYS_INTB,
+	.init_ack_masked = true,
+	.num_regs = 3,
+	.irq_reg_stride = 1,
+};
+
 static const struct regmap_config bd96801_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
-	.volatile_table = &volatile_regs,
+	.volatile_table = &bd96801_volatile_regs,
+	.cache_type = REGCACHE_MAPLE,
+};
+
+static const struct regmap_config bd96802_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.volatile_table = &bd96802_volatile_regs,
 	.cache_type = REGCACHE_MAPLE,
 };
 
+static const struct bd968xx bd96801_data = {
+	.errb_irqs = bd96801_reg_errb_irqs,
+	.intb_irqs = bd96801_reg_intb_irqs,
+	.num_errb_irqs = ARRAY_SIZE(bd96801_reg_errb_irqs),
+	.num_intb_irqs = ARRAY_SIZE(bd96801_reg_intb_irqs),
+	.errb_irq_chip = &bd96801_irq_chip_errb,
+	.intb_irq_chip = &bd96801_irq_chip_intb,
+	.regmap_config = &bd96801_regmap_config,
+	.cells = bd96801_cells,
+	.num_cells = ARRAY_SIZE(bd96801_cells),
+	.unlock_reg = BD96801_LOCK_REG,
+	.unlock_val = BD96801_UNLOCK,
+};
+
+static const struct bd968xx bd96802_data = {
+	.errb_irqs = bd96802_reg_errb_irqs,
+	.intb_irqs = bd96802_reg_intb_irqs,
+	.num_errb_irqs = ARRAY_SIZE(bd96802_reg_errb_irqs),
+	.num_intb_irqs = ARRAY_SIZE(bd96802_reg_intb_irqs),
+	.errb_irq_chip = &bd96802_irq_chip_errb,
+	.intb_irq_chip = &bd96802_irq_chip_intb,
+	.regmap_config = &bd96802_regmap_config,
+	.cells = bd96802_cells,
+	.num_cells = ARRAY_SIZE(bd96802_cells),
+	.unlock_reg = BD96801_LOCK_REG,
+	.unlock_val = BD96801_UNLOCK,
+};
+
+static const struct bd968xx bd96805_data = {
+	.errb_irqs = bd96801_reg_errb_irqs,
+	.intb_irqs = bd96801_reg_intb_irqs,
+	.num_errb_irqs = ARRAY_SIZE(bd96801_reg_errb_irqs),
+	.num_intb_irqs = ARRAY_SIZE(bd96801_reg_intb_irqs),
+	.errb_irq_chip = &bd96801_irq_chip_errb,
+	.intb_irq_chip = &bd96801_irq_chip_intb,
+	.regmap_config = &bd96801_regmap_config,
+	.cells = bd96805_cells,
+	.num_cells = ARRAY_SIZE(bd96805_cells),
+	.unlock_reg = BD96801_LOCK_REG,
+	.unlock_val = BD96801_UNLOCK,
+};
+
+static struct bd968xx bd96806_data = {
+	.errb_irqs = bd96802_reg_errb_irqs,
+	.intb_irqs = bd96802_reg_intb_irqs,
+	.num_errb_irqs = ARRAY_SIZE(bd96802_reg_errb_irqs),
+	.num_intb_irqs = ARRAY_SIZE(bd96802_reg_intb_irqs),
+	.errb_irq_chip = &bd96802_irq_chip_errb,
+	.intb_irq_chip = &bd96802_irq_chip_intb,
+	.regmap_config = &bd96802_regmap_config,
+	.cells = bd96806_cells,
+	.num_cells = ARRAY_SIZE(bd96806_cells),
+	.unlock_reg = BD96801_LOCK_REG,
+	.unlock_val = BD96801_UNLOCK,
+};
+
 static int bd96801_i2c_probe(struct i2c_client *i2c)
 {
 	struct regmap_irq_chip_data *intb_irq_data, *errb_irq_data;
 	struct irq_domain *intb_domain, *errb_domain;
+	const struct bd968xx *ddata;
 	const struct fwnode_handle *fwnode;
 	struct resource *regulator_res;
 	struct resource wdg_irq;
 	struct regmap *regmap;
-	int intb_irq, errb_irq, num_intb, num_errb = 0;
+	int intb_irq, errb_irq, num_errb = 0;
 	int num_regu_irqs, wdg_irq_no;
+	unsigned int chip_type;
 	int i, ret;
 
+	chip_type = (unsigned int)(uintptr_t)device_get_match_data(&i2c->dev);
+	switch (chip_type) {
+	case ROHM_CHIP_TYPE_BD96801:
+		ddata = &bd96801_data;
+		break;
+	case ROHM_CHIP_TYPE_BD96802:
+		ddata = &bd96802_data;
+		break;
+	case ROHM_CHIP_TYPE_BD96805:
+		ddata = &bd96805_data;
+		break;
+	case ROHM_CHIP_TYPE_BD96806:
+		ddata = &bd96806_data;
+		break;
+	default:
+		dev_err(&i2c->dev, "Unknown IC\n");
+		return -EINVAL;
+	}
+
 	fwnode = dev_fwnode(&i2c->dev);
 	if (!fwnode)
 		return dev_err_probe(&i2c->dev, -EINVAL, "Failed to find fwnode\n");
@@ -365,34 +677,32 @@ static int bd96801_i2c_probe(struct i2c_client *i2c)
 	if (intb_irq < 0)
 		return dev_err_probe(&i2c->dev, intb_irq, "INTB IRQ not configured\n");
 
-	num_intb =  ARRAY_SIZE(regulator_intb_irqs);
-
 	/* ERRB may be omitted if processor is powered by the PMIC */
 	errb_irq = fwnode_irq_get_byname(fwnode, "errb");
-	if (errb_irq < 0)
-		errb_irq = 0;
+	if (errb_irq == -EPROBE_DEFER)
+		return errb_irq;
 
-	if (errb_irq)
-		num_errb = ARRAY_SIZE(regulator_errb_irqs);
+	if (errb_irq > 0)
+		num_errb = ddata->num_errb_irqs;
 
-	num_regu_irqs = num_intb + num_errb;
+	num_regu_irqs = ddata->num_intb_irqs + num_errb;
 
 	regulator_res = devm_kcalloc(&i2c->dev, num_regu_irqs,
 				     sizeof(*regulator_res), GFP_KERNEL);
 	if (!regulator_res)
 		return -ENOMEM;
 
-	regmap = devm_regmap_init_i2c(i2c, &bd96801_regmap_config);
+	regmap = devm_regmap_init_i2c(i2c, ddata->regmap_config);
 	if (IS_ERR(regmap))
 		return dev_err_probe(&i2c->dev, PTR_ERR(regmap),
 				    "Regmap initialization failed\n");
 
-	ret = regmap_write(regmap, BD96801_LOCK_REG, BD96801_UNLOCK);
+	ret = regmap_write(regmap, ddata->unlock_reg, ddata->unlock_val);
 	if (ret)
 		return dev_err_probe(&i2c->dev, ret, "Failed to unlock PMIC\n");
 
 	ret = devm_regmap_add_irq_chip(&i2c->dev, regmap, intb_irq,
-				       IRQF_ONESHOT, 0, &bd96801_irq_chip_intb,
+				       IRQF_ONESHOT, 0, ddata->intb_irq_chip,
 				       &intb_irq_data);
 	if (ret)
 		return dev_err_probe(&i2c->dev, ret, "Failed to add INTB IRQ chip\n");
@@ -404,24 +714,25 @@ static int bd96801_i2c_probe(struct i2c_client *i2c)
 	 * has two domains so we do IRQ mapping here and provide the
 	 * already mapped IRQ numbers to sub-devices.
 	 */
-	for (i = 0; i < num_intb; i++) {
+	for (i = 0; i < ddata->num_intb_irqs; i++) {
 		struct resource *res = &regulator_res[i];
 
-		*res = regulator_intb_irqs[i];
+		*res = ddata->intb_irqs[i];
 		res->start = res->end = irq_create_mapping(intb_domain,
 							    res->start);
 	}
 
 	wdg_irq_no = irq_create_mapping(intb_domain, BD96801_WDT_ERR_STAT);
 	wdg_irq = DEFINE_RES_IRQ_NAMED(wdg_irq_no, "bd96801-wdg");
-	bd96801_cells[WDG_CELL].resources = &wdg_irq;
-	bd96801_cells[WDG_CELL].num_resources = 1;
+
+	ddata->cells[WDG_CELL].resources = &wdg_irq;
+	ddata->cells[WDG_CELL].num_resources = 1;
 
 	if (!num_errb)
 		goto skip_errb;
 
 	ret = devm_regmap_add_irq_chip(&i2c->dev, regmap, errb_irq, IRQF_ONESHOT,
-				       0, &bd96801_irq_chip_errb, &errb_irq_data);
+				       0, ddata->errb_irq_chip, &errb_irq_data);
 	if (ret)
 		return dev_err_probe(&i2c->dev, ret,
 				     "Failed to add ERRB IRQ chip\n");
@@ -429,18 +740,17 @@ static int bd96801_i2c_probe(struct i2c_client *i2c)
 	errb_domain = regmap_irq_get_domain(errb_irq_data);
 
 	for (i = 0; i < num_errb; i++) {
-		struct resource *res = &regulator_res[num_intb + i];
+		struct resource *res = &regulator_res[ddata->num_intb_irqs + i];
 
-		*res = regulator_errb_irqs[i];
+		*res = ddata->errb_irqs[i];
 		res->start = res->end = irq_create_mapping(errb_domain, res->start);
 	}
 
 skip_errb:
-	bd96801_cells[REGULATOR_CELL].resources = regulator_res;
-	bd96801_cells[REGULATOR_CELL].num_resources = num_regu_irqs;
-
-	ret = devm_mfd_add_devices(&i2c->dev, PLATFORM_DEVID_AUTO, bd96801_cells,
-				   ARRAY_SIZE(bd96801_cells), NULL, 0, NULL);
+	ddata->cells[REGULATOR_CELL].resources = regulator_res;
+	ddata->cells[REGULATOR_CELL].num_resources = num_regu_irqs;
+	ret = devm_mfd_add_devices(&i2c->dev, PLATFORM_DEVID_AUTO, ddata->cells,
+				   ddata->num_cells, NULL, 0, NULL);
 	if (ret)
 		dev_err_probe(&i2c->dev, ret, "Failed to create subdevices\n");
 
@@ -448,7 +758,10 @@ skip_errb:
 }
 
 static const struct of_device_id bd96801_of_match[] = {
-	{ .compatible = "rohm,bd96801",	},
+	{ .compatible = "rohm,bd96801", .data = (void *)ROHM_CHIP_TYPE_BD96801 },
+	{ .compatible = "rohm,bd96802", .data = (void *)ROHM_CHIP_TYPE_BD96802 },
+	{ .compatible = "rohm,bd96805", .data = (void *)ROHM_CHIP_TYPE_BD96805 },
+	{ .compatible = "rohm,bd96806", .data = (void *)ROHM_CHIP_TYPE_BD96806 },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, bd96801_of_match);
@@ -476,5 +789,5 @@ static void __exit bd96801_i2c_exit(void)
 module_exit(bd96801_i2c_exit);
 
 MODULE_AUTHOR("Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>");
-MODULE_DESCRIPTION("ROHM BD96801 Power Management IC driver");
+MODULE_DESCRIPTION("ROHM BD9680X Power Management IC driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/rt5033.c b/drivers/mfd/rt5033.c
index 84ebc96f58e4..2204bf1c5a51 100644
--- a/drivers/mfd/rt5033.c
+++ b/drivers/mfd/rt5033.c
@@ -98,7 +98,11 @@ static int rt5033_i2c_probe(struct i2c_client *i2c)
 		return ret;
 	}
 
-	device_init_wakeup(rt5033->dev, rt5033->wakeup);
+	if (rt5033->wakeup) {
+		ret = devm_device_init_wakeup(rt5033->dev);
+		if (ret)
+			return dev_err_probe(rt5033->dev, ret, "Failed to init wakeup\n");
+	}
 
 	return 0;
 }
diff --git a/drivers/mfd/sec-acpm.c b/drivers/mfd/sec-acpm.c
new file mode 100644
index 000000000000..8b31c816d65b
--- /dev/null
+++ b/drivers/mfd/sec-acpm.c
@@ -0,0 +1,442 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2020 Google Inc
+ * Copyright 2025 Linaro Ltd.
+ *
+ * Samsung S2MPG1x ACPM driver
+ */
+
+#include <linux/array_size.h>
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/firmware/samsung/exynos-acpm-protocol.h>
+#include <linux/mfd/samsung/core.h>
+#include <linux/mfd/samsung/rtc.h>
+#include <linux/mfd/samsung/s2mpg10.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+#include "sec-core.h"
+
+#define ACPM_ADDR_BITS       8
+#define ACPM_MAX_BULK_DATA   8
+
+struct sec_pmic_acpm_platform_data {
+	int device_type;
+
+	unsigned int acpm_chan_id;
+	u8 speedy_channel;
+
+	const struct regmap_config *regmap_cfg_common;
+	const struct regmap_config *regmap_cfg_pmic;
+	const struct regmap_config *regmap_cfg_rtc;
+	const struct regmap_config *regmap_cfg_meter;
+};
+
+static const struct regmap_range s2mpg10_common_registers[] = {
+	regmap_reg_range(0x00, 0x02), /* CHIP_ID_M, INT, INT_MASK */
+	regmap_reg_range(0x0a, 0x0c), /* Speedy control */
+	regmap_reg_range(0x1a, 0x2a), /* Debug */
+};
+
+static const struct regmap_range s2mpg10_common_ro_registers[] = {
+	regmap_reg_range(0x00, 0x01), /* CHIP_ID_M, INT */
+	regmap_reg_range(0x28, 0x2a), /* Debug */
+};
+
+static const struct regmap_range s2mpg10_common_nonvolatile_registers[] = {
+	regmap_reg_range(0x00, 0x00), /* CHIP_ID_M */
+	regmap_reg_range(0x02, 0x02), /* INT_MASK */
+	regmap_reg_range(0x0a, 0x0c), /* Speedy control */
+};
+
+static const struct regmap_range s2mpg10_common_precious_registers[] = {
+	regmap_reg_range(0x01, 0x01), /* INT */
+};
+
+static const struct regmap_access_table s2mpg10_common_wr_table = {
+	.yes_ranges = s2mpg10_common_registers,
+	.n_yes_ranges = ARRAY_SIZE(s2mpg10_common_registers),
+	.no_ranges = s2mpg10_common_ro_registers,
+	.n_no_ranges = ARRAY_SIZE(s2mpg10_common_ro_registers),
+};
+
+static const struct regmap_access_table s2mpg10_common_rd_table = {
+	.yes_ranges = s2mpg10_common_registers,
+	.n_yes_ranges = ARRAY_SIZE(s2mpg10_common_registers),
+};
+
+static const struct regmap_access_table s2mpg10_common_volatile_table = {
+	.no_ranges = s2mpg10_common_nonvolatile_registers,
+	.n_no_ranges = ARRAY_SIZE(s2mpg10_common_nonvolatile_registers),
+};
+
+static const struct regmap_access_table s2mpg10_common_precious_table = {
+	.yes_ranges = s2mpg10_common_precious_registers,
+	.n_yes_ranges = ARRAY_SIZE(s2mpg10_common_precious_registers),
+};
+
+static const struct regmap_config s2mpg10_regmap_config_common = {
+	.name = "common",
+	.reg_bits = ACPM_ADDR_BITS,
+	.val_bits = 8,
+	.max_register = S2MPG10_COMMON_SPD_DEBUG4,
+	.wr_table = &s2mpg10_common_wr_table,
+	.rd_table = &s2mpg10_common_rd_table,
+	.volatile_table = &s2mpg10_common_volatile_table,
+	.precious_table = &s2mpg10_common_precious_table,
+	.num_reg_defaults_raw = S2MPG10_COMMON_SPD_DEBUG4 + 1,
+	.cache_type = REGCACHE_FLAT,
+};
+
+static const struct regmap_range s2mpg10_pmic_registers[] = {
+	regmap_reg_range(0x00, 0xf6), /* All PMIC registers */
+};
+
+static const struct regmap_range s2mpg10_pmic_ro_registers[] = {
+	regmap_reg_range(0x00, 0x05), /* INTx */
+	regmap_reg_range(0x0c, 0x0f), /* STATUSx PWRONSRC OFFSRC */
+	regmap_reg_range(0xc7, 0xc7), /* GPIO input */
+};
+
+static const struct regmap_range s2mpg10_pmic_nonvolatile_registers[] = {
+	regmap_reg_range(0x06, 0x0b), /* INTxM */
+};
+
+static const struct regmap_range s2mpg10_pmic_precious_registers[] = {
+	regmap_reg_range(0x00, 0x05), /* INTx */
+};
+
+static const struct regmap_access_table s2mpg10_pmic_wr_table = {
+	.yes_ranges = s2mpg10_pmic_registers,
+	.n_yes_ranges = ARRAY_SIZE(s2mpg10_pmic_registers),
+	.no_ranges = s2mpg10_pmic_ro_registers,
+	.n_no_ranges = ARRAY_SIZE(s2mpg10_pmic_ro_registers),
+};
+
+static const struct regmap_access_table s2mpg10_pmic_rd_table = {
+	.yes_ranges = s2mpg10_pmic_registers,
+	.n_yes_ranges = ARRAY_SIZE(s2mpg10_pmic_registers),
+};
+
+static const struct regmap_access_table s2mpg10_pmic_volatile_table = {
+	.no_ranges = s2mpg10_pmic_nonvolatile_registers,
+	.n_no_ranges = ARRAY_SIZE(s2mpg10_pmic_nonvolatile_registers),
+};
+
+static const struct regmap_access_table s2mpg10_pmic_precious_table = {
+	.yes_ranges = s2mpg10_pmic_precious_registers,
+	.n_yes_ranges = ARRAY_SIZE(s2mpg10_pmic_precious_registers),
+};
+
+static const struct regmap_config s2mpg10_regmap_config_pmic = {
+	.name = "pmic",
+	.reg_bits = ACPM_ADDR_BITS,
+	.val_bits = 8,
+	.max_register = S2MPG10_PMIC_LDO_SENSE4,
+	.wr_table = &s2mpg10_pmic_wr_table,
+	.rd_table = &s2mpg10_pmic_rd_table,
+	.volatile_table = &s2mpg10_pmic_volatile_table,
+	.precious_table = &s2mpg10_pmic_precious_table,
+	.num_reg_defaults_raw = S2MPG10_PMIC_LDO_SENSE4 + 1,
+	.cache_type = REGCACHE_FLAT,
+};
+
+static const struct regmap_range s2mpg10_rtc_registers[] = {
+	regmap_reg_range(0x00, 0x2b), /* All RTC registers */
+};
+
+static const struct regmap_range s2mpg10_rtc_volatile_registers[] = {
+	regmap_reg_range(0x01, 0x01), /* RTC_UPDATE */
+	regmap_reg_range(0x05, 0x0c), /* Time / date */
+};
+
+static const struct regmap_access_table s2mpg10_rtc_rd_table = {
+	.yes_ranges = s2mpg10_rtc_registers,
+	.n_yes_ranges = ARRAY_SIZE(s2mpg10_rtc_registers),
+};
+
+static const struct regmap_access_table s2mpg10_rtc_volatile_table = {
+	.yes_ranges = s2mpg10_rtc_volatile_registers,
+	.n_yes_ranges = ARRAY_SIZE(s2mpg10_rtc_volatile_registers),
+};
+
+static const struct regmap_config s2mpg10_regmap_config_rtc = {
+	.name = "rtc",
+	.reg_bits = ACPM_ADDR_BITS,
+	.val_bits = 8,
+	.max_register = S2MPG10_RTC_OSC_CTRL,
+	.rd_table = &s2mpg10_rtc_rd_table,
+	.volatile_table = &s2mpg10_rtc_volatile_table,
+	.num_reg_defaults_raw = S2MPG10_RTC_OSC_CTRL + 1,
+	.cache_type = REGCACHE_FLAT,
+};
+
+static const struct regmap_range s2mpg10_meter_registers[] = {
+	regmap_reg_range(0x00, 0x21), /* Meter config */
+	regmap_reg_range(0x40, 0x8a), /* Meter data */
+	regmap_reg_range(0xee, 0xee), /* Offset */
+	regmap_reg_range(0xf1, 0xf1), /* Trim */
+};
+
+static const struct regmap_range s2mpg10_meter_ro_registers[] = {
+	regmap_reg_range(0x40, 0x8a), /* Meter data */
+};
+
+static const struct regmap_access_table s2mpg10_meter_wr_table = {
+	.yes_ranges = s2mpg10_meter_registers,
+	.n_yes_ranges = ARRAY_SIZE(s2mpg10_meter_registers),
+	.no_ranges = s2mpg10_meter_ro_registers,
+	.n_no_ranges = ARRAY_SIZE(s2mpg10_meter_ro_registers),
+};
+
+static const struct regmap_access_table s2mpg10_meter_rd_table = {
+	.yes_ranges = s2mpg10_meter_registers,
+	.n_yes_ranges = ARRAY_SIZE(s2mpg10_meter_registers),
+};
+
+static const struct regmap_access_table s2mpg10_meter_volatile_table = {
+	.yes_ranges = s2mpg10_meter_ro_registers,
+	.n_yes_ranges = ARRAY_SIZE(s2mpg10_meter_ro_registers),
+};
+
+static const struct regmap_config s2mpg10_regmap_config_meter = {
+	.name = "meter",
+	.reg_bits = ACPM_ADDR_BITS,
+	.val_bits = 8,
+	.max_register = S2MPG10_METER_BUCK_METER_TRIM3,
+	.wr_table = &s2mpg10_meter_wr_table,
+	.rd_table = &s2mpg10_meter_rd_table,
+	.volatile_table = &s2mpg10_meter_volatile_table,
+	.num_reg_defaults_raw = S2MPG10_METER_BUCK_METER_TRIM3 + 1,
+	.cache_type = REGCACHE_FLAT,
+};
+
+struct sec_pmic_acpm_shared_bus_context {
+	const struct acpm_handle *acpm;
+	unsigned int acpm_chan_id;
+	u8 speedy_channel;
+};
+
+enum sec_pmic_acpm_accesstype {
+	SEC_PMIC_ACPM_ACCESSTYPE_COMMON = 0x00,
+	SEC_PMIC_ACPM_ACCESSTYPE_PMIC = 0x01,
+	SEC_PMIC_ACPM_ACCESSTYPE_RTC = 0x02,
+	SEC_PMIC_ACPM_ACCESSTYPE_METER = 0x0a,
+	SEC_PMIC_ACPM_ACCESSTYPE_WLWP = 0x0b,
+	SEC_PMIC_ACPM_ACCESSTYPE_TRIM = 0x0f,
+};
+
+struct sec_pmic_acpm_bus_context {
+	struct sec_pmic_acpm_shared_bus_context *shared;
+	enum sec_pmic_acpm_accesstype type;
+};
+
+static int sec_pmic_acpm_bus_write(void *context, const void *data,
+				   size_t count)
+{
+	struct sec_pmic_acpm_bus_context *ctx = context;
+	const struct acpm_handle *acpm = ctx->shared->acpm;
+	const struct acpm_pmic_ops *pmic_ops = &acpm->ops.pmic_ops;
+	size_t val_count = count - BITS_TO_BYTES(ACPM_ADDR_BITS);
+	const u8 *d = data;
+	const u8 *vals = &d[BITS_TO_BYTES(ACPM_ADDR_BITS)];
+	u8 reg;
+
+	if (val_count < 1 || val_count > ACPM_MAX_BULK_DATA)
+		return -EINVAL;
+
+	reg = d[0];
+
+	return pmic_ops->bulk_write(acpm, ctx->shared->acpm_chan_id, ctx->type, reg,
+				    ctx->shared->speedy_channel, val_count, vals);
+}
+
+static int sec_pmic_acpm_bus_read(void *context, const void *reg_buf, size_t reg_size,
+				  void *val_buf, size_t val_size)
+{
+	struct sec_pmic_acpm_bus_context *ctx = context;
+	const struct acpm_handle *acpm = ctx->shared->acpm;
+	const struct acpm_pmic_ops *pmic_ops = &acpm->ops.pmic_ops;
+	const u8 *r = reg_buf;
+	u8 reg;
+
+	if (reg_size != BITS_TO_BYTES(ACPM_ADDR_BITS) || !val_size ||
+	    val_size > ACPM_MAX_BULK_DATA)
+		return -EINVAL;
+
+	reg = r[0];
+
+	return pmic_ops->bulk_read(acpm, ctx->shared->acpm_chan_id, ctx->type, reg,
+				   ctx->shared->speedy_channel, val_size, val_buf);
+}
+
+static int sec_pmic_acpm_bus_reg_update_bits(void *context, unsigned int reg, unsigned int mask,
+					     unsigned int val)
+{
+	struct sec_pmic_acpm_bus_context *ctx = context;
+	const struct acpm_handle *acpm = ctx->shared->acpm;
+	const struct acpm_pmic_ops *pmic_ops = &acpm->ops.pmic_ops;
+
+	return pmic_ops->update_reg(acpm, ctx->shared->acpm_chan_id, ctx->type, reg & 0xff,
+				    ctx->shared->speedy_channel, val, mask);
+}
+
+static const struct regmap_bus sec_pmic_acpm_regmap_bus = {
+	.write = sec_pmic_acpm_bus_write,
+	.read = sec_pmic_acpm_bus_read,
+	.reg_update_bits = sec_pmic_acpm_bus_reg_update_bits,
+	.max_raw_read = ACPM_MAX_BULK_DATA,
+	.max_raw_write = ACPM_MAX_BULK_DATA,
+};
+
+static struct regmap *sec_pmic_acpm_regmap_init(struct device *dev,
+						struct sec_pmic_acpm_shared_bus_context *shared_ctx,
+						enum sec_pmic_acpm_accesstype type,
+						const struct regmap_config *cfg, bool do_attach)
+{
+	struct sec_pmic_acpm_bus_context *ctx;
+	struct regmap *regmap;
+
+	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return ERR_PTR(-ENOMEM);
+
+	ctx->shared = shared_ctx;
+	ctx->type = type;
+
+	regmap = devm_regmap_init(dev, &sec_pmic_acpm_regmap_bus, ctx, cfg);
+	if (IS_ERR(regmap))
+		return dev_err_cast_probe(dev, regmap, "regmap init (%s) failed\n", cfg->name);
+
+	if (do_attach) {
+		int ret;
+
+		ret = regmap_attach_dev(dev, regmap, cfg);
+		if (ret)
+			return dev_err_ptr_probe(dev, ret, "regmap attach (%s) failed\n",
+						 cfg->name);
+	}
+
+	return regmap;
+}
+
+static void sec_pmic_acpm_mask_common_irqs(void *regmap_common)
+{
+	regmap_write(regmap_common, S2MPG10_COMMON_INT_MASK, S2MPG10_COMMON_INT_SRC);
+}
+
+static int sec_pmic_acpm_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap_common, *regmap_pmic, *regmap;
+	const struct sec_pmic_acpm_platform_data *pdata;
+	struct sec_pmic_acpm_shared_bus_context *shared_ctx;
+	const struct acpm_handle *acpm;
+	struct device *dev = &pdev->dev;
+	int ret, irq;
+
+	pdata = device_get_match_data(dev);
+	if (!pdata)
+		return dev_err_probe(dev, -ENODEV, "unsupported device type\n");
+
+	acpm = devm_acpm_get_by_node(dev, dev->parent->of_node);
+	if (IS_ERR(acpm))
+		return dev_err_probe(dev, PTR_ERR(acpm), "failed to get acpm\n");
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	shared_ctx = devm_kzalloc(dev, sizeof(*shared_ctx), GFP_KERNEL);
+	if (!shared_ctx)
+		return -ENOMEM;
+
+	shared_ctx->acpm = acpm;
+	shared_ctx->acpm_chan_id = pdata->acpm_chan_id;
+	shared_ctx->speedy_channel = pdata->speedy_channel;
+
+	regmap_common = sec_pmic_acpm_regmap_init(dev, shared_ctx, SEC_PMIC_ACPM_ACCESSTYPE_COMMON,
+						  pdata->regmap_cfg_common, false);
+	if (IS_ERR(regmap_common))
+		return PTR_ERR(regmap_common);
+
+	/* Mask all interrupts from 'common' block, until successful init */
+	ret = regmap_write(regmap_common, S2MPG10_COMMON_INT_MASK, S2MPG10_COMMON_INT_SRC);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to mask common block interrupts\n");
+
+	regmap_pmic = sec_pmic_acpm_regmap_init(dev, shared_ctx, SEC_PMIC_ACPM_ACCESSTYPE_PMIC,
+						pdata->regmap_cfg_pmic, false);
+	if (IS_ERR(regmap_pmic))
+		return PTR_ERR(regmap_pmic);
+
+	regmap = sec_pmic_acpm_regmap_init(dev, shared_ctx, SEC_PMIC_ACPM_ACCESSTYPE_RTC,
+					   pdata->regmap_cfg_rtc, true);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	regmap = sec_pmic_acpm_regmap_init(dev, shared_ctx, SEC_PMIC_ACPM_ACCESSTYPE_METER,
+					   pdata->regmap_cfg_meter, true);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	ret = sec_pmic_probe(dev, pdata->device_type, irq, regmap_pmic, NULL);
+	if (ret)
+		return ret;
+
+	if (device_property_read_bool(dev, "wakeup-source"))
+		devm_device_init_wakeup(dev);
+
+	/* Unmask PMIC interrupt from 'common' block, now that everything is in place. */
+	ret = regmap_clear_bits(regmap_common, S2MPG10_COMMON_INT_MASK,
+				S2MPG10_COMMON_INT_SRC_PMIC);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to unmask PMIC interrupt\n");
+
+	/* Mask all interrupts from 'common' block on shutdown */
+	ret = devm_add_action_or_reset(dev, sec_pmic_acpm_mask_common_irqs, regmap_common);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void sec_pmic_acpm_shutdown(struct platform_device *pdev)
+{
+	sec_pmic_shutdown(&pdev->dev);
+}
+
+static const struct sec_pmic_acpm_platform_data s2mpg10_data = {
+	.device_type = S2MPG10,
+	.acpm_chan_id = 2,
+	.speedy_channel = 0,
+	.regmap_cfg_common = &s2mpg10_regmap_config_common,
+	.regmap_cfg_pmic = &s2mpg10_regmap_config_pmic,
+	.regmap_cfg_rtc = &s2mpg10_regmap_config_rtc,
+	.regmap_cfg_meter = &s2mpg10_regmap_config_meter,
+};
+
+static const struct of_device_id sec_pmic_acpm_of_match[] = {
+	{ .compatible = "samsung,s2mpg10-pmic", .data = &s2mpg10_data, },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, sec_pmic_acpm_of_match);
+
+static struct platform_driver sec_pmic_acpm_driver = {
+	.driver = {
+		.name = "sec-pmic-acpm",
+		.pm = pm_sleep_ptr(&sec_pmic_pm_ops),
+		.of_match_table = sec_pmic_acpm_of_match,
+	},
+	.probe = sec_pmic_acpm_probe,
+	.shutdown = sec_pmic_acpm_shutdown,
+};
+module_platform_driver(sec_pmic_acpm_driver);
+
+MODULE_AUTHOR("André Draszik <andre.draszik@linaro.org>");
+MODULE_DESCRIPTION("ACPM driver for the Samsung S2MPG1x");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/sec-common.c b/drivers/mfd/sec-common.c
new file mode 100644
index 000000000000..42d55e70e34c
--- /dev/null
+++ b/drivers/mfd/sec-common.c
@@ -0,0 +1,301 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2012 Samsung Electronics Co., Ltd
+ *                http://www.samsung.com
+ * Copyright 2025 Linaro Ltd.
+ *
+ * Samsung SxM core driver
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/samsung/core.h>
+#include <linux/mfd/samsung/irq.h>
+#include <linux/mfd/samsung/s2mps11.h>
+#include <linux/mfd/samsung/s2mps13.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include "sec-core.h"
+
+static const struct mfd_cell s5m8767_devs[] = {
+	MFD_CELL_NAME("s5m8767-pmic"),
+	MFD_CELL_NAME("s5m-rtc"),
+	MFD_CELL_OF("s5m8767-clk", NULL, NULL, 0, 0, "samsung,s5m8767-clk"),
+};
+
+static const struct mfd_cell s2dos05_devs[] = {
+	MFD_CELL_NAME("s2dos05-regulator"),
+};
+
+static const struct mfd_cell s2mpg10_devs[] = {
+	MFD_CELL_NAME("s2mpg10-meter"),
+	MFD_CELL_NAME("s2mpg10-regulator"),
+	MFD_CELL_NAME("s2mpg10-rtc"),
+	MFD_CELL_OF("s2mpg10-clk", NULL, NULL, 0, 0, "samsung,s2mpg10-clk"),
+	MFD_CELL_OF("s2mpg10-gpio", NULL, NULL, 0, 0, "samsung,s2mpg10-gpio"),
+};
+
+static const struct mfd_cell s2mps11_devs[] = {
+	MFD_CELL_NAME("s2mps11-regulator"),
+	MFD_CELL_NAME("s2mps14-rtc"),
+	MFD_CELL_OF("s2mps11-clk", NULL, NULL, 0, 0, "samsung,s2mps11-clk"),
+};
+
+static const struct mfd_cell s2mps13_devs[] = {
+	MFD_CELL_NAME("s2mps13-regulator"),
+	MFD_CELL_NAME("s2mps13-rtc"),
+	MFD_CELL_OF("s2mps13-clk", NULL, NULL, 0, 0, "samsung,s2mps13-clk"),
+};
+
+static const struct mfd_cell s2mps14_devs[] = {
+	MFD_CELL_NAME("s2mps14-regulator"),
+	MFD_CELL_NAME("s2mps14-rtc"),
+	MFD_CELL_OF("s2mps14-clk", NULL, NULL, 0, 0, "samsung,s2mps14-clk"),
+};
+
+static const struct mfd_cell s2mps15_devs[] = {
+	MFD_CELL_NAME("s2mps15-regulator"),
+	MFD_CELL_NAME("s2mps15-rtc"),
+	MFD_CELL_OF("s2mps13-clk", NULL, NULL, 0, 0, "samsung,s2mps13-clk"),
+};
+
+static const struct mfd_cell s2mpa01_devs[] = {
+	MFD_CELL_NAME("s2mpa01-pmic"),
+	MFD_CELL_NAME("s2mps14-rtc"),
+};
+
+static const struct mfd_cell s2mpu02_devs[] = {
+	MFD_CELL_NAME("s2mpu02-regulator"),
+};
+
+static const struct mfd_cell s2mpu05_devs[] = {
+	MFD_CELL_NAME("s2mpu05-regulator"),
+	MFD_CELL_NAME("s2mps15-rtc"),
+};
+
+static void sec_pmic_dump_rev(struct sec_pmic_dev *sec_pmic)
+{
+	unsigned int val;
+
+	/* For s2mpg1x, the revision is in a different regmap */
+	if (sec_pmic->device_type == S2MPG10)
+		return;
+
+	/* For each device type, the REG_ID is always the first register */
+	if (!regmap_read(sec_pmic->regmap_pmic, S2MPS11_REG_ID, &val))
+		dev_dbg(sec_pmic->dev, "Revision: 0x%x\n", val);
+}
+
+static void sec_pmic_configure(struct sec_pmic_dev *sec_pmic)
+{
+	int err;
+
+	if (sec_pmic->device_type != S2MPS13X)
+		return;
+
+	if (sec_pmic->pdata->disable_wrstbi) {
+		/*
+		 * If WRSTBI pin is pulled down this feature must be disabled
+		 * because each Suspend to RAM will trigger buck voltage reset
+		 * to default values.
+		 */
+		err = regmap_update_bits(sec_pmic->regmap_pmic,
+					 S2MPS13_REG_WRSTBI,
+					 S2MPS13_REG_WRSTBI_MASK, 0x0);
+		if (err)
+			dev_warn(sec_pmic->dev,
+				 "Cannot initialize WRSTBI config: %d\n",
+				 err);
+	}
+}
+
+/*
+ * Only the common platform data elements for s5m8767 are parsed here from the
+ * device tree. Other sub-modules of s5m8767 such as pmic, rtc , charger and
+ * others have to parse their own platform data elements from device tree.
+ *
+ * The s5m8767 platform data structure is instantiated here and the drivers for
+ * the sub-modules need not instantiate another instance while parsing their
+ * platform data.
+ */
+static struct sec_platform_data *
+sec_pmic_parse_dt_pdata(struct device *dev)
+{
+	struct sec_platform_data *pd;
+
+	pd = devm_kzalloc(dev, sizeof(*pd), GFP_KERNEL);
+	if (!pd)
+		return ERR_PTR(-ENOMEM);
+
+	pd->manual_poweroff = of_property_read_bool(dev->of_node,
+						    "samsung,s2mps11-acokb-ground");
+	pd->disable_wrstbi = of_property_read_bool(dev->of_node,
+						   "samsung,s2mps11-wrstbi-ground");
+	return pd;
+}
+
+int sec_pmic_probe(struct device *dev, int device_type, unsigned int irq,
+		   struct regmap *regmap, struct i2c_client *client)
+{
+	struct sec_platform_data *pdata;
+	const struct mfd_cell *sec_devs;
+	struct sec_pmic_dev *sec_pmic;
+	int ret, num_sec_devs;
+
+	sec_pmic = devm_kzalloc(dev, sizeof(*sec_pmic), GFP_KERNEL);
+	if (!sec_pmic)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, sec_pmic);
+	sec_pmic->dev = dev;
+	sec_pmic->device_type = device_type;
+	sec_pmic->i2c = client;
+	sec_pmic->irq = irq;
+	sec_pmic->regmap_pmic = regmap;
+
+	pdata = sec_pmic_parse_dt_pdata(sec_pmic->dev);
+	if (IS_ERR(pdata)) {
+		ret = PTR_ERR(pdata);
+		return ret;
+	}
+
+	sec_pmic->pdata = pdata;
+
+	ret = sec_irq_init(sec_pmic);
+	if (ret)
+		return ret;
+
+	pm_runtime_set_active(sec_pmic->dev);
+
+	switch (sec_pmic->device_type) {
+	case S5M8767X:
+		sec_devs = s5m8767_devs;
+		num_sec_devs = ARRAY_SIZE(s5m8767_devs);
+		break;
+	case S2DOS05:
+		sec_devs = s2dos05_devs;
+		num_sec_devs = ARRAY_SIZE(s2dos05_devs);
+		break;
+	case S2MPA01:
+		sec_devs = s2mpa01_devs;
+		num_sec_devs = ARRAY_SIZE(s2mpa01_devs);
+		break;
+	case S2MPG10:
+		sec_devs = s2mpg10_devs;
+		num_sec_devs = ARRAY_SIZE(s2mpg10_devs);
+		break;
+	case S2MPS11X:
+		sec_devs = s2mps11_devs;
+		num_sec_devs = ARRAY_SIZE(s2mps11_devs);
+		break;
+	case S2MPS13X:
+		sec_devs = s2mps13_devs;
+		num_sec_devs = ARRAY_SIZE(s2mps13_devs);
+		break;
+	case S2MPS14X:
+		sec_devs = s2mps14_devs;
+		num_sec_devs = ARRAY_SIZE(s2mps14_devs);
+		break;
+	case S2MPS15X:
+		sec_devs = s2mps15_devs;
+		num_sec_devs = ARRAY_SIZE(s2mps15_devs);
+		break;
+	case S2MPU02:
+		sec_devs = s2mpu02_devs;
+		num_sec_devs = ARRAY_SIZE(s2mpu02_devs);
+		break;
+	case S2MPU05:
+		sec_devs = s2mpu05_devs;
+		num_sec_devs = ARRAY_SIZE(s2mpu05_devs);
+		break;
+	default:
+		return dev_err_probe(sec_pmic->dev, -EINVAL,
+				     "Unsupported device type %d\n",
+				     sec_pmic->device_type);
+	}
+	ret = devm_mfd_add_devices(sec_pmic->dev, -1, sec_devs, num_sec_devs,
+				   NULL, 0, NULL);
+	if (ret)
+		return ret;
+
+	sec_pmic_configure(sec_pmic);
+	sec_pmic_dump_rev(sec_pmic);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sec_pmic_probe);
+
+void sec_pmic_shutdown(struct device *dev)
+{
+	struct sec_pmic_dev *sec_pmic = dev_get_drvdata(dev);
+	unsigned int reg, mask;
+
+	if (!sec_pmic->pdata->manual_poweroff)
+		return;
+
+	switch (sec_pmic->device_type) {
+	case S2MPS11X:
+		reg = S2MPS11_REG_CTRL1;
+		mask = S2MPS11_CTRL1_PWRHOLD_MASK;
+		break;
+	default:
+		/*
+		 * Currently only one board with S2MPS11 needs this, so just
+		 * ignore the rest.
+		 */
+		dev_warn(sec_pmic->dev,
+			 "Unsupported device %d for manual power off\n",
+			 sec_pmic->device_type);
+		return;
+	}
+
+	regmap_update_bits(sec_pmic->regmap_pmic, reg, mask, 0);
+}
+EXPORT_SYMBOL_GPL(sec_pmic_shutdown);
+
+static int sec_pmic_suspend(struct device *dev)
+{
+	struct sec_pmic_dev *sec_pmic = dev_get_drvdata(dev);
+
+	if (device_may_wakeup(dev))
+		enable_irq_wake(sec_pmic->irq);
+	/*
+	 * PMIC IRQ must be disabled during suspend for RTC alarm
+	 * to work properly.
+	 * When device is woken up from suspend, an
+	 * interrupt occurs before resuming I2C bus controller.
+	 * The interrupt is handled by regmap_irq_thread which tries
+	 * to read RTC registers. This read fails (I2C is still
+	 * suspended) and RTC Alarm interrupt is disabled.
+	 */
+	disable_irq(sec_pmic->irq);
+
+	return 0;
+}
+
+static int sec_pmic_resume(struct device *dev)
+{
+	struct sec_pmic_dev *sec_pmic = dev_get_drvdata(dev);
+
+	if (device_may_wakeup(dev))
+		disable_irq_wake(sec_pmic->irq);
+	enable_irq(sec_pmic->irq);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_DEV_PM_OPS(sec_pmic_pm_ops, sec_pmic_suspend, sec_pmic_resume);
+EXPORT_SYMBOL_GPL(sec_pmic_pm_ops);
+
+MODULE_AUTHOR("Chanwoo Choi <cw00.choi@samsung.com>");
+MODULE_AUTHOR("Krzysztof Kozlowski <krzk@kernel.org>");
+MODULE_AUTHOR("Sangbeom Kim <sbkim73@samsung.com>");
+MODULE_AUTHOR("André Draszik <andre.draszik@linaro.org>");
+MODULE_DESCRIPTION("Core driver for the Samsung S5M");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c
deleted file mode 100644
index 3e9b65c988a7..000000000000
--- a/drivers/mfd/sec-core.c
+++ /dev/null
@@ -1,481 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-//
-// Copyright (c) 2012 Samsung Electronics Co., Ltd
-//              http://www.samsung.com
-
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/init.h>
-#include <linux/err.h>
-#include <linux/slab.h>
-#include <linux/i2c.h>
-#include <linux/of.h>
-#include <linux/interrupt.h>
-#include <linux/pm_runtime.h>
-#include <linux/mutex.h>
-#include <linux/mfd/core.h>
-#include <linux/mfd/samsung/core.h>
-#include <linux/mfd/samsung/irq.h>
-#include <linux/mfd/samsung/s2mpa01.h>
-#include <linux/mfd/samsung/s2mps11.h>
-#include <linux/mfd/samsung/s2mps13.h>
-#include <linux/mfd/samsung/s2mps14.h>
-#include <linux/mfd/samsung/s2mps15.h>
-#include <linux/mfd/samsung/s2mpu02.h>
-#include <linux/mfd/samsung/s5m8767.h>
-#include <linux/regmap.h>
-
-static const struct mfd_cell s5m8767_devs[] = {
-	{ .name = "s5m8767-pmic", },
-	{ .name = "s5m-rtc", },
-	{
-		.name = "s5m8767-clk",
-		.of_compatible = "samsung,s5m8767-clk",
-	},
-};
-
-static const struct mfd_cell s2dos05_devs[] = {
-	{ .name = "s2dos05-regulator", },
-};
-
-static const struct mfd_cell s2mps11_devs[] = {
-	{ .name = "s2mps11-regulator", },
-	{ .name = "s2mps14-rtc", },
-	{
-		.name = "s2mps11-clk",
-		.of_compatible = "samsung,s2mps11-clk",
-	},
-};
-
-static const struct mfd_cell s2mps13_devs[] = {
-	{ .name = "s2mps13-regulator", },
-	{ .name = "s2mps13-rtc", },
-	{
-		.name = "s2mps13-clk",
-		.of_compatible = "samsung,s2mps13-clk",
-	},
-};
-
-static const struct mfd_cell s2mps14_devs[] = {
-	{ .name = "s2mps14-regulator", },
-	{ .name = "s2mps14-rtc", },
-	{
-		.name = "s2mps14-clk",
-		.of_compatible = "samsung,s2mps14-clk",
-	},
-};
-
-static const struct mfd_cell s2mps15_devs[] = {
-	{ .name = "s2mps15-regulator", },
-	{ .name = "s2mps15-rtc", },
-	{
-		.name = "s2mps13-clk",
-		.of_compatible = "samsung,s2mps13-clk",
-	},
-};
-
-static const struct mfd_cell s2mpa01_devs[] = {
-	{ .name = "s2mpa01-pmic", },
-	{ .name = "s2mps14-rtc", },
-};
-
-static const struct mfd_cell s2mpu02_devs[] = {
-	{ .name = "s2mpu02-regulator", },
-};
-
-static const struct mfd_cell s2mpu05_devs[] = {
-	{ .name = "s2mpu05-regulator", },
-	{ .name = "s2mps15-rtc", },
-};
-
-static const struct of_device_id sec_dt_match[] = {
-	{
-		.compatible = "samsung,s5m8767-pmic",
-		.data = (void *)S5M8767X,
-	}, {
-		.compatible = "samsung,s2dos05",
-		.data = (void *)S2DOS05,
-	}, {
-		.compatible = "samsung,s2mps11-pmic",
-		.data = (void *)S2MPS11X,
-	}, {
-		.compatible = "samsung,s2mps13-pmic",
-		.data = (void *)S2MPS13X,
-	}, {
-		.compatible = "samsung,s2mps14-pmic",
-		.data = (void *)S2MPS14X,
-	}, {
-		.compatible = "samsung,s2mps15-pmic",
-		.data = (void *)S2MPS15X,
-	}, {
-		.compatible = "samsung,s2mpa01-pmic",
-		.data = (void *)S2MPA01,
-	}, {
-		.compatible = "samsung,s2mpu02-pmic",
-		.data = (void *)S2MPU02,
-	}, {
-		.compatible = "samsung,s2mpu05-pmic",
-		.data = (void *)S2MPU05,
-	}, {
-		/* Sentinel */
-	},
-};
-MODULE_DEVICE_TABLE(of, sec_dt_match);
-
-static bool s2mpa01_volatile(struct device *dev, unsigned int reg)
-{
-	switch (reg) {
-	case S2MPA01_REG_INT1M:
-	case S2MPA01_REG_INT2M:
-	case S2MPA01_REG_INT3M:
-		return false;
-	default:
-		return true;
-	}
-}
-
-static bool s2mps11_volatile(struct device *dev, unsigned int reg)
-{
-	switch (reg) {
-	case S2MPS11_REG_INT1M:
-	case S2MPS11_REG_INT2M:
-	case S2MPS11_REG_INT3M:
-		return false;
-	default:
-		return true;
-	}
-}
-
-static bool s2mpu02_volatile(struct device *dev, unsigned int reg)
-{
-	switch (reg) {
-	case S2MPU02_REG_INT1M:
-	case S2MPU02_REG_INT2M:
-	case S2MPU02_REG_INT3M:
-		return false;
-	default:
-		return true;
-	}
-}
-
-static const struct regmap_config sec_regmap_config = {
-	.reg_bits = 8,
-	.val_bits = 8,
-};
-
-static const struct regmap_config s2mpa01_regmap_config = {
-	.reg_bits = 8,
-	.val_bits = 8,
-
-	.max_register = S2MPA01_REG_LDO_OVCB4,
-	.volatile_reg = s2mpa01_volatile,
-	.cache_type = REGCACHE_FLAT,
-};
-
-static const struct regmap_config s2mps11_regmap_config = {
-	.reg_bits = 8,
-	.val_bits = 8,
-
-	.max_register = S2MPS11_REG_L38CTRL,
-	.volatile_reg = s2mps11_volatile,
-	.cache_type = REGCACHE_FLAT,
-};
-
-static const struct regmap_config s2mps13_regmap_config = {
-	.reg_bits = 8,
-	.val_bits = 8,
-
-	.max_register = S2MPS13_REG_LDODSCH5,
-	.volatile_reg = s2mps11_volatile,
-	.cache_type = REGCACHE_FLAT,
-};
-
-static const struct regmap_config s2mps14_regmap_config = {
-	.reg_bits = 8,
-	.val_bits = 8,
-
-	.max_register = S2MPS14_REG_LDODSCH3,
-	.volatile_reg = s2mps11_volatile,
-	.cache_type = REGCACHE_FLAT,
-};
-
-static const struct regmap_config s2mps15_regmap_config = {
-	.reg_bits = 8,
-	.val_bits = 8,
-
-	.max_register = S2MPS15_REG_LDODSCH4,
-	.volatile_reg = s2mps11_volatile,
-	.cache_type = REGCACHE_FLAT,
-};
-
-static const struct regmap_config s2mpu02_regmap_config = {
-	.reg_bits = 8,
-	.val_bits = 8,
-
-	.max_register = S2MPU02_REG_DVSDATA,
-	.volatile_reg = s2mpu02_volatile,
-	.cache_type = REGCACHE_FLAT,
-};
-
-static const struct regmap_config s5m8767_regmap_config = {
-	.reg_bits = 8,
-	.val_bits = 8,
-
-	.max_register = S5M8767_REG_LDO28CTRL,
-	.volatile_reg = s2mps11_volatile,
-	.cache_type = REGCACHE_FLAT,
-};
-
-static void sec_pmic_dump_rev(struct sec_pmic_dev *sec_pmic)
-{
-	unsigned int val;
-
-	/* For each device type, the REG_ID is always the first register */
-	if (!regmap_read(sec_pmic->regmap_pmic, S2MPS11_REG_ID, &val))
-		dev_dbg(sec_pmic->dev, "Revision: 0x%x\n", val);
-}
-
-static void sec_pmic_configure(struct sec_pmic_dev *sec_pmic)
-{
-	int err;
-
-	if (sec_pmic->device_type != S2MPS13X)
-		return;
-
-	if (sec_pmic->pdata->disable_wrstbi) {
-		/*
-		 * If WRSTBI pin is pulled down this feature must be disabled
-		 * because each Suspend to RAM will trigger buck voltage reset
-		 * to default values.
-		 */
-		err = regmap_update_bits(sec_pmic->regmap_pmic,
-					 S2MPS13_REG_WRSTBI,
-					 S2MPS13_REG_WRSTBI_MASK, 0x0);
-		if (err)
-			dev_warn(sec_pmic->dev,
-				 "Cannot initialize WRSTBI config: %d\n",
-				 err);
-	}
-}
-
-/*
- * Only the common platform data elements for s5m8767 are parsed here from the
- * device tree. Other sub-modules of s5m8767 such as pmic, rtc , charger and
- * others have to parse their own platform data elements from device tree.
- *
- * The s5m8767 platform data structure is instantiated here and the drivers for
- * the sub-modules need not instantiate another instance while parsing their
- * platform data.
- */
-static struct sec_platform_data *
-sec_pmic_i2c_parse_dt_pdata(struct device *dev)
-{
-	struct sec_platform_data *pd;
-
-	pd = devm_kzalloc(dev, sizeof(*pd), GFP_KERNEL);
-	if (!pd)
-		return ERR_PTR(-ENOMEM);
-
-	pd->manual_poweroff = of_property_read_bool(dev->of_node,
-						"samsung,s2mps11-acokb-ground");
-	pd->disable_wrstbi = of_property_read_bool(dev->of_node,
-						"samsung,s2mps11-wrstbi-ground");
-	return pd;
-}
-
-static int sec_pmic_probe(struct i2c_client *i2c)
-{
-	const struct regmap_config *regmap;
-	struct sec_platform_data *pdata;
-	const struct mfd_cell *sec_devs;
-	struct sec_pmic_dev *sec_pmic;
-	int ret, num_sec_devs;
-
-	sec_pmic = devm_kzalloc(&i2c->dev, sizeof(struct sec_pmic_dev),
-				GFP_KERNEL);
-	if (sec_pmic == NULL)
-		return -ENOMEM;
-
-	i2c_set_clientdata(i2c, sec_pmic);
-	sec_pmic->dev = &i2c->dev;
-	sec_pmic->i2c = i2c;
-	sec_pmic->irq = i2c->irq;
-
-	pdata = sec_pmic_i2c_parse_dt_pdata(sec_pmic->dev);
-	if (IS_ERR(pdata)) {
-		ret = PTR_ERR(pdata);
-		return ret;
-	}
-
-	sec_pmic->device_type = (unsigned long)of_device_get_match_data(sec_pmic->dev);
-	sec_pmic->pdata = pdata;
-
-	switch (sec_pmic->device_type) {
-	case S2MPA01:
-		regmap = &s2mpa01_regmap_config;
-		break;
-	case S2MPS11X:
-		regmap = &s2mps11_regmap_config;
-		break;
-	case S2MPS13X:
-		regmap = &s2mps13_regmap_config;
-		break;
-	case S2MPS14X:
-		regmap = &s2mps14_regmap_config;
-		break;
-	case S2MPS15X:
-		regmap = &s2mps15_regmap_config;
-		break;
-	case S5M8767X:
-		regmap = &s5m8767_regmap_config;
-		break;
-	case S2MPU02:
-		regmap = &s2mpu02_regmap_config;
-		break;
-	default:
-		regmap = &sec_regmap_config;
-		break;
-	}
-
-	sec_pmic->regmap_pmic = devm_regmap_init_i2c(i2c, regmap);
-	if (IS_ERR(sec_pmic->regmap_pmic)) {
-		ret = PTR_ERR(sec_pmic->regmap_pmic);
-		dev_err(&i2c->dev, "Failed to allocate register map: %d\n",
-			ret);
-		return ret;
-	}
-
-	sec_irq_init(sec_pmic);
-
-	pm_runtime_set_active(sec_pmic->dev);
-
-	switch (sec_pmic->device_type) {
-	case S5M8767X:
-		sec_devs = s5m8767_devs;
-		num_sec_devs = ARRAY_SIZE(s5m8767_devs);
-		break;
-	case S2DOS05:
-		sec_devs = s2dos05_devs;
-		num_sec_devs = ARRAY_SIZE(s2dos05_devs);
-		break;
-	case S2MPA01:
-		sec_devs = s2mpa01_devs;
-		num_sec_devs = ARRAY_SIZE(s2mpa01_devs);
-		break;
-	case S2MPS11X:
-		sec_devs = s2mps11_devs;
-		num_sec_devs = ARRAY_SIZE(s2mps11_devs);
-		break;
-	case S2MPS13X:
-		sec_devs = s2mps13_devs;
-		num_sec_devs = ARRAY_SIZE(s2mps13_devs);
-		break;
-	case S2MPS14X:
-		sec_devs = s2mps14_devs;
-		num_sec_devs = ARRAY_SIZE(s2mps14_devs);
-		break;
-	case S2MPS15X:
-		sec_devs = s2mps15_devs;
-		num_sec_devs = ARRAY_SIZE(s2mps15_devs);
-		break;
-	case S2MPU02:
-		sec_devs = s2mpu02_devs;
-		num_sec_devs = ARRAY_SIZE(s2mpu02_devs);
-		break;
-	case S2MPU05:
-		sec_devs = s2mpu05_devs;
-		num_sec_devs = ARRAY_SIZE(s2mpu05_devs);
-		break;
-	default:
-		dev_err(&i2c->dev, "Unsupported device type (%lu)\n",
-			sec_pmic->device_type);
-		return -ENODEV;
-	}
-	ret = devm_mfd_add_devices(sec_pmic->dev, -1, sec_devs, num_sec_devs,
-				   NULL, 0, NULL);
-	if (ret)
-		return ret;
-
-	sec_pmic_configure(sec_pmic);
-	sec_pmic_dump_rev(sec_pmic);
-
-	return ret;
-}
-
-static void sec_pmic_shutdown(struct i2c_client *i2c)
-{
-	struct sec_pmic_dev *sec_pmic = i2c_get_clientdata(i2c);
-	unsigned int reg, mask;
-
-	if (!sec_pmic->pdata->manual_poweroff)
-		return;
-
-	switch (sec_pmic->device_type) {
-	case S2MPS11X:
-		reg = S2MPS11_REG_CTRL1;
-		mask = S2MPS11_CTRL1_PWRHOLD_MASK;
-		break;
-	default:
-		/*
-		 * Currently only one board with S2MPS11 needs this, so just
-		 * ignore the rest.
-		 */
-		dev_warn(sec_pmic->dev,
-			"Unsupported device %lu for manual power off\n",
-			sec_pmic->device_type);
-		return;
-	}
-
-	regmap_update_bits(sec_pmic->regmap_pmic, reg, mask, 0);
-}
-
-static int sec_pmic_suspend(struct device *dev)
-{
-	struct i2c_client *i2c = to_i2c_client(dev);
-	struct sec_pmic_dev *sec_pmic = i2c_get_clientdata(i2c);
-
-	if (device_may_wakeup(dev))
-		enable_irq_wake(sec_pmic->irq);
-	/*
-	 * PMIC IRQ must be disabled during suspend for RTC alarm
-	 * to work properly.
-	 * When device is woken up from suspend, an
-	 * interrupt occurs before resuming I2C bus controller.
-	 * The interrupt is handled by regmap_irq_thread which tries
-	 * to read RTC registers. This read fails (I2C is still
-	 * suspended) and RTC Alarm interrupt is disabled.
-	 */
-	disable_irq(sec_pmic->irq);
-
-	return 0;
-}
-
-static int sec_pmic_resume(struct device *dev)
-{
-	struct i2c_client *i2c = to_i2c_client(dev);
-	struct sec_pmic_dev *sec_pmic = i2c_get_clientdata(i2c);
-
-	if (device_may_wakeup(dev))
-		disable_irq_wake(sec_pmic->irq);
-	enable_irq(sec_pmic->irq);
-
-	return 0;
-}
-
-static DEFINE_SIMPLE_DEV_PM_OPS(sec_pmic_pm_ops,
-				sec_pmic_suspend, sec_pmic_resume);
-
-static struct i2c_driver sec_pmic_driver = {
-	.driver = {
-		   .name = "sec_pmic",
-		   .pm = pm_sleep_ptr(&sec_pmic_pm_ops),
-		   .of_match_table = sec_dt_match,
-	},
-	.probe = sec_pmic_probe,
-	.shutdown = sec_pmic_shutdown,
-};
-module_i2c_driver(sec_pmic_driver);
-
-MODULE_AUTHOR("Sangbeom Kim <sbkim73@samsung.com>");
-MODULE_DESCRIPTION("Core support for the S5M MFD");
-MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/sec-core.h b/drivers/mfd/sec-core.h
new file mode 100644
index 000000000000..92c7558ab8b0
--- /dev/null
+++ b/drivers/mfd/sec-core.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright 2012 Samsung Electronics Co., Ltd
+ *                http://www.samsung.com
+ * Copyright 2025 Linaro Ltd.
+ *
+ * Samsung SxM core driver internal data
+ */
+
+#ifndef __SEC_CORE_INT_H
+#define __SEC_CORE_INT_H
+
+struct i2c_client;
+
+extern const struct dev_pm_ops sec_pmic_pm_ops;
+
+int sec_pmic_probe(struct device *dev, int device_type, unsigned int irq,
+		   struct regmap *regmap, struct i2c_client *client);
+void sec_pmic_shutdown(struct device *dev);
+
+int sec_irq_init(struct sec_pmic_dev *sec_pmic);
+
+#endif /* __SEC_CORE_INT_H */
diff --git a/drivers/mfd/sec-i2c.c b/drivers/mfd/sec-i2c.c
new file mode 100644
index 000000000000..3132b849b4bc
--- /dev/null
+++ b/drivers/mfd/sec-i2c.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2012 Samsung Electronics Co., Ltd
+ *                http://www.samsung.com
+ * Copyright 2025 Linaro Ltd.
+ *
+ * Samsung SxM I2C driver
+ */
+
+#include <linux/dev_printk.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/mfd/samsung/core.h>
+#include <linux/mfd/samsung/s2mpa01.h>
+#include <linux/mfd/samsung/s2mps11.h>
+#include <linux/mfd/samsung/s2mps13.h>
+#include <linux/mfd/samsung/s2mps14.h>
+#include <linux/mfd/samsung/s2mps15.h>
+#include <linux/mfd/samsung/s2mpu02.h>
+#include <linux/mfd/samsung/s5m8767.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/pm.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+#include "sec-core.h"
+
+struct sec_pmic_i2c_platform_data {
+	const struct regmap_config *regmap_cfg;
+	int device_type;
+};
+
+static bool s2mpa01_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case S2MPA01_REG_INT1M:
+	case S2MPA01_REG_INT2M:
+	case S2MPA01_REG_INT3M:
+		return false;
+	default:
+		return true;
+	}
+}
+
+static bool s2mps11_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case S2MPS11_REG_INT1M:
+	case S2MPS11_REG_INT2M:
+	case S2MPS11_REG_INT3M:
+		return false;
+	default:
+		return true;
+	}
+}
+
+static bool s2mpu02_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case S2MPU02_REG_INT1M:
+	case S2MPU02_REG_INT2M:
+	case S2MPU02_REG_INT3M:
+		return false;
+	default:
+		return true;
+	}
+}
+
+static const struct regmap_config s2dos05_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+};
+
+static const struct regmap_config s2mpa01_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = S2MPA01_REG_LDO_OVCB4,
+	.volatile_reg = s2mpa01_volatile,
+	.cache_type = REGCACHE_FLAT,
+};
+
+static const struct regmap_config s2mps11_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = S2MPS11_REG_L38CTRL,
+	.volatile_reg = s2mps11_volatile,
+	.cache_type = REGCACHE_FLAT,
+};
+
+static const struct regmap_config s2mps13_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = S2MPS13_REG_LDODSCH5,
+	.volatile_reg = s2mps11_volatile,
+	.cache_type = REGCACHE_FLAT,
+};
+
+static const struct regmap_config s2mps14_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = S2MPS14_REG_LDODSCH3,
+	.volatile_reg = s2mps11_volatile,
+	.cache_type = REGCACHE_FLAT,
+};
+
+static const struct regmap_config s2mps15_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = S2MPS15_REG_LDODSCH4,
+	.volatile_reg = s2mps11_volatile,
+	.cache_type = REGCACHE_FLAT,
+};
+
+static const struct regmap_config s2mpu02_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = S2MPU02_REG_DVSDATA,
+	.volatile_reg = s2mpu02_volatile,
+	.cache_type = REGCACHE_FLAT,
+};
+
+static const struct regmap_config s2mpu05_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+};
+
+static const struct regmap_config s5m8767_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = S5M8767_REG_LDO28CTRL,
+	.volatile_reg = s2mps11_volatile,
+	.cache_type = REGCACHE_FLAT,
+};
+
+static int sec_pmic_i2c_probe(struct i2c_client *client)
+{
+	const struct sec_pmic_i2c_platform_data *pdata;
+	struct regmap *regmap_pmic;
+
+	pdata = device_get_match_data(&client->dev);
+	if (!pdata)
+		return dev_err_probe(&client->dev, -ENODEV,
+				     "Unsupported device type\n");
+
+	regmap_pmic = devm_regmap_init_i2c(client, pdata->regmap_cfg);
+	if (IS_ERR(regmap_pmic))
+		return dev_err_probe(&client->dev, PTR_ERR(regmap_pmic),
+				     "regmap init failed\n");
+
+	return sec_pmic_probe(&client->dev, pdata->device_type, client->irq,
+			      regmap_pmic, client);
+}
+
+static void sec_pmic_i2c_shutdown(struct i2c_client *i2c)
+{
+	sec_pmic_shutdown(&i2c->dev);
+}
+
+static const struct sec_pmic_i2c_platform_data s2dos05_data = {
+	.regmap_cfg = &s2dos05_regmap_config,
+	.device_type = S2DOS05
+};
+
+static const struct sec_pmic_i2c_platform_data s2mpa01_data = {
+	.regmap_cfg = &s2mpa01_regmap_config,
+	.device_type = S2MPA01,
+};
+
+static const struct sec_pmic_i2c_platform_data s2mps11_data = {
+	.regmap_cfg = &s2mps11_regmap_config,
+	.device_type = S2MPS11X,
+};
+
+static const struct sec_pmic_i2c_platform_data s2mps13_data = {
+	.regmap_cfg = &s2mps13_regmap_config,
+	.device_type = S2MPS13X,
+};
+
+static const struct sec_pmic_i2c_platform_data s2mps14_data = {
+	.regmap_cfg = &s2mps14_regmap_config,
+	.device_type = S2MPS14X,
+};
+
+static const struct sec_pmic_i2c_platform_data s2mps15_data = {
+	.regmap_cfg = &s2mps15_regmap_config,
+	.device_type = S2MPS15X,
+};
+
+static const struct sec_pmic_i2c_platform_data s2mpu02_data = {
+	.regmap_cfg = &s2mpu02_regmap_config,
+	.device_type = S2MPU02,
+};
+
+static const struct sec_pmic_i2c_platform_data s2mpu05_data = {
+	.regmap_cfg = &s2mpu05_regmap_config,
+	.device_type = S2MPU05,
+};
+
+static const struct sec_pmic_i2c_platform_data s5m8767_data = {
+	.regmap_cfg = &s5m8767_regmap_config,
+	.device_type = S5M8767X,
+};
+
+static const struct of_device_id sec_pmic_i2c_of_match[] = {
+	{ .compatible = "samsung,s2dos05", .data = &s2dos05_data, },
+	{ .compatible = "samsung,s2mpa01-pmic", .data = &s2mpa01_data, },
+	{ .compatible = "samsung,s2mps11-pmic", .data = &s2mps11_data, },
+	{ .compatible = "samsung,s2mps13-pmic", .data = &s2mps13_data, },
+	{ .compatible = "samsung,s2mps14-pmic", .data = &s2mps14_data, },
+	{ .compatible = "samsung,s2mps15-pmic", .data = &s2mps15_data, },
+	{ .compatible = "samsung,s2mpu02-pmic", .data = &s2mpu02_data, },
+	{ .compatible = "samsung,s2mpu05-pmic", .data = &s2mpu05_data, },
+	{ .compatible = "samsung,s5m8767-pmic", .data = &s5m8767_data, },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, sec_pmic_i2c_of_match);
+
+static struct i2c_driver sec_pmic_i2c_driver = {
+	.driver = {
+		.name = "sec-pmic-i2c",
+		.pm = pm_sleep_ptr(&sec_pmic_pm_ops),
+		.of_match_table = sec_pmic_i2c_of_match,
+	},
+	.probe = sec_pmic_i2c_probe,
+	.shutdown = sec_pmic_i2c_shutdown,
+};
+module_i2c_driver(sec_pmic_i2c_driver);
+
+MODULE_AUTHOR("Sangbeom Kim <sbkim73@samsung.com>");
+MODULE_AUTHOR("André Draszik <andre.draszik@linaro.org>");
+MODULE_DESCRIPTION("I2C driver for the Samsung S5M");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/sec-irq.c b/drivers/mfd/sec-irq.c
index 047fc065fcf1..c5c80b1ba104 100644
--- a/drivers/mfd/sec-irq.c
+++ b/drivers/mfd/sec-irq.c
@@ -3,227 +3,139 @@
 // Copyright (c) 2011-2014 Samsung Electronics Co., Ltd
 //              http://www.samsung.com
 
-#include <linux/device.h>
+#include <linux/array_size.h>
+#include <linux/build_bug.h>
+#include <linux/dev_printk.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <linux/module.h>
-#include <linux/regmap.h>
-
 #include <linux/mfd/samsung/core.h>
 #include <linux/mfd/samsung/irq.h>
+#include <linux/mfd/samsung/s2mpg10.h>
 #include <linux/mfd/samsung/s2mps11.h>
 #include <linux/mfd/samsung/s2mps14.h>
 #include <linux/mfd/samsung/s2mpu02.h>
 #include <linux/mfd/samsung/s2mpu05.h>
 #include <linux/mfd/samsung/s5m8767.h>
+#include <linux/regmap.h>
+#include "sec-core.h"
+
+static const struct regmap_irq s2mpg10_irqs[] = {
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PWRONF, 0, S2MPG10_IRQ_PWRONF_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PWRONR, 0, S2MPG10_IRQ_PWRONR_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_JIGONBF, 0, S2MPG10_IRQ_JIGONBF_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_JIGONBR, 0, S2MPG10_IRQ_JIGONBR_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_ACOKBF, 0, S2MPG10_IRQ_ACOKBF_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_ACOKBR, 0, S2MPG10_IRQ_ACOKBR_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PWRON1S, 0, S2MPG10_IRQ_PWRON1S_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_MRB, 0, S2MPG10_IRQ_MRB_MASK),
+
+	REGMAP_IRQ_REG(S2MPG10_IRQ_RTC60S, 1, S2MPG10_IRQ_RTC60S_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_RTCA1, 1, S2MPG10_IRQ_RTCA1_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_RTCA0, 1, S2MPG10_IRQ_RTCA0_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_RTC1S, 1, S2MPG10_IRQ_RTC1S_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_WTSR_COLDRST, 1, S2MPG10_IRQ_WTSR_COLDRST_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_WTSR, 1, S2MPG10_IRQ_WTSR_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_WRST, 1, S2MPG10_IRQ_WRST_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_SMPL, 1, S2MPG10_IRQ_SMPL_MASK),
+
+	REGMAP_IRQ_REG(S2MPG10_IRQ_120C, 2, S2MPG10_IRQ_INT120C_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_140C, 2, S2MPG10_IRQ_INT140C_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_TSD, 2, S2MPG10_IRQ_TSD_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PIF_TIMEOUT1, 2, S2MPG10_IRQ_PIF_TIMEOUT1_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PIF_TIMEOUT2, 2, S2MPG10_IRQ_PIF_TIMEOUT2_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_SPD_PARITY_ERR, 2, S2MPG10_IRQ_SPD_PARITY_ERR_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_SPD_ABNORMAL_STOP, 2, S2MPG10_IRQ_SPD_ABNORMAL_STOP_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PMETER_OVERF, 2, S2MPG10_IRQ_PMETER_OVERF_MASK),
+
+	REGMAP_IRQ_REG(S2MPG10_IRQ_OCP_B1M, 3, S2MPG10_IRQ_OCP_B1M_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_OCP_B2M, 3, S2MPG10_IRQ_OCP_B2M_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_OCP_B3M, 3, S2MPG10_IRQ_OCP_B3M_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_OCP_B4M, 3, S2MPG10_IRQ_OCP_B4M_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_OCP_B5M, 3, S2MPG10_IRQ_OCP_B5M_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_OCP_B6M, 3, S2MPG10_IRQ_OCP_B6M_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_OCP_B7M, 3, S2MPG10_IRQ_OCP_B7M_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_OCP_B8M, 3, S2MPG10_IRQ_OCP_B8M_MASK),
+
+	REGMAP_IRQ_REG(S2MPG10_IRQ_OCP_B9M, 4, S2MPG10_IRQ_OCP_B9M_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_OCP_B10M, 4, S2MPG10_IRQ_OCP_B10M_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_WLWP_ACC, 4, S2MPG10_IRQ_WLWP_ACC_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_SMPL_TIMEOUT, 4, S2MPG10_IRQ_SMPL_TIMEOUT_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_WTSR_TIMEOUT, 4, S2MPG10_IRQ_WTSR_TIMEOUT_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_SPD_SRP_PKT_RST, 4, S2MPG10_IRQ_SPD_SRP_PKT_RST_MASK),
+
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PWR_WARN_CH0, 5, S2MPG10_IRQ_PWR_WARN_CH0_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PWR_WARN_CH1, 5, S2MPG10_IRQ_PWR_WARN_CH1_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PWR_WARN_CH2, 5, S2MPG10_IRQ_PWR_WARN_CH2_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PWR_WARN_CH3, 5, S2MPG10_IRQ_PWR_WARN_CH3_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PWR_WARN_CH4, 5, S2MPG10_IRQ_PWR_WARN_CH4_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PWR_WARN_CH5, 5, S2MPG10_IRQ_PWR_WARN_CH5_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PWR_WARN_CH6, 5, S2MPG10_IRQ_PWR_WARN_CH6_MASK),
+	REGMAP_IRQ_REG(S2MPG10_IRQ_PWR_WARN_CH7, 5, S2MPG10_IRQ_PWR_WARN_CH7_MASK),
+};
 
 static const struct regmap_irq s2mps11_irqs[] = {
-	[S2MPS11_IRQ_PWRONF] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_PWRONF_MASK,
-	},
-	[S2MPS11_IRQ_PWRONR] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_PWRONR_MASK,
-	},
-	[S2MPS11_IRQ_JIGONBF] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_JIGONBF_MASK,
-	},
-	[S2MPS11_IRQ_JIGONBR] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_JIGONBR_MASK,
-	},
-	[S2MPS11_IRQ_ACOKBF] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_ACOKBF_MASK,
-	},
-	[S2MPS11_IRQ_ACOKBR] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_ACOKBR_MASK,
-	},
-	[S2MPS11_IRQ_PWRON1S] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_PWRON1S_MASK,
-	},
-	[S2MPS11_IRQ_MRB] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_MRB_MASK,
-	},
-	[S2MPS11_IRQ_RTC60S] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTC60S_MASK,
-	},
-	[S2MPS11_IRQ_RTCA1] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTCA1_MASK,
-	},
-	[S2MPS11_IRQ_RTCA0] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTCA0_MASK,
-	},
-	[S2MPS11_IRQ_SMPL] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_SMPL_MASK,
-	},
-	[S2MPS11_IRQ_RTC1S] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTC1S_MASK,
-	},
-	[S2MPS11_IRQ_WTSR] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_WTSR_MASK,
-	},
-	[S2MPS11_IRQ_INT120C] = {
-		.reg_offset = 2,
-		.mask = S2MPS11_IRQ_INT120C_MASK,
-	},
-	[S2MPS11_IRQ_INT140C] = {
-		.reg_offset = 2,
-		.mask = S2MPS11_IRQ_INT140C_MASK,
-	},
+	REGMAP_IRQ_REG(S2MPS11_IRQ_PWRONF, 0, S2MPS11_IRQ_PWRONF_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_PWRONR, 0, S2MPS11_IRQ_PWRONR_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_JIGONBF, 0, S2MPS11_IRQ_JIGONBF_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_JIGONBR, 0, S2MPS11_IRQ_JIGONBR_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_ACOKBF, 0, S2MPS11_IRQ_ACOKBF_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_ACOKBR, 0, S2MPS11_IRQ_ACOKBR_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_PWRON1S, 0, S2MPS11_IRQ_PWRON1S_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_MRB, 0, S2MPS11_IRQ_MRB_MASK),
+
+	REGMAP_IRQ_REG(S2MPS11_IRQ_RTC60S, 1, S2MPS11_IRQ_RTC60S_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_RTCA1, 1, S2MPS11_IRQ_RTCA1_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_RTCA0, 1, S2MPS11_IRQ_RTCA0_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_SMPL, 1, S2MPS11_IRQ_SMPL_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_RTC1S, 1, S2MPS11_IRQ_RTC1S_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_WTSR, 1, S2MPS11_IRQ_WTSR_MASK),
+
+	REGMAP_IRQ_REG(S2MPS11_IRQ_INT120C, 2, S2MPS11_IRQ_INT120C_MASK),
+	REGMAP_IRQ_REG(S2MPS11_IRQ_INT140C, 2, S2MPS11_IRQ_INT140C_MASK),
 };
 
 static const struct regmap_irq s2mps14_irqs[] = {
-	[S2MPS14_IRQ_PWRONF] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_PWRONF_MASK,
-	},
-	[S2MPS14_IRQ_PWRONR] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_PWRONR_MASK,
-	},
-	[S2MPS14_IRQ_JIGONBF] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_JIGONBF_MASK,
-	},
-	[S2MPS14_IRQ_JIGONBR] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_JIGONBR_MASK,
-	},
-	[S2MPS14_IRQ_ACOKBF] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_ACOKBF_MASK,
-	},
-	[S2MPS14_IRQ_ACOKBR] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_ACOKBR_MASK,
-	},
-	[S2MPS14_IRQ_PWRON1S] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_PWRON1S_MASK,
-	},
-	[S2MPS14_IRQ_MRB] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_MRB_MASK,
-	},
-	[S2MPS14_IRQ_RTC60S] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTC60S_MASK,
-	},
-	[S2MPS14_IRQ_RTCA1] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTCA1_MASK,
-	},
-	[S2MPS14_IRQ_RTCA0] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTCA0_MASK,
-	},
-	[S2MPS14_IRQ_SMPL] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_SMPL_MASK,
-	},
-	[S2MPS14_IRQ_RTC1S] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTC1S_MASK,
-	},
-	[S2MPS14_IRQ_WTSR] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_WTSR_MASK,
-	},
-	[S2MPS14_IRQ_INT120C] = {
-		.reg_offset = 2,
-		.mask = S2MPS11_IRQ_INT120C_MASK,
-	},
-	[S2MPS14_IRQ_INT140C] = {
-		.reg_offset = 2,
-		.mask = S2MPS11_IRQ_INT140C_MASK,
-	},
-	[S2MPS14_IRQ_TSD] = {
-		.reg_offset = 2,
-		.mask = S2MPS14_IRQ_TSD_MASK,
-	},
+	REGMAP_IRQ_REG(S2MPS14_IRQ_PWRONF, 0, S2MPS11_IRQ_PWRONF_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_PWRONR, 0, S2MPS11_IRQ_PWRONR_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_JIGONBF, 0, S2MPS11_IRQ_JIGONBF_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_JIGONBR, 0, S2MPS11_IRQ_JIGONBR_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_ACOKBF, 0, S2MPS11_IRQ_ACOKBF_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_ACOKBR, 0, S2MPS11_IRQ_ACOKBR_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_PWRON1S, 0, S2MPS11_IRQ_PWRON1S_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_MRB, 0, S2MPS11_IRQ_MRB_MASK),
+
+	REGMAP_IRQ_REG(S2MPS14_IRQ_RTC60S, 1, S2MPS11_IRQ_RTC60S_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_RTCA1, 1, S2MPS11_IRQ_RTCA1_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_RTCA0, 1, S2MPS11_IRQ_RTCA0_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_SMPL, 1, S2MPS11_IRQ_SMPL_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_RTC1S, 1, S2MPS11_IRQ_RTC1S_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_WTSR, 1, S2MPS11_IRQ_WTSR_MASK),
+
+	REGMAP_IRQ_REG(S2MPS14_IRQ_INT120C, 2, S2MPS11_IRQ_INT120C_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_INT140C, 2, S2MPS11_IRQ_INT140C_MASK),
+	REGMAP_IRQ_REG(S2MPS14_IRQ_TSD, 2, S2MPS14_IRQ_TSD_MASK),
 };
 
 static const struct regmap_irq s2mpu02_irqs[] = {
-	[S2MPU02_IRQ_PWRONF] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_PWRONF_MASK,
-	},
-	[S2MPU02_IRQ_PWRONR] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_PWRONR_MASK,
-	},
-	[S2MPU02_IRQ_JIGONBF] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_JIGONBF_MASK,
-	},
-	[S2MPU02_IRQ_JIGONBR] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_JIGONBR_MASK,
-	},
-	[S2MPU02_IRQ_ACOKBF] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_ACOKBF_MASK,
-	},
-	[S2MPU02_IRQ_ACOKBR] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_ACOKBR_MASK,
-	},
-	[S2MPU02_IRQ_PWRON1S] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_PWRON1S_MASK,
-	},
-	[S2MPU02_IRQ_MRB] = {
-		.reg_offset = 0,
-		.mask = S2MPS11_IRQ_MRB_MASK,
-	},
-	[S2MPU02_IRQ_RTC60S] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTC60S_MASK,
-	},
-	[S2MPU02_IRQ_RTCA1] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTCA1_MASK,
-	},
-	[S2MPU02_IRQ_RTCA0] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTCA0_MASK,
-	},
-	[S2MPU02_IRQ_SMPL] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_SMPL_MASK,
-	},
-	[S2MPU02_IRQ_RTC1S] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTC1S_MASK,
-	},
-	[S2MPU02_IRQ_WTSR] = {
-		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_WTSR_MASK,
-	},
-	[S2MPU02_IRQ_INT120C] = {
-		.reg_offset = 2,
-		.mask = S2MPS11_IRQ_INT120C_MASK,
-	},
-	[S2MPU02_IRQ_INT140C] = {
-		.reg_offset = 2,
-		.mask = S2MPS11_IRQ_INT140C_MASK,
-	},
-	[S2MPU02_IRQ_TSD] = {
-		.reg_offset = 2,
-		.mask = S2MPS14_IRQ_TSD_MASK,
-	},
+	REGMAP_IRQ_REG(S2MPU02_IRQ_PWRONF, 0, S2MPS11_IRQ_PWRONF_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_PWRONR, 0, S2MPS11_IRQ_PWRONR_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_JIGONBF, 0, S2MPS11_IRQ_JIGONBF_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_JIGONBR, 0, S2MPS11_IRQ_JIGONBR_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_ACOKBF, 0, S2MPS11_IRQ_ACOKBF_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_ACOKBR, 0, S2MPS11_IRQ_ACOKBR_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_PWRON1S, 0, S2MPS11_IRQ_PWRON1S_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_MRB, 0, S2MPS11_IRQ_MRB_MASK),
+
+	REGMAP_IRQ_REG(S2MPU02_IRQ_RTC60S, 1, S2MPS11_IRQ_RTC60S_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_RTCA1, 1, S2MPS11_IRQ_RTCA1_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_RTCA0, 1, S2MPS11_IRQ_RTCA0_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_SMPL, 1, S2MPS11_IRQ_SMPL_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_RTC1S, 1, S2MPS11_IRQ_RTC1S_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_WTSR, 1, S2MPS11_IRQ_WTSR_MASK),
+
+	REGMAP_IRQ_REG(S2MPU02_IRQ_INT120C, 2, S2MPS11_IRQ_INT120C_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_INT140C, 2, S2MPS11_IRQ_INT140C_MASK),
+	REGMAP_IRQ_REG(S2MPU02_IRQ_TSD, 2, S2MPS14_IRQ_TSD_MASK),
 };
 
 static const struct regmap_irq s2mpu05_irqs[] = {
@@ -247,74 +159,35 @@ static const struct regmap_irq s2mpu05_irqs[] = {
 };
 
 static const struct regmap_irq s5m8767_irqs[] = {
-	[S5M8767_IRQ_PWRR] = {
-		.reg_offset = 0,
-		.mask = S5M8767_IRQ_PWRR_MASK,
-	},
-	[S5M8767_IRQ_PWRF] = {
-		.reg_offset = 0,
-		.mask = S5M8767_IRQ_PWRF_MASK,
-	},
-	[S5M8767_IRQ_PWR1S] = {
-		.reg_offset = 0,
-		.mask = S5M8767_IRQ_PWR1S_MASK,
-	},
-	[S5M8767_IRQ_JIGR] = {
-		.reg_offset = 0,
-		.mask = S5M8767_IRQ_JIGR_MASK,
-	},
-	[S5M8767_IRQ_JIGF] = {
-		.reg_offset = 0,
-		.mask = S5M8767_IRQ_JIGF_MASK,
-	},
-	[S5M8767_IRQ_LOWBAT2] = {
-		.reg_offset = 0,
-		.mask = S5M8767_IRQ_LOWBAT2_MASK,
-	},
-	[S5M8767_IRQ_LOWBAT1] = {
-		.reg_offset = 0,
-		.mask = S5M8767_IRQ_LOWBAT1_MASK,
-	},
-	[S5M8767_IRQ_MRB] = {
-		.reg_offset = 1,
-		.mask = S5M8767_IRQ_MRB_MASK,
-	},
-	[S5M8767_IRQ_DVSOK2] = {
-		.reg_offset = 1,
-		.mask = S5M8767_IRQ_DVSOK2_MASK,
-	},
-	[S5M8767_IRQ_DVSOK3] = {
-		.reg_offset = 1,
-		.mask = S5M8767_IRQ_DVSOK3_MASK,
-	},
-	[S5M8767_IRQ_DVSOK4] = {
-		.reg_offset = 1,
-		.mask = S5M8767_IRQ_DVSOK4_MASK,
-	},
-	[S5M8767_IRQ_RTC60S] = {
-		.reg_offset = 2,
-		.mask = S5M8767_IRQ_RTC60S_MASK,
-	},
-	[S5M8767_IRQ_RTCA1] = {
-		.reg_offset = 2,
-		.mask = S5M8767_IRQ_RTCA1_MASK,
-	},
-	[S5M8767_IRQ_RTCA2] = {
-		.reg_offset = 2,
-		.mask = S5M8767_IRQ_RTCA2_MASK,
-	},
-	[S5M8767_IRQ_SMPL] = {
-		.reg_offset = 2,
-		.mask = S5M8767_IRQ_SMPL_MASK,
-	},
-	[S5M8767_IRQ_RTC1S] = {
-		.reg_offset = 2,
-		.mask = S5M8767_IRQ_RTC1S_MASK,
-	},
-	[S5M8767_IRQ_WTSR] = {
-		.reg_offset = 2,
-		.mask = S5M8767_IRQ_WTSR_MASK,
-	},
+	REGMAP_IRQ_REG(S5M8767_IRQ_PWRR, 0, S5M8767_IRQ_PWRR_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_PWRF, 0, S5M8767_IRQ_PWRF_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_PWR1S, 0, S5M8767_IRQ_PWR1S_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_JIGR, 0, S5M8767_IRQ_JIGR_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_JIGF, 0, S5M8767_IRQ_JIGF_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_LOWBAT2, 0, S5M8767_IRQ_LOWBAT2_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_LOWBAT1, 0, S5M8767_IRQ_LOWBAT1_MASK),
+
+	REGMAP_IRQ_REG(S5M8767_IRQ_MRB, 1, S5M8767_IRQ_MRB_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_DVSOK2, 1, S5M8767_IRQ_DVSOK2_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_DVSOK3, 1, S5M8767_IRQ_DVSOK3_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_DVSOK4, 1, S5M8767_IRQ_DVSOK4_MASK),
+
+	REGMAP_IRQ_REG(S5M8767_IRQ_RTC60S, 2, S5M8767_IRQ_RTC60S_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_RTCA1, 2, S5M8767_IRQ_RTCA1_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_RTCA2, 2, S5M8767_IRQ_RTCA2_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_SMPL, 2, S5M8767_IRQ_SMPL_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_RTC1S, 2, S5M8767_IRQ_RTC1S_MASK),
+	REGMAP_IRQ_REG(S5M8767_IRQ_WTSR, 2, S5M8767_IRQ_WTSR_MASK),
+};
+
+/* All S2MPG10 interrupt sources are read-only and don't require clearing */
+static const struct regmap_irq_chip s2mpg10_irq_chip = {
+	.name = "s2mpg10",
+	.irqs = s2mpg10_irqs,
+	.num_irqs = ARRAY_SIZE(s2mpg10_irqs),
+	.num_regs = 6,
+	.status_base = S2MPG10_PMIC_INT1,
+	.mask_base = S2MPG10_PMIC_INT1M,
 };
 
 static const struct regmap_irq_chip s2mps11_irq_chip = {
@@ -382,23 +255,21 @@ static const struct regmap_irq_chip s5m8767_irq_chip = {
 
 int sec_irq_init(struct sec_pmic_dev *sec_pmic)
 {
-	int ret = 0;
-	int type = sec_pmic->device_type;
 	const struct regmap_irq_chip *sec_irq_chip;
+	int ret;
 
-	if (!sec_pmic->irq) {
-		dev_warn(sec_pmic->dev,
-			 "No interrupt specified, no interrupts\n");
-		return 0;
-	}
-
-	switch (type) {
+	switch (sec_pmic->device_type) {
 	case S5M8767X:
 		sec_irq_chip = &s5m8767_irq_chip;
 		break;
+	case S2DOS05:
+		return 0;
 	case S2MPA01:
 		sec_irq_chip = &s2mps14_irq_chip;
 		break;
+	case S2MPG10:
+		sec_irq_chip = &s2mpg10_irq_chip;
+		break;
 	case S2MPS11X:
 		sec_irq_chip = &s2mps11_irq_chip;
 		break;
@@ -418,18 +289,24 @@ int sec_irq_init(struct sec_pmic_dev *sec_pmic)
 		sec_irq_chip = &s2mpu05_irq_chip;
 		break;
 	default:
-		dev_err(sec_pmic->dev, "Unknown device type %lu\n",
-			sec_pmic->device_type);
-		return -EINVAL;
+		return dev_err_probe(sec_pmic->dev, -EINVAL,
+				     "Unsupported device type %d\n",
+				     sec_pmic->device_type);
+	}
+
+	if (!sec_pmic->irq) {
+		dev_warn(sec_pmic->dev,
+			 "No interrupt specified, no interrupts\n");
+		return 0;
 	}
 
 	ret = devm_regmap_add_irq_chip(sec_pmic->dev, sec_pmic->regmap_pmic,
 				       sec_pmic->irq, IRQF_ONESHOT,
 				       0, sec_irq_chip, &sec_pmic->irq_data);
-	if (ret != 0) {
-		dev_err(sec_pmic->dev, "Failed to register IRQ chip: %d\n", ret);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(sec_pmic->dev, ret,
+				     "Failed to add %s IRQ chip\n",
+				     sec_irq_chip->name);
 
 	/*
 	 * The rtc-s5m driver requests S2MPS14_IRQ_RTCA0 also for S2MPS11
@@ -439,10 +316,3 @@ int sec_irq_init(struct sec_pmic_dev *sec_pmic)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(sec_irq_init);
-
-MODULE_AUTHOR("Sangbeom Kim <sbkim73@samsung.com>");
-MODULE_AUTHOR("Chanwoo Choi <cw00.choi@samsung.com>");
-MODULE_AUTHOR("Krzysztof Kozlowski <krzk@kernel.org>");
-MODULE_DESCRIPTION("Interrupt support for the S5M MFD");
-MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c
index 7ee293b09f62..a5f9241fa3f2 100644
--- a/drivers/mfd/sm501.c
+++ b/drivers/mfd/sm501.c
@@ -631,49 +631,6 @@ unsigned long sm501_set_clock(struct device *dev,
 
 EXPORT_SYMBOL_GPL(sm501_set_clock);
 
-/* sm501_find_clock
- *
- * finds the closest available frequency for a given clock
-*/
-
-unsigned long sm501_find_clock(struct device *dev,
-			       int clksrc,
-			       unsigned long req_freq)
-{
-	struct sm501_devdata *sm = dev_get_drvdata(dev);
-	unsigned long sm501_freq; /* the frequency achieveable by the 501 */
-	struct sm501_clock to;
-
-	switch (clksrc) {
-	case SM501_CLOCK_P2XCLK:
-		if (sm->rev >= 0xC0) {
-			/* SM502 -> use the programmable PLL */
-			sm501_freq = (sm501_calc_pll(2 * req_freq,
-						     &to, 5) / 2);
-		} else {
-			sm501_freq = (sm501_select_clock(2 * req_freq,
-							 &to, 5) / 2);
-		}
-		break;
-
-	case SM501_CLOCK_V2XCLK:
-		sm501_freq = (sm501_select_clock(2 * req_freq, &to, 3) / 2);
-		break;
-
-	case SM501_CLOCK_MCLK:
-	case SM501_CLOCK_M1XCLK:
-		sm501_freq = sm501_select_clock(req_freq, &to, 3);
-		break;
-
-	default:
-		sm501_freq = 0;		/* error */
-	}
-
-	return sm501_freq;
-}
-
-EXPORT_SYMBOL_GPL(sm501_find_clock);
-
 static struct sm501_device *to_sm_device(struct platform_device *pdev)
 {
 	return container_of(pdev, struct sm501_device, pdev);
@@ -915,7 +872,8 @@ static void sm501_gpio_ensure_gpio(struct sm501_gpio_chip *smchip,
 	}
 }
 
-static void sm501_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+static int sm501_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			  int value)
 
 {
 	struct sm501_gpio_chip *smchip = gpiochip_get_data(chip);
@@ -939,6 +897,8 @@ static void sm501_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 	sm501_gpio_ensure_gpio(smchip, bit);
 
 	spin_unlock_irqrestore(&smgpio->lock, save);
+
+	return 0;
 }
 
 static int sm501_gpio_input(struct gpio_chip *chip, unsigned offset)
@@ -1005,7 +965,7 @@ static const struct gpio_chip gpio_chip_template = {
 	.ngpio			= 32,
 	.direction_input	= sm501_gpio_input,
 	.direction_output	= sm501_gpio_output,
-	.set			= sm501_gpio_set,
+	.set_rv			= sm501_gpio_set,
 	.get			= sm501_gpio_get,
 };
 
diff --git a/drivers/mfd/sprd-sc27xx-spi.c b/drivers/mfd/sprd-sc27xx-spi.c
index 7186e2108108..d6b4350779e6 100644
--- a/drivers/mfd/sprd-sc27xx-spi.c
+++ b/drivers/mfd/sprd-sc27xx-spi.c
@@ -210,7 +210,10 @@ static int sprd_pmic_probe(struct spi_device *spi)
 		return ret;
 	}
 
-	device_init_wakeup(&spi->dev, true);
+	ret = devm_device_init_wakeup(&spi->dev);
+	if (ret)
+		return dev_err_probe(&spi->dev, ret, "Failed to init wakeup\n");
+
 	return 0;
 }
 
diff --git a/drivers/mfd/stm32-lptimer.c b/drivers/mfd/stm32-lptimer.c
index b2704a9809c7..09073dbc9c80 100644
--- a/drivers/mfd/stm32-lptimer.c
+++ b/drivers/mfd/stm32-lptimer.c
@@ -6,6 +6,7 @@
  * Inspired by Benjamin Gaignard's stm32-timers driver
  */
 
+#include <linux/bitfield.h>
 #include <linux/mfd/stm32-lptimer.h>
 #include <linux/module.h>
 #include <linux/of_platform.h>
@@ -49,6 +50,36 @@ static int stm32_lptimer_detect_encoder(struct stm32_lptimer *ddata)
 	return 0;
 }
 
+static int stm32_lptimer_detect_hwcfgr(struct stm32_lptimer *ddata)
+{
+	u32 val;
+	int ret;
+
+	ret = regmap_read(ddata->regmap, STM32_LPTIM_VERR, &ddata->version);
+	if (ret)
+		return ret;
+
+	/* Try to guess parameters from HWCFGR: e.g. encoder mode (STM32MP15) */
+	ret = regmap_read(ddata->regmap, STM32_LPTIM_HWCFGR1, &val);
+	if (ret)
+		return ret;
+
+	/* Fallback to legacy init if HWCFGR isn't present */
+	if (!val)
+		return stm32_lptimer_detect_encoder(ddata);
+
+	ddata->has_encoder = FIELD_GET(STM32_LPTIM_HWCFGR1_ENCODER, val);
+
+	ret = regmap_read(ddata->regmap, STM32_LPTIM_HWCFGR2, &val);
+	if (ret)
+		return ret;
+
+	/* Number of capture/compare channels */
+	ddata->num_cc_chans = FIELD_GET(STM32_LPTIM_HWCFGR2_CHAN_NUM, val);
+
+	return 0;
+}
+
 static int stm32_lptimer_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -73,7 +104,7 @@ static int stm32_lptimer_probe(struct platform_device *pdev)
 	if (IS_ERR(ddata->clk))
 		return PTR_ERR(ddata->clk);
 
-	ret = stm32_lptimer_detect_encoder(ddata);
+	ret = stm32_lptimer_detect_hwcfgr(ddata);
 	if (ret)
 		return ret;
 
diff --git a/drivers/mfd/stmpe-spi.c b/drivers/mfd/stmpe-spi.c
index 792236f56399..b9cc85ea2c40 100644
--- a/drivers/mfd/stmpe-spi.c
+++ b/drivers/mfd/stmpe-spi.c
@@ -129,7 +129,7 @@ static const struct spi_device_id stmpe_spi_id[] = {
 	{ "stmpe2403", STMPE2403 },
 	{ }
 };
-MODULE_DEVICE_TABLE(spi, stmpe_id);
+MODULE_DEVICE_TABLE(spi, stmpe_spi_id);
 
 static struct spi_driver stmpe_spi_driver = {
 	.driver = {
diff --git a/drivers/mfd/tps65010.c b/drivers/mfd/tps65010.c
index 00fb12c4f491..03bd5cd66798 100644
--- a/drivers/mfd/tps65010.c
+++ b/drivers/mfd/tps65010.c
@@ -446,7 +446,7 @@ static irqreturn_t tps65010_irq(int irq, void *_tps)
  * offsets 4..5 == LED1/nPG, LED2 (we set one of the non-BLINK modes)
  * offset 6 == vibrator motor driver
  */
-static void
+static int
 tps65010_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 {
 	if (offset < 4)
@@ -455,6 +455,8 @@ tps65010_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 		tps65010_set_led(offset - 3, value ? ON : OFF);
 	else
 		tps65010_set_vib(value);
+
+	return 0;
 }
 
 static int
@@ -512,7 +514,6 @@ static void tps65010_remove(struct i2c_client *client)
 	if (client->irq > 0)
 		free_irq(client->irq, tps);
 	cancel_delayed_work_sync(&tps->work);
-	debugfs_remove(tps->file);
 	the_tps = NULL;
 }
 
@@ -608,7 +609,7 @@ static int tps65010_probe(struct i2c_client *client)
 
 	tps65010_work(&tps->work.work);
 
-	tps->file = debugfs_create_file(DRIVER_NAME, S_IRUGO, NULL,
+	tps->file = debugfs_create_file(DRIVER_NAME, S_IRUGO, client->debugfs,
 				tps, DEBUG_FOPS);
 
 	/* optionally register GPIOs */
@@ -619,7 +620,7 @@ static int tps65010_probe(struct i2c_client *client)
 		tps->chip.parent = &client->dev;
 		tps->chip.owner = THIS_MODULE;
 
-		tps->chip.set = tps65010_gpio_set;
+		tps->chip.set_rv = tps65010_gpio_set;
 		tps->chip.direction_output = tps65010_output;
 
 		/* NOTE:  only partial support for inputs; nyet IRQs */
diff --git a/drivers/mfd/ucb1x00-core.c b/drivers/mfd/ucb1x00-core.c
index fc4d4c844a81..fd71ba29f6b5 100644
--- a/drivers/mfd/ucb1x00-core.c
+++ b/drivers/mfd/ucb1x00-core.c
@@ -104,7 +104,8 @@ unsigned int ucb1x00_io_read(struct ucb1x00 *ucb)
 	return ucb1x00_reg_read(ucb, UCB_IO_DATA);
 }
 
-static void ucb1x00_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+static int ucb1x00_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			    int value)
 {
 	struct ucb1x00 *ucb = gpiochip_get_data(chip);
 	unsigned long flags;
@@ -119,6 +120,8 @@ static void ucb1x00_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 	ucb1x00_reg_write(ucb, UCB_IO_DATA, ucb->io_out);
 	ucb1x00_disable(ucb);
 	spin_unlock_irqrestore(&ucb->io_lock, flags);
+
+	return 0;
 }
 
 static int ucb1x00_gpio_get(struct gpio_chip *chip, unsigned offset)
@@ -567,7 +570,7 @@ static int ucb1x00_probe(struct mcp *mcp)
 		ucb->gpio.owner = THIS_MODULE;
 		ucb->gpio.base = pdata->gpio_base;
 		ucb->gpio.ngpio = 10;
-		ucb->gpio.set = ucb1x00_gpio_set;
+		ucb->gpio.set_rv = ucb1x00_gpio_set;
 		ucb->gpio.get = ucb1x00_gpio_get;
 		ucb->gpio.direction_input = ucb1x00_gpio_direction_input;
 		ucb->gpio.direction_output = ucb1x00_gpio_direction_output;
diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index 7d3066691d5d..52301511ed1b 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -966,7 +966,7 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		u32 status, tx_nr_packets_max;
 
 		netdev = alloc_candev(sizeof(struct kvaser_pciefd_can),
-				      KVASER_PCIEFD_CAN_TX_MAX_COUNT);
+				      roundup_pow_of_two(KVASER_PCIEFD_CAN_TX_MAX_COUNT));
 		if (!netdev)
 			return -ENOMEM;
 
@@ -995,7 +995,6 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		can->tx_max_count = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1);
 
 		can->can.clock.freq = pcie->freq;
-		can->can.echo_skb_max = roundup_pow_of_two(can->tx_max_count);
 		spin_lock_init(&can->lock);
 
 		can->can.bittiming_const = &kvaser_pciefd_bittiming_const;
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 132683ed3abe..862bdccb7439 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -22,6 +22,7 @@
 #include <linux/gpio.h>
 #include <linux/kernel.h>
 #include <linux/math.h>
+#include <linux/minmax.h>
 #include <linux/module.h>
 #include <linux/platform_data/b53.h>
 #include <linux/phy.h>
@@ -1322,41 +1323,17 @@ static void b53_adjust_63xx_rgmii(struct dsa_switch *ds, int port,
 				  phy_interface_t interface)
 {
 	struct b53_device *dev = ds->priv;
-	u8 rgmii_ctrl = 0, off;
-
-	if (port == dev->imp_port)
-		off = B53_RGMII_CTRL_IMP;
-	else
-		off = B53_RGMII_CTRL_P(port);
+	u8 rgmii_ctrl = 0;
 
-	b53_read8(dev, B53_CTRL_PAGE, off, &rgmii_ctrl);
-
-	switch (interface) {
-	case PHY_INTERFACE_MODE_RGMII_ID:
-		rgmii_ctrl |= (RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC);
-		break;
-	case PHY_INTERFACE_MODE_RGMII_RXID:
-		rgmii_ctrl &= ~(RGMII_CTRL_DLL_TXC);
-		rgmii_ctrl |= RGMII_CTRL_DLL_RXC;
-		break;
-	case PHY_INTERFACE_MODE_RGMII_TXID:
-		rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC);
-		rgmii_ctrl |= RGMII_CTRL_DLL_TXC;
-		break;
-	case PHY_INTERFACE_MODE_RGMII:
-	default:
-		rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC);
-		break;
-	}
+	b53_read8(dev, B53_CTRL_PAGE, B53_RGMII_CTRL_P(port), &rgmii_ctrl);
+	rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC);
 
-	if (port != dev->imp_port) {
-		if (is63268(dev))
-			rgmii_ctrl |= RGMII_CTRL_MII_OVERRIDE;
+	if (is63268(dev))
+		rgmii_ctrl |= RGMII_CTRL_MII_OVERRIDE;
 
-		rgmii_ctrl |= RGMII_CTRL_ENABLE_GMII;
-	}
+	rgmii_ctrl |= RGMII_CTRL_ENABLE_GMII;
 
-	b53_write8(dev, B53_CTRL_PAGE, off, rgmii_ctrl);
+	b53_write8(dev, B53_CTRL_PAGE, B53_RGMII_CTRL_P(port), rgmii_ctrl);
 
 	dev_dbg(ds->dev, "Configured port %d for %s\n", port,
 		phy_modes(interface));
@@ -1377,8 +1354,7 @@ static void b53_adjust_531x5_rgmii(struct dsa_switch *ds, int port,
 	 * tx_clk aligned timing (restoring to reset defaults)
 	 */
 	b53_read8(dev, B53_CTRL_PAGE, off, &rgmii_ctrl);
-	rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC |
-			RGMII_CTRL_TIMING_SEL);
+	rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC);
 
 	/* PHY_INTERFACE_MODE_RGMII_TXID means TX internal delay, make
 	 * sure that we enable the port TX clock internal delay to
@@ -1398,7 +1374,10 @@ static void b53_adjust_531x5_rgmii(struct dsa_switch *ds, int port,
 		rgmii_ctrl |= RGMII_CTRL_DLL_TXC;
 	if (interface == PHY_INTERFACE_MODE_RGMII)
 		rgmii_ctrl |= RGMII_CTRL_DLL_TXC | RGMII_CTRL_DLL_RXC;
-	rgmii_ctrl |= RGMII_CTRL_TIMING_SEL;
+
+	if (dev->chip_id != BCM53115_DEVICE_ID)
+		rgmii_ctrl |= RGMII_CTRL_TIMING_SEL;
+
 	b53_write8(dev, B53_CTRL_PAGE, off, rgmii_ctrl);
 
 	dev_info(ds->dev, "Configured port %d for %s\n", port,
@@ -1462,6 +1441,10 @@ static void b53_phylink_get_caps(struct dsa_switch *ds, int port,
 	__set_bit(PHY_INTERFACE_MODE_MII, config->supported_interfaces);
 	__set_bit(PHY_INTERFACE_MODE_REVMII, config->supported_interfaces);
 
+	/* BCM63xx RGMII ports support RGMII */
+	if (is63xx(dev) && in_range(port, B53_63XX_RGMII0, 4))
+		phy_interface_set_rgmii(config->supported_interfaces);
+
 	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 		MAC_10 | MAC_100;
 
@@ -1501,7 +1484,7 @@ static void b53_phylink_mac_config(struct phylink_config *config,
 	struct b53_device *dev = ds->priv;
 	int port = dp->index;
 
-	if (is63xx(dev) && port >= B53_63XX_RGMII0)
+	if (is63xx(dev) && in_range(port, B53_63XX_RGMII0, 4))
 		b53_adjust_63xx_rgmii(ds, port, interface);
 
 	if (mode == MLO_AN_FIXED) {
@@ -2353,6 +2336,9 @@ int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy)
 {
 	int ret;
 
+	if (!b53_support_eee(ds, port))
+		return 0;
+
 	ret = phy_init_eee(phy, false);
 	if (ret)
 		return 0;
@@ -2367,7 +2353,7 @@ bool b53_support_eee(struct dsa_switch *ds, int port)
 {
 	struct b53_device *dev = ds->priv;
 
-	return !is5325(dev) && !is5365(dev);
+	return !is5325(dev) && !is5365(dev) && !is63xx(dev);
 }
 EXPORT_SYMBOL(b53_support_eee);
 
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index d1d3b854361e..a7ec609d64de 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -84,6 +84,8 @@ static void airoha_set_macaddr(struct airoha_gdm_port *port, const u8 *addr)
 	val = (addr[3] << 16) | (addr[4] << 8) | addr[5];
 	airoha_fe_wr(eth, REG_FE_MAC_LMIN(reg), val);
 	airoha_fe_wr(eth, REG_FE_MAC_LMAX(reg), val);
+
+	airoha_ppe_init_upd_mem(port);
 }
 
 static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr,
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index b815697302bf..a970b789cf23 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -614,6 +614,7 @@ void airoha_ppe_check_skb(struct airoha_ppe *ppe, struct sk_buff *skb,
 int airoha_ppe_setup_tc_block_cb(struct net_device *dev, void *type_data);
 int airoha_ppe_init(struct airoha_eth *eth);
 void airoha_ppe_deinit(struct airoha_eth *eth);
+void airoha_ppe_init_upd_mem(struct airoha_gdm_port *port);
 struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe,
 						  u32 hash);
 void airoha_ppe_foe_entry_get_stats(struct airoha_ppe *ppe, u32 hash,
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index 12d32c92717a..9067d2fc7706 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -223,6 +223,7 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
 	int dsa_port = airoha_get_dsa_port(&dev);
 	struct airoha_foe_mac_info_common *l2;
 	u32 qdata, ports_pad, val;
+	u8 smac_id = 0xf;
 
 	memset(hwe, 0, sizeof(*hwe));
 
@@ -257,6 +258,8 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
 		 */
 		if (airhoa_is_lan_gdm_port(port))
 			val |= AIROHA_FOE_IB2_FAST_PATH;
+
+		smac_id = port->id;
 	}
 
 	if (is_multicast_ether_addr(data->eth.h_dest))
@@ -291,7 +294,7 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
 		hwe->ipv4.l2.src_mac_lo =
 			get_unaligned_be16(data->eth.h_source + 4);
 	} else {
-		l2->src_mac_hi = FIELD_PREP(AIROHA_FOE_MAC_SMAC_ID, 0xf);
+		l2->src_mac_hi = FIELD_PREP(AIROHA_FOE_MAC_SMAC_ID, smac_id);
 	}
 
 	if (data->vlan.num) {
@@ -636,7 +639,6 @@ airoha_ppe_foe_commit_subflow_entry(struct airoha_ppe *ppe,
 	u32 mask = AIROHA_FOE_IB1_BIND_PACKET_TYPE | AIROHA_FOE_IB1_BIND_UDP;
 	struct airoha_foe_entry *hwe_p, hwe;
 	struct airoha_flow_table_entry *f;
-	struct airoha_foe_mac_info *l2;
 	int type;
 
 	hwe_p = airoha_ppe_foe_get_entry(ppe, hash);
@@ -653,18 +655,25 @@ airoha_ppe_foe_commit_subflow_entry(struct airoha_ppe *ppe,
 
 	memcpy(&hwe, hwe_p, sizeof(*hwe_p));
 	hwe.ib1 = (hwe.ib1 & mask) | (e->data.ib1 & ~mask);
-	l2 = &hwe.bridge.l2;
-	memcpy(l2, &e->data.bridge.l2, sizeof(*l2));
 
 	type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe.ib1);
-	if (type == PPE_PKT_TYPE_IPV4_HNAPT)
-		memcpy(&hwe.ipv4.new_tuple, &hwe.ipv4.orig_tuple,
-		       sizeof(hwe.ipv4.new_tuple));
-	else if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T &&
-		 l2->common.etype == ETH_P_IP)
-		l2->common.etype = ETH_P_IPV6;
-
-	hwe.bridge.ib2 = e->data.bridge.ib2;
+	if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+		memcpy(&hwe.ipv6.l2, &e->data.bridge.l2, sizeof(hwe.ipv6.l2));
+		hwe.ipv6.ib2 = e->data.bridge.ib2;
+		/* setting smac_id to 0xf instruct the hw to keep original
+		 * source mac address
+		 */
+		hwe.ipv6.l2.src_mac_hi = FIELD_PREP(AIROHA_FOE_MAC_SMAC_ID,
+						    0xf);
+	} else {
+		memcpy(&hwe.bridge.l2, &e->data.bridge.l2,
+		       sizeof(hwe.bridge.l2));
+		hwe.bridge.ib2 = e->data.bridge.ib2;
+		if (type == PPE_PKT_TYPE_IPV4_HNAPT)
+			memcpy(&hwe.ipv4.new_tuple, &hwe.ipv4.orig_tuple,
+			       sizeof(hwe.ipv4.new_tuple));
+	}
+
 	hwe.bridge.data = e->data.bridge.data;
 	airoha_ppe_foe_commit_entry(ppe, &hwe, hash);
 
@@ -1238,6 +1247,27 @@ void airoha_ppe_check_skb(struct airoha_ppe *ppe, struct sk_buff *skb,
 	airoha_ppe_foe_insert_entry(ppe, skb, hash);
 }
 
+void airoha_ppe_init_upd_mem(struct airoha_gdm_port *port)
+{
+	struct airoha_eth *eth = port->qdma->eth;
+	struct net_device *dev = port->dev;
+	const u8 *addr = dev->dev_addr;
+	u32 val;
+
+	val = (addr[2] << 24) | (addr[3] << 16) | (addr[4] << 8) | addr[5];
+	airoha_fe_wr(eth, REG_UPDMEM_DATA(0), val);
+	airoha_fe_wr(eth, REG_UPDMEM_CTRL(0),
+		     FIELD_PREP(PPE_UPDMEM_ADDR_MASK, port->id) |
+		     PPE_UPDMEM_WR_MASK | PPE_UPDMEM_REQ_MASK);
+
+	val = (addr[0] << 8) | addr[1];
+	airoha_fe_wr(eth, REG_UPDMEM_DATA(0), val);
+	airoha_fe_wr(eth, REG_UPDMEM_CTRL(0),
+		     FIELD_PREP(PPE_UPDMEM_ADDR_MASK, port->id) |
+		     FIELD_PREP(PPE_UPDMEM_OFFSET_MASK, 1) |
+		     PPE_UPDMEM_WR_MASK | PPE_UPDMEM_REQ_MASK);
+}
+
 int airoha_ppe_init(struct airoha_eth *eth)
 {
 	struct airoha_ppe *ppe;
diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h
index d931530fc96f..04187eb40ec6 100644
--- a/drivers/net/ethernet/airoha/airoha_regs.h
+++ b/drivers/net/ethernet/airoha/airoha_regs.h
@@ -313,6 +313,16 @@
 #define REG_PPE_RAM_BASE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x320)
 #define REG_PPE_RAM_ENTRY(_m, _n)		(REG_PPE_RAM_BASE(_m) + ((_n) << 2))
 
+#define REG_UPDMEM_CTRL(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x370)
+#define PPE_UPDMEM_ACK_MASK			BIT(31)
+#define PPE_UPDMEM_ADDR_MASK			GENMASK(11, 8)
+#define PPE_UPDMEM_OFFSET_MASK			GENMASK(7, 4)
+#define PPE_UPDMEM_SEL_MASK			GENMASK(3, 2)
+#define PPE_UPDMEM_WR_MASK			BIT(1)
+#define PPE_UPDMEM_REQ_MASK			BIT(0)
+
+#define REG_UPDMEM_DATA(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x374)
+
 #define REG_FE_GDM_TX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x280)
 #define REG_FE_GDM_TX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x284)
 #define REG_FE_GDM_TX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x288)
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 636520bb4b8c..81a74e07464f 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -96,7 +96,6 @@ config BNX2
 config CNIC
 	tristate "QLogic CNIC support"
 	depends on PCI && (IPV6 || IPV6=n)
-	depends on MMU
 	select BNX2
 	select UIO
 	help
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index e1ffbd561fac..7cd1eda0b449 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -2153,7 +2153,7 @@ void gve_handle_report_stats(struct gve_priv *priv)
 			};
 			stats[stats_idx++] = (struct stats) {
 				.stat_name = cpu_to_be32(RX_BUFFERS_POSTED),
-				.value = cpu_to_be64(priv->rx[0].fill_cnt),
+				.value = cpu_to_be64(priv->rx[idx].fill_cnt),
 				.queue_id = cpu_to_be32(idx),
 			};
 		}
diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index a27f1574a733..9d705d94b065 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -764,6 +764,9 @@ static int gve_tx_add_skb_dqo(struct gve_tx_ring *tx,
 	s16 completion_tag;
 
 	pkt = gve_alloc_pending_packet(tx);
+	if (!pkt)
+		return -ENOMEM;
+
 	pkt->skb = skb;
 	completion_tag = pkt - tx->dqo.pending_packets;
 
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_main.c b/drivers/net/ethernet/huawei/hinic3/hinic3_main.c
index 093aa6d775ff..497f2a36f35d 100644
--- a/drivers/net/ethernet/huawei/hinic3/hinic3_main.c
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_main.c
@@ -324,8 +324,6 @@ static __init int hinic3_nic_lld_init(void)
 {
 	int err;
 
-	pr_info("%s: %s\n", HINIC3_NIC_DRV_NAME, HINIC3_NIC_DRV_DESC);
-
 	err = hinic3_lld_init();
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 9de3e0ba3731..f7a98ff43a57 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -268,7 +268,6 @@ struct iavf_adapter {
 	struct list_head vlan_filter_list;
 	int num_vlan_filters;
 	struct list_head mac_filter_list;
-	struct mutex crit_lock;
 	/* Lock to protect accesses to MAC and VLAN lists */
 	spinlock_t mac_vlan_list_lock;
 	char misc_vector_name[IFNAMSIZ + 9];
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 288bb5b2e72e..2b2b315205b5 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -4,6 +4,8 @@
 #include <linux/bitfield.h>
 #include <linux/uaccess.h>
 
+#include <net/netdev_lock.h>
+
 /* ethtool support for iavf */
 #include "iavf.h"
 
@@ -1256,9 +1258,10 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 {
 	struct ethtool_rx_flow_spec *fsp = &cmd->fs;
 	struct iavf_fdir_fltr *fltr;
-	int count = 50;
 	int err;
 
+	netdev_assert_locked(adapter->netdev);
+
 	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
@@ -1277,14 +1280,6 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	if (!fltr)
 		return -ENOMEM;
 
-	while (!mutex_trylock(&adapter->crit_lock)) {
-		if (--count == 0) {
-			kfree(fltr);
-			return -EINVAL;
-		}
-		udelay(1);
-	}
-
 	err = iavf_add_fdir_fltr_info(adapter, fsp, fltr);
 	if (!err)
 		err = iavf_fdir_add_fltr(adapter, fltr);
@@ -1292,7 +1287,6 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	if (err)
 		kfree(fltr);
 
-	mutex_unlock(&adapter->crit_lock);
 	return err;
 }
 
@@ -1435,11 +1429,13 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 {
 	struct iavf_adv_rss *rss_old, *rss_new;
 	bool rss_new_add = false;
-	int count = 50, err = 0;
 	bool symm = false;
 	u64 hash_flds;
+	int err = 0;
 	u32 hdrs;
 
+	netdev_assert_locked(adapter->netdev);
+
 	if (!ADV_RSS_SUPPORT(adapter))
 		return -EOPNOTSUPP;
 
@@ -1463,15 +1459,6 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 		return -EINVAL;
 	}
 
-	while (!mutex_trylock(&adapter->crit_lock)) {
-		if (--count == 0) {
-			kfree(rss_new);
-			return -EINVAL;
-		}
-
-		udelay(1);
-	}
-
 	spin_lock_bh(&adapter->adv_rss_lock);
 	rss_old = iavf_find_adv_rss_cfg_by_hdrs(adapter, hdrs);
 	if (rss_old) {
@@ -1500,8 +1487,6 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 	if (!err)
 		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_ADV_RSS_CFG);
 
-	mutex_unlock(&adapter->crit_lock);
-
 	if (!rss_new_add)
 		kfree(rss_new);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 6d7ba4d67a19..2c0bb41809a4 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1287,11 +1287,11 @@ static void iavf_configure(struct iavf_adapter *adapter)
 /**
  * iavf_up_complete - Finish the last steps of bringing up a connection
  * @adapter: board private structure
- *
- * Expects to be called while holding crit_lock.
- **/
+ */
 static void iavf_up_complete(struct iavf_adapter *adapter)
 {
+	netdev_assert_locked(adapter->netdev);
+
 	iavf_change_state(adapter, __IAVF_RUNNING);
 	clear_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
 
@@ -1410,13 +1410,13 @@ static void iavf_clear_adv_rss_conf(struct iavf_adapter *adapter)
 /**
  * iavf_down - Shutdown the connection processing
  * @adapter: board private structure
- *
- * Expects to be called while holding crit_lock.
- **/
+ */
 void iavf_down(struct iavf_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 
+	netdev_assert_locked(netdev);
+
 	if (adapter->state <= __IAVF_DOWN_PENDING)
 		return;
 
@@ -2025,22 +2025,21 @@ err:
  * iavf_finish_config - do all netdev work that needs RTNL
  * @work: our work_struct
  *
- * Do work that needs both RTNL and crit_lock.
- **/
+ * Do work that needs RTNL.
+ */
 static void iavf_finish_config(struct work_struct *work)
 {
 	struct iavf_adapter *adapter;
-	bool locks_released = false;
+	bool netdev_released = false;
 	int pairs, err;
 
 	adapter = container_of(work, struct iavf_adapter, finish_config);
 
 	/* Always take RTNL first to prevent circular lock dependency;
-	 * The dev->lock is needed to update the queue number
+	 * the dev->lock (== netdev lock) is needed to update the queue number.
 	 */
 	rtnl_lock();
 	netdev_lock(adapter->netdev);
-	mutex_lock(&adapter->crit_lock);
 
 	if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) &&
 	    adapter->netdev->reg_state == NETREG_REGISTERED &&
@@ -2059,22 +2058,21 @@ static void iavf_finish_config(struct work_struct *work)
 		netif_set_real_num_tx_queues(adapter->netdev, pairs);
 
 		if (adapter->netdev->reg_state != NETREG_REGISTERED) {
-			mutex_unlock(&adapter->crit_lock);
 			netdev_unlock(adapter->netdev);
-			locks_released = true;
+			netdev_released = true;
 			err = register_netdevice(adapter->netdev);
 			if (err) {
 				dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n",
 					err);
 
 				/* go back and try again.*/
-				mutex_lock(&adapter->crit_lock);
+				netdev_lock(adapter->netdev);
 				iavf_free_rss(adapter);
 				iavf_free_misc_irq(adapter);
 				iavf_reset_interrupt_capability(adapter);
 				iavf_change_state(adapter,
 						  __IAVF_INIT_CONFIG_ADAPTER);
-				mutex_unlock(&adapter->crit_lock);
+				netdev_unlock(adapter->netdev);
 				goto out;
 			}
 		}
@@ -2090,10 +2088,8 @@ static void iavf_finish_config(struct work_struct *work)
 	}
 
 out:
-	if (!locks_released) {
-		mutex_unlock(&adapter->crit_lock);
+	if (!netdev_released)
 		netdev_unlock(adapter->netdev);
-	}
 	rtnl_unlock();
 }
 
@@ -2911,28 +2907,15 @@ err:
 	iavf_change_state(adapter, __IAVF_INIT_FAILED);
 }
 
-/**
- * iavf_watchdog_task - Periodic call-back task
- * @work: pointer to work_struct
- **/
-static void iavf_watchdog_task(struct work_struct *work)
+static const int IAVF_NO_RESCHED = -1;
+
+/* return: msec delay for requeueing itself */
+static int iavf_watchdog_step(struct iavf_adapter *adapter)
 {
-	struct iavf_adapter *adapter = container_of(work,
-						    struct iavf_adapter,
-						    watchdog_task.work);
-	struct net_device *netdev = adapter->netdev;
 	struct iavf_hw *hw = &adapter->hw;
 	u32 reg_val;
 
-	netdev_lock(netdev);
-	if (!mutex_trylock(&adapter->crit_lock)) {
-		if (adapter->state == __IAVF_REMOVE) {
-			netdev_unlock(netdev);
-			return;
-		}
-
-		goto restart_watchdog;
-	}
+	netdev_assert_locked(adapter->netdev);
 
 	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
 		iavf_change_state(adapter, __IAVF_COMM_FAILED);
@@ -2940,39 +2923,19 @@ static void iavf_watchdog_task(struct work_struct *work)
 	switch (adapter->state) {
 	case __IAVF_STARTUP:
 		iavf_startup(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		netdev_unlock(netdev);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(30));
-		return;
+		return 30;
 	case __IAVF_INIT_VERSION_CHECK:
 		iavf_init_version_check(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		netdev_unlock(netdev);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(30));
-		return;
+		return 30;
 	case __IAVF_INIT_GET_RESOURCES:
 		iavf_init_get_resources(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		netdev_unlock(netdev);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(1));
-		return;
+		return 1;
 	case __IAVF_INIT_EXTENDED_CAPS:
 		iavf_init_process_extended_caps(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		netdev_unlock(netdev);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(1));
-		return;
+		return 1;
 	case __IAVF_INIT_CONFIG_ADAPTER:
 		iavf_init_config_adapter(adapter);
-		mutex_unlock(&adapter->crit_lock);
-		netdev_unlock(netdev);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(1));
-		return;
+		return 1;
 	case __IAVF_INIT_FAILED:
 		if (test_bit(__IAVF_IN_REMOVE_TASK,
 			     &adapter->crit_section)) {
@@ -2980,27 +2943,18 @@ static void iavf_watchdog_task(struct work_struct *work)
 			 * watchdog task, iavf_remove should handle this state
 			 * as it can loop forever
 			 */
-			mutex_unlock(&adapter->crit_lock);
-			netdev_unlock(netdev);
-			return;
+			return IAVF_NO_RESCHED;
 		}
 		if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) {
 			dev_err(&adapter->pdev->dev,
 				"Failed to communicate with PF; waiting before retry\n");
 			adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
 			iavf_shutdown_adminq(hw);
-			mutex_unlock(&adapter->crit_lock);
-			netdev_unlock(netdev);
-			queue_delayed_work(adapter->wq,
-					   &adapter->watchdog_task, (5 * HZ));
-			return;
+			return 5000;
 		}
 		/* Try again from failed step*/
 		iavf_change_state(adapter, adapter->last_state);
-		mutex_unlock(&adapter->crit_lock);
-		netdev_unlock(netdev);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ);
-		return;
+		return 1000;
 	case __IAVF_COMM_FAILED:
 		if (test_bit(__IAVF_IN_REMOVE_TASK,
 			     &adapter->crit_section)) {
@@ -3010,9 +2964,7 @@ static void iavf_watchdog_task(struct work_struct *work)
 			 */
 			iavf_change_state(adapter, __IAVF_INIT_FAILED);
 			adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED;
-			mutex_unlock(&adapter->crit_lock);
-			netdev_unlock(netdev);
-			return;
+			return IAVF_NO_RESCHED;
 		}
 		reg_val = rd32(hw, IAVF_VFGEN_RSTAT) &
 			  IAVF_VFGEN_RSTAT_VFR_STATE_MASK;
@@ -3030,18 +2982,9 @@ static void iavf_watchdog_task(struct work_struct *work)
 		}
 		adapter->aq_required = 0;
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
-		mutex_unlock(&adapter->crit_lock);
-		netdev_unlock(netdev);
-		queue_delayed_work(adapter->wq,
-				   &adapter->watchdog_task,
-				   msecs_to_jiffies(10));
-		return;
+		return 10;
 	case __IAVF_RESETTING:
-		mutex_unlock(&adapter->crit_lock);
-		netdev_unlock(netdev);
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   HZ * 2);
-		return;
+		return 2000;
 	case __IAVF_DOWN:
 	case __IAVF_DOWN_PENDING:
 	case __IAVF_TESTING:
@@ -3068,9 +3011,7 @@ static void iavf_watchdog_task(struct work_struct *work)
 		break;
 	case __IAVF_REMOVE:
 	default:
-		mutex_unlock(&adapter->crit_lock);
-		netdev_unlock(netdev);
-		return;
+		return IAVF_NO_RESCHED;
 	}
 
 	/* check for hw reset */
@@ -3080,24 +3021,29 @@ static void iavf_watchdog_task(struct work_struct *work)
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
 		dev_err(&adapter->pdev->dev, "Hardware reset detected\n");
 		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING);
-		mutex_unlock(&adapter->crit_lock);
-		netdev_unlock(netdev);
-		queue_delayed_work(adapter->wq,
-				   &adapter->watchdog_task, HZ * 2);
-		return;
 	}
 
-	mutex_unlock(&adapter->crit_lock);
-restart_watchdog:
-	netdev_unlock(netdev);
+	return adapter->aq_required ? 20 : 2000;
+}
+
+static void iavf_watchdog_task(struct work_struct *work)
+{
+	struct iavf_adapter *adapter = container_of(work,
+						    struct iavf_adapter,
+						    watchdog_task.work);
+	struct net_device *netdev = adapter->netdev;
+	int msec_delay;
+
+	netdev_lock(netdev);
+	msec_delay = iavf_watchdog_step(adapter);
+	/* note that we schedule a different task */
 	if (adapter->state >= __IAVF_DOWN)
 		queue_work(adapter->wq, &adapter->adminq_task);
-	if (adapter->aq_required)
-		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   msecs_to_jiffies(20));
-	else
+
+	if (msec_delay != IAVF_NO_RESCHED)
 		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
-				   HZ * 2);
+				   msecs_to_jiffies(msec_delay));
+	netdev_unlock(netdev);
 }
 
 /**
@@ -3105,14 +3051,15 @@ restart_watchdog:
  * @adapter: board private structure
  *
  * Set communication failed flag and free all resources.
- * NOTE: This function is expected to be called with crit_lock being held.
- **/
+ */
 static void iavf_disable_vf(struct iavf_adapter *adapter)
 {
 	struct iavf_mac_filter *f, *ftmp;
 	struct iavf_vlan_filter *fv, *fvtmp;
 	struct iavf_cloud_filter *cf, *cftmp;
 
+	netdev_assert_locked(adapter->netdev);
+
 	adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
 
 	/* We don't use netif_running() because it may be true prior to
@@ -3212,17 +3159,7 @@ static void iavf_reset_task(struct work_struct *work)
 	int i = 0, err;
 	bool running;
 
-	/* When device is being removed it doesn't make sense to run the reset
-	 * task, just return in such a case.
-	 */
 	netdev_lock(netdev);
-	if (!mutex_trylock(&adapter->crit_lock)) {
-		if (adapter->state != __IAVF_REMOVE)
-			queue_work(adapter->wq, &adapter->reset_task);
-
-		netdev_unlock(netdev);
-		return;
-	}
 
 	iavf_misc_irq_disable(adapter);
 	if (adapter->flags & IAVF_FLAG_RESET_NEEDED) {
@@ -3267,7 +3204,6 @@ static void iavf_reset_task(struct work_struct *work)
 		dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
 			reg_val);
 		iavf_disable_vf(adapter);
-		mutex_unlock(&adapter->crit_lock);
 		netdev_unlock(netdev);
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}
@@ -3411,7 +3347,6 @@ continue_reset:
 	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
 
 	wake_up(&adapter->reset_waitqueue);
-	mutex_unlock(&adapter->crit_lock);
 	netdev_unlock(netdev);
 
 	return;
@@ -3422,7 +3357,6 @@ reset_err:
 	}
 	iavf_disable_vf(adapter);
 
-	mutex_unlock(&adapter->crit_lock);
 	netdev_unlock(netdev);
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
 }
@@ -3435,6 +3369,7 @@ static void iavf_adminq_task(struct work_struct *work)
 {
 	struct iavf_adapter *adapter =
 		container_of(work, struct iavf_adapter, adminq_task);
+	struct net_device *netdev = adapter->netdev;
 	struct iavf_hw *hw = &adapter->hw;
 	struct iavf_arq_event_info event;
 	enum virtchnl_ops v_op;
@@ -3442,13 +3377,7 @@ static void iavf_adminq_task(struct work_struct *work)
 	u32 val, oldval;
 	u16 pending;
 
-	if (!mutex_trylock(&adapter->crit_lock)) {
-		if (adapter->state == __IAVF_REMOVE)
-			return;
-
-		queue_work(adapter->wq, &adapter->adminq_task);
-		goto out;
-	}
+	netdev_lock(netdev);
 
 	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
 		goto unlock;
@@ -3515,8 +3444,7 @@ static void iavf_adminq_task(struct work_struct *work)
 freedom:
 	kfree(event.msg_buf);
 unlock:
-	mutex_unlock(&adapter->crit_lock);
-out:
+	netdev_unlock(netdev);
 	/* re-enable Admin queue interrupt cause */
 	iavf_misc_irq_enable(adapter);
 }
@@ -4209,8 +4137,8 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter,
 				    struct flow_cls_offload *cls_flower)
 {
 	int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid);
-	struct iavf_cloud_filter *filter = NULL;
-	int err = -EINVAL, count = 50;
+	struct iavf_cloud_filter *filter;
+	int err;
 
 	if (tc < 0) {
 		dev_err(&adapter->pdev->dev, "Invalid traffic class\n");
@@ -4220,17 +4148,10 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter,
 	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
 	if (!filter)
 		return -ENOMEM;
-
-	while (!mutex_trylock(&adapter->crit_lock)) {
-		if (--count == 0) {
-			kfree(filter);
-			return err;
-		}
-		udelay(1);
-	}
-
 	filter->cookie = cls_flower->cookie;
 
+	netdev_lock(adapter->netdev);
+
 	/* bail out here if filter already exists */
 	spin_lock_bh(&adapter->cloud_filter_list_lock);
 	if (iavf_find_cf(adapter, &cls_flower->cookie)) {
@@ -4264,7 +4185,7 @@ err:
 	if (err)
 		kfree(filter);
 
-	mutex_unlock(&adapter->crit_lock);
+	netdev_unlock(adapter->netdev);
 	return err;
 }
 
@@ -4568,28 +4489,13 @@ static int iavf_open(struct net_device *netdev)
 		return -EIO;
 	}
 
-	while (!mutex_trylock(&adapter->crit_lock)) {
-		/* If we are in __IAVF_INIT_CONFIG_ADAPTER state the crit_lock
-		 * is already taken and iavf_open is called from an upper
-		 * device's notifier reacting on NETDEV_REGISTER event.
-		 * We have to leave here to avoid dead lock.
-		 */
-		if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER)
-			return -EBUSY;
-
-		usleep_range(500, 1000);
-	}
-
-	if (adapter->state != __IAVF_DOWN) {
-		err = -EBUSY;
-		goto err_unlock;
-	}
+	if (adapter->state != __IAVF_DOWN)
+		return -EBUSY;
 
 	if (adapter->state == __IAVF_RUNNING &&
 	    !test_bit(__IAVF_VSI_DOWN, adapter->vsi.state)) {
 		dev_dbg(&adapter->pdev->dev, "VF is already open.\n");
-		err = 0;
-		goto err_unlock;
+		return 0;
 	}
 
 	/* allocate transmit descriptors */
@@ -4608,9 +4514,7 @@ static int iavf_open(struct net_device *netdev)
 		goto err_req_irq;
 
 	spin_lock_bh(&adapter->mac_vlan_list_lock);
-
 	iavf_add_filter(adapter, adapter->hw.mac.addr);
-
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
 	/* Restore filters that were removed with IFF_DOWN */
@@ -4623,8 +4527,6 @@ static int iavf_open(struct net_device *netdev)
 
 	iavf_irq_enable(adapter, true);
 
-	mutex_unlock(&adapter->crit_lock);
-
 	return 0;
 
 err_req_irq:
@@ -4634,8 +4536,6 @@ err_setup_rx:
 	iavf_free_all_rx_resources(adapter);
 err_setup_tx:
 	iavf_free_all_tx_resources(adapter);
-err_unlock:
-	mutex_unlock(&adapter->crit_lock);
 
 	return err;
 }
@@ -4659,12 +4559,8 @@ static int iavf_close(struct net_device *netdev)
 
 	netdev_assert_locked(netdev);
 
-	mutex_lock(&adapter->crit_lock);
-
-	if (adapter->state <= __IAVF_DOWN_PENDING) {
-		mutex_unlock(&adapter->crit_lock);
+	if (adapter->state <= __IAVF_DOWN_PENDING)
 		return 0;
-	}
 
 	set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
 	/* We cannot send IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS before
@@ -4695,7 +4591,6 @@ static int iavf_close(struct net_device *netdev)
 	iavf_change_state(adapter, __IAVF_DOWN_PENDING);
 	iavf_free_traffic_irqs(adapter);
 
-	mutex_unlock(&adapter->crit_lock);
 	netdev_unlock(netdev);
 
 	/* We explicitly don't free resources here because the hardware is
@@ -4714,11 +4609,10 @@ static int iavf_close(struct net_device *netdev)
 				    msecs_to_jiffies(500));
 	if (!status)
 		netdev_warn(netdev, "Device resources not yet released\n");
-
 	netdev_lock(netdev);
-	mutex_lock(&adapter->crit_lock);
+
 	adapter->aq_required |= aq_to_restore;
-	mutex_unlock(&adapter->crit_lock);
+
 	return 0;
 }
 
@@ -5227,15 +5121,16 @@ iavf_shaper_set(struct net_shaper_binding *binding,
 	struct iavf_adapter *adapter = netdev_priv(binding->netdev);
 	const struct net_shaper_handle *handle = &shaper->handle;
 	struct iavf_ring *tx_ring;
-	int ret = 0;
+	int ret;
+
+	netdev_assert_locked(adapter->netdev);
 
-	mutex_lock(&adapter->crit_lock);
 	if (handle->id >= adapter->num_active_queues)
-		goto unlock;
+		return 0;
 
 	ret = iavf_verify_shaper(binding, shaper, extack);
 	if (ret)
-		goto unlock;
+		return ret;
 
 	tx_ring = &adapter->tx_rings[handle->id];
 
@@ -5245,9 +5140,7 @@ iavf_shaper_set(struct net_shaper_binding *binding,
 
 	adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW;
 
-unlock:
-	mutex_unlock(&adapter->crit_lock);
-	return ret;
+	return 0;
 }
 
 static int iavf_shaper_del(struct net_shaper_binding *binding,
@@ -5257,9 +5150,10 @@ static int iavf_shaper_del(struct net_shaper_binding *binding,
 	struct iavf_adapter *adapter = netdev_priv(binding->netdev);
 	struct iavf_ring *tx_ring;
 
-	mutex_lock(&adapter->crit_lock);
+	netdev_assert_locked(adapter->netdev);
+
 	if (handle->id >= adapter->num_active_queues)
-		goto unlock;
+		return 0;
 
 	tx_ring = &adapter->tx_rings[handle->id];
 	tx_ring->q_shaper.bw_min = 0;
@@ -5268,8 +5162,6 @@ static int iavf_shaper_del(struct net_shaper_binding *binding,
 
 	adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW;
 
-unlock:
-	mutex_unlock(&adapter->crit_lock);
 	return 0;
 }
 
@@ -5530,10 +5422,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_alloc_qos_cap;
 	}
 
-	/* set up the locks for the AQ, do this only once in probe
-	 * and destroy them only once in remove
-	 */
-	mutex_init(&adapter->crit_lock);
 	mutex_init(&hw->aq.asq_mutex);
 	mutex_init(&hw->aq.arq_mutex);
 
@@ -5596,22 +5484,24 @@ static int iavf_suspend(struct device *dev_d)
 {
 	struct net_device *netdev = dev_get_drvdata(dev_d);
 	struct iavf_adapter *adapter = netdev_priv(netdev);
+	bool running;
 
 	netif_device_detach(netdev);
 
+	running = netif_running(netdev);
+	if (running)
+		rtnl_lock();
 	netdev_lock(netdev);
-	mutex_lock(&adapter->crit_lock);
 
-	if (netif_running(netdev)) {
-		rtnl_lock();
+	if (running)
 		iavf_down(adapter);
-		rtnl_unlock();
-	}
+
 	iavf_free_misc_irq(adapter);
 	iavf_reset_interrupt_capability(adapter);
 
-	mutex_unlock(&adapter->crit_lock);
 	netdev_unlock(netdev);
+	if (running)
+		rtnl_unlock();
 
 	return 0;
 }
@@ -5688,20 +5578,20 @@ static void iavf_remove(struct pci_dev *pdev)
 	 * There are flows where register/unregister netdev may race.
 	 */
 	while (1) {
-		mutex_lock(&adapter->crit_lock);
+		netdev_lock(netdev);
 		if (adapter->state == __IAVF_RUNNING ||
 		    adapter->state == __IAVF_DOWN ||
 		    adapter->state == __IAVF_INIT_FAILED) {
-			mutex_unlock(&adapter->crit_lock);
+			netdev_unlock(netdev);
 			break;
 		}
 		/* Simply return if we already went through iavf_shutdown */
 		if (adapter->state == __IAVF_REMOVE) {
-			mutex_unlock(&adapter->crit_lock);
+			netdev_unlock(netdev);
 			return;
 		}
 
-		mutex_unlock(&adapter->crit_lock);
+		netdev_unlock(netdev);
 		usleep_range(500, 1000);
 	}
 	cancel_delayed_work_sync(&adapter->watchdog_task);
@@ -5711,7 +5601,6 @@ static void iavf_remove(struct pci_dev *pdev)
 		unregister_netdev(netdev);
 
 	netdev_lock(netdev);
-	mutex_lock(&adapter->crit_lock);
 	dev_info(&adapter->pdev->dev, "Removing device\n");
 	iavf_change_state(adapter, __IAVF_REMOVE);
 
@@ -5727,9 +5616,11 @@ static void iavf_remove(struct pci_dev *pdev)
 
 	iavf_misc_irq_disable(adapter);
 	/* Shut down all the garbage mashers on the detention level */
+	netdev_unlock(netdev);
 	cancel_work_sync(&adapter->reset_task);
 	cancel_delayed_work_sync(&adapter->watchdog_task);
 	cancel_work_sync(&adapter->adminq_task);
+	netdev_lock(netdev);
 
 	adapter->aq_required = 0;
 	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
@@ -5747,8 +5638,6 @@ static void iavf_remove(struct pci_dev *pdev)
 	/* destroy the locks only once, here */
 	mutex_destroy(&hw->aq.arq_mutex);
 	mutex_destroy(&hw->aq.asq_mutex);
-	mutex_unlock(&adapter->crit_lock);
-	mutex_destroy(&adapter->crit_lock);
 	netdev_unlock(netdev);
 
 	iounmap(hw->hw_addr);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 20d3baf955e3..d97d4b25b30d 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2741,6 +2741,27 @@ void ice_map_xdp_rings(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_unmap_xdp_rings - Unmap XDP rings from interrupt vectors
+ * @vsi: the VSI with XDP rings being unmapped
+ */
+static void ice_unmap_xdp_rings(struct ice_vsi *vsi)
+{
+	int v_idx;
+
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+		struct ice_tx_ring *ring;
+
+		ice_for_each_tx_ring(ring, q_vector->tx)
+			if (!ring->tx_buf || !ice_ring_is_xdp(ring))
+				break;
+
+		/* restore the value of last node prior to XDP setup */
+		q_vector->tx.tx_ring = ring;
+	}
+}
+
+/**
  * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP
  * @vsi: VSI to bring up Tx rings used by XDP
  * @prog: bpf program that will be assigned to VSI
@@ -2803,7 +2824,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 	if (status) {
 		dev_err(dev, "Failed VSI LAN queue config for XDP, error: %d\n",
 			status);
-		goto clear_xdp_rings;
+		goto unmap_xdp_rings;
 	}
 
 	/* assign the prog only when it's not already present on VSI;
@@ -2819,6 +2840,8 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
 		ice_vsi_assign_bpf_prog(vsi, prog);
 
 	return 0;
+unmap_xdp_rings:
+	ice_unmap_xdp_rings(vsi);
 clear_xdp_rings:
 	ice_for_each_xdp_txq(vsi, i)
 		if (vsi->xdp_rings[i]) {
@@ -2835,6 +2858,8 @@ err_map_xdp:
 	mutex_unlock(&pf->avail_q_mutex);
 
 	devm_kfree(dev, vsi->xdp_rings);
+	vsi->xdp_rings = NULL;
+
 	return -ENOMEM;
 }
 
@@ -2850,7 +2875,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
 	struct ice_pf *pf = vsi->back;
-	int i, v_idx;
+	int i;
 
 	/* q_vectors are freed in reset path so there's no point in detaching
 	 * rings
@@ -2858,17 +2883,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type)
 	if (cfg_type == ICE_XDP_CFG_PART)
 		goto free_qmap;
 
-	ice_for_each_q_vector(vsi, v_idx) {
-		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
-		struct ice_tx_ring *ring;
-
-		ice_for_each_tx_ring(ring, q_vector->tx)
-			if (!ring->tx_buf || !ice_ring_is_xdp(ring))
-				break;
-
-		/* restore the value of last node prior to XDP setup */
-		q_vector->tx.tx_ring = ring;
-	}
+	ice_unmap_xdp_rings(vsi);
 
 free_qmap:
 	mutex_lock(&pf->avail_q_mutex);
@@ -3013,11 +3028,14 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 		xdp_ring_err = ice_vsi_determine_xdp_res(vsi);
 		if (xdp_ring_err) {
 			NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP");
+			goto resume_if;
 		} else {
 			xdp_ring_err = ice_prepare_xdp_rings(vsi, prog,
 							     ICE_XDP_CFG_FULL);
-			if (xdp_ring_err)
+			if (xdp_ring_err) {
 				NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed");
+				goto resume_if;
+			}
 		}
 		xdp_features_set_redirect_target(vsi->netdev, true);
 		/* reallocate Rx queues that are used for zero-copy */
@@ -3035,6 +3053,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Rx resources failed");
 	}
 
+resume_if:
 	if (if_running)
 		ret = ice_up(vsi);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 6ca13c5dcb14..d9d09296d1d4 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -85,6 +85,27 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid)
 }
 
 /**
+ * ice_sched_find_next_vsi_node - find the next node for a given VSI
+ * @vsi_node: VSI support node to start search with
+ *
+ * Return: Next VSI support node, or NULL.
+ *
+ * The function returns a pointer to the next node from the VSI layer
+ * assigned to the given VSI, or NULL if there is no such a node.
+ */
+static struct ice_sched_node *
+ice_sched_find_next_vsi_node(struct ice_sched_node *vsi_node)
+{
+	unsigned int vsi_handle = vsi_node->vsi_handle;
+
+	while ((vsi_node = vsi_node->sibling) != NULL)
+		if (vsi_node->vsi_handle == vsi_handle)
+			break;
+
+	return vsi_node;
+}
+
+/**
  * ice_aqc_send_sched_elem_cmd - send scheduling elements cmd
  * @hw: pointer to the HW struct
  * @cmd_opc: cmd opcode
@@ -1084,8 +1105,10 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi,
 		if (parent->num_children < max_child_nodes) {
 			new_num_nodes = max_child_nodes - parent->num_children;
 		} else {
-			/* This parent is full, try the next sibling */
-			parent = parent->sibling;
+			/* This parent is full,
+			 * try the next available sibling.
+			 */
+			parent = ice_sched_find_next_vsi_node(parent);
 			/* Don't modify the first node TEID memory if the
 			 * first node was added already in the above call.
 			 * Instead send some temp memory for all other
@@ -1528,12 +1551,23 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 	/* get the first queue group node from VSI sub-tree */
 	qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer);
 	while (qgrp_node) {
+		struct ice_sched_node *next_vsi_node;
+
 		/* make sure the qgroup node is part of the VSI subtree */
 		if (ice_sched_find_node_in_subtree(pi->hw, vsi_node, qgrp_node))
 			if (qgrp_node->num_children < max_children &&
 			    qgrp_node->owner == owner)
 				break;
 		qgrp_node = qgrp_node->sibling;
+		if (qgrp_node)
+			continue;
+
+		next_vsi_node = ice_sched_find_next_vsi_node(vsi_node);
+		if (!next_vsi_node)
+			break;
+
+		vsi_node = next_vsi_node;
+		qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer);
 	}
 
 	/* Select the best queue group */
@@ -1604,16 +1638,16 @@ ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node,
 /**
  * ice_sched_calc_vsi_child_nodes - calculate number of VSI child nodes
  * @hw: pointer to the HW struct
- * @num_qs: number of queues
+ * @num_new_qs: number of new queues that will be added to the tree
  * @num_nodes: num nodes array
  *
  * This function calculates the number of VSI child nodes based on the
  * number of queues.
  */
 static void
-ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes)
+ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_new_qs, u16 *num_nodes)
 {
-	u16 num = num_qs;
+	u16 num = num_new_qs;
 	u8 i, qgl, vsil;
 
 	qgl = ice_sched_get_qgrp_layer(hw);
@@ -1779,7 +1813,11 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle,
 		if (!parent)
 			return -EIO;
 
-		if (i == vsil)
+		/* Do not modify the VSI handle for already existing VSI nodes,
+		 * (if no new VSI node was added to the tree).
+		 * Assign the VSI handle only to newly added VSI nodes.
+		 */
+		if (i == vsil && num_added)
 			parent->vsi_handle = vsi_handle;
 	}
 
@@ -1813,6 +1851,41 @@ ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_handle, u8 tc)
 }
 
 /**
+ * ice_sched_recalc_vsi_support_nodes - recalculate VSI support nodes count
+ * @hw: pointer to the HW struct
+ * @vsi_node: pointer to the leftmost VSI node that needs to be extended
+ * @new_numqs: new number of queues that has to be handled by the VSI
+ * @new_num_nodes: pointer to nodes count table to modify the VSI layer entry
+ *
+ * This function recalculates the number of supported nodes that need to
+ * be added after adding more Tx queues for a given VSI.
+ * The number of new VSI support nodes that shall be added will be saved
+ * to the @new_num_nodes table for the VSI layer.
+ */
+static void
+ice_sched_recalc_vsi_support_nodes(struct ice_hw *hw,
+				   struct ice_sched_node *vsi_node,
+				   unsigned int new_numqs, u16 *new_num_nodes)
+{
+	u32 vsi_nodes_cnt = 1;
+	u32 max_queue_cnt = 1;
+	u32 qgl, vsil;
+
+	qgl = ice_sched_get_qgrp_layer(hw);
+	vsil = ice_sched_get_vsi_layer(hw);
+
+	for (u32 i = vsil; i <= qgl; i++)
+		max_queue_cnt *= hw->max_children[i];
+
+	while ((vsi_node = ice_sched_find_next_vsi_node(vsi_node)) != NULL)
+		vsi_nodes_cnt++;
+
+	if (new_numqs > (max_queue_cnt * vsi_nodes_cnt))
+		new_num_nodes[vsil] = DIV_ROUND_UP(new_numqs, max_queue_cnt) -
+				      vsi_nodes_cnt;
+}
+
+/**
  * ice_sched_update_vsi_child_nodes - update VSI child nodes
  * @pi: port information structure
  * @vsi_handle: software VSI handle
@@ -1863,15 +1936,25 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 			return status;
 	}
 
-	if (new_numqs)
-		ice_sched_calc_vsi_child_nodes(hw, new_numqs, new_num_nodes);
-	/* Keep the max number of queue configuration all the time. Update the
-	 * tree only if number of queues > previous number of queues. This may
+	ice_sched_recalc_vsi_support_nodes(hw, vsi_node,
+					   new_numqs, new_num_nodes);
+	ice_sched_calc_vsi_child_nodes(hw, new_numqs - prev_numqs,
+				       new_num_nodes);
+
+	/* Never decrease the number of queues in the tree. Update the tree
+	 * only if number of queues > previous number of queues. This may
 	 * leave some extra nodes in the tree if number of queues < previous
 	 * number but that wouldn't harm anything. Removing those extra nodes
 	 * may complicate the code if those nodes are part of SRL or
 	 * individually rate limited.
+	 * Also, add the required VSI support nodes if the existing ones cannot
+	 * handle the requested new number of queues.
 	 */
+	status = ice_sched_add_vsi_support_nodes(pi, vsi_handle, tc_node,
+						 new_num_nodes);
+	if (status)
+		return status;
+
 	status = ice_sched_add_vsi_child_nodes(pi, vsi_handle, tc_node,
 					       new_num_nodes, owner);
 	if (status)
@@ -2013,6 +2096,58 @@ static bool ice_sched_is_leaf_node_present(struct ice_sched_node *node)
 }
 
 /**
+ * ice_sched_rm_vsi_subtree - remove all nodes assigned to a given VSI
+ * @pi: port information structure
+ * @vsi_node: pointer to the leftmost node of the VSI to be removed
+ * @owner: LAN or RDMA
+ * @tc: TC number
+ *
+ * Return: Zero in case of success, or -EBUSY if the VSI has leaf nodes in TC.
+ *
+ * This function removes all the VSI support nodes associated with a given VSI
+ * and its LAN or RDMA children nodes from the scheduler tree.
+ */
+static int
+ice_sched_rm_vsi_subtree(struct ice_port_info *pi,
+			 struct ice_sched_node *vsi_node, u8 owner, u8 tc)
+{
+	u16 vsi_handle = vsi_node->vsi_handle;
+	bool all_vsi_nodes_removed = true;
+	int j = 0;
+
+	while (vsi_node) {
+		struct ice_sched_node *next_vsi_node;
+
+		if (ice_sched_is_leaf_node_present(vsi_node)) {
+			ice_debug(pi->hw, ICE_DBG_SCHED, "VSI has leaf nodes in TC %d\n", tc);
+			return -EBUSY;
+		}
+		while (j < vsi_node->num_children) {
+			if (vsi_node->children[j]->owner == owner)
+				ice_free_sched_node(pi, vsi_node->children[j]);
+			else
+				j++;
+		}
+
+		next_vsi_node = ice_sched_find_next_vsi_node(vsi_node);
+
+		/* remove the VSI if it has no children */
+		if (!vsi_node->num_children)
+			ice_free_sched_node(pi, vsi_node);
+		else
+			all_vsi_nodes_removed = false;
+
+		vsi_node = next_vsi_node;
+	}
+
+	/* clean up aggregator related VSI info if any */
+	if (all_vsi_nodes_removed)
+		ice_sched_rm_agg_vsi_info(pi, vsi_handle);
+
+	return 0;
+}
+
+/**
  * ice_sched_rm_vsi_cfg - remove the VSI and its children nodes
  * @pi: port information structure
  * @vsi_handle: software VSI handle
@@ -2038,7 +2173,6 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 
 	ice_for_each_traffic_class(i) {
 		struct ice_sched_node *vsi_node, *tc_node;
-		u8 j = 0;
 
 		tc_node = ice_sched_get_tc_node(pi, i);
 		if (!tc_node)
@@ -2048,31 +2182,12 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 		if (!vsi_node)
 			continue;
 
-		if (ice_sched_is_leaf_node_present(vsi_node)) {
-			ice_debug(pi->hw, ICE_DBG_SCHED, "VSI has leaf nodes in TC %d\n", i);
-			status = -EBUSY;
+		status = ice_sched_rm_vsi_subtree(pi, vsi_node, owner, i);
+		if (status)
 			goto exit_sched_rm_vsi_cfg;
-		}
-		while (j < vsi_node->num_children) {
-			if (vsi_node->children[j]->owner == owner) {
-				ice_free_sched_node(pi, vsi_node->children[j]);
 
-				/* reset the counter again since the num
-				 * children will be updated after node removal
-				 */
-				j = 0;
-			} else {
-				j++;
-			}
-		}
-		/* remove the VSI if it has no children */
-		if (!vsi_node->num_children) {
-			ice_free_sched_node(pi, vsi_node);
-			vsi_ctx->sched.vsi_node[i] = NULL;
+		vsi_ctx->sched.vsi_node[i] = NULL;
 
-			/* clean up aggregator related VSI info if any */
-			ice_sched_rm_agg_vsi_info(pi, vsi_handle);
-		}
 		if (owner == ICE_SCHED_NODE_OWNER_LAN)
 			vsi_ctx->sched.max_lanq[i] = 0;
 		else
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index bab12ecb2df5..4eb20ec2accb 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -1801,11 +1801,19 @@ void idpf_vc_event_task(struct work_struct *work)
 	if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags))
 		return;
 
-	if (test_bit(IDPF_HR_FUNC_RESET, adapter->flags) ||
-	    test_bit(IDPF_HR_DRV_LOAD, adapter->flags)) {
-		set_bit(IDPF_HR_RESET_IN_PROG, adapter->flags);
-		idpf_init_hard_reset(adapter);
-	}
+	if (test_bit(IDPF_HR_FUNC_RESET, adapter->flags))
+		goto func_reset;
+
+	if (test_bit(IDPF_HR_DRV_LOAD, adapter->flags))
+		goto drv_load;
+
+	return;
+
+func_reset:
+	idpf_vc_xn_shutdown(adapter->vcxn_mngr);
+drv_load:
+	set_bit(IDPF_HR_RESET_IN_PROG, adapter->flags);
+	idpf_init_hard_reset(adapter);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index 2e356dd10812..993c354aa27a 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -362,17 +362,18 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 {
 	struct idpf_tx_offload_params offload = { };
 	struct idpf_tx_buf *first;
+	int csum, tso, needed;
 	unsigned int count;
 	__be16 protocol;
-	int csum, tso;
 
 	count = idpf_tx_desc_count_required(tx_q, skb);
 	if (unlikely(!count))
 		return idpf_tx_drop_skb(tx_q, skb);
 
-	if (idpf_tx_maybe_stop_common(tx_q,
-				      count + IDPF_TX_DESCS_PER_CACHE_LINE +
-				      IDPF_TX_DESCS_FOR_CTX)) {
+	needed = count + IDPF_TX_DESCS_PER_CACHE_LINE + IDPF_TX_DESCS_FOR_CTX;
+	if (!netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
+				       IDPF_DESC_UNUSED(tx_q),
+				       needed, needed)) {
 		idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false);
 
 		u64_stats_update_begin(&tx_q->stats_sync);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 631679cdaa6f..5cf440e09d0a 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -2184,6 +2184,19 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 	desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag);
 }
 
+/* Global conditions to tell whether the txq (and related resources)
+ * has room to allow the use of "size" descriptors.
+ */
+static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 size)
+{
+	if (IDPF_DESC_UNUSED(tx_q) < size ||
+	    IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) >
+		IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq) ||
+	    IDPF_TX_BUF_RSV_LOW(tx_q))
+		return 0;
+	return 1;
+}
+
 /**
  * idpf_tx_maybe_stop_splitq - 1st level check for Tx splitq stop conditions
  * @tx_q: the queue to be checked
@@ -2194,29 +2207,11 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q,
 				     unsigned int descs_needed)
 {
-	if (idpf_tx_maybe_stop_common(tx_q, descs_needed))
-		goto out;
-
-	/* If there are too many outstanding completions expected on the
-	 * completion queue, stop the TX queue to give the device some time to
-	 * catch up
-	 */
-	if (unlikely(IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) >
-		     IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq)))
-		goto splitq_stop;
-
-	/* Also check for available book keeping buffers; if we are low, stop
-	 * the queue to wait for more completions
-	 */
-	if (unlikely(IDPF_TX_BUF_RSV_LOW(tx_q)))
-		goto splitq_stop;
-
-	return 0;
-
-splitq_stop:
-	netif_stop_subqueue(tx_q->netdev, tx_q->idx);
+	if (netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
+				      idpf_txq_has_room(tx_q, descs_needed),
+				      1, 1))
+		return 0;
 
-out:
 	u64_stats_update_begin(&tx_q->stats_sync);
 	u64_stats_inc(&tx_q->q_stats.q_busy);
 	u64_stats_update_end(&tx_q->stats_sync);
@@ -2242,12 +2237,6 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 	nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
 	tx_q->next_to_use = val;
 
-	if (idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED)) {
-		u64_stats_update_begin(&tx_q->stats_sync);
-		u64_stats_inc(&tx_q->q_stats.q_busy);
-		u64_stats_update_end(&tx_q->stats_sync);
-	}
-
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.  (Only
 	 * applicable for weak-ordered memory model archs,
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index c779fe71df99..36a0f828a6f8 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -1049,12 +1049,4 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rxq,
 				      u16 cleaned_count);
 int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off);
 
-static inline bool idpf_tx_maybe_stop_common(struct idpf_tx_queue *tx_q,
-					     u32 needed)
-{
-	return !netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
-					  IDPF_DESC_UNUSED(tx_q),
-					  needed, needed);
-}
-
 #endif /* !_IDPF_TXRX_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index 07a9f5ae34fd..24febaaa8fbb 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -347,7 +347,7 @@ static void idpf_vc_xn_init(struct idpf_vc_xn_manager *vcxn_mngr)
  * All waiting threads will be woken-up and their transaction aborted. Further
  * operations on that object will fail.
  */
-static void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr)
+void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr)
 {
 	int i;
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
index 3522c1238ea2..77578206bada 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
@@ -150,5 +150,6 @@ int idpf_send_get_stats_msg(struct idpf_vport *vport);
 int idpf_send_set_sriov_vfs_msg(struct idpf_adapter *adapter, u16 num_vfs);
 int idpf_send_get_set_rss_key_msg(struct idpf_vport *vport, bool get);
 int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get);
+void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr);
 
 #endif /* _IDPF_VIRTCHNL_H_ */
diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index b175119a6a7d..b83886a41121 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1463,6 +1463,8 @@ static __maybe_unused int mtk_star_suspend(struct device *dev)
 	if (netif_running(ndev))
 		mtk_star_disable(ndev);
 
+	netif_device_detach(ndev);
+
 	clk_bulk_disable_unprepare(MTK_STAR_NCLKS, priv->clks);
 
 	return 0;
@@ -1487,6 +1489,8 @@ static __maybe_unused int mtk_star_resume(struct device *dev)
 			clk_bulk_disable_unprepare(MTK_STAR_NCLKS, priv->clks);
 	}
 
+	netif_device_attach(ndev);
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index cd754cd76bde..d73a2044dc26 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -249,7 +249,7 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = {
 static u32 freq_to_shift(u16 freq)
 {
 	u32 freq_khz = freq * 1000;
-	u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
+	u64 max_val_cycles = freq_khz * 1000ULL * MLX4_EN_WRAP_AROUND_SEC;
 	u64 max_val_cycles_rounded = 1ULL << fls64(max_val_cycles - 1);
 	/* calculate max possible multiplier in order to fit in 64bit */
 	u64 max_mul = div64_u64(ULLONG_MAX, max_val_cycles_rounded);
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 427bdc0e4908..7001584f1b7a 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -879,6 +879,7 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p,
 	lan966x_vlan_port_set_vlan_aware(port, 0);
 	lan966x_vlan_port_set_vid(port, HOST_PVID, false, false);
 	lan966x_vlan_port_apply(port);
+	lan966x_vlan_port_rew_host(port);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index 1f9df67f0504..4f75f0688369 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -497,6 +497,7 @@ void lan966x_vlan_port_apply(struct lan966x_port *port);
 bool lan966x_vlan_cpu_member_cpu_vlan_mask(struct lan966x *lan966x, u16 vid);
 void lan966x_vlan_port_set_vlan_aware(struct lan966x_port *port,
 				      bool vlan_aware);
+void lan966x_vlan_port_rew_host(struct lan966x_port *port);
 int lan966x_vlan_port_set_vid(struct lan966x_port *port,
 			      u16 vid,
 			      bool pvid,
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c
index 1c88120eb291..bcb4db76b75c 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c
@@ -297,6 +297,7 @@ static void lan966x_port_bridge_leave(struct lan966x_port *port,
 	lan966x_vlan_port_set_vlan_aware(port, false);
 	lan966x_vlan_port_set_vid(port, HOST_PVID, false, false);
 	lan966x_vlan_port_apply(port);
+	lan966x_vlan_port_rew_host(port);
 }
 
 int lan966x_port_changeupper(struct net_device *dev,
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
index fa34a739c748..7da22520724c 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
@@ -149,6 +149,27 @@ void lan966x_vlan_port_set_vlan_aware(struct lan966x_port *port,
 	port->vlan_aware = vlan_aware;
 }
 
+/* When the interface is in host mode, the interface should not be vlan aware
+ * but it should insert all the tags that it gets from the network stack.
+ * The tags are not in the data of the frame but actually in the skb and the ifh
+ * is configured already to get this tag. So what we need to do is to update the
+ * rewriter to insert the vlan tag for all frames which have a vlan tag
+ * different than 0.
+ */
+void lan966x_vlan_port_rew_host(struct lan966x_port *port)
+{
+	struct lan966x *lan966x = port->lan966x;
+	u32 val;
+
+	/* Tag all frames except when VID=0*/
+	val = REW_TAG_CFG_TAG_CFG_SET(2);
+
+	/* Update only some bits in the register */
+	lan_rmw(val,
+		REW_TAG_CFG_TAG_CFG,
+		lan966x, REW_TAG_CFG(port->chip_port));
+}
+
 void lan966x_vlan_port_apply(struct lan966x_port *port)
 {
 	struct lan966x *lan966x = port->lan966x;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c
index c9693f77e1f6..ac6f2e3a3fcd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c
@@ -32,6 +32,11 @@ static int est_configure(struct stmmac_priv *priv, struct stmmac_est *cfg,
 	int i, ret = 0;
 	u32 ctrl;
 
+	if (!ptp_rate) {
+		netdev_warn(priv->dev, "Invalid PTP rate");
+		return -EINVAL;
+	}
+
 	ret |= est_write(est_addr, EST_BTR_LOW, cfg->btr[0], false);
 	ret |= est_write(est_addr, EST_BTR_HIGH, cfg->btr[1], false);
 	ret |= est_write(est_addr, EST_TER, cfg->ter, false);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 085c09039af4..1369fa70bc58 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -805,6 +805,11 @@ int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags)
 	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
 		return -EOPNOTSUPP;
 
+	if (!priv->plat->clk_ptp_rate) {
+		netdev_err(priv->dev, "Invalid PTP clock rate");
+		return -EINVAL;
+	}
+
 	stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags);
 	priv->systime_flags = systime_flags;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 43c869f64c39..b80c1efdb323 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -430,6 +430,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	struct device_node *np = pdev->dev.of_node;
 	struct plat_stmmacenet_data *plat;
 	struct stmmac_dma_cfg *dma_cfg;
+	static int bus_id = -ENODEV;
 	int phy_mode;
 	void *ret;
 	int rc;
@@ -465,8 +466,14 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	of_property_read_u32(np, "max-speed", &plat->max_speed);
 
 	plat->bus_id = of_alias_get_id(np, "ethernet");
-	if (plat->bus_id < 0)
-		plat->bus_id = 0;
+	if (plat->bus_id < 0) {
+		if (bus_id < 0)
+			bus_id = of_alias_get_highest_id("ethernet");
+		/* No ethernet alias found, init at -1 so first bus_id is 0 */
+		if (bus_id < 0)
+			bus_id = -1;
+		plat->bus_id = ++bus_id;
+	}
 
 	/* Default to phy auto-detection */
 	plat->phy_addr = -1;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 429b2d357813..3767ba495e78 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -317,7 +317,7 @@ void stmmac_ptp_register(struct stmmac_priv *priv)
 
 	/* Calculate the clock domain crossing (CDC) error if necessary */
 	priv->plat->cdc_error_adj = 0;
-	if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate)
+	if (priv->plat->has_gmac4)
 		priv->plat->cdc_error_adj = (2 * NSEC_PER_SEC) / priv->plat->clk_ptp_rate;
 
 	/* Update the ptp clock parameters based on feature discovery, when
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c
index e8241e998aa9..7159baa0155c 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c
@@ -28,6 +28,14 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
 	spin_lock(&prueth->stats_lock);
 
 	for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) {
+		/* In MII mode TX lines are swapped inside ICSSG, so read Tx stats
+		 * from slice1 for port0 and slice0 for port1 to get accurate Tx
+		 * stats for a given port
+		 */
+		if (emac->phy_if == PHY_INTERFACE_MODE_MII &&
+		    icssg_all_miig_stats[i].offset >= ICSSG_TX_PACKET_OFFSET &&
+		    icssg_all_miig_stats[i].offset <= ICSSG_TX_BYTE_OFFSET)
+			base = stats_base[slice ^ 1];
 		regmap_read(prueth->miig_rt,
 			    base + icssg_all_miig_stats[i].offset,
 			    &val);
diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c
index e01c5997a551..1dd3755d9e6d 100644
--- a/drivers/net/hyperv/netvsc_bpf.c
+++ b/drivers/net/hyperv/netvsc_bpf.c
@@ -183,7 +183,7 @@ int netvsc_vf_setxdp(struct net_device *vf_netdev, struct bpf_prog *prog)
 	xdp.command = XDP_SETUP_PROG;
 	xdp.prog = prog;
 
-	ret = dev_xdp_propagate(vf_netdev, &xdp);
+	ret = netif_xdp_propagate(vf_netdev, &xdp);
 
 	if (ret && prog)
 		bpf_prog_put(prog);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 14a0d04e21ae..c41a025c66f0 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2462,8 +2462,6 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
 
 	netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
 
-	netvsc_vf_setxdp(vf_netdev, NULL);
-
 	reinit_completion(&net_device_ctx->vf_add);
 	netdev_rx_handler_unregister(vf_netdev);
 	netdev_upper_dev_unlink(vf_netdev, ndev);
@@ -2631,7 +2629,9 @@ static int netvsc_probe(struct hv_device *dev,
 			continue;
 
 		netvsc_prepare_bonding(vf_netdev);
+		netdev_lock_ops(vf_netdev);
 		netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE);
+		netdev_unlock_ops(vf_netdev);
 		__netvsc_vf_setup(net, vf_netdev);
 		break;
 	}
diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c
index 10d8afecec55..ebf1e849506b 100644
--- a/drivers/net/ovpn/io.c
+++ b/drivers/net/ovpn/io.c
@@ -134,7 +134,7 @@ void ovpn_decrypt_post(void *data, int ret)
 
 	rcu_read_lock();
 	sock = rcu_dereference(peer->sock);
-	if (sock && sock->sock->sk->sk_protocol == IPPROTO_UDP)
+	if (sock && sock->sk->sk_protocol == IPPROTO_UDP)
 		/* check if this peer changed local or remote endpoint */
 		ovpn_peer_endpoints_update(peer, skb);
 	rcu_read_unlock();
@@ -270,12 +270,12 @@ void ovpn_encrypt_post(void *data, int ret)
 	if (unlikely(!sock))
 		goto err_unlock;
 
-	switch (sock->sock->sk->sk_protocol) {
+	switch (sock->sk->sk_protocol) {
 	case IPPROTO_UDP:
-		ovpn_udp_send_skb(peer, sock->sock, skb);
+		ovpn_udp_send_skb(peer, sock->sk, skb);
 		break;
 	case IPPROTO_TCP:
-		ovpn_tcp_send_skb(peer, sock->sock, skb);
+		ovpn_tcp_send_skb(peer, sock->sk, skb);
 		break;
 	default:
 		/* no transport configured yet */
diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c
index bea03913bfb1..a4ec53def46e 100644
--- a/drivers/net/ovpn/netlink.c
+++ b/drivers/net/ovpn/netlink.c
@@ -501,7 +501,7 @@ int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info)
 	/* when using a TCP socket the remote IP is not expected */
 	rcu_read_lock();
 	sock = rcu_dereference(peer->sock);
-	if (sock && sock->sock->sk->sk_protocol == IPPROTO_TCP &&
+	if (sock && sock->sk->sk_protocol == IPPROTO_TCP &&
 	    (attrs[OVPN_A_PEER_REMOTE_IPV4] ||
 	     attrs[OVPN_A_PEER_REMOTE_IPV6])) {
 		rcu_read_unlock();
@@ -559,14 +559,14 @@ static int ovpn_nl_send_peer(struct sk_buff *skb, const struct genl_info *info,
 		goto err_unlock;
 	}
 
-	if (!net_eq(genl_info_net(info), sock_net(sock->sock->sk))) {
+	if (!net_eq(genl_info_net(info), sock_net(sock->sk))) {
 		id = peernet2id_alloc(genl_info_net(info),
-				      sock_net(sock->sock->sk),
+				      sock_net(sock->sk),
 				      GFP_ATOMIC);
 		if (nla_put_s32(skb, OVPN_A_PEER_SOCKET_NETNSID, id))
 			goto err_unlock;
 	}
-	local_port = inet_sk(sock->sock->sk)->inet_sport;
+	local_port = inet_sk(sock->sk)->inet_sport;
 	rcu_read_unlock();
 
 	if (nla_put_u32(skb, OVPN_A_PEER_ID, peer->id))
@@ -1153,8 +1153,8 @@ int ovpn_nl_peer_del_notify(struct ovpn_peer *peer)
 		ret = -EINVAL;
 		goto err_unlock;
 	}
-	genlmsg_multicast_netns(&ovpn_nl_family, sock_net(sock->sock->sk),
-				msg, 0, OVPN_NLGRP_PEERS, GFP_ATOMIC);
+	genlmsg_multicast_netns(&ovpn_nl_family, sock_net(sock->sk), msg, 0,
+				OVPN_NLGRP_PEERS, GFP_ATOMIC);
 	rcu_read_unlock();
 
 	return 0;
@@ -1218,8 +1218,8 @@ int ovpn_nl_key_swap_notify(struct ovpn_peer *peer, u8 key_id)
 		ret = -EINVAL;
 		goto err_unlock;
 	}
-	genlmsg_multicast_netns(&ovpn_nl_family, sock_net(sock->sock->sk),
-				msg, 0, OVPN_NLGRP_PEERS, GFP_ATOMIC);
+	genlmsg_multicast_netns(&ovpn_nl_family, sock_net(sock->sk), msg, 0,
+				OVPN_NLGRP_PEERS, GFP_ATOMIC);
 	rcu_read_unlock();
 
 	return 0;
diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
index a1fd27b9c038..4bfcab0c8652 100644
--- a/drivers/net/ovpn/peer.c
+++ b/drivers/net/ovpn/peer.c
@@ -1145,7 +1145,7 @@ static void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk,
 
 	if (sk) {
 		ovpn_sock = rcu_access_pointer(peer->sock);
-		if (!ovpn_sock || ovpn_sock->sock->sk != sk) {
+		if (!ovpn_sock || ovpn_sock->sk != sk) {
 			spin_unlock_bh(&ovpn->lock);
 			ovpn_peer_put(peer);
 			return;
@@ -1175,7 +1175,7 @@ static void ovpn_peers_release_mp(struct ovpn_priv *ovpn, struct sock *sk,
 		if (sk) {
 			rcu_read_lock();
 			ovpn_sock = rcu_dereference(peer->sock);
-			remove = ovpn_sock && ovpn_sock->sock->sk == sk;
+			remove = ovpn_sock && ovpn_sock->sk == sk;
 			rcu_read_unlock();
 		}
 
diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c
index a83cbab72591..9750871ab65c 100644
--- a/drivers/net/ovpn/socket.c
+++ b/drivers/net/ovpn/socket.c
@@ -24,9 +24,9 @@ static void ovpn_socket_release_kref(struct kref *kref)
 	struct ovpn_socket *sock = container_of(kref, struct ovpn_socket,
 						refcount);
 
-	if (sock->sock->sk->sk_protocol == IPPROTO_UDP)
+	if (sock->sk->sk_protocol == IPPROTO_UDP)
 		ovpn_udp_socket_detach(sock);
-	else if (sock->sock->sk->sk_protocol == IPPROTO_TCP)
+	else if (sock->sk->sk_protocol == IPPROTO_TCP)
 		ovpn_tcp_socket_detach(sock);
 }
 
@@ -75,14 +75,6 @@ void ovpn_socket_release(struct ovpn_peer *peer)
 	if (!sock)
 		return;
 
-	/* sanity check: we should not end up here if the socket
-	 * was already closed
-	 */
-	if (!sock->sock->sk) {
-		DEBUG_NET_WARN_ON_ONCE(1);
-		return;
-	}
-
 	/* Drop the reference while holding the sock lock to avoid
 	 * concurrent ovpn_socket_new call to mess up with a partially
 	 * detached socket.
@@ -90,22 +82,24 @@ void ovpn_socket_release(struct ovpn_peer *peer)
 	 * Holding the lock ensures that a socket with refcnt 0 is fully
 	 * detached before it can be picked by a concurrent reader.
 	 */
-	lock_sock(sock->sock->sk);
+	lock_sock(sock->sk);
 	released = ovpn_socket_put(peer, sock);
-	release_sock(sock->sock->sk);
+	release_sock(sock->sk);
 
 	/* align all readers with sk_user_data being NULL */
 	synchronize_rcu();
 
 	/* following cleanup should happen with lock released */
 	if (released) {
-		if (sock->sock->sk->sk_protocol == IPPROTO_UDP) {
+		if (sock->sk->sk_protocol == IPPROTO_UDP) {
 			netdev_put(sock->ovpn->dev, &sock->dev_tracker);
-		} else if (sock->sock->sk->sk_protocol == IPPROTO_TCP) {
+		} else if (sock->sk->sk_protocol == IPPROTO_TCP) {
 			/* wait for TCP jobs to terminate */
 			ovpn_tcp_socket_wait_finish(sock);
 			ovpn_peer_put(sock->peer);
 		}
+		/* drop reference acquired in ovpn_socket_new() */
+		sock_put(sock->sk);
 		/* we can call plain kfree() because we already waited one RCU
 		 * period due to synchronize_rcu()
 		 */
@@ -118,12 +112,14 @@ static bool ovpn_socket_hold(struct ovpn_socket *sock)
 	return kref_get_unless_zero(&sock->refcount);
 }
 
-static int ovpn_socket_attach(struct ovpn_socket *sock, struct ovpn_peer *peer)
+static int ovpn_socket_attach(struct ovpn_socket *ovpn_sock,
+			      struct socket *sock,
+			      struct ovpn_peer *peer)
 {
-	if (sock->sock->sk->sk_protocol == IPPROTO_UDP)
-		return ovpn_udp_socket_attach(sock, peer->ovpn);
-	else if (sock->sock->sk->sk_protocol == IPPROTO_TCP)
-		return ovpn_tcp_socket_attach(sock, peer);
+	if (sock->sk->sk_protocol == IPPROTO_UDP)
+		return ovpn_udp_socket_attach(ovpn_sock, sock, peer->ovpn);
+	else if (sock->sk->sk_protocol == IPPROTO_TCP)
+		return ovpn_tcp_socket_attach(ovpn_sock, peer);
 
 	return -EOPNOTSUPP;
 }
@@ -138,14 +134,15 @@ static int ovpn_socket_attach(struct ovpn_socket *sock, struct ovpn_peer *peer)
 struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer)
 {
 	struct ovpn_socket *ovpn_sock;
+	struct sock *sk = sock->sk;
 	int ret;
 
-	lock_sock(sock->sk);
+	lock_sock(sk);
 
 	/* a TCP socket can only be owned by a single peer, therefore there
 	 * can't be any other user
 	 */
-	if (sock->sk->sk_protocol == IPPROTO_TCP && sock->sk->sk_user_data) {
+	if (sk->sk_protocol == IPPROTO_TCP && sk->sk_user_data) {
 		ovpn_sock = ERR_PTR(-EBUSY);
 		goto sock_release;
 	}
@@ -153,8 +150,8 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer)
 	/* a UDP socket can be shared across multiple peers, but we must make
 	 * sure it is not owned by something else
 	 */
-	if (sock->sk->sk_protocol == IPPROTO_UDP) {
-		u8 type = READ_ONCE(udp_sk(sock->sk)->encap_type);
+	if (sk->sk_protocol == IPPROTO_UDP) {
+		u8 type = READ_ONCE(udp_sk(sk)->encap_type);
 
 		/* socket owned by other encapsulation module */
 		if (type && type != UDP_ENCAP_OVPNINUDP) {
@@ -163,7 +160,7 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer)
 		}
 
 		rcu_read_lock();
-		ovpn_sock = rcu_dereference_sk_user_data(sock->sk);
+		ovpn_sock = rcu_dereference_sk_user_data(sk);
 		if (ovpn_sock) {
 			/* socket owned by another ovpn instance, we can't use it */
 			if (ovpn_sock->ovpn != peer->ovpn) {
@@ -200,11 +197,22 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer)
 		goto sock_release;
 	}
 
-	ovpn_sock->sock = sock;
+	ovpn_sock->sk = sk;
 	kref_init(&ovpn_sock->refcount);
 
-	ret = ovpn_socket_attach(ovpn_sock, peer);
+	/* the newly created ovpn_socket is holding reference to sk,
+	 * therefore we increase its refcounter.
+	 *
+	 * This ovpn_socket instance is referenced by all peers
+	 * using the same socket.
+	 *
+	 * ovpn_socket_release() will take care of dropping the reference.
+	 */
+	sock_hold(sk);
+
+	ret = ovpn_socket_attach(ovpn_sock, sock, peer);
 	if (ret < 0) {
+		sock_put(sk);
 		kfree(ovpn_sock);
 		ovpn_sock = ERR_PTR(ret);
 		goto sock_release;
@@ -213,11 +221,11 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer)
 	/* TCP sockets are per-peer, therefore they are linked to their unique
 	 * peer
 	 */
-	if (sock->sk->sk_protocol == IPPROTO_TCP) {
+	if (sk->sk_protocol == IPPROTO_TCP) {
 		INIT_WORK(&ovpn_sock->tcp_tx_work, ovpn_tcp_tx_work);
 		ovpn_sock->peer = peer;
 		ovpn_peer_hold(peer);
-	} else if (sock->sk->sk_protocol == IPPROTO_UDP) {
+	} else if (sk->sk_protocol == IPPROTO_UDP) {
 		/* in UDP we only link the ovpn instance since the socket is
 		 * shared among multiple peers
 		 */
@@ -226,8 +234,8 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer)
 			    GFP_KERNEL);
 	}
 
-	rcu_assign_sk_user_data(sock->sk, ovpn_sock);
+	rcu_assign_sk_user_data(sk, ovpn_sock);
 sock_release:
-	release_sock(sock->sk);
+	release_sock(sk);
 	return ovpn_sock;
 }
diff --git a/drivers/net/ovpn/socket.h b/drivers/net/ovpn/socket.h
index 00d856b1a5d8..4afcec71040d 100644
--- a/drivers/net/ovpn/socket.h
+++ b/drivers/net/ovpn/socket.h
@@ -22,7 +22,7 @@ struct ovpn_peer;
  * @ovpn: ovpn instance owning this socket (UDP only)
  * @dev_tracker: reference tracker for associated dev (UDP only)
  * @peer: unique peer transmitting over this socket (TCP only)
- * @sock: the low level sock object
+ * @sk: the low level sock object
  * @refcount: amount of contexts currently referencing this object
  * @work: member used to schedule release routine (it may block)
  * @tcp_tx_work: work for deferring outgoing packet processing (TCP only)
@@ -36,7 +36,7 @@ struct ovpn_socket {
 		struct ovpn_peer *peer;
 	};
 
-	struct socket *sock;
+	struct sock *sk;
 	struct kref refcount;
 	struct work_struct work;
 	struct work_struct tcp_tx_work;
diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c
index 7c42d84987ad..289f62c5d2c7 100644
--- a/drivers/net/ovpn/tcp.c
+++ b/drivers/net/ovpn/tcp.c
@@ -124,14 +124,18 @@ static void ovpn_tcp_rcv(struct strparser *strp, struct sk_buff *skb)
 	 * this peer, therefore ovpn_peer_hold() is not expected to fail
 	 */
 	if (WARN_ON(!ovpn_peer_hold(peer)))
-		goto err;
+		goto err_nopeer;
 
 	ovpn_recv(peer, skb);
 	return;
 err:
+	/* take reference for deferred peer deletion. should never fail */
+	if (WARN_ON(!ovpn_peer_hold(peer)))
+		goto err_nopeer;
+	schedule_work(&peer->tcp.defer_del_work);
 	dev_dstats_rx_dropped(peer->ovpn->dev);
+err_nopeer:
 	kfree_skb(skb);
-	ovpn_peer_del(peer, OVPN_DEL_PEER_REASON_TRANSPORT_ERROR);
 }
 
 static int ovpn_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
@@ -186,18 +190,18 @@ out:
 void ovpn_tcp_socket_detach(struct ovpn_socket *ovpn_sock)
 {
 	struct ovpn_peer *peer = ovpn_sock->peer;
-	struct socket *sock = ovpn_sock->sock;
+	struct sock *sk = ovpn_sock->sk;
 
 	strp_stop(&peer->tcp.strp);
 	skb_queue_purge(&peer->tcp.user_queue);
 
 	/* restore CBs that were saved in ovpn_sock_set_tcp_cb() */
-	sock->sk->sk_data_ready = peer->tcp.sk_cb.sk_data_ready;
-	sock->sk->sk_write_space = peer->tcp.sk_cb.sk_write_space;
-	sock->sk->sk_prot = peer->tcp.sk_cb.prot;
-	sock->sk->sk_socket->ops = peer->tcp.sk_cb.ops;
+	sk->sk_data_ready = peer->tcp.sk_cb.sk_data_ready;
+	sk->sk_write_space = peer->tcp.sk_cb.sk_write_space;
+	sk->sk_prot = peer->tcp.sk_cb.prot;
+	sk->sk_socket->ops = peer->tcp.sk_cb.ops;
 
-	rcu_assign_sk_user_data(sock->sk, NULL);
+	rcu_assign_sk_user_data(sk, NULL);
 }
 
 void ovpn_tcp_socket_wait_finish(struct ovpn_socket *sock)
@@ -283,10 +287,10 @@ void ovpn_tcp_tx_work(struct work_struct *work)
 
 	sock = container_of(work, struct ovpn_socket, tcp_tx_work);
 
-	lock_sock(sock->sock->sk);
+	lock_sock(sock->sk);
 	if (sock->peer)
-		ovpn_tcp_send_sock(sock->peer, sock->sock->sk);
-	release_sock(sock->sock->sk);
+		ovpn_tcp_send_sock(sock->peer, sock->sk);
+	release_sock(sock->sk);
 }
 
 static void ovpn_tcp_send_sock_skb(struct ovpn_peer *peer, struct sock *sk,
@@ -307,15 +311,15 @@ static void ovpn_tcp_send_sock_skb(struct ovpn_peer *peer, struct sock *sk,
 	ovpn_tcp_send_sock(peer, sk);
 }
 
-void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct socket *sock,
+void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct sock *sk,
 		       struct sk_buff *skb)
 {
 	u16 len = skb->len;
 
 	*(__be16 *)__skb_push(skb, sizeof(u16)) = htons(len);
 
-	spin_lock_nested(&sock->sk->sk_lock.slock, OVPN_TCP_DEPTH_NESTING);
-	if (sock_owned_by_user(sock->sk)) {
+	spin_lock_nested(&sk->sk_lock.slock, OVPN_TCP_DEPTH_NESTING);
+	if (sock_owned_by_user(sk)) {
 		if (skb_queue_len(&peer->tcp.out_queue) >=
 		    READ_ONCE(net_hotdata.max_backlog)) {
 			dev_dstats_tx_dropped(peer->ovpn->dev);
@@ -324,10 +328,10 @@ void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct socket *sock,
 		}
 		__skb_queue_tail(&peer->tcp.out_queue, skb);
 	} else {
-		ovpn_tcp_send_sock_skb(peer, sock->sk, skb);
+		ovpn_tcp_send_sock_skb(peer, sk, skb);
 	}
 unlock:
-	spin_unlock(&sock->sk->sk_lock.slock);
+	spin_unlock(&sk->sk_lock.slock);
 }
 
 static void ovpn_tcp_release(struct sock *sk)
@@ -474,7 +478,6 @@ static void ovpn_tcp_peer_del_work(struct work_struct *work)
 int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock,
 			   struct ovpn_peer *peer)
 {
-	struct socket *sock = ovpn_sock->sock;
 	struct strp_callbacks cb = {
 		.rcv_msg = ovpn_tcp_rcv,
 		.parse_msg = ovpn_tcp_parse,
@@ -482,20 +485,20 @@ int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock,
 	int ret;
 
 	/* make sure no pre-existing encapsulation handler exists */
-	if (sock->sk->sk_user_data)
+	if (ovpn_sock->sk->sk_user_data)
 		return -EBUSY;
 
 	/* only a fully connected socket is expected. Connection should be
 	 * handled in userspace
 	 */
-	if (sock->sk->sk_state != TCP_ESTABLISHED) {
+	if (ovpn_sock->sk->sk_state != TCP_ESTABLISHED) {
 		net_err_ratelimited("%s: provided TCP socket is not in ESTABLISHED state: %d\n",
 				    netdev_name(peer->ovpn->dev),
-				    sock->sk->sk_state);
+				    ovpn_sock->sk->sk_state);
 		return -EINVAL;
 	}
 
-	ret = strp_init(&peer->tcp.strp, sock->sk, &cb);
+	ret = strp_init(&peer->tcp.strp, ovpn_sock->sk, &cb);
 	if (ret < 0) {
 		DEBUG_NET_WARN_ON_ONCE(1);
 		return ret;
@@ -503,31 +506,31 @@ int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock,
 
 	INIT_WORK(&peer->tcp.defer_del_work, ovpn_tcp_peer_del_work);
 
-	__sk_dst_reset(sock->sk);
+	__sk_dst_reset(ovpn_sock->sk);
 	skb_queue_head_init(&peer->tcp.user_queue);
 	skb_queue_head_init(&peer->tcp.out_queue);
 
 	/* save current CBs so that they can be restored upon socket release */
-	peer->tcp.sk_cb.sk_data_ready = sock->sk->sk_data_ready;
-	peer->tcp.sk_cb.sk_write_space = sock->sk->sk_write_space;
-	peer->tcp.sk_cb.prot = sock->sk->sk_prot;
-	peer->tcp.sk_cb.ops = sock->sk->sk_socket->ops;
+	peer->tcp.sk_cb.sk_data_ready = ovpn_sock->sk->sk_data_ready;
+	peer->tcp.sk_cb.sk_write_space = ovpn_sock->sk->sk_write_space;
+	peer->tcp.sk_cb.prot = ovpn_sock->sk->sk_prot;
+	peer->tcp.sk_cb.ops = ovpn_sock->sk->sk_socket->ops;
 
 	/* assign our static CBs and prot/ops */
-	sock->sk->sk_data_ready = ovpn_tcp_data_ready;
-	sock->sk->sk_write_space = ovpn_tcp_write_space;
+	ovpn_sock->sk->sk_data_ready = ovpn_tcp_data_ready;
+	ovpn_sock->sk->sk_write_space = ovpn_tcp_write_space;
 
-	if (sock->sk->sk_family == AF_INET) {
-		sock->sk->sk_prot = &ovpn_tcp_prot;
-		sock->sk->sk_socket->ops = &ovpn_tcp_ops;
+	if (ovpn_sock->sk->sk_family == AF_INET) {
+		ovpn_sock->sk->sk_prot = &ovpn_tcp_prot;
+		ovpn_sock->sk->sk_socket->ops = &ovpn_tcp_ops;
 	} else {
-		sock->sk->sk_prot = &ovpn_tcp6_prot;
-		sock->sk->sk_socket->ops = &ovpn_tcp6_ops;
+		ovpn_sock->sk->sk_prot = &ovpn_tcp6_prot;
+		ovpn_sock->sk->sk_socket->ops = &ovpn_tcp6_ops;
 	}
 
 	/* avoid using task_frag */
-	sock->sk->sk_allocation = GFP_ATOMIC;
-	sock->sk->sk_use_task_frag = false;
+	ovpn_sock->sk->sk_allocation = GFP_ATOMIC;
+	ovpn_sock->sk->sk_use_task_frag = false;
 
 	/* enqueue the RX worker */
 	strp_check_rcv(&peer->tcp.strp);
diff --git a/drivers/net/ovpn/tcp.h b/drivers/net/ovpn/tcp.h
index 10aefa834cf3..a3aa3570ae5e 100644
--- a/drivers/net/ovpn/tcp.h
+++ b/drivers/net/ovpn/tcp.h
@@ -30,7 +30,8 @@ void ovpn_tcp_socket_wait_finish(struct ovpn_socket *sock);
  * Required by the OpenVPN protocol in order to extract packets from
  * the TCP stream on the receiver side.
  */
-void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct socket *sock, struct sk_buff *skb);
+void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct sock *sk,
+		       struct sk_buff *skb);
 void ovpn_tcp_tx_work(struct work_struct *work);
 
 #endif /* _NET_OVPN_TCP_H_ */
diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c
index aef8c0406ec9..bff00946eae2 100644
--- a/drivers/net/ovpn/udp.c
+++ b/drivers/net/ovpn/udp.c
@@ -43,7 +43,7 @@ static struct ovpn_socket *ovpn_socket_from_udp_sock(struct sock *sk)
 		return NULL;
 
 	/* make sure that sk matches our stored transport socket */
-	if (unlikely(!ovpn_sock->sock || sk != ovpn_sock->sock->sk))
+	if (unlikely(!ovpn_sock->sk || sk != ovpn_sock->sk))
 		return NULL;
 
 	return ovpn_sock;
@@ -335,32 +335,22 @@ out:
 /**
  * ovpn_udp_send_skb - prepare skb and send it over via UDP
  * @peer: the destination peer
- * @sock: the RCU protected peer socket
+ * @sk: peer socket
  * @skb: the packet to send
  */
-void ovpn_udp_send_skb(struct ovpn_peer *peer, struct socket *sock,
+void ovpn_udp_send_skb(struct ovpn_peer *peer, struct sock *sk,
 		       struct sk_buff *skb)
 {
-	int ret = -1;
+	int ret;
 
 	skb->dev = peer->ovpn->dev;
 	/* no checksum performed at this layer */
 	skb->ip_summed = CHECKSUM_NONE;
 
-	/* get socket info */
-	if (unlikely(!sock)) {
-		net_warn_ratelimited("%s: no sock for remote peer %u\n",
-				     netdev_name(peer->ovpn->dev), peer->id);
-		goto out;
-	}
-
 	/* crypto layer -> transport (UDP) */
-	ret = ovpn_udp_output(peer, &peer->dst_cache, sock->sk, skb);
-out:
-	if (unlikely(ret < 0)) {
+	ret = ovpn_udp_output(peer, &peer->dst_cache, sk, skb);
+	if (unlikely(ret < 0))
 		kfree_skb(skb);
-		return;
-	}
 }
 
 static void ovpn_udp_encap_destroy(struct sock *sk)
@@ -383,6 +373,7 @@ static void ovpn_udp_encap_destroy(struct sock *sk)
 /**
  * ovpn_udp_socket_attach - set udp-tunnel CBs on socket and link it to ovpn
  * @ovpn_sock: socket to configure
+ * @sock: the socket container to be passed to setup_udp_tunnel_sock()
  * @ovpn: the openvp instance to link
  *
  * After invoking this function, the sock will be controlled by ovpn so that
@@ -390,7 +381,7 @@ static void ovpn_udp_encap_destroy(struct sock *sk)
  *
  * Return: 0 on success or a negative error code otherwise
  */
-int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
+int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock, struct socket *sock,
 			   struct ovpn_priv *ovpn)
 {
 	struct udp_tunnel_sock_cfg cfg = {
@@ -398,17 +389,16 @@ int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
 		.encap_rcv = ovpn_udp_encap_recv,
 		.encap_destroy = ovpn_udp_encap_destroy,
 	};
-	struct socket *sock = ovpn_sock->sock;
 	struct ovpn_socket *old_data;
 	int ret;
 
 	/* make sure no pre-existing encapsulation handler exists */
 	rcu_read_lock();
-	old_data = rcu_dereference_sk_user_data(sock->sk);
+	old_data = rcu_dereference_sk_user_data(ovpn_sock->sk);
 	if (!old_data) {
 		/* socket is currently unused - we can take it */
 		rcu_read_unlock();
-		setup_udp_tunnel_sock(sock_net(sock->sk), sock, &cfg);
+		setup_udp_tunnel_sock(sock_net(ovpn_sock->sk), sock, &cfg);
 		return 0;
 	}
 
@@ -421,7 +411,7 @@ int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
 	 * Unlikely TCP, a single UDP socket can be used to talk to many remote
 	 * hosts and therefore openvpn instantiates one only for all its peers
 	 */
-	if ((READ_ONCE(udp_sk(sock->sk)->encap_type) == UDP_ENCAP_OVPNINUDP) &&
+	if ((READ_ONCE(udp_sk(ovpn_sock->sk)->encap_type) == UDP_ENCAP_OVPNINUDP) &&
 	    old_data->ovpn == ovpn) {
 		netdev_dbg(ovpn->dev,
 			   "provided socket already owned by this interface\n");
@@ -442,8 +432,16 @@ int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
  */
 void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock)
 {
-	struct udp_tunnel_sock_cfg cfg = { };
+	struct sock *sk = ovpn_sock->sk;
+
+	/* Re-enable multicast loopback */
+	inet_set_bit(MC_LOOP, sk);
+	/* Disable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
+	inet_dec_convert_csum(sk);
+
+	WRITE_ONCE(udp_sk(sk)->encap_type, 0);
+	WRITE_ONCE(udp_sk(sk)->encap_rcv, NULL);
+	WRITE_ONCE(udp_sk(sk)->encap_destroy, NULL);
 
-	setup_udp_tunnel_sock(sock_net(ovpn_sock->sock->sk), ovpn_sock->sock,
-			      &cfg);
+	rcu_assign_sk_user_data(sk, NULL);
 }
diff --git a/drivers/net/ovpn/udp.h b/drivers/net/ovpn/udp.h
index 9994eb6e0428..fe26fbe25c5a 100644
--- a/drivers/net/ovpn/udp.h
+++ b/drivers/net/ovpn/udp.h
@@ -15,11 +15,11 @@ struct ovpn_peer;
 struct ovpn_priv;
 struct socket;
 
-int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
+int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock, struct socket *sock,
 			   struct ovpn_priv *ovpn);
 void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock);
 
-void ovpn_udp_send_skb(struct ovpn_peer *peer, struct socket *sock,
+void ovpn_udp_send_skb(struct ovpn_peer *peer, struct sock *sk,
 		       struct sk_buff *skb);
 
 #endif /* _NET_OVPN_UDP_H_ */
diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 453a2cf82753..9201ee10a13f 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -31,11 +31,11 @@ static int aqc111_read_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value,
 				   USB_RECIP_DEVICE, value, index, data, size);
 
 	if (unlikely(ret < size)) {
-		ret = ret < 0 ? ret : -ENODATA;
-
 		netdev_warn(dev->net,
 			    "Failed to read(0x%x) reg index 0x%04x: %d\n",
 			    cmd, index, ret);
+
+		ret = ret < 0 ? ret : -ENODATA;
 	}
 
 	return ret;
@@ -50,11 +50,11 @@ static int aqc111_read_cmd(struct usbnet *dev, u8 cmd, u16 value,
 			      USB_RECIP_DEVICE, value, index, data, size);
 
 	if (unlikely(ret < size)) {
-		ret = ret < 0 ? ret : -ENODATA;
-
 		netdev_warn(dev->net,
 			    "Failed to read(0x%x) reg index 0x%04x: %d\n",
 			    cmd, index, ret);
+
+		ret = ret < 0 ? ret : -ENODATA;
 	}
 
 	return ret;
diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c
index f69d9b902da0..a206ffa76f1b 100644
--- a/drivers/net/usb/ch9200.c
+++ b/drivers/net/usb/ch9200.c
@@ -178,6 +178,7 @@ static int ch9200_mdio_read(struct net_device *netdev, int phy_id, int loc)
 {
 	struct usbnet *dev = netdev_priv(netdev);
 	unsigned char buff[2];
+	int ret;
 
 	netdev_dbg(netdev, "%s phy_id:%02x loc:%02x\n",
 		   __func__, phy_id, loc);
@@ -185,8 +186,10 @@ static int ch9200_mdio_read(struct net_device *netdev, int phy_id, int loc)
 	if (phy_id != 0)
 		return -ENODEV;
 
-	control_read(dev, REQUEST_READ, 0, loc * 2, buff, 0x02,
-		     CONTROL_TIMEOUT_MS);
+	ret = control_read(dev, REQUEST_READ, 0, loc * 2, buff, 0x02,
+			   CONTROL_TIMEOUT_MS);
+	if (ret < 0)
+		return ret;
 
 	return (buff[0] | buff[1] << 8);
 }
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 2440e30c5bd1..0572f6a9bdb6 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1572,6 +1572,30 @@ vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb,
 	return (hlen + (hdr.tcp->doff << 2));
 }
 
+static void
+vmxnet3_lro_tunnel(struct sk_buff *skb, __be16 ip_proto)
+{
+	struct udphdr *uh = NULL;
+
+	if (ip_proto == htons(ETH_P_IP)) {
+		struct iphdr *iph = (struct iphdr *)skb->data;
+
+		if (iph->protocol == IPPROTO_UDP)
+			uh = (struct udphdr *)(iph + 1);
+	} else {
+		struct ipv6hdr *iph = (struct ipv6hdr *)skb->data;
+
+		if (iph->nexthdr == IPPROTO_UDP)
+			uh = (struct udphdr *)(iph + 1);
+	}
+	if (uh) {
+		if (uh->check)
+			skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+		else
+			skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
+	}
+}
+
 static int
 vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 		       struct vmxnet3_adapter *adapter, int quota)
@@ -1885,6 +1909,8 @@ sop_done:
 			if (segCnt != 0 && mss != 0) {
 				skb_shinfo(skb)->gso_type = rcd->v4 ?
 					SKB_GSO_TCPV4 : SKB_GSO_TCPV6;
+				if (encap_lro)
+					vmxnet3_lro_tunnel(skb, skb->protocol);
 				skb_shinfo(skb)->gso_size = mss;
 				skb_shinfo(skb)->gso_segs = segCnt;
 			} else if ((segCnt != 0 || skb->len > mtu) && !encap_lro) {
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 3ffeeba5dccf..4a529f1f9bea 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -366,6 +366,7 @@ static int wg_newlink(struct net_device *dev,
 	if (ret < 0)
 		goto err_free_handshake_queue;
 
+	dev_set_threaded(dev, true);
 	ret = register_netdevice(dev);
 	if (ret < 0)
 		goto err_uninit_ratelimiter;
diff --git a/drivers/net/wireless/ath/ath11k/Kconfig b/drivers/net/wireless/ath/ath11k/Kconfig
index 2e935d381b6b..659ef134ef16 100644
--- a/drivers/net/wireless/ath/ath11k/Kconfig
+++ b/drivers/net/wireless/ath/ath11k/Kconfig
@@ -24,7 +24,7 @@ config ATH11K_PCI
 	select MHI_BUS
 	select QRTR
 	select QRTR_MHI
-	select PCI_PWRCTL_PWRSEQ if HAVE_PWRCTL
+	select PCI_PWRCTRL_PWRSEQ if HAVE_PWRCTRL
 	help
 	  This module adds support for PCIE bus
 
diff --git a/drivers/net/wireless/ath/ath12k/Kconfig b/drivers/net/wireless/ath/ath12k/Kconfig
index b3b15e1eb282..1ea1af1b8f6c 100644
--- a/drivers/net/wireless/ath/ath12k/Kconfig
+++ b/drivers/net/wireless/ath/ath12k/Kconfig
@@ -7,7 +7,7 @@ config ATH12K
 	select MHI_BUS
 	select QRTR
 	select QRTR_MHI
-	select PCI_PWRCTL_PWRSEQ if HAVE_PWRCTL
+	select PCI_PWRCTRL_PWRSEQ if HAVE_PWRCTRL
 	help
 	  Enable support for Qualcomm Technologies Wi-Fi 7 (IEEE
 	  802.11be) family of chipsets, for example WCN7850 and
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/fw.c b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
index 73ed8d5cab43..9d2c087360e7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
@@ -349,10 +349,6 @@ int iwl_mld_load_fw(struct iwl_mld *mld)
 	if (ret)
 		goto err;
 
-	ret = iwl_mld_init_mcc(mld);
-	if (ret)
-		goto err;
-
 	mld->fw_status.running = true;
 
 	return 0;
@@ -546,6 +542,10 @@ int iwl_mld_start_fw(struct iwl_mld *mld)
 	if (ret)
 		goto error;
 
+	ret = iwl_mld_init_mcc(mld);
+	if (ret)
+		goto error;
+
 	return 0;
 
 error:
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.c b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
index 8cdd960c5245..e8820e7cf8fa 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
@@ -653,7 +653,8 @@ iwl_mld_nic_error(struct iwl_op_mode *op_mode,
 	 * It might not actually be true that we'll restart, but the
 	 * setting doesn't matter if we're going to be unbound either.
 	 */
-	if (type != IWL_ERR_TYPE_RESET_HS_TIMEOUT)
+	if (type != IWL_ERR_TYPE_RESET_HS_TIMEOUT &&
+	    mld->fw_status.running)
 		mld->fw_status.in_hw_restart = true;
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 0f056a6641bd..956b491ae5a4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -6360,8 +6360,8 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
 			(struct iwl_mvm_internal_rxq_notif *)cmd->payload;
 	struct iwl_host_cmd hcmd = {
 		.id = WIDE_ID(DATA_PATH_GROUP, TRIGGER_RX_QUEUES_NOTIF_CMD),
-		.data[0] = &cmd,
-		.len[0] = sizeof(cmd),
+		.data[0] = cmd,
+		.len[0] = __struct_size(cmd),
 		.data[1] = data,
 		.len[1] = size,
 		.flags = CMD_SEND_IN_RFKILL | (sync ? 0 : CMD_ASYNC),
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
index 38ad719161e6..c8f4f3a1d2eb 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -125,7 +125,7 @@ void iwl_trans_pcie_fw_reset_handshake(struct iwl_trans *trans)
 			reset_done =
 				inta_hw & MSIX_HW_INT_CAUSES_REG_RESET_DONE;
 		} else {
-			inta_hw = iwl_read32(trans, CSR_INT_MASK);
+			inta_hw = iwl_read32(trans, CSR_INT);
 			reset_done = inta_hw & CSR_INT_BIT_RESET_DONE;
 		}
 
diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c
index 8755c5e6a65b..c814fbd756a1 100644
--- a/drivers/net/wwan/mhi_wwan_mbim.c
+++ b/drivers/net/wwan/mhi_wwan_mbim.c
@@ -550,8 +550,8 @@ static int mhi_mbim_newlink(void *ctxt, struct net_device *ndev, u32 if_id,
 	struct mhi_mbim_link *link = wwan_netdev_drvpriv(ndev);
 	struct mhi_mbim_context *mbim = ctxt;
 
-	link->session = if_id;
 	link->mbim = mbim;
+	link->session = mhi_mbim_get_link_mux_id(link->mbim->mdev->mhi_cntrl) + if_id;
 	link->ndev = ndev;
 	u64_stats_init(&link->rx_syncp);
 	u64_stats_init(&link->tx_syncp);
@@ -607,7 +607,7 @@ static int mhi_mbim_probe(struct mhi_device *mhi_dev, const struct mhi_device_id
 {
 	struct mhi_controller *cntrl = mhi_dev->mhi_cntrl;
 	struct mhi_mbim_context *mbim;
-	int err, link_id;
+	int err;
 
 	mbim = devm_kzalloc(&mhi_dev->dev, sizeof(*mbim), GFP_KERNEL);
 	if (!mbim)
@@ -628,11 +628,8 @@ static int mhi_mbim_probe(struct mhi_device *mhi_dev, const struct mhi_device_id
 	/* Number of transfer descriptors determines size of the queue */
 	mbim->rx_queue_sz = mhi_get_free_desc_count(mhi_dev, DMA_FROM_DEVICE);
 
-	/* Get the corresponding mux_id from mhi */
-	link_id = mhi_mbim_get_link_mux_id(cntrl);
-
 	/* Register wwan link ops with MHI controller representing WWAN instance */
-	return wwan_register_ops(&cntrl->mhi_dev->dev, &mhi_mbim_wwan_ops, mbim, link_id);
+	return wwan_register_ops(&cntrl->mhi_dev->dev, &mhi_mbim_wwan_ops, mbim, 0);
 }
 
 static void mhi_mbim_remove(struct mhi_device *mhi_dev)
diff --git a/drivers/net/wwan/t7xx/t7xx_netdev.c b/drivers/net/wwan/t7xx/t7xx_netdev.c
index 91fa082e9cab..fc0a7cb181df 100644
--- a/drivers/net/wwan/t7xx/t7xx_netdev.c
+++ b/drivers/net/wwan/t7xx/t7xx_netdev.c
@@ -302,7 +302,7 @@ static int t7xx_ccmni_wwan_newlink(void *ctxt, struct net_device *dev, u32 if_id
 	ccmni->ctlb = ctlb;
 	ccmni->dev = dev;
 	atomic_set(&ccmni->usage, 0);
-	ctlb->ccmni_inst[if_id] = ccmni;
+	WRITE_ONCE(ctlb->ccmni_inst[if_id], ccmni);
 
 	ret = register_netdevice(dev);
 	if (ret)
@@ -324,6 +324,7 @@ static void t7xx_ccmni_wwan_dellink(void *ctxt, struct net_device *dev, struct l
 	if (WARN_ON(ctlb->ccmni_inst[if_id] != ccmni))
 		return;
 
+	WRITE_ONCE(ctlb->ccmni_inst[if_id], NULL);
 	unregister_netdevice(dev);
 }
 
@@ -419,7 +420,7 @@ static void t7xx_ccmni_recv_skb(struct t7xx_ccmni_ctrl *ccmni_ctlb, struct sk_bu
 
 	skb_cb = T7XX_SKB_CB(skb);
 	netif_id = skb_cb->netif_idx;
-	ccmni = ccmni_ctlb->ccmni_inst[netif_id];
+	ccmni = READ_ONCE(ccmni_ctlb->ccmni_inst[netif_id]);
 	if (!ccmni) {
 		dev_kfree_skb(skb);
 		return;
@@ -441,7 +442,7 @@ static void t7xx_ccmni_recv_skb(struct t7xx_ccmni_ctrl *ccmni_ctlb, struct sk_bu
 
 static void t7xx_ccmni_queue_tx_irq_notify(struct t7xx_ccmni_ctrl *ctlb, int qno)
 {
-	struct t7xx_ccmni *ccmni = ctlb->ccmni_inst[0];
+	struct t7xx_ccmni *ccmni = READ_ONCE(ctlb->ccmni_inst[0]);
 	struct netdev_queue *net_queue;
 
 	if (netif_running(ccmni->dev) && atomic_read(&ccmni->usage) > 0) {
@@ -453,7 +454,7 @@ static void t7xx_ccmni_queue_tx_irq_notify(struct t7xx_ccmni_ctrl *ctlb, int qno
 
 static void t7xx_ccmni_queue_tx_full_notify(struct t7xx_ccmni_ctrl *ctlb, int qno)
 {
-	struct t7xx_ccmni *ccmni = ctlb->ccmni_inst[0];
+	struct t7xx_ccmni *ccmni = READ_ONCE(ctlb->ccmni_inst[0]);
 	struct netdev_queue *net_queue;
 
 	if (atomic_read(&ccmni->usage) > 0) {
@@ -471,7 +472,7 @@ static void t7xx_ccmni_queue_state_notify(struct t7xx_pci_dev *t7xx_dev,
 	if (ctlb->md_sta != MD_STATE_READY)
 		return;
 
-	if (!ctlb->ccmni_inst[0]) {
+	if (!READ_ONCE(ctlb->ccmni_inst[0])) {
 		dev_warn(&t7xx_dev->pdev->dev, "No netdev registered yet\n");
 		return;
 	}
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index da28295b4aac..9c0e4aaf4e8c 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -21,6 +21,7 @@ config GENERIC_PCI_IOMAP
 menuconfig PCI
 	bool "PCI support"
 	depends on HAVE_PCI
+	depends on MMU
 	help
 	  This option enables support for the PCI local bus, including
 	  support for PCI-X and the foundations for PCI Express support.
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index b6851101ac36..69048869ef1c 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -369,7 +369,9 @@ void pci_bus_add_device(struct pci_dev *dev)
 				pdev->name);
 	}
 
-	dev->match_driver = !dn || of_device_is_available(dn);
+	if (!dn || of_device_is_available(dn))
+		pci_dev_allow_binding(dev);
+
 	retval = device_attach(&dev->dev);
 	if (retval < 0 && retval != -EPROBE_DEFER)
 		pci_warn(dev, "device attach failed (%d)\n", retval);
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index eb3cc28d43f8..886f6f43a895 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -3,6 +3,10 @@
 menu "PCI controller drivers"
 	depends on PCI
 
+config PCI_HOST_COMMON
+	tristate
+	select PCI_ECAM
+
 config PCI_AARDVARK
 	tristate "Aardvark PCIe controller"
 	depends on (ARCH_MVEBU && ARM64) || COMPILE_TEST
@@ -120,10 +124,6 @@ config PCI_FTPCI100
 	depends on OF
 	default ARCH_GEMINI
 
-config PCI_HOST_COMMON
-	tristate
-	select PCI_ECAM
-
 config PCI_HOST_GENERIC
 	tristate "Generic PCI host controller"
 	depends on OF
diff --git a/drivers/pci/controller/cadence/Kconfig b/drivers/pci/controller/cadence/Kconfig
index 8a0044bb3989..666e16b6367f 100644
--- a/drivers/pci/controller/cadence/Kconfig
+++ b/drivers/pci/controller/cadence/Kconfig
@@ -4,16 +4,16 @@ menu "Cadence-based PCIe controllers"
 	depends on PCI
 
 config PCIE_CADENCE
-	bool
+	tristate
 
 config PCIE_CADENCE_HOST
-	bool
+	tristate
 	depends on OF
 	select IRQ_DOMAIN
 	select PCIE_CADENCE
 
 config PCIE_CADENCE_EP
-	bool
+	tristate
 	depends on OF
 	depends on PCI_ENDPOINT
 	select PCIE_CADENCE
@@ -43,13 +43,14 @@ config PCIE_CADENCE_PLAT_EP
 	  different vendors SoCs.
 
 config PCI_J721E
-	bool
+	tristate
+	select PCIE_CADENCE_HOST if PCI_J721E_HOST != n
+	select PCIE_CADENCE_EP if PCI_J721E_EP != n
 
 config PCI_J721E_HOST
-	bool "TI J721E PCIe controller (host mode)"
+	tristate "TI J721E PCIe controller (host mode)"
 	depends on ARCH_K3 || COMPILE_TEST
 	depends on OF
-	select PCIE_CADENCE_HOST
 	select PCI_J721E
 	help
 	  Say Y here if you want to support the TI J721E PCIe platform
@@ -57,11 +58,10 @@ config PCI_J721E_HOST
 	  core.
 
 config PCI_J721E_EP
-	bool "TI J721E PCIe controller (endpoint mode)"
+	tristate "TI J721E PCIe controller (endpoint mode)"
 	depends on ARCH_K3 || COMPILE_TEST
 	depends on OF
 	depends on PCI_ENDPOINT
-	select PCIE_CADENCE_EP
 	select PCI_J721E
 	help
 	  Say Y here if you want to support the TI J721E PCIe platform
diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c
index ef1cfdae33bb..6c93f39d0288 100644
--- a/drivers/pci/controller/cadence/pci-j721e.c
+++ b/drivers/pci/controller/cadence/pci-j721e.c
@@ -15,6 +15,7 @@
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/mfd/syscon.h>
+#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
@@ -27,6 +28,7 @@
 #define cdns_pcie_to_rc(p) container_of(p, struct cdns_pcie_rc, pcie)
 
 #define ENABLE_REG_SYS_2	0x108
+#define ENABLE_CLR_REG_SYS_2	0x308
 #define STATUS_REG_SYS_2	0x508
 #define STATUS_CLR_REG_SYS_2	0x708
 #define LINK_DOWN		BIT(1)
@@ -116,6 +118,15 @@ static irqreturn_t j721e_pcie_link_irq_handler(int irq, void *priv)
 	return IRQ_HANDLED;
 }
 
+static void j721e_pcie_disable_link_irq(struct j721e_pcie *pcie)
+{
+	u32 reg;
+
+	reg = j721e_pcie_intd_readl(pcie, ENABLE_CLR_REG_SYS_2);
+	reg |= pcie->linkdown_irq_regfield;
+	j721e_pcie_intd_writel(pcie, ENABLE_CLR_REG_SYS_2, reg);
+}
+
 static void j721e_pcie_config_link_irq(struct j721e_pcie *pcie)
 {
 	u32 reg;
@@ -153,11 +164,7 @@ static bool j721e_pcie_link_up(struct cdns_pcie *cdns_pcie)
 	u32 reg;
 
 	reg = j721e_pcie_user_readl(pcie, J721E_PCIE_USER_LINKSTATUS);
-	reg &= LINK_STATUS;
-	if (reg == LINK_UP_DL_COMPLETED)
-		return true;
-
-	return false;
+	return (reg & LINK_STATUS) == LINK_UP_DL_COMPLETED;
 }
 
 static const struct cdns_pcie_ops j721e_pcie_ops = {
@@ -464,7 +471,7 @@ static int j721e_pcie_probe(struct platform_device *pdev)
 
 	switch (mode) {
 	case PCI_MODE_RC:
-		if (!IS_ENABLED(CONFIG_PCIE_CADENCE_HOST))
+		if (!IS_ENABLED(CONFIG_PCI_J721E_HOST))
 			return -ENODEV;
 
 		bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc));
@@ -483,7 +490,7 @@ static int j721e_pcie_probe(struct platform_device *pdev)
 		pcie->cdns_pcie = cdns_pcie;
 		break;
 	case PCI_MODE_EP:
-		if (!IS_ENABLED(CONFIG_PCIE_CADENCE_EP))
+		if (!IS_ENABLED(CONFIG_PCI_J721E_EP))
 			return -ENODEV;
 
 		ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL);
@@ -633,9 +640,22 @@ static void j721e_pcie_remove(struct platform_device *pdev)
 	struct j721e_pcie *pcie = platform_get_drvdata(pdev);
 	struct cdns_pcie *cdns_pcie = pcie->cdns_pcie;
 	struct device *dev = &pdev->dev;
+	struct cdns_pcie_ep *ep;
+	struct cdns_pcie_rc *rc;
+
+	if (pcie->mode == PCI_MODE_RC) {
+		rc = container_of(cdns_pcie, struct cdns_pcie_rc, pcie);
+		cdns_pcie_host_disable(rc);
+	} else {
+		ep = container_of(cdns_pcie, struct cdns_pcie_ep, pcie);
+		cdns_pcie_ep_disable(ep);
+	}
+
+	gpiod_set_value_cansleep(pcie->reset_gpio, 0);
 
 	clk_disable_unprepare(pcie->refclk);
 	cdns_pcie_disable_phy(cdns_pcie);
+	j721e_pcie_disable_link_irq(pcie);
 	pm_runtime_put(dev);
 	pm_runtime_disable(dev);
 }
@@ -730,4 +750,8 @@ static struct platform_driver j721e_pcie_driver = {
 		.pm	= pm_sleep_ptr(&j721e_pcie_pm_ops),
 	},
 };
-builtin_platform_driver(j721e_pcie_driver);
+module_platform_driver(j721e_pcie_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("PCIe controller driver for TI's J721E and related SoCs");
+MODULE_AUTHOR("Kishon Vijay Abraham I <kishon@ti.com>");
diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c
index 599ec4b1223e..8ab6cf70c18e 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-ep.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c
@@ -6,12 +6,14 @@
 #include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/pci-epc.h>
 #include <linux/platform_device.h>
 #include <linux/sizes.h>
 
 #include "pcie-cadence.h"
+#include "../../pci.h"
 
 #define CDNS_PCIE_EP_MIN_APERTURE		128	/* 128 bytes */
 #define CDNS_PCIE_EP_IRQ_PCI_ADDR_NONE		0x1
@@ -220,10 +222,11 @@ static void cdns_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn,
 	clear_bit(r, &ep->ob_region_map);
 }
 
-static int cdns_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 mmc)
+static int cdns_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 nr_irqs)
 {
 	struct cdns_pcie_ep *ep = epc_get_drvdata(epc);
 	struct cdns_pcie *pcie = &ep->pcie;
+	u8 mmc = order_base_2(nr_irqs);
 	u32 cap = CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET;
 	u16 flags;
 
@@ -262,7 +265,7 @@ static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn)
 	 */
 	mme = FIELD_GET(PCI_MSI_FLAGS_QSIZE, flags);
 
-	return mme;
+	return 1 << mme;
 }
 
 static int cdns_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
@@ -281,12 +284,11 @@ static int cdns_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 
 	val &= PCI_MSIX_FLAGS_QSIZE;
 
-	return val;
+	return val + 1;
 }
 
 static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn,
-				 u16 interrupts, enum pci_barno bir,
-				 u32 offset)
+				 u16 nr_irqs, enum pci_barno bir, u32 offset)
 {
 	struct cdns_pcie_ep *ep = epc_get_drvdata(epc);
 	struct cdns_pcie *pcie = &ep->pcie;
@@ -298,7 +300,7 @@ static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn,
 	reg = cap + PCI_MSIX_FLAGS;
 	val = cdns_pcie_ep_fn_readw(pcie, fn, reg);
 	val &= ~PCI_MSIX_FLAGS_QSIZE;
-	val |= interrupts;
+	val |= nr_irqs - 1; /* encoded as N-1 */
 	cdns_pcie_ep_fn_writew(pcie, fn, reg, val);
 
 	/* Set MSI-X BAR and offset */
@@ -308,7 +310,7 @@ static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn,
 
 	/* Set PBA BAR and offset.  BAR must match MSI-X BAR */
 	reg = cap + PCI_MSIX_PBA;
-	val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir;
+	val = (offset + (nr_irqs * PCI_MSIX_ENTRY_SIZE)) | bir;
 	cdns_pcie_ep_fn_writel(pcie, fn, reg, val);
 
 	return 0;
@@ -337,10 +339,10 @@ static void cdns_pcie_ep_assert_intx(struct cdns_pcie_ep *ep, u8 fn, u8 intx,
 
 	if (is_asserted) {
 		ep->irq_pending |= BIT(intx);
-		msg_code = MSG_CODE_ASSERT_INTA + intx;
+		msg_code = PCIE_MSG_CODE_ASSERT_INTA + intx;
 	} else {
 		ep->irq_pending &= ~BIT(intx);
-		msg_code = MSG_CODE_DEASSERT_INTA + intx;
+		msg_code = PCIE_MSG_CODE_DEASSERT_INTA + intx;
 	}
 
 	spin_lock_irqsave(&ep->lock, flags);
@@ -644,6 +646,17 @@ static const struct pci_epc_ops cdns_pcie_epc_ops = {
 	.get_features	= cdns_pcie_ep_get_features,
 };
 
+void cdns_pcie_ep_disable(struct cdns_pcie_ep *ep)
+{
+	struct device *dev = ep->pcie.dev;
+	struct pci_epc *epc = to_pci_epc(dev);
+
+	pci_epc_deinit_notify(epc);
+	pci_epc_mem_free_addr(epc, ep->irq_phys_addr, ep->irq_cpu_addr,
+			      SZ_128K);
+	pci_epc_mem_exit(epc);
+}
+EXPORT_SYMBOL_GPL(cdns_pcie_ep_disable);
 
 int cdns_pcie_ep_setup(struct cdns_pcie_ep *ep)
 {
@@ -751,3 +764,8 @@ int cdns_pcie_ep_setup(struct cdns_pcie_ep *ep)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(cdns_pcie_ep_setup);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Cadence PCIe endpoint controller driver");
+MODULE_AUTHOR("Cyrille Pitchen <cyrille.pitchen@free-electrons.com>");
diff --git a/drivers/pci/controller/cadence/pcie-cadence-host.c b/drivers/pci/controller/cadence/pcie-cadence-host.c
index 8af95e9da7ce..59a4631de79f 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-host.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-host.c
@@ -5,6 +5,7 @@
 
 #include <linux/delay.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/list_sort.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
@@ -72,6 +73,7 @@ void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn,
 
 	return rc->cfg_base + (where & 0xfff);
 }
+EXPORT_SYMBOL_GPL(cdns_pci_map_bus);
 
 static struct pci_ops cdns_pcie_host_ops = {
 	.map_bus	= cdns_pci_map_bus,
@@ -150,6 +152,14 @@ static int cdns_pcie_retrain(struct cdns_pcie *pcie)
 	return ret;
 }
 
+static void cdns_pcie_host_disable_ptm_response(struct cdns_pcie *pcie)
+{
+	u32 val;
+
+	val = cdns_pcie_readl(pcie, CDNS_PCIE_LM_PTM_CTRL);
+	cdns_pcie_writel(pcie, CDNS_PCIE_LM_PTM_CTRL, val & ~CDNS_PCIE_LM_TPM_CTRL_PTMRSEN);
+}
+
 static void cdns_pcie_host_enable_ptm_response(struct cdns_pcie *pcie)
 {
 	u32 val;
@@ -175,6 +185,26 @@ static int cdns_pcie_host_start_link(struct cdns_pcie_rc *rc)
 	return ret;
 }
 
+static void cdns_pcie_host_deinit_root_port(struct cdns_pcie_rc *rc)
+{
+	struct cdns_pcie *pcie = &rc->pcie;
+	u32 value, ctrl;
+
+	cdns_pcie_rp_writew(pcie, PCI_CLASS_DEVICE, 0xffff);
+	cdns_pcie_rp_writeb(pcie, PCI_CLASS_PROG, 0xff);
+	cdns_pcie_rp_writeb(pcie, PCI_CLASS_REVISION, 0xff);
+	cdns_pcie_writel(pcie, CDNS_PCIE_LM_ID, 0xffffffff);
+	cdns_pcie_rp_writew(pcie, PCI_DEVICE_ID, 0xffff);
+	ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_DISABLED;
+	value = ~(CDNS_PCIE_LM_RC_BAR_CFG_BAR0_CTRL(ctrl) |
+		CDNS_PCIE_LM_RC_BAR_CFG_BAR1_CTRL(ctrl) |
+		CDNS_PCIE_LM_RC_BAR_CFG_PREFETCH_MEM_ENABLE |
+		CDNS_PCIE_LM_RC_BAR_CFG_PREFETCH_MEM_64BITS |
+		CDNS_PCIE_LM_RC_BAR_CFG_IO_ENABLE |
+		CDNS_PCIE_LM_RC_BAR_CFG_IO_32BITS);
+	cdns_pcie_writel(pcie, CDNS_PCIE_LM_RC_BAR_CFG, value);
+}
+
 static int cdns_pcie_host_init_root_port(struct cdns_pcie_rc *rc)
 {
 	struct cdns_pcie *pcie = &rc->pcie;
@@ -391,6 +421,32 @@ static int cdns_pcie_host_dma_ranges_cmp(void *priv, const struct list_head *a,
         return resource_size(entry2->res) - resource_size(entry1->res);
 }
 
+static void cdns_pcie_host_unmap_dma_ranges(struct cdns_pcie_rc *rc)
+{
+	struct cdns_pcie *pcie = &rc->pcie;
+	enum cdns_pcie_rp_bar bar;
+	u32 value;
+
+	/* Reset inbound configuration for all BARs which were being used */
+	for (bar = RP_BAR0; bar <= RP_NO_BAR; bar++) {
+		if (rc->avail_ib_bar[bar])
+			continue;
+
+		cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_RP_BAR_ADDR0(bar), 0);
+		cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_RP_BAR_ADDR1(bar), 0);
+
+		if (bar == RP_NO_BAR)
+			continue;
+
+		value = ~(LM_RC_BAR_CFG_CTRL_MEM_64BITS(bar) |
+			  LM_RC_BAR_CFG_CTRL_PREF_MEM_64BITS(bar) |
+			  LM_RC_BAR_CFG_CTRL_MEM_32BITS(bar) |
+			  LM_RC_BAR_CFG_CTRL_PREF_MEM_32BITS(bar) |
+			  LM_RC_BAR_CFG_APERTURE(bar, bar_aperture_mask[bar] + 2));
+		cdns_pcie_writel(pcie, CDNS_PCIE_LM_RC_BAR_CFG, value);
+	}
+}
+
 static int cdns_pcie_host_map_dma_ranges(struct cdns_pcie_rc *rc)
 {
 	struct cdns_pcie *pcie = &rc->pcie;
@@ -428,6 +484,29 @@ static int cdns_pcie_host_map_dma_ranges(struct cdns_pcie_rc *rc)
 	return 0;
 }
 
+static void cdns_pcie_host_deinit_address_translation(struct cdns_pcie_rc *rc)
+{
+	struct cdns_pcie *pcie = &rc->pcie;
+	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(rc);
+	struct resource_entry *entry;
+	int r;
+
+	cdns_pcie_host_unmap_dma_ranges(rc);
+
+	/*
+	 * Reset outbound region 0 which was reserved for configuration space
+	 * accesses.
+	 */
+	cdns_pcie_reset_outbound_region(pcie, 0);
+
+	/* Reset rest of the outbound regions */
+	r = 1;
+	resource_list_for_each_entry(entry, &bridge->windows) {
+		cdns_pcie_reset_outbound_region(pcie, r);
+		r++;
+	}
+}
+
 static int cdns_pcie_host_init_address_translation(struct cdns_pcie_rc *rc)
 {
 	struct cdns_pcie *pcie = &rc->pcie;
@@ -485,6 +564,12 @@ static int cdns_pcie_host_init_address_translation(struct cdns_pcie_rc *rc)
 	return cdns_pcie_host_map_dma_ranges(rc);
 }
 
+static void cdns_pcie_host_deinit(struct cdns_pcie_rc *rc)
+{
+	cdns_pcie_host_deinit_address_translation(rc);
+	cdns_pcie_host_deinit_root_port(rc);
+}
+
 int cdns_pcie_host_init(struct cdns_pcie_rc *rc)
 {
 	int err;
@@ -495,6 +580,15 @@ int cdns_pcie_host_init(struct cdns_pcie_rc *rc)
 
 	return cdns_pcie_host_init_address_translation(rc);
 }
+EXPORT_SYMBOL_GPL(cdns_pcie_host_init);
+
+static void cdns_pcie_host_link_disable(struct cdns_pcie_rc *rc)
+{
+	struct cdns_pcie *pcie = &rc->pcie;
+
+	cdns_pcie_stop_link(pcie);
+	cdns_pcie_host_disable_ptm_response(pcie);
+}
 
 int cdns_pcie_host_link_setup(struct cdns_pcie_rc *rc)
 {
@@ -519,6 +613,20 @@ int cdns_pcie_host_link_setup(struct cdns_pcie_rc *rc)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(cdns_pcie_host_link_setup);
+
+void cdns_pcie_host_disable(struct cdns_pcie_rc *rc)
+{
+	struct pci_host_bridge *bridge;
+
+	bridge = pci_host_bridge_from_priv(rc);
+	pci_stop_root_bus(bridge->bus);
+	pci_remove_root_bus(bridge->bus);
+
+	cdns_pcie_host_deinit(rc);
+	cdns_pcie_host_link_disable(rc);
+}
+EXPORT_SYMBOL_GPL(cdns_pcie_host_disable);
 
 int cdns_pcie_host_setup(struct cdns_pcie_rc *rc)
 {
@@ -570,14 +678,10 @@ int cdns_pcie_host_setup(struct cdns_pcie_rc *rc)
 	if (!bridge->ops)
 		bridge->ops = &cdns_pcie_host_ops;
 
-	ret = pci_host_probe(bridge);
-	if (ret < 0)
-		goto err_init;
-
-	return 0;
-
- err_init:
-	pm_runtime_put_sync(dev);
-
-	return ret;
+	return pci_host_probe(bridge);
 }
+EXPORT_SYMBOL_GPL(cdns_pcie_host_setup);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Cadence PCIe host controller driver");
+MODULE_AUTHOR("Cyrille Pitchen <cyrille.pitchen@free-electrons.com>");
diff --git a/drivers/pci/controller/cadence/pcie-cadence.c b/drivers/pci/controller/cadence/pcie-cadence.c
index 204e045aed8c..70a19573440e 100644
--- a/drivers/pci/controller/cadence/pcie-cadence.c
+++ b/drivers/pci/controller/cadence/pcie-cadence.c
@@ -4,6 +4,7 @@
 // Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com>
 
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/of.h>
 
 #include "pcie-cadence.h"
@@ -23,6 +24,7 @@ void cdns_pcie_detect_quiet_min_delay_set(struct cdns_pcie *pcie)
 
 	cdns_pcie_writel(pcie, CDNS_PCIE_LTSSM_CONTROL_CAP, ltssm_control_cap);
 }
+EXPORT_SYMBOL_GPL(cdns_pcie_detect_quiet_min_delay_set);
 
 void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 busnr, u8 fn,
 				   u32 r, bool is_io,
@@ -100,6 +102,7 @@ void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 busnr, u8 fn,
 	cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(r), addr0);
 	cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(r), addr1);
 }
+EXPORT_SYMBOL_GPL(cdns_pcie_set_outbound_region);
 
 void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie,
 						  u8 busnr, u8 fn,
@@ -134,6 +137,7 @@ void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie,
 	cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(r), addr0);
 	cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(r), addr1);
 }
+EXPORT_SYMBOL_GPL(cdns_pcie_set_outbound_region_for_normal_msg);
 
 void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r)
 {
@@ -146,6 +150,7 @@ void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r)
 	cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(r), 0);
 	cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(r), 0);
 }
+EXPORT_SYMBOL_GPL(cdns_pcie_reset_outbound_region);
 
 void cdns_pcie_disable_phy(struct cdns_pcie *pcie)
 {
@@ -156,6 +161,7 @@ void cdns_pcie_disable_phy(struct cdns_pcie *pcie)
 		phy_exit(pcie->phy[i]);
 	}
 }
+EXPORT_SYMBOL_GPL(cdns_pcie_disable_phy);
 
 int cdns_pcie_enable_phy(struct cdns_pcie *pcie)
 {
@@ -184,6 +190,7 @@ err_phy:
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(cdns_pcie_enable_phy);
 
 int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie)
 {
@@ -243,6 +250,7 @@ err_phy:
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(cdns_pcie_init_phy);
 
 static int cdns_pcie_suspend_noirq(struct device *dev)
 {
@@ -271,3 +279,7 @@ const struct dev_pm_ops cdns_pcie_pm_ops = {
 	NOIRQ_SYSTEM_SLEEP_PM_OPS(cdns_pcie_suspend_noirq,
 				  cdns_pcie_resume_noirq)
 };
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Cadence PCIe controller driver");
+MODULE_AUTHOR("Cyrille Pitchen <cyrille.pitchen@free-electrons.com>");
diff --git a/drivers/pci/controller/cadence/pcie-cadence.h b/drivers/pci/controller/cadence/pcie-cadence.h
index 39ee9945c903..a149845d341a 100644
--- a/drivers/pci/controller/cadence/pcie-cadence.h
+++ b/drivers/pci/controller/cadence/pcie-cadence.h
@@ -250,17 +250,6 @@ struct cdns_pcie_rp_ib_bar {
 
 struct cdns_pcie;
 
-enum cdns_pcie_msg_code {
-	MSG_CODE_ASSERT_INTA	= 0x20,
-	MSG_CODE_ASSERT_INTB	= 0x21,
-	MSG_CODE_ASSERT_INTC	= 0x22,
-	MSG_CODE_ASSERT_INTD	= 0x23,
-	MSG_CODE_DEASSERT_INTA	= 0x24,
-	MSG_CODE_DEASSERT_INTB	= 0x25,
-	MSG_CODE_DEASSERT_INTC	= 0x26,
-	MSG_CODE_DEASSERT_INTD	= 0x27,
-};
-
 enum cdns_pcie_msg_routing {
 	/* Route to Root Complex */
 	MSG_ROUTING_TO_RC,
@@ -519,10 +508,11 @@ static inline bool cdns_pcie_link_up(struct cdns_pcie *pcie)
 	return true;
 }
 
-#ifdef CONFIG_PCIE_CADENCE_HOST
+#if IS_ENABLED(CONFIG_PCIE_CADENCE_HOST)
 int cdns_pcie_host_link_setup(struct cdns_pcie_rc *rc);
 int cdns_pcie_host_init(struct cdns_pcie_rc *rc);
 int cdns_pcie_host_setup(struct cdns_pcie_rc *rc);
+void cdns_pcie_host_disable(struct cdns_pcie_rc *rc);
 void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn,
 			       int where);
 #else
@@ -541,6 +531,10 @@ static inline int cdns_pcie_host_setup(struct cdns_pcie_rc *rc)
 	return 0;
 }
 
+static inline void cdns_pcie_host_disable(struct cdns_pcie_rc *rc)
+{
+}
+
 static inline void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn,
 					     int where)
 {
@@ -548,13 +542,18 @@ static inline void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int d
 }
 #endif
 
-#ifdef CONFIG_PCIE_CADENCE_EP
+#if IS_ENABLED(CONFIG_PCIE_CADENCE_EP)
 int cdns_pcie_ep_setup(struct cdns_pcie_ep *ep);
+void cdns_pcie_ep_disable(struct cdns_pcie_ep *ep);
 #else
 static inline int cdns_pcie_ep_setup(struct cdns_pcie_ep *ep)
 {
 	return 0;
 }
+
+static inline void cdns_pcie_ep_disable(struct cdns_pcie_ep *ep)
+{
+}
 #endif
 
 void cdns_pcie_detect_quiet_min_delay_set(struct cdns_pcie *pcie);
diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index 3219704aba0e..f97f5266d196 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -118,12 +118,12 @@ static u64 dra7xx_pcie_cpu_addr_fixup(struct dw_pcie *pci, u64 cpu_addr)
 	return cpu_addr & DRA7XX_CPU_TO_BUS_ADDR;
 }
 
-static int dra7xx_pcie_link_up(struct dw_pcie *pci)
+static bool dra7xx_pcie_link_up(struct dw_pcie *pci)
 {
 	struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci);
 	u32 reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_PHY_CS);
 
-	return !!(reg & LINK_UP);
+	return reg & LINK_UP;
 }
 
 static void dra7xx_pcie_stop_link(struct dw_pcie *pci)
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index ace736b025b1..1f0e98d07109 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -209,12 +209,12 @@ static struct pci_ops exynos_pci_ops = {
 	.write = exynos_pcie_wr_own_conf,
 };
 
-static int exynos_pcie_link_up(struct dw_pcie *pci)
+static bool exynos_pcie_link_up(struct dw_pcie *pci)
 {
 	struct exynos_pcie *ep = to_exynos_pcie(pci);
 	u32 val = exynos_pcie_readl(ep->elbi_base, PCIE_ELBI_RDLH_LINKUP);
 
-	return (val & PCIE_ELBI_XMLH_LINKUP);
+	return val & PCIE_ELBI_XMLH_LINKUP;
 }
 
 static int exynos_pcie_host_init(struct dw_pcie_rp *pp)
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 5f267dd261b5..5a38cfaf989b 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -45,9 +45,14 @@
 #define IMX95_PCIE_PHY_GEN_CTRL			0x0
 #define IMX95_PCIE_REF_USE_PAD			BIT(17)
 
+#define IMX95_PCIE_PHY_MPLLA_CTRL		0x10
+#define IMX95_PCIE_PHY_MPLL_STATE		BIT(30)
+
 #define IMX95_PCIE_SS_RW_REG_0			0xf0
 #define IMX95_PCIE_REF_CLKEN			BIT(23)
 #define IMX95_PCIE_PHY_CR_PARA_SEL		BIT(9)
+#define IMX95_PCIE_SS_RW_REG_1			0xf4
+#define IMX95_PCIE_SYS_AUX_PWR_DET		BIT(31)
 
 #define IMX95_PE0_GEN_CTRL_1			0x1050
 #define IMX95_PCIE_DEVICE_TYPE			GENMASK(3, 0)
@@ -71,6 +76,9 @@
 #define IMX95_SID_MASK				GENMASK(5, 0)
 #define IMX95_MAX_LUT				32
 
+#define IMX95_PCIE_RST_CTRL			0x3010
+#define IMX95_PCIE_COLD_RST			BIT(0)
+
 #define to_imx_pcie(x)	dev_get_drvdata((x)->dev)
 
 enum imx_pcie_variants {
@@ -91,7 +99,7 @@ enum imx_pcie_variants {
 };
 
 #define IMX_PCIE_FLAG_IMX_PHY			BIT(0)
-#define IMX_PCIE_FLAG_IMX_SPEED_CHANGE		BIT(1)
+#define IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND	BIT(1)
 #define IMX_PCIE_FLAG_SUPPORTS_SUSPEND		BIT(2)
 #define IMX_PCIE_FLAG_HAS_PHYDRV		BIT(3)
 #define IMX_PCIE_FLAG_HAS_APP_RESET		BIT(4)
@@ -105,6 +113,7 @@ enum imx_pcie_variants {
  */
 #define IMX_PCIE_FLAG_BROKEN_SUSPEND		BIT(9)
 #define IMX_PCIE_FLAG_HAS_LUT			BIT(10)
+#define IMX_PCIE_FLAG_8GT_ECN_ERR051586		BIT(11)
 
 #define imx_check_flag(pci, val)	(pci->drvdata->flags & val)
 
@@ -126,9 +135,15 @@ struct imx_pcie_drvdata {
 	int (*init_phy)(struct imx_pcie *pcie);
 	int (*enable_ref_clk)(struct imx_pcie *pcie, bool enable);
 	int (*core_reset)(struct imx_pcie *pcie, bool assert);
+	int (*wait_pll_lock)(struct imx_pcie *pcie);
 	const struct dw_pcie_host_ops *ops;
 };
 
+struct imx_lut_data {
+	u32 data1;
+	u32 data2;
+};
+
 struct imx_pcie {
 	struct dw_pcie		*pci;
 	struct gpio_desc	*reset_gpiod;
@@ -148,6 +163,8 @@ struct imx_pcie {
 	struct regulator	*vph;
 	void __iomem		*phy_base;
 
+	/* LUT data for pcie */
+	struct imx_lut_data	luts[IMX95_MAX_LUT];
 	/* power domain for pcie */
 	struct device		*pd_pcie;
 	/* power domain for pcie phy */
@@ -224,6 +241,19 @@ static unsigned int imx_pcie_grp_offset(const struct imx_pcie *imx_pcie)
 
 static int imx95_pcie_init_phy(struct imx_pcie *imx_pcie)
 {
+	/*
+	 * ERR051624: The Controller Without Vaux Cannot Exit L23 Ready
+	 * Through Beacon or PERST# De-assertion
+	 *
+	 * When the auxiliary power is not available, the controller
+	 * cannot exit from L23 Ready with beacon or PERST# de-assertion
+	 * when main power is not removed.
+	 *
+	 * Workaround: Set SS_RW_REG_1[SYS_AUX_PWR_DET] to 1.
+	 */
+	regmap_set_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_SS_RW_REG_1,
+			IMX95_PCIE_SYS_AUX_PWR_DET);
+
 	regmap_update_bits(imx_pcie->iomuxc_gpr,
 			IMX95_PCIE_SS_RW_REG_0,
 			IMX95_PCIE_PHY_CR_PARA_SEL,
@@ -460,6 +490,23 @@ static void imx7d_pcie_wait_for_phy_pll_lock(struct imx_pcie *imx_pcie)
 		dev_err(dev, "PCIe PLL lock timeout\n");
 }
 
+static int imx95_pcie_wait_for_phy_pll_lock(struct imx_pcie *imx_pcie)
+{
+	u32 val;
+	struct device *dev = imx_pcie->pci->dev;
+
+	if (regmap_read_poll_timeout(imx_pcie->iomuxc_gpr,
+				     IMX95_PCIE_PHY_MPLLA_CTRL, val,
+				     val & IMX95_PCIE_PHY_MPLL_STATE,
+				     PHY_PLL_LOCK_WAIT_USLEEP_MAX,
+				     PHY_PLL_LOCK_WAIT_TIMEOUT)) {
+		dev_err(dev, "PCIe PLL lock timeout\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
 static int imx_setup_phy_mpll(struct imx_pcie *imx_pcie)
 {
 	unsigned long phy_rate = 0;
@@ -773,6 +820,43 @@ static int imx7d_pcie_core_reset(struct imx_pcie *imx_pcie, bool assert)
 	return 0;
 }
 
+static int imx95_pcie_core_reset(struct imx_pcie *imx_pcie, bool assert)
+{
+	u32 val;
+
+	if (assert) {
+		/*
+		 * From i.MX95 PCIe PHY perspective, the COLD reset toggle
+		 * should be complete after power-up by the following sequence.
+		 *                 > 10us(at power-up)
+		 *                 > 10ns(warm reset)
+		 *               |<------------>|
+		 *                ______________
+		 * phy_reset ____/              \________________
+		 *                                   ____________
+		 * ref_clk_en_______________________/
+		 * Toggle COLD reset aligned with this sequence for i.MX95 PCIe.
+		 */
+		regmap_set_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_RST_CTRL,
+				IMX95_PCIE_COLD_RST);
+		/*
+		 * Make sure the write to IMX95_PCIE_RST_CTRL is flushed to the
+		 * hardware by doing a read. Otherwise, there is no guarantee
+		 * that the write has reached the hardware before udelay().
+		 */
+		regmap_read_bypassed(imx_pcie->iomuxc_gpr, IMX95_PCIE_RST_CTRL,
+				     &val);
+		udelay(15);
+		regmap_clear_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_RST_CTRL,
+				  IMX95_PCIE_COLD_RST);
+		regmap_read_bypassed(imx_pcie->iomuxc_gpr, IMX95_PCIE_RST_CTRL,
+				     &val);
+		udelay(10);
+	}
+
+	return 0;
+}
+
 static void imx_pcie_assert_core_reset(struct imx_pcie *imx_pcie)
 {
 	reset_control_assert(imx_pcie->pciephy_reset);
@@ -860,6 +944,12 @@ static int imx_pcie_start_link(struct dw_pcie *pci)
 	u32 tmp;
 	int ret;
 
+	if (!(imx_pcie->drvdata->flags &
+	    IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND)) {
+		imx_pcie_ltssm_enable(dev);
+		return 0;
+	}
+
 	/*
 	 * Force Gen1 operation when starting the link.  In case the link is
 	 * started in Gen2 mode, there is a possibility the devices on the
@@ -875,11 +965,11 @@ static int imx_pcie_start_link(struct dw_pcie *pci)
 	/* Start LTSSM. */
 	imx_pcie_ltssm_enable(dev);
 
-	ret = dw_pcie_wait_for_link(pci);
-	if (ret)
-		goto err_reset_phy;
-
 	if (pci->max_link_speed > 1) {
+		ret = dw_pcie_wait_for_link(pci);
+		if (ret)
+			goto err_reset_phy;
+
 		/* Allow faster modes after the link is up */
 		dw_pcie_dbi_ro_wr_en(pci);
 		tmp = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP);
@@ -896,34 +986,15 @@ static int imx_pcie_start_link(struct dw_pcie *pci)
 		dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, tmp);
 		dw_pcie_dbi_ro_wr_dis(pci);
 
-		if (imx_pcie->drvdata->flags &
-		    IMX_PCIE_FLAG_IMX_SPEED_CHANGE) {
-
-			/*
-			 * On i.MX7, DIRECT_SPEED_CHANGE behaves differently
-			 * from i.MX6 family when no link speed transition
-			 * occurs and we go Gen1 -> yep, Gen1. The difference
-			 * is that, in such case, it will not be cleared by HW
-			 * which will cause the following code to report false
-			 * failure.
-			 */
-			ret = imx_pcie_wait_for_speed_change(imx_pcie);
-			if (ret) {
-				dev_err(dev, "Failed to bring link up!\n");
-				goto err_reset_phy;
-			}
-		}
-
-		/* Make sure link training is finished as well! */
-		ret = dw_pcie_wait_for_link(pci);
-		if (ret)
+		ret = imx_pcie_wait_for_speed_change(imx_pcie);
+		if (ret) {
+			dev_err(dev, "Failed to bring link up!\n");
 			goto err_reset_phy;
+		}
 	} else {
 		dev_info(dev, "Link: Only Gen1 is enabled\n");
 	}
 
-	tmp = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA);
-	dev_info(dev, "Link up, Gen%i\n", tmp & PCI_EXP_LNKSTA_CLS);
 	return 0;
 
 err_reset_phy:
@@ -1182,6 +1253,12 @@ static int imx_pcie_host_init(struct dw_pcie_rp *pp)
 		goto err_phy_off;
 	}
 
+	if (imx_pcie->drvdata->wait_pll_lock) {
+		ret = imx_pcie->drvdata->wait_pll_lock(imx_pcie);
+		if (ret < 0)
+			goto err_phy_off;
+	}
+
 	imx_setup_phy_mpll(imx_pcie);
 
 	return 0;
@@ -1214,6 +1291,32 @@ static void imx_pcie_host_exit(struct dw_pcie_rp *pp)
 		regulator_disable(imx_pcie->vpcie);
 }
 
+static void imx_pcie_host_post_init(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct imx_pcie *imx_pcie = to_imx_pcie(pci);
+	u32 val;
+
+	if (imx_pcie->drvdata->flags & IMX_PCIE_FLAG_8GT_ECN_ERR051586) {
+		/*
+		 * ERR051586: Compliance with 8GT/s Receiver Impedance ECN
+		 *
+		 * The default value of GEN3_RELATED_OFF[GEN3_ZRXDC_NONCOMPL]
+		 * is 1 which makes receiver non-compliant with the ZRX-DC
+		 * parameter for 2.5 GT/s when operating at 8 GT/s or higher.
+		 * It causes unnecessary timeout in L1.
+		 *
+		 * Workaround: Program GEN3_RELATED_OFF[GEN3_ZRXDC_NONCOMPL]
+		 * to 0.
+		 */
+		dw_pcie_dbi_ro_wr_en(pci);
+		val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF);
+		val &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL;
+		dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val);
+		dw_pcie_dbi_ro_wr_dis(pci);
+	}
+}
+
 /*
  * In old DWC implementations, PCIE_ATU_INHIBIT_PAYLOAD in iATU Ctrl2
  * register is reserved, so the generic DWC implementation of sending the
@@ -1239,6 +1342,7 @@ static const struct dw_pcie_host_ops imx_pcie_host_ops = {
 static const struct dw_pcie_host_ops imx_pcie_host_dw_pme_ops = {
 	.init = imx_pcie_host_init,
 	.deinit = imx_pcie_host_exit,
+	.post_init = imx_pcie_host_post_init,
 };
 
 static const struct dw_pcie_ops dw_pcie_ops = {
@@ -1350,6 +1454,7 @@ static int imx_add_pcie_ep(struct imx_pcie *imx_pcie,
 		dev_err(dev, "failed to initialize endpoint\n");
 		return ret;
 	}
+	imx_pcie_host_post_init(pp);
 
 	ret = dw_pcie_ep_init_registers(ep);
 	if (ret) {
@@ -1386,6 +1491,42 @@ static void imx_pcie_msi_save_restore(struct imx_pcie *imx_pcie, bool save)
 	}
 }
 
+static void imx_pcie_lut_save(struct imx_pcie *imx_pcie)
+{
+	u32 data1, data2;
+	int i;
+
+	for (i = 0; i < IMX95_MAX_LUT; i++) {
+		regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_ACSCTRL,
+			     IMX95_PEO_LUT_RWA | i);
+		regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1, &data1);
+		regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, &data2);
+		if (data1 & IMX95_PE0_LUT_VLD) {
+			imx_pcie->luts[i].data1 = data1;
+			imx_pcie->luts[i].data2 = data2;
+		} else {
+			imx_pcie->luts[i].data1 = 0;
+			imx_pcie->luts[i].data2 = 0;
+		}
+	}
+}
+
+static void imx_pcie_lut_restore(struct imx_pcie *imx_pcie)
+{
+	int i;
+
+	for (i = 0; i < IMX95_MAX_LUT; i++) {
+		if ((imx_pcie->luts[i].data1 & IMX95_PE0_LUT_VLD) == 0)
+			continue;
+
+		regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1,
+			     imx_pcie->luts[i].data1);
+		regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2,
+			     imx_pcie->luts[i].data2);
+		regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_ACSCTRL, i);
+	}
+}
+
 static int imx_pcie_suspend_noirq(struct device *dev)
 {
 	struct imx_pcie *imx_pcie = dev_get_drvdata(dev);
@@ -1394,6 +1535,8 @@ static int imx_pcie_suspend_noirq(struct device *dev)
 		return 0;
 
 	imx_pcie_msi_save_restore(imx_pcie, true);
+	if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_LUT))
+		imx_pcie_lut_save(imx_pcie);
 	if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_BROKEN_SUSPEND)) {
 		/*
 		 * The minimum for a workaround would be to set PERST# and to
@@ -1438,6 +1581,8 @@ static int imx_pcie_resume_noirq(struct device *dev)
 		if (ret)
 			return ret;
 	}
+	if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_LUT))
+		imx_pcie_lut_restore(imx_pcie);
 	imx_pcie_msi_save_restore(imx_pcie, false);
 
 	return 0;
@@ -1649,7 +1794,7 @@ static const struct imx_pcie_drvdata drvdata[] = {
 	[IMX6Q] = {
 		.variant = IMX6Q,
 		.flags = IMX_PCIE_FLAG_IMX_PHY |
-			 IMX_PCIE_FLAG_IMX_SPEED_CHANGE |
+			 IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND |
 			 IMX_PCIE_FLAG_BROKEN_SUSPEND |
 			 IMX_PCIE_FLAG_SUPPORTS_SUSPEND,
 		.dbi_length = 0x200,
@@ -1665,7 +1810,7 @@ static const struct imx_pcie_drvdata drvdata[] = {
 	[IMX6SX] = {
 		.variant = IMX6SX,
 		.flags = IMX_PCIE_FLAG_IMX_PHY |
-			 IMX_PCIE_FLAG_IMX_SPEED_CHANGE |
+			 IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND |
 			 IMX_PCIE_FLAG_SUPPORTS_SUSPEND,
 		.gpr = "fsl,imx6q-iomuxc-gpr",
 		.ltssm_off = IOMUXC_GPR12,
@@ -1680,7 +1825,7 @@ static const struct imx_pcie_drvdata drvdata[] = {
 	[IMX6QP] = {
 		.variant = IMX6QP,
 		.flags = IMX_PCIE_FLAG_IMX_PHY |
-			 IMX_PCIE_FLAG_IMX_SPEED_CHANGE |
+			 IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND |
 			 IMX_PCIE_FLAG_SUPPORTS_SUSPEND,
 		.dbi_length = 0x200,
 		.gpr = "fsl,imx6q-iomuxc-gpr",
@@ -1747,12 +1892,15 @@ static const struct imx_pcie_drvdata drvdata[] = {
 		.variant = IMX95,
 		.flags = IMX_PCIE_FLAG_HAS_SERDES |
 			 IMX_PCIE_FLAG_HAS_LUT |
+			 IMX_PCIE_FLAG_8GT_ECN_ERR051586 |
 			 IMX_PCIE_FLAG_SUPPORTS_SUSPEND,
 		.ltssm_off = IMX95_PE0_GEN_CTRL_3,
 		.ltssm_mask = IMX95_PCIE_LTSSM_EN,
 		.mode_off[0]  = IMX95_PE0_GEN_CTRL_1,
 		.mode_mask[0] = IMX95_PCIE_DEVICE_TYPE,
+		.core_reset = imx95_pcie_core_reset,
 		.init_phy = imx95_pcie_init_phy,
+		.wait_pll_lock = imx95_pcie_wait_for_phy_pll_lock,
 	},
 	[IMX8MQ_EP] = {
 		.variant = IMX8MQ_EP,
@@ -1799,12 +1947,15 @@ static const struct imx_pcie_drvdata drvdata[] = {
 	[IMX95_EP] = {
 		.variant = IMX95_EP,
 		.flags = IMX_PCIE_FLAG_HAS_SERDES |
+			 IMX_PCIE_FLAG_8GT_ECN_ERR051586 |
 			 IMX_PCIE_FLAG_SUPPORT_64BIT,
 		.ltssm_off = IMX95_PE0_GEN_CTRL_3,
 		.ltssm_mask = IMX95_PCIE_LTSSM_EN,
 		.mode_off[0]  = IMX95_PE0_GEN_CTRL_1,
 		.mode_mask[0] = IMX95_PCIE_DEVICE_TYPE,
 		.init_phy = imx95_pcie_init_phy,
+		.core_reset = imx95_pcie_core_reset,
+		.wait_pll_lock = imx95_pcie_wait_for_phy_pll_lock,
 		.epc_features = &imx95_pcie_epc_features,
 		.mode = DW_PCIE_EP_TYPE,
 	},
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 1385d9db7b32..2b2632e513b5 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -492,13 +492,12 @@ static struct pci_ops ks_pcie_ops = {
  * @pci: A pointer to the dw_pcie structure which holds the DesignWare PCIe host
  *	 controller driver information.
  */
-static int ks_pcie_link_up(struct dw_pcie *pci)
+static bool ks_pcie_link_up(struct dw_pcie *pci)
 {
 	u32 val;
 
 	val = dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG0);
-	val &= PORT_LOGIC_LTSSM_STATE_MASK;
-	return (val == PORT_LOGIC_LTSSM_STATE_L0);
+	return (val & PORT_LOGIC_LTSSM_STATE_MASK) == PORT_LOGIC_LTSSM_STATE_L0;
 }
 
 static void ks_pcie_stop_link(struct dw_pcie *pci)
diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c
index db9482a113e9..787469d1b396 100644
--- a/drivers/pci/controller/dwc/pci-meson.c
+++ b/drivers/pci/controller/dwc/pci-meson.c
@@ -335,7 +335,7 @@ static struct pci_ops meson_pci_ops = {
 	.write = pci_generic_config_write,
 };
 
-static int meson_pcie_link_up(struct dw_pcie *pci)
+static bool meson_pcie_link_up(struct dw_pcie *pci)
 {
 	struct meson_pcie *mp = to_meson_pcie(pci);
 	struct device *dev = pci->dev;
@@ -363,7 +363,7 @@ static int meson_pcie_link_up(struct dw_pcie *pci)
 			dev_dbg(dev, "speed_okay\n");
 
 		if (smlh_up && rdlh_up && ltssm_up && speed_okay)
-			return 1;
+			return true;
 
 		cnt++;
 
@@ -371,7 +371,7 @@ static int meson_pcie_link_up(struct dw_pcie *pci)
 	} while (cnt < WAIT_LINKUP_TIMEOUT);
 
 	dev_err(dev, "error: wait linkup timeout\n");
-	return 0;
+	return false;
 }
 
 static int meson_pcie_host_init(struct dw_pcie_rp *pp)
diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c
index b5c599ccaacf..c2650fd0d458 100644
--- a/drivers/pci/controller/dwc/pcie-armada8k.c
+++ b/drivers/pci/controller/dwc/pcie-armada8k.c
@@ -139,7 +139,7 @@ static int armada8k_pcie_setup_phys(struct armada8k_pcie *pcie)
 	return ret;
 }
 
-static int armada8k_pcie_link_up(struct dw_pcie *pci)
+static bool armada8k_pcie_link_up(struct dw_pcie *pci)
 {
 	u32 reg;
 	u32 mask = PCIE_GLB_STS_RDLH_LINK_UP | PCIE_GLB_STS_PHY_LINK_UP;
@@ -147,10 +147,10 @@ static int armada8k_pcie_link_up(struct dw_pcie *pci)
 	reg = dw_pcie_readl_dbi(pci, PCIE_GLOBAL_STATUS_REG);
 
 	if ((reg & mask) == mask)
-		return 1;
+		return true;
 
 	dev_dbg(pci->dev, "No link detected (Global-Status: 0x%08x).\n", reg);
-	return 0;
+	return false;
 }
 
 static int armada8k_pcie_start_link(struct dw_pcie *pci)
diff --git a/drivers/pci/controller/dwc/pcie-designware-debugfs.c b/drivers/pci/controller/dwc/pcie-designware-debugfs.c
index 9e6f4d00f262..c67601096c48 100644
--- a/drivers/pci/controller/dwc/pcie-designware-debugfs.c
+++ b/drivers/pci/controller/dwc/pcie-designware-debugfs.c
@@ -642,16 +642,262 @@ static void dwc_pcie_ltssm_debugfs_init(struct dw_pcie *pci, struct dentry *dir)
 			    &dwc_pcie_ltssm_status_ops);
 }
 
+static int dw_pcie_ptm_check_capability(void *drvdata)
+{
+	struct dw_pcie *pci = drvdata;
+
+	pci->ptm_vsec_offset = dw_pcie_find_ptm_capability(pci);
+
+	return pci->ptm_vsec_offset;
+}
+
+static int dw_pcie_ptm_context_update_write(void *drvdata, u8 mode)
+{
+	struct dw_pcie *pci = drvdata;
+	u32 val;
+
+	if (mode == PCIE_PTM_CONTEXT_UPDATE_AUTO) {
+		val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL);
+		val |= PTM_REQ_AUTO_UPDATE_ENABLED;
+		dw_pcie_writel_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL, val);
+	} else if (mode == PCIE_PTM_CONTEXT_UPDATE_MANUAL) {
+		val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL);
+		val &= ~PTM_REQ_AUTO_UPDATE_ENABLED;
+		val |= PTM_REQ_START_UPDATE;
+		dw_pcie_writel_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL, val);
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int dw_pcie_ptm_context_update_read(void *drvdata, u8 *mode)
+{
+	struct dw_pcie *pci = drvdata;
+	u32 val;
+
+	val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL);
+	if (FIELD_GET(PTM_REQ_AUTO_UPDATE_ENABLED, val))
+		*mode = PCIE_PTM_CONTEXT_UPDATE_AUTO;
+	else
+		/*
+		 * PTM_REQ_START_UPDATE is a self clearing register bit. So if
+		 * PTM_REQ_AUTO_UPDATE_ENABLED is not set, then it implies that
+		 * manual update is used.
+		 */
+		*mode = PCIE_PTM_CONTEXT_UPDATE_MANUAL;
+
+	return 0;
+}
+
+static int dw_pcie_ptm_context_valid_write(void *drvdata, bool valid)
+{
+	struct dw_pcie *pci = drvdata;
+	u32 val;
+
+	if (valid) {
+		val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL);
+		val |= PTM_RES_CCONTEXT_VALID;
+		dw_pcie_writel_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL, val);
+	} else {
+		val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL);
+		val &= ~PTM_RES_CCONTEXT_VALID;
+		dw_pcie_writel_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL, val);
+	}
+
+	return 0;
+}
+
+static int dw_pcie_ptm_context_valid_read(void *drvdata, bool *valid)
+{
+	struct dw_pcie *pci = drvdata;
+	u32 val;
+
+	val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL);
+	*valid = !!FIELD_GET(PTM_RES_CCONTEXT_VALID, val);
+
+	return 0;
+}
+
+static int dw_pcie_ptm_local_clock_read(void *drvdata, u64 *clock)
+{
+	struct dw_pcie *pci = drvdata;
+	u32 msb, lsb;
+
+	do {
+		msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_LOCAL_MSB);
+		lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_LOCAL_LSB);
+	} while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_LOCAL_MSB));
+
+	*clock = ((u64) msb) << 32 | lsb;
+
+	return 0;
+}
+
+static int dw_pcie_ptm_master_clock_read(void *drvdata, u64 *clock)
+{
+	struct dw_pcie *pci = drvdata;
+	u32 msb, lsb;
+
+	do {
+		msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_MASTER_MSB);
+		lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_MASTER_LSB);
+	} while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_MASTER_MSB));
+
+	*clock = ((u64) msb) << 32 | lsb;
+
+	return 0;
+}
+
+static int dw_pcie_ptm_t1_read(void *drvdata, u64 *clock)
+{
+	struct dw_pcie *pci = drvdata;
+	u32 msb, lsb;
+
+	do {
+		msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_MSB);
+		lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_LSB);
+	} while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_MSB));
+
+	*clock = ((u64) msb) << 32 | lsb;
+
+	return 0;
+}
+
+static int dw_pcie_ptm_t2_read(void *drvdata, u64 *clock)
+{
+	struct dw_pcie *pci = drvdata;
+	u32 msb, lsb;
+
+	do {
+		msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_MSB);
+		lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_LSB);
+	} while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_MSB));
+
+	*clock = ((u64) msb) << 32 | lsb;
+
+	return 0;
+}
+
+static int dw_pcie_ptm_t3_read(void *drvdata, u64 *clock)
+{
+	struct dw_pcie *pci = drvdata;
+	u32 msb, lsb;
+
+	do {
+		msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_MSB);
+		lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_LSB);
+	} while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_MSB));
+
+	*clock = ((u64) msb) << 32 | lsb;
+
+	return 0;
+}
+
+static int dw_pcie_ptm_t4_read(void *drvdata, u64 *clock)
+{
+	struct dw_pcie *pci = drvdata;
+	u32 msb, lsb;
+
+	do {
+		msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_MSB);
+		lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_LSB);
+	} while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_MSB));
+
+	*clock = ((u64) msb) << 32 | lsb;
+
+	return 0;
+}
+
+static bool dw_pcie_ptm_context_update_visible(void *drvdata)
+{
+	struct dw_pcie *pci = drvdata;
+
+	return (pci->mode == DW_PCIE_EP_TYPE) ? true : false;
+}
+
+static bool dw_pcie_ptm_context_valid_visible(void *drvdata)
+{
+	struct dw_pcie *pci = drvdata;
+
+	return (pci->mode == DW_PCIE_RC_TYPE) ? true : false;
+}
+
+static bool dw_pcie_ptm_local_clock_visible(void *drvdata)
+{
+	/* PTM local clock is always visible */
+	return true;
+}
+
+static bool dw_pcie_ptm_master_clock_visible(void *drvdata)
+{
+	struct dw_pcie *pci = drvdata;
+
+	return (pci->mode == DW_PCIE_EP_TYPE) ? true : false;
+}
+
+static bool dw_pcie_ptm_t1_visible(void *drvdata)
+{
+	struct dw_pcie *pci = drvdata;
+
+	return (pci->mode == DW_PCIE_EP_TYPE) ? true : false;
+}
+
+static bool dw_pcie_ptm_t2_visible(void *drvdata)
+{
+	struct dw_pcie *pci = drvdata;
+
+	return (pci->mode == DW_PCIE_RC_TYPE) ? true : false;
+}
+
+static bool dw_pcie_ptm_t3_visible(void *drvdata)
+{
+	struct dw_pcie *pci = drvdata;
+
+	return (pci->mode == DW_PCIE_RC_TYPE) ? true : false;
+}
+
+static bool dw_pcie_ptm_t4_visible(void *drvdata)
+{
+	struct dw_pcie *pci = drvdata;
+
+	return (pci->mode == DW_PCIE_EP_TYPE) ? true : false;
+}
+
+const struct pcie_ptm_ops dw_pcie_ptm_ops = {
+	.check_capability = dw_pcie_ptm_check_capability,
+	.context_update_write = dw_pcie_ptm_context_update_write,
+	.context_update_read = dw_pcie_ptm_context_update_read,
+	.context_valid_write = dw_pcie_ptm_context_valid_write,
+	.context_valid_read = dw_pcie_ptm_context_valid_read,
+	.local_clock_read = dw_pcie_ptm_local_clock_read,
+	.master_clock_read = dw_pcie_ptm_master_clock_read,
+	.t1_read = dw_pcie_ptm_t1_read,
+	.t2_read = dw_pcie_ptm_t2_read,
+	.t3_read = dw_pcie_ptm_t3_read,
+	.t4_read = dw_pcie_ptm_t4_read,
+	.context_update_visible = dw_pcie_ptm_context_update_visible,
+	.context_valid_visible = dw_pcie_ptm_context_valid_visible,
+	.local_clock_visible = dw_pcie_ptm_local_clock_visible,
+	.master_clock_visible = dw_pcie_ptm_master_clock_visible,
+	.t1_visible = dw_pcie_ptm_t1_visible,
+	.t2_visible = dw_pcie_ptm_t2_visible,
+	.t3_visible = dw_pcie_ptm_t3_visible,
+	.t4_visible = dw_pcie_ptm_t4_visible,
+};
+
 void dwc_pcie_debugfs_deinit(struct dw_pcie *pci)
 {
 	if (!pci->debugfs)
 		return;
 
+	pcie_ptm_destroy_debugfs(pci->ptm_debugfs);
 	dwc_pcie_rasdes_debugfs_deinit(pci);
 	debugfs_remove_recursive(pci->debugfs->debug_dir);
 }
 
-void dwc_pcie_debugfs_init(struct dw_pcie *pci)
+void dwc_pcie_debugfs_init(struct dw_pcie *pci, enum dw_pcie_device_mode mode)
 {
 	char dirname[DWC_DEBUGFS_BUF_MAX];
 	struct device *dev = pci->dev;
@@ -674,4 +920,8 @@ void dwc_pcie_debugfs_init(struct dw_pcie *pci)
 			err);
 
 	dwc_pcie_ltssm_debugfs_init(pci, dir);
+
+	pci->mode = mode;
+	pci->ptm_debugfs = pcie_ptm_create_debugfs(pci->dev, pci,
+						   &dw_pcie_ptm_ops);
 }
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 1a0bf9341542..0ae54a94809b 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -256,11 +256,11 @@ static unsigned int dw_pcie_ep_get_rebar_offset(struct dw_pcie *pci,
 		return offset;
 
 	reg = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL);
-	nbars = (reg & PCI_REBAR_CTRL_NBAR_MASK) >> PCI_REBAR_CTRL_NBAR_SHIFT;
+	nbars = FIELD_GET(PCI_REBAR_CTRL_NBAR_MASK, reg);
 
 	for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL) {
 		reg = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL);
-		bar_index = reg & PCI_REBAR_CTRL_BAR_IDX;
+		bar_index = FIELD_GET(PCI_REBAR_CTRL_BAR_IDX, reg);
 		if (bar_index == bar)
 			return offset;
 	}
@@ -532,15 +532,16 @@ static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 
 	val = FIELD_GET(PCI_MSI_FLAGS_QSIZE, val);
 
-	return val;
+	return 1 << val;
 }
 
 static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-			      u8 interrupts)
+			      u8 nr_irqs)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct dw_pcie_ep_func *ep_func;
+	u8 mmc = order_base_2(nr_irqs);
 	u32 val, reg;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
@@ -550,7 +551,7 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	reg = ep_func->msi_cap + PCI_MSI_FLAGS;
 	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	val &= ~PCI_MSI_FLAGS_QMASK;
-	val |= FIELD_PREP(PCI_MSI_FLAGS_QMASK, interrupts);
+	val |= FIELD_PREP(PCI_MSI_FLAGS_QMASK, mmc);
 	dw_pcie_dbi_ro_wr_en(pci);
 	dw_pcie_ep_writew_dbi(ep, func_no, reg, val);
 	dw_pcie_dbi_ro_wr_dis(pci);
@@ -575,11 +576,11 @@ static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 
 	val &= PCI_MSIX_FLAGS_QSIZE;
 
-	return val;
+	return val + 1;
 }
 
 static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-			       u16 interrupts, enum pci_barno bir, u32 offset)
+			       u16 nr_irqs, enum pci_barno bir, u32 offset)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
@@ -595,7 +596,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	reg = ep_func->msix_cap + PCI_MSIX_FLAGS;
 	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	val &= ~PCI_MSIX_FLAGS_QSIZE;
-	val |= interrupts;
+	val |= nr_irqs - 1; /* encoded as N-1 */
 	dw_pcie_writew_dbi(pci, reg, val);
 
 	reg = ep_func->msix_cap + PCI_MSIX_TABLE;
@@ -603,7 +604,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	dw_pcie_ep_writel_dbi(ep, func_no, reg, val);
 
 	reg = ep_func->msix_cap + PCI_MSIX_PBA;
-	val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir;
+	val = (offset + (nr_irqs * PCI_MSIX_ENTRY_SIZE)) | bir;
 	dw_pcie_ep_writel_dbi(ep, func_no, reg, val);
 
 	dw_pcie_dbi_ro_wr_dis(pci);
@@ -671,7 +672,7 @@ static const struct pci_epc_ops epc_ops = {
  * @ep: DWC EP device
  * @func_no: Function number of the endpoint
  *
- * Return: 0 if success, errono otherwise.
+ * Return: 0 if success, errno otherwise.
  */
 int dw_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep, u8 func_no)
 {
@@ -690,7 +691,7 @@ EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_intx_irq);
  * @func_no: Function number of the endpoint
  * @interrupt_num: Interrupt number to be raised
  *
- * Return: 0 if success, errono otherwise.
+ * Return: 0 if success, errno otherwise.
  */
 int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 			     u8 interrupt_num)
@@ -875,8 +876,7 @@ static void dw_pcie_ep_init_non_sticky_registers(struct dw_pcie *pci)
 
 	if (offset) {
 		reg = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL);
-		nbars = (reg & PCI_REBAR_CTRL_NBAR_MASK) >>
-			PCI_REBAR_CTRL_NBAR_SHIFT;
+		nbars = FIELD_GET(PCI_REBAR_CTRL_NBAR_MASK, reg);
 
 		/*
 		 * PCIe r6.0, sec 7.8.6.2 require us to support at least one
@@ -897,7 +897,7 @@ static void dw_pcie_ep_init_non_sticky_registers(struct dw_pcie *pci)
 			 * is why RESBAR_CAP_REG is written here.
 			 */
 			val = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL);
-			bar = val & PCI_REBAR_CTRL_BAR_IDX;
+			bar = FIELD_GET(PCI_REBAR_CTRL_BAR_IDX, val);
 			if (ep->epf_bar[bar])
 				pci_epc_bar_size_to_rebar_cap(ep->epf_bar[bar]->size, &val);
 			else
@@ -1013,7 +1013,7 @@ int dw_pcie_ep_init_registers(struct dw_pcie_ep *ep)
 
 	dw_pcie_ep_init_non_sticky_registers(pci);
 
-	dwc_pcie_debugfs_init(pci);
+	dwc_pcie_debugfs_init(pci, DW_PCIE_EP_TYPE);
 
 	return 0;
 
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index d1cd48efad43..906277f9ffaf 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -523,6 +523,13 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 
 	dw_pcie_iatu_detect(pci);
 
+	if (pci->num_lanes < 1)
+		pci->num_lanes = dw_pcie_link_get_max_link_width(pci);
+
+	ret = of_pci_get_equalization_presets(dev, &pp->presets, pci->num_lanes);
+	if (ret)
+		goto err_free_msi;
+
 	/*
 	 * Allocate the resource for MSG TLP before programming the iATU
 	 * outbound window in dw_pcie_setup_rc(). Since the allocation depends
@@ -567,7 +574,7 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp)
 	if (pp->ops->post_init)
 		pp->ops->post_init(pp);
 
-	dwc_pcie_debugfs_init(pci);
+	dwc_pcie_debugfs_init(pci, DW_PCIE_RC_TYPE);
 
 	return 0;
 
@@ -828,6 +835,77 @@ static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp)
 	return 0;
 }
 
+static void dw_pcie_program_presets(struct dw_pcie_rp *pp, enum pci_bus_speed speed)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	u8 lane_eq_offset, lane_reg_size, cap_id;
+	u8 *presets;
+	u32 cap;
+	int i;
+
+	if (speed == PCIE_SPEED_8_0GT) {
+		presets = (u8 *)pp->presets.eq_presets_8gts;
+		lane_eq_offset =  PCI_SECPCI_LE_CTRL;
+		cap_id = PCI_EXT_CAP_ID_SECPCI;
+		/* For data rate of 8 GT/S each lane equalization control is 16bits wide*/
+		lane_reg_size = 0x2;
+	} else if (speed == PCIE_SPEED_16_0GT) {
+		presets = pp->presets.eq_presets_Ngts[EQ_PRESET_TYPE_16GTS - 1];
+		lane_eq_offset = PCI_PL_16GT_LE_CTRL;
+		cap_id = PCI_EXT_CAP_ID_PL_16GT;
+		lane_reg_size = 0x1;
+	} else if (speed == PCIE_SPEED_32_0GT) {
+		presets =  pp->presets.eq_presets_Ngts[EQ_PRESET_TYPE_32GTS - 1];
+		lane_eq_offset = PCI_PL_32GT_LE_CTRL;
+		cap_id = PCI_EXT_CAP_ID_PL_32GT;
+		lane_reg_size = 0x1;
+	} else if (speed == PCIE_SPEED_64_0GT) {
+		presets =  pp->presets.eq_presets_Ngts[EQ_PRESET_TYPE_64GTS - 1];
+		lane_eq_offset = PCI_PL_64GT_LE_CTRL;
+		cap_id = PCI_EXT_CAP_ID_PL_64GT;
+		lane_reg_size = 0x1;
+	} else {
+		return;
+	}
+
+	if (presets[0] == PCI_EQ_RESV)
+		return;
+
+	cap = dw_pcie_find_ext_capability(pci, cap_id);
+	if (!cap)
+		return;
+
+	/*
+	 * Write preset values to the registers byte-by-byte for the given
+	 * number of lanes and register size.
+	 */
+	for (i = 0; i < pci->num_lanes * lane_reg_size; i++)
+		dw_pcie_writeb_dbi(pci, cap + lane_eq_offset + i, presets[i]);
+}
+
+static void dw_pcie_config_presets(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	enum pci_bus_speed speed = pcie_link_speed[pci->max_link_speed];
+
+	/*
+	 * Lane equalization settings need to be applied for all data rates the
+	 * controller supports and for all supported lanes.
+	 */
+
+	if (speed >= PCIE_SPEED_8_0GT)
+		dw_pcie_program_presets(pp, PCIE_SPEED_8_0GT);
+
+	if (speed >= PCIE_SPEED_16_0GT)
+		dw_pcie_program_presets(pp, PCIE_SPEED_16_0GT);
+
+	if (speed >= PCIE_SPEED_32_0GT)
+		dw_pcie_program_presets(pp, PCIE_SPEED_32_0GT);
+
+	if (speed >= PCIE_SPEED_64_0GT)
+		dw_pcie_program_presets(pp, PCIE_SPEED_64_0GT);
+}
+
 int dw_pcie_setup_rc(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
@@ -881,6 +959,7 @@ int dw_pcie_setup_rc(struct dw_pcie_rp *pp)
 		PCI_COMMAND_MASTER | PCI_COMMAND_SERR;
 	dw_pcie_writel_dbi(pci, PCI_COMMAND, val);
 
+	dw_pcie_config_presets(pp);
 	/*
 	 * If the platform provides its own child bus config accesses, it means
 	 * the platform uses its own address translation component rather than
diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index 97d76d3dc066..4d794964fa0f 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -54,6 +54,14 @@ static const char * const dw_pcie_core_rsts[DW_PCIE_NUM_CORE_RSTS] = {
 	[DW_PCIE_PWR_RST] = "pwr",
 };
 
+static const struct dwc_pcie_vsec_id dwc_pcie_ptm_vsec_ids[] = {
+	{ .vendor_id = PCI_VENDOR_ID_QCOM, /* EP */
+	  .vsec_id = 0x03, .vsec_rev = 0x1 },
+	{ .vendor_id = PCI_VENDOR_ID_QCOM, /* RC */
+	  .vsec_id = 0x04, .vsec_rev = 0x1 },
+	{ }
+};
+
 static int dw_pcie_get_clocks(struct dw_pcie *pci)
 {
 	int i, ret;
@@ -330,6 +338,12 @@ u16 dw_pcie_find_rasdes_capability(struct dw_pcie *pci)
 }
 EXPORT_SYMBOL_GPL(dw_pcie_find_rasdes_capability);
 
+u16 dw_pcie_find_ptm_capability(struct dw_pcie *pci)
+{
+	return dw_pcie_find_vsec_capability(pci, dwc_pcie_ptm_vsec_ids);
+}
+EXPORT_SYMBOL_GPL(dw_pcie_find_ptm_capability);
+
 int dw_pcie_read(void __iomem *addr, int size, u32 *val)
 {
 	if (!IS_ALIGNED((uintptr_t)addr, size)) {
@@ -711,7 +725,7 @@ int dw_pcie_wait_for_link(struct dw_pcie *pci)
 }
 EXPORT_SYMBOL_GPL(dw_pcie_wait_for_link);
 
-int dw_pcie_link_up(struct dw_pcie *pci)
+bool dw_pcie_link_up(struct dw_pcie *pci)
 {
 	u32 val;
 
@@ -781,6 +795,14 @@ static void dw_pcie_link_set_max_speed(struct dw_pcie *pci)
 
 }
 
+int dw_pcie_link_get_max_link_width(struct dw_pcie *pci)
+{
+	u8 cap = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
+	u32 lnkcap = dw_pcie_readl_dbi(pci, cap + PCI_EXP_LNKCAP);
+
+	return FIELD_GET(PCI_EXP_LNKCAP_MLW, lnkcap);
+}
+
 static void dw_pcie_link_set_max_link_width(struct dw_pcie *pci, u32 num_lanes)
 {
 	u32 lnkcap, lwsc, plc;
@@ -797,22 +819,19 @@ static void dw_pcie_link_set_max_link_width(struct dw_pcie *pci, u32 num_lanes)
 	/* Set link width speed control register */
 	lwsc = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL);
 	lwsc &= ~PORT_LOGIC_LINK_WIDTH_MASK;
+	lwsc |= PORT_LOGIC_LINK_WIDTH_1_LANES;
 	switch (num_lanes) {
 	case 1:
 		plc |= PORT_LINK_MODE_1_LANES;
-		lwsc |= PORT_LOGIC_LINK_WIDTH_1_LANES;
 		break;
 	case 2:
 		plc |= PORT_LINK_MODE_2_LANES;
-		lwsc |= PORT_LOGIC_LINK_WIDTH_2_LANES;
 		break;
 	case 4:
 		plc |= PORT_LINK_MODE_4_LANES;
-		lwsc |= PORT_LOGIC_LINK_WIDTH_4_LANES;
 		break;
 	case 8:
 		plc |= PORT_LINK_MODE_8_LANES;
-		lwsc |= PORT_LOGIC_LINK_WIDTH_8_LANES;
 		break;
 	default:
 		dev_err(pci->dev, "num-lanes %u: invalid value\n", num_lanes);
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 56aafdbcdaca..ce9e18554e42 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -25,6 +25,8 @@
 #include <linux/pci-epc.h>
 #include <linux/pci-epf.h>
 
+#include "../../pci.h"
+
 /* DWC PCIe IP-core versions (native support since v4.70a) */
 #define DW_PCIE_VER_365A		0x3336352a
 #define DW_PCIE_VER_460A		0x3436302a
@@ -260,6 +262,21 @@
 
 #define PCIE_RAS_DES_EVENT_COUNTER_DATA		0xc
 
+/* PTM register definitions */
+#define PTM_RES_REQ_CTRL		0x8
+#define PTM_RES_CCONTEXT_VALID		BIT(0)
+#define PTM_REQ_AUTO_UPDATE_ENABLED	BIT(0)
+#define PTM_REQ_START_UPDATE		BIT(1)
+
+#define PTM_LOCAL_LSB			0x10
+#define PTM_LOCAL_MSB			0x14
+#define PTM_T1_T2_LSB			0x18
+#define PTM_T1_T2_MSB			0x1c
+#define PTM_T3_T4_LSB			0x28
+#define PTM_T3_T4_MSB			0x2c
+#define PTM_MASTER_LSB			0x38
+#define PTM_MASTER_MSB			0x3c
+
 /*
  * The default address offset between dbi_base and atu_base. Root controller
  * drivers are not required to initialize atu_base if the offset matches this
@@ -412,6 +429,7 @@ struct dw_pcie_rp {
 	int			msg_atu_index;
 	struct resource		*msg_res;
 	bool			use_linkup_irq;
+	struct pci_eq_presets	presets;
 };
 
 struct dw_pcie_ep_ops {
@@ -462,7 +480,7 @@ struct dw_pcie_ops {
 			     size_t size, u32 val);
 	void    (*write_dbi2)(struct dw_pcie *pcie, void __iomem *base, u32 reg,
 			      size_t size, u32 val);
-	int	(*link_up)(struct dw_pcie *pcie);
+	bool	(*link_up)(struct dw_pcie *pcie);
 	enum dw_pcie_ltssm (*get_ltssm)(struct dw_pcie *pcie);
 	int	(*start_link)(struct dw_pcie *pcie);
 	void	(*stop_link)(struct dw_pcie *pcie);
@@ -503,6 +521,9 @@ struct dw_pcie {
 	struct gpio_desc		*pe_rst;
 	bool			suspended;
 	struct debugfs_info	*debugfs;
+	enum			dw_pcie_device_mode mode;
+	u16			ptm_vsec_offset;
+	struct pci_ptm_debugfs	*ptm_debugfs;
 
 	/*
 	 * If iATU input addresses are offset from CPU physical addresses,
@@ -530,6 +551,7 @@ void dw_pcie_version_detect(struct dw_pcie *pci);
 u8 dw_pcie_find_capability(struct dw_pcie *pci, u8 cap);
 u16 dw_pcie_find_ext_capability(struct dw_pcie *pci, u8 cap);
 u16 dw_pcie_find_rasdes_capability(struct dw_pcie *pci);
+u16 dw_pcie_find_ptm_capability(struct dw_pcie *pci);
 
 int dw_pcie_read(void __iomem *addr, int size, u32 *val);
 int dw_pcie_write(void __iomem *addr, int size, u32 val);
@@ -537,9 +559,10 @@ int dw_pcie_write(void __iomem *addr, int size, u32 val);
 u32 dw_pcie_read_dbi(struct dw_pcie *pci, u32 reg, size_t size);
 void dw_pcie_write_dbi(struct dw_pcie *pci, u32 reg, size_t size, u32 val);
 void dw_pcie_write_dbi2(struct dw_pcie *pci, u32 reg, size_t size, u32 val);
-int dw_pcie_link_up(struct dw_pcie *pci);
+bool dw_pcie_link_up(struct dw_pcie *pci);
 void dw_pcie_upconfig_setup(struct dw_pcie *pci);
 int dw_pcie_wait_for_link(struct dw_pcie *pci);
+int dw_pcie_link_get_max_link_width(struct dw_pcie *pci);
 int dw_pcie_prog_outbound_atu(struct dw_pcie *pci,
 			      const struct dw_pcie_ob_atu_cfg *atu);
 int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type,
@@ -871,10 +894,11 @@ dw_pcie_ep_get_func_from_ep(struct dw_pcie_ep *ep, u8 func_no)
 #endif
 
 #ifdef CONFIG_PCIE_DW_DEBUGFS
-void dwc_pcie_debugfs_init(struct dw_pcie *pci);
+void dwc_pcie_debugfs_init(struct dw_pcie *pci, enum dw_pcie_device_mode mode);
 void dwc_pcie_debugfs_deinit(struct dw_pcie *pci);
 #else
-static inline void dwc_pcie_debugfs_init(struct dw_pcie *pci)
+static inline void dwc_pcie_debugfs_init(struct dw_pcie *pci,
+					 enum dw_pcie_device_mode mode)
 {
 }
 static inline void dwc_pcie_debugfs_deinit(struct dw_pcie *pci)
diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
index 678d510a261d..93171a392879 100644
--- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c
+++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
@@ -8,6 +8,7 @@
  * Author: Simon Xue <xxm@rock-chips.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/gpio/consumer.h>
 #include <linux/irqchip/chained_irq.h>
@@ -21,6 +22,7 @@
 #include <linux/regmap.h>
 #include <linux/reset.h>
 
+#include "../../pci.h"
 #include "pcie-designware.h"
 
 /*
@@ -33,26 +35,36 @@
 
 #define to_rockchip_pcie(x) dev_get_drvdata((x)->dev)
 
-#define PCIE_CLIENT_RC_MODE		HIWORD_UPDATE_BIT(0x40)
-#define PCIE_CLIENT_EP_MODE		HIWORD_UPDATE(0xf0, 0x0)
-#define PCIE_CLIENT_ENABLE_LTSSM	HIWORD_UPDATE_BIT(0xc)
-#define PCIE_CLIENT_DISABLE_LTSSM	HIWORD_UPDATE(0x0c, 0x8)
-#define PCIE_CLIENT_INTR_STATUS_MISC	0x10
-#define PCIE_CLIENT_INTR_MASK_MISC	0x24
-#define PCIE_SMLH_LINKUP		BIT(16)
-#define PCIE_RDLH_LINKUP		BIT(17)
-#define PCIE_LINKUP			(PCIE_SMLH_LINKUP | PCIE_RDLH_LINKUP)
-#define PCIE_RDLH_LINK_UP_CHGED		BIT(1)
-#define PCIE_LINK_REQ_RST_NOT_INT	BIT(2)
-#define PCIE_L0S_ENTRY			0x11
-#define PCIE_CLIENT_GENERAL_CONTROL	0x0
+/* General Control Register */
+#define PCIE_CLIENT_GENERAL_CON		0x0
+#define  PCIE_CLIENT_RC_MODE		HIWORD_UPDATE_BIT(0x40)
+#define  PCIE_CLIENT_EP_MODE		HIWORD_UPDATE(0xf0, 0x0)
+#define  PCIE_CLIENT_ENABLE_LTSSM	HIWORD_UPDATE_BIT(0xc)
+#define  PCIE_CLIENT_DISABLE_LTSSM	HIWORD_UPDATE(0x0c, 0x8)
+
+/* Interrupt Status Register Related to Legacy Interrupt */
 #define PCIE_CLIENT_INTR_STATUS_LEGACY	0x8
+
+/* Interrupt Status Register Related to Miscellaneous Operation */
+#define PCIE_CLIENT_INTR_STATUS_MISC	0x10
+#define  PCIE_RDLH_LINK_UP_CHGED	BIT(1)
+#define  PCIE_LINK_REQ_RST_NOT_INT	BIT(2)
+
+/* Interrupt Mask Register Related to Legacy Interrupt */
 #define PCIE_CLIENT_INTR_MASK_LEGACY	0x1c
-#define PCIE_CLIENT_GENERAL_DEBUG	0x104
+
+/* Interrupt Mask Register Related to Miscellaneous Operation */
+#define PCIE_CLIENT_INTR_MASK_MISC	0x24
+
+/* Hot Reset Control Register */
 #define PCIE_CLIENT_HOT_RESET_CTRL	0x180
+#define  PCIE_LTSSM_ENABLE_ENHANCE	BIT(4)
+
+/* LTSSM Status Register */
 #define PCIE_CLIENT_LTSSM_STATUS	0x300
-#define PCIE_LTSSM_ENABLE_ENHANCE	BIT(4)
-#define PCIE_LTSSM_STATUS_MASK		GENMASK(5, 0)
+#define  PCIE_LINKUP			0x3
+#define  PCIE_LINKUP_MASK		GENMASK(17, 16)
+#define  PCIE_LTSSM_STATUS_MASK		GENMASK(5, 0)
 
 struct rockchip_pcie {
 	struct dw_pcie pci;
@@ -163,25 +175,36 @@ static u32 rockchip_pcie_get_ltssm(struct rockchip_pcie *rockchip)
 static void rockchip_pcie_enable_ltssm(struct rockchip_pcie *rockchip)
 {
 	rockchip_pcie_writel_apb(rockchip, PCIE_CLIENT_ENABLE_LTSSM,
-				 PCIE_CLIENT_GENERAL_CONTROL);
+				 PCIE_CLIENT_GENERAL_CON);
 }
 
 static void rockchip_pcie_disable_ltssm(struct rockchip_pcie *rockchip)
 {
 	rockchip_pcie_writel_apb(rockchip, PCIE_CLIENT_DISABLE_LTSSM,
-				 PCIE_CLIENT_GENERAL_CONTROL);
+				 PCIE_CLIENT_GENERAL_CON);
 }
 
-static int rockchip_pcie_link_up(struct dw_pcie *pci)
+static bool rockchip_pcie_link_up(struct dw_pcie *pci)
 {
 	struct rockchip_pcie *rockchip = to_rockchip_pcie(pci);
 	u32 val = rockchip_pcie_get_ltssm(rockchip);
 
-	if ((val & PCIE_LINKUP) == PCIE_LINKUP &&
-	    (val & PCIE_LTSSM_STATUS_MASK) == PCIE_L0S_ENTRY)
-		return 1;
+	return FIELD_GET(PCIE_LINKUP_MASK, val) == PCIE_LINKUP;
+}
 
-	return 0;
+static void rockchip_pcie_enable_l0s(struct dw_pcie *pci)
+{
+	u32 cap, lnkcap;
+
+	/* Enable L0S capability for all SoCs */
+	cap = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
+	if (cap) {
+		lnkcap = dw_pcie_readl_dbi(pci, cap + PCI_EXP_LNKCAP);
+		lnkcap |= PCI_EXP_LNKCAP_ASPM_L0S;
+		dw_pcie_dbi_ro_wr_en(pci);
+		dw_pcie_writel_dbi(pci, cap + PCI_EXP_LNKCAP, lnkcap);
+		dw_pcie_dbi_ro_wr_dis(pci);
+	}
 }
 
 static int rockchip_pcie_start_link(struct dw_pcie *pci)
@@ -202,7 +225,7 @@ static int rockchip_pcie_start_link(struct dw_pcie *pci)
 	 * We need more extra time as before, rather than setting just
 	 * 100us as we don't know how long should the device need to reset.
 	 */
-	msleep(100);
+	msleep(PCIE_T_PVPERL_MS);
 	gpiod_set_value_cansleep(rockchip->rst_gpio, 1);
 
 	return 0;
@@ -233,6 +256,8 @@ static int rockchip_pcie_host_init(struct dw_pcie_rp *pp)
 	irq_set_chained_handler_and_data(irq, rockchip_pcie_intx_handler,
 					 rockchip);
 
+	rockchip_pcie_enable_l0s(pci);
+
 	return 0;
 }
 
@@ -263,16 +288,14 @@ static void rockchip_pcie_ep_hide_broken_ats_cap_rk3588(struct dw_pcie_ep *ep)
 		dev_err(dev, "failed to hide ATS capability\n");
 }
 
-static void rockchip_pcie_ep_pre_init(struct dw_pcie_ep *ep)
-{
-	rockchip_pcie_ep_hide_broken_ats_cap_rk3588(ep);
-}
-
 static void rockchip_pcie_ep_init(struct dw_pcie_ep *ep)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	enum pci_barno bar;
 
+	rockchip_pcie_enable_l0s(pci);
+	rockchip_pcie_ep_hide_broken_ats_cap_rk3588(ep);
+
 	for (bar = 0; bar < PCI_STD_NUM_BARS; bar++)
 		dw_pcie_ep_reset_bar(pci, bar);
 };
@@ -342,7 +365,6 @@ rockchip_pcie_get_features(struct dw_pcie_ep *ep)
 
 static const struct dw_pcie_ep_ops rockchip_pcie_ep_ops = {
 	.init = rockchip_pcie_ep_init,
-	.pre_init = rockchip_pcie_ep_pre_init,
 	.raise_irq = rockchip_pcie_raise_irq,
 	.get_features = rockchip_pcie_get_features,
 };
@@ -410,8 +432,8 @@ static int rockchip_pcie_phy_init(struct rockchip_pcie *rockchip)
 
 static void rockchip_pcie_phy_deinit(struct rockchip_pcie *rockchip)
 {
-	phy_exit(rockchip->phy);
 	phy_power_off(rockchip->phy);
+	phy_exit(rockchip->phy);
 }
 
 static const struct dw_pcie_ops dw_pcie_ops = {
@@ -426,7 +448,7 @@ static irqreturn_t rockchip_pcie_rc_sys_irq_thread(int irq, void *arg)
 	struct dw_pcie *pci = &rockchip->pci;
 	struct dw_pcie_rp *pp = &pci->pp;
 	struct device *dev = pci->dev;
-	u32 reg, val;
+	u32 reg;
 
 	reg = rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_INTR_STATUS_MISC);
 	rockchip_pcie_writel_apb(rockchip, reg, PCIE_CLIENT_INTR_STATUS_MISC);
@@ -435,8 +457,7 @@ static irqreturn_t rockchip_pcie_rc_sys_irq_thread(int irq, void *arg)
 	dev_dbg(dev, "LTSSM_STATUS: %#x\n", rockchip_pcie_get_ltssm(rockchip));
 
 	if (reg & PCIE_RDLH_LINK_UP_CHGED) {
-		val = rockchip_pcie_get_ltssm(rockchip);
-		if ((val & PCIE_LINKUP) == PCIE_LINKUP) {
+		if (rockchip_pcie_link_up(pci)) {
 			dev_dbg(dev, "Received Link up event. Starting enumeration!\n");
 			/* Rescan the bus to enumerate endpoint devices */
 			pci_lock_rescan_remove();
@@ -453,7 +474,7 @@ static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg)
 	struct rockchip_pcie *rockchip = arg;
 	struct dw_pcie *pci = &rockchip->pci;
 	struct device *dev = pci->dev;
-	u32 reg, val;
+	u32 reg;
 
 	reg = rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_INTR_STATUS_MISC);
 	rockchip_pcie_writel_apb(rockchip, reg, PCIE_CLIENT_INTR_STATUS_MISC);
@@ -467,8 +488,7 @@ static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg)
 	}
 
 	if (reg & PCIE_RDLH_LINK_UP_CHGED) {
-		val = rockchip_pcie_get_ltssm(rockchip);
-		if ((val & PCIE_LINKUP) == PCIE_LINKUP) {
+		if (rockchip_pcie_link_up(pci)) {
 			dev_dbg(dev, "link up\n");
 			dw_pcie_ep_linkup(&pci->ep);
 		}
@@ -505,7 +525,7 @@ static int rockchip_pcie_configure_rc(struct platform_device *pdev,
 	rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_HOT_RESET_CTRL);
 
 	rockchip_pcie_writel_apb(rockchip, PCIE_CLIENT_RC_MODE,
-				 PCIE_CLIENT_GENERAL_CONTROL);
+				 PCIE_CLIENT_GENERAL_CON);
 
 	pp = &rockchip->pci.pp;
 	pp->ops = &rockchip_pcie_host_ops;
@@ -551,7 +571,7 @@ static int rockchip_pcie_configure_ep(struct platform_device *pdev,
 	rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_HOT_RESET_CTRL);
 
 	rockchip_pcie_writel_apb(rockchip, PCIE_CLIENT_EP_MODE,
-				 PCIE_CLIENT_GENERAL_CONTROL);
+				 PCIE_CLIENT_GENERAL_CON);
 
 	rockchip->pci.ep.ops = &rockchip_pcie_ep_ops;
 	rockchip->pci.ep.page_size = SZ_64K;
@@ -601,6 +621,10 @@ static int rockchip_pcie_probe(struct platform_device *pdev)
 	rockchip->pci.ops = &dw_pcie_ops;
 	rockchip->data = data;
 
+	/* Default N_FTS value (210) is broken, override it to 255 */
+	rockchip->pci.n_fts[0] = 255; /* Gen1 */
+	rockchip->pci.n_fts[1] = 255; /* Gen2+ */
+
 	ret = rockchip_pcie_resource_get(pdev, rockchip);
 	if (ret)
 		return ret;
diff --git a/drivers/pci/controller/dwc/pcie-hisi.c b/drivers/pci/controller/dwc/pcie-hisi.c
index 8904b5b85ee5..3c17897e56fc 100644
--- a/drivers/pci/controller/dwc/pcie-hisi.c
+++ b/drivers/pci/controller/dwc/pcie-hisi.c
@@ -15,6 +15,7 @@
 #include <linux/pci-acpi.h>
 #include <linux/pci-ecam.h>
 #include "../../pci.h"
+#include "../pci-host-common.h"
 
 #if defined(CONFIG_PCI_HISI) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS))
 
diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c
index 1f2f4c28a949..a52071589377 100644
--- a/drivers/pci/controller/dwc/pcie-histb.c
+++ b/drivers/pci/controller/dwc/pcie-histb.c
@@ -151,7 +151,7 @@ static struct pci_ops histb_pci_ops = {
 	.write = histb_pcie_wr_own_conf,
 };
 
-static int histb_pcie_link_up(struct dw_pcie *pci)
+static bool histb_pcie_link_up(struct dw_pcie *pci)
 {
 	struct histb_pcie *hipcie = to_histb_pcie(pci);
 	u32 regval;
@@ -160,11 +160,8 @@ static int histb_pcie_link_up(struct dw_pcie *pci)
 	regval = histb_pcie_readl(hipcie, PCIE_SYS_STAT0);
 	status = histb_pcie_readl(hipcie, PCIE_SYS_STAT4);
 	status &= PCIE_LTSSM_STATE_MASK;
-	if ((regval & PCIE_XMLH_LINK_UP) && (regval & PCIE_RDLH_LINK_UP) &&
-	    (status == PCIE_LTSSM_STATE_ACTIVE))
-		return 1;
-
-	return 0;
+	return ((regval & PCIE_XMLH_LINK_UP) && (regval & PCIE_RDLH_LINK_UP) &&
+		(status == PCIE_LTSSM_STATE_ACTIVE));
 }
 
 static int histb_pcie_start_link(struct dw_pcie *pci)
diff --git a/drivers/pci/controller/dwc/pcie-keembay.c b/drivers/pci/controller/dwc/pcie-keembay.c
index 278205db60a2..67dd3337b447 100644
--- a/drivers/pci/controller/dwc/pcie-keembay.c
+++ b/drivers/pci/controller/dwc/pcie-keembay.c
@@ -101,7 +101,7 @@ static void keembay_pcie_ltssm_set(struct keembay_pcie *pcie, bool enable)
 	writel(val, pcie->apb_base + PCIE_REGS_PCIE_APP_CNTRL);
 }
 
-static int keembay_pcie_link_up(struct dw_pcie *pci)
+static bool keembay_pcie_link_up(struct dw_pcie *pci)
 {
 	struct keembay_pcie *pcie = dev_get_drvdata(pci->dev);
 	u32 val;
diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
index d0e6a3811b00..91559c8b1866 100644
--- a/drivers/pci/controller/dwc/pcie-kirin.c
+++ b/drivers/pci/controller/dwc/pcie-kirin.c
@@ -586,16 +586,13 @@ static void kirin_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base,
 	kirin_pcie_sideband_dbi_w_mode(kirin_pcie, false);
 }
 
-static int kirin_pcie_link_up(struct dw_pcie *pci)
+static bool kirin_pcie_link_up(struct dw_pcie *pci)
 {
 	struct kirin_pcie *kirin_pcie = to_kirin_pcie(pci);
 	u32 val;
 
 	regmap_read(kirin_pcie->apb, PCIE_APB_PHY_STATUS0, &val);
-	if ((val & PCIE_LINKUP_ENABLE) == PCIE_LINKUP_ENABLE)
-		return 1;
-
-	return 0;
+	return (val & PCIE_LINKUP_ENABLE) == PCIE_LINKUP_ENABLE;
 }
 
 static int kirin_pcie_start_link(struct dw_pcie *pci)
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index 46b1c6d19974..bf7c6ac0f3e3 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -60,6 +60,7 @@
 #define PARF_DEVICE_TYPE			0x1000
 #define PARF_BDF_TO_SID_CFG			0x2c00
 #define PARF_INT_ALL_5_MASK			0x2dcc
+#define PARF_INT_ALL_3_MASK			0x2e18
 
 /* PARF_INT_ALL_{STATUS/CLEAR/MASK} register fields */
 #define PARF_INT_ALL_LINK_DOWN			BIT(1)
@@ -132,6 +133,9 @@
 /* PARF_INT_ALL_5_MASK fields */
 #define PARF_INT_ALL_5_MHI_RAM_DATA_PARITY_ERR	BIT(0)
 
+/* PARF_INT_ALL_3_MASK fields */
+#define PARF_INT_ALL_3_PTM_UPDATING		BIT(4)
+
 /* ELBI registers */
 #define ELBI_SYS_STTS				0x08
 #define ELBI_CS2_ENABLE				0xa4
@@ -261,7 +265,7 @@ static void qcom_pcie_ep_configure_tcsr(struct qcom_pcie_ep *pcie_ep)
 	}
 }
 
-static int qcom_pcie_dw_link_up(struct dw_pcie *pci)
+static bool qcom_pcie_dw_link_up(struct dw_pcie *pci)
 {
 	struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci);
 	u32 reg;
@@ -497,6 +501,10 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci)
 		writel_relaxed(val, pcie_ep->parf + PARF_INT_ALL_5_MASK);
 	}
 
+	val = readl_relaxed(pcie_ep->parf + PARF_INT_ALL_3_MASK);
+	val &= ~PARF_INT_ALL_3_PTM_UPDATING;
+	writel_relaxed(val, pcie_ep->parf + PARF_INT_ALL_3_MASK);
+
 	ret = dw_pcie_ep_init_registers(&pcie_ep->pci.ep);
 	if (ret) {
 		dev_err(dev, "Failed to complete initialization: %d\n", ret);
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index dc98ae63362d..c789e3f85655 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -289,7 +289,7 @@ static void qcom_ep_reset_assert(struct qcom_pcie *pcie)
 static void qcom_ep_reset_deassert(struct qcom_pcie *pcie)
 {
 	/* Ensure that PERST has been asserted for at least 100 ms */
-	msleep(100);
+	msleep(PCIE_T_PVPERL_MS);
 	gpiod_set_value_cansleep(pcie->reset, 0);
 	usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500);
 }
@@ -1221,12 +1221,12 @@ static int qcom_pcie_post_init_2_9_0(struct qcom_pcie *pcie)
 	return 0;
 }
 
-static int qcom_pcie_link_up(struct dw_pcie *pci)
+static bool qcom_pcie_link_up(struct dw_pcie *pci)
 {
 	u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
 	u16 val = readw(pci->dbi_base + offset + PCI_EXP_LNKSTA);
 
-	return !!(val & PCI_EXP_LNKSTA_DLLLA);
+	return val & PCI_EXP_LNKSTA_DLLLA;
 }
 
 static int qcom_pcie_host_init(struct dw_pcie_rp *pp)
@@ -1840,6 +1840,7 @@ static const struct of_device_id qcom_pcie_match[] = {
 	{ .compatible = "qcom,pcie-apq8064", .data = &cfg_2_1_0 },
 	{ .compatible = "qcom,pcie-apq8084", .data = &cfg_1_0_0 },
 	{ .compatible = "qcom,pcie-ipq4019", .data = &cfg_2_4_0 },
+	{ .compatible = "qcom,pcie-ipq5018", .data = &cfg_2_9_0 },
 	{ .compatible = "qcom,pcie-ipq6018", .data = &cfg_2_9_0 },
 	{ .compatible = "qcom,pcie-ipq8064", .data = &cfg_2_1_0 },
 	{ .compatible = "qcom,pcie-ipq8064-v2", .data = &cfg_2_1_0 },
diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index fc872dd35029..18055807a4f5 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -87,7 +87,7 @@ struct rcar_gen4_pcie {
 #define to_rcar_gen4_pcie(_dw)	container_of(_dw, struct rcar_gen4_pcie, dw)
 
 /* Common */
-static int rcar_gen4_pcie_link_up(struct dw_pcie *dw)
+static bool rcar_gen4_pcie_link_up(struct dw_pcie *dw)
 {
 	struct rcar_gen4_pcie *rcar = to_rcar_gen4_pcie(dw);
 	u32 val, mask;
@@ -403,6 +403,7 @@ static const struct pci_epc_features rcar_gen4_pcie_epc_features = {
 	.msix_capable = false,
 	.bar[BAR_1] = { .type = BAR_RESERVED, },
 	.bar[BAR_3] = { .type = BAR_RESERVED, },
+	.bar[BAR_4] = { .type = BAR_FIXED, .fixed_size = 256 },
 	.bar[BAR_5] = { .type = BAR_RESERVED, },
 	.align = SZ_1M,
 };
diff --git a/drivers/pci/controller/dwc/pcie-spear13xx.c b/drivers/pci/controller/dwc/pcie-spear13xx.c
index ff986ced56b2..01794a9d3ad2 100644
--- a/drivers/pci/controller/dwc/pcie-spear13xx.c
+++ b/drivers/pci/controller/dwc/pcie-spear13xx.c
@@ -110,15 +110,12 @@ static void spear13xx_pcie_enable_interrupts(struct spear13xx_pcie *spear13xx_pc
 				MSI_CTRL_INT, &app_reg->int_mask);
 }
 
-static int spear13xx_pcie_link_up(struct dw_pcie *pci)
+static bool spear13xx_pcie_link_up(struct dw_pcie *pci)
 {
 	struct spear13xx_pcie *spear13xx_pcie = to_spear13xx_pcie(pci);
 	struct pcie_app_reg __iomem *app_reg = spear13xx_pcie->app_base;
 
-	if (readl(&app_reg->app_status_1) & XMLH_LINK_UP)
-		return 1;
-
-	return 0;
+	return readl(&app_reg->app_status_1) & XMLH_LINK_UP;
 }
 
 static int spear13xx_pcie_host_init(struct dw_pcie_rp *pp)
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index 5103995cd6c7..4f26086f25da 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -713,7 +713,16 @@ static void init_host_aspm(struct tegra_pcie_dw *pcie)
 
 static void init_debugfs(struct tegra_pcie_dw *pcie)
 {
-	debugfs_create_devm_seqfile(pcie->dev, "aspm_state_cnt", pcie->debugfs,
+	struct device *dev = pcie->dev;
+	char *name;
+
+	name = devm_kasprintf(dev, GFP_KERNEL, "%pOFP", dev->of_node);
+	if (!name)
+		return;
+
+	pcie->debugfs = debugfs_create_dir(name, NULL);
+
+	debugfs_create_devm_seqfile(dev, "aspm_state_cnt", pcie->debugfs,
 				    aspm_state_cnt);
 }
 #else
@@ -1027,12 +1036,12 @@ retry_link:
 	return 0;
 }
 
-static int tegra_pcie_dw_link_up(struct dw_pcie *pci)
+static bool tegra_pcie_dw_link_up(struct dw_pcie *pci)
 {
 	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 	u32 val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA);
 
-	return !!(val & PCI_EXP_LNKSTA_DLLLA);
+	return val & PCI_EXP_LNKSTA_DLLLA;
 }
 
 static void tegra_pcie_dw_stop_link(struct dw_pcie *pci)
@@ -1634,7 +1643,6 @@ static void tegra_pcie_deinit_controller(struct tegra_pcie_dw *pcie)
 static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie)
 {
 	struct device *dev = pcie->dev;
-	char *name;
 	int ret;
 
 	pm_runtime_enable(dev);
@@ -1664,13 +1672,6 @@ static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie)
 		goto fail_host_init;
 	}
 
-	name = devm_kasprintf(dev, GFP_KERNEL, "%pOFP", dev->of_node);
-	if (!name) {
-		ret = -ENOMEM;
-		goto fail_host_init;
-	}
-
-	pcie->debugfs = debugfs_create_dir(name, NULL);
 	init_debugfs(pcie);
 
 	return ret;
diff --git a/drivers/pci/controller/dwc/pcie-uniphier.c b/drivers/pci/controller/dwc/pcie-uniphier.c
index 43b28f826edd..297e7a3d9b36 100644
--- a/drivers/pci/controller/dwc/pcie-uniphier.c
+++ b/drivers/pci/controller/dwc/pcie-uniphier.c
@@ -135,7 +135,7 @@ static int uniphier_pcie_wait_rc(struct uniphier_pcie *pcie)
 	return 0;
 }
 
-static int uniphier_pcie_link_up(struct dw_pcie *pci)
+static bool uniphier_pcie_link_up(struct dw_pcie *pci)
 {
 	struct uniphier_pcie *pcie = to_uniphier_pcie(pci);
 	u32 val, mask;
diff --git a/drivers/pci/controller/dwc/pcie-visconti.c b/drivers/pci/controller/dwc/pcie-visconti.c
index 318c278e65c8..cdeac6177143 100644
--- a/drivers/pci/controller/dwc/pcie-visconti.c
+++ b/drivers/pci/controller/dwc/pcie-visconti.c
@@ -121,13 +121,13 @@ static u32 visconti_mpu_readl(struct visconti_pcie *pcie, u32 reg)
 	return readl_relaxed(pcie->mpu_base + reg);
 }
 
-static int visconti_pcie_link_up(struct dw_pcie *pci)
+static bool visconti_pcie_link_up(struct dw_pcie *pci)
 {
 	struct visconti_pcie *pcie = dev_get_drvdata(pci->dev);
 	void __iomem *addr = pcie->ulreg_base;
 	u32 val = readl_relaxed(addr + PCIE_UL_REG_V_PHY_ST_02);
 
-	return !!(val & PCIE_UL_S_L0);
+	return val & PCIE_UL_S_L0;
 }
 
 static int visconti_pcie_start_link(struct dw_pcie *pci)
diff --git a/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c b/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c
index 5af22bee913b..4919b27eaf44 100644
--- a/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c
+++ b/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c
@@ -53,18 +53,13 @@ static inline void ls_g4_pcie_pf_writel(struct ls_g4_pcie *pcie,
 	iowrite32(val, pcie->pci.csr_axi_slave_base + PCIE_PF_OFF + off);
 }
 
-static int ls_g4_pcie_link_up(struct mobiveil_pcie *pci)
+static bool ls_g4_pcie_link_up(struct mobiveil_pcie *pci)
 {
 	struct ls_g4_pcie *pcie = to_ls_g4_pcie(pci);
 	u32 state;
 
 	state = ls_g4_pcie_pf_readl(pcie, PCIE_PF_DBG);
-	state =	state & PF_DBG_LTSSM_MASK;
-
-	if (state == PF_DBG_LTSSM_L0)
-		return 1;
-
-	return 0;
+	return (state & PF_DBG_LTSSM_MASK) == PF_DBG_LTSSM_L0;
 }
 
 static void ls_g4_pcie_disable_interrupt(struct ls_g4_pcie *pcie)
@@ -174,8 +169,7 @@ static int ls_g4_pcie_interrupt_init(struct mobiveil_pcie *mv_pci)
 
 static void ls_g4_pcie_reset(struct work_struct *work)
 {
-	struct delayed_work *dwork = container_of(work, struct delayed_work,
-						  work);
+	struct delayed_work *dwork = to_delayed_work(work);
 	struct ls_g4_pcie *pcie = container_of(dwork, struct ls_g4_pcie, dwork);
 	struct mobiveil_pcie *mv_pci = &pcie->pci;
 	u16 ctrl;
diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil.h b/drivers/pci/controller/mobiveil/pcie-mobiveil.h
index e63abb887ee3..662f17f9bf65 100644
--- a/drivers/pci/controller/mobiveil/pcie-mobiveil.h
+++ b/drivers/pci/controller/mobiveil/pcie-mobiveil.h
@@ -160,7 +160,7 @@ struct mobiveil_root_port {
 };
 
 struct mobiveil_pab_ops {
-	int (*link_up)(struct mobiveil_pcie *pcie);
+	bool (*link_up)(struct mobiveil_pcie *pcie);
 };
 
 struct mobiveil_pcie {
diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c
index f441bfd6f96a..b0992325dd65 100644
--- a/drivers/pci/controller/pci-host-common.c
+++ b/drivers/pci/controller/pci-host-common.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Generic PCI host driver common code
+ * Common library for PCI host controller drivers
  *
  * Copyright (C) 2014 ARM Limited
  *
@@ -15,6 +15,8 @@
 #include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
 
+#include "pci-host-common.h"
+
 static void gen_pci_unmap_cfg(void *ptr)
 {
 	pci_ecam_free((struct pci_config_window *)ptr);
@@ -49,23 +51,17 @@ static struct pci_config_window *gen_pci_init(struct device *dev,
 	return cfg;
 }
 
-int pci_host_common_probe(struct platform_device *pdev)
+int pci_host_common_init(struct platform_device *pdev,
+			 const struct pci_ecam_ops *ops)
 {
 	struct device *dev = &pdev->dev;
 	struct pci_host_bridge *bridge;
 	struct pci_config_window *cfg;
-	const struct pci_ecam_ops *ops;
-
-	ops = of_device_get_match_data(&pdev->dev);
-	if (!ops)
-		return -ENODEV;
 
 	bridge = devm_pci_alloc_host_bridge(dev, 0);
 	if (!bridge)
 		return -ENOMEM;
 
-	platform_set_drvdata(pdev, bridge);
-
 	of_pci_check_probe_only();
 
 	/* Parse and map our Configuration Space windows */
@@ -73,6 +69,8 @@ int pci_host_common_probe(struct platform_device *pdev)
 	if (IS_ERR(cfg))
 		return PTR_ERR(cfg);
 
+	platform_set_drvdata(pdev, bridge);
+
 	bridge->sysdata = cfg;
 	bridge->ops = (struct pci_ops *)&ops->pci_ops;
 	bridge->enable_device = ops->enable_device;
@@ -81,6 +79,18 @@ int pci_host_common_probe(struct platform_device *pdev)
 
 	return pci_host_probe(bridge);
 }
+EXPORT_SYMBOL_GPL(pci_host_common_init);
+
+int pci_host_common_probe(struct platform_device *pdev)
+{
+	const struct pci_ecam_ops *ops;
+
+	ops = of_device_get_match_data(&pdev->dev);
+	if (!ops)
+		return -ENODEV;
+
+	return pci_host_common_init(pdev, ops);
+}
 EXPORT_SYMBOL_GPL(pci_host_common_probe);
 
 void pci_host_common_remove(struct platform_device *pdev)
@@ -94,5 +104,5 @@ void pci_host_common_remove(struct platform_device *pdev)
 }
 EXPORT_SYMBOL_GPL(pci_host_common_remove);
 
-MODULE_DESCRIPTION("Generic PCI host common driver");
+MODULE_DESCRIPTION("Common library for PCI host controller drivers");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pci-host-common.h b/drivers/pci/controller/pci-host-common.h
new file mode 100644
index 000000000000..65bd9e032353
--- /dev/null
+++ b/drivers/pci/controller/pci-host-common.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common library for PCI host controller drivers
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#ifndef _PCI_HOST_COMMON_H
+#define _PCI_HOST_COMMON_H
+
+struct pci_ecam_ops;
+
+int pci_host_common_probe(struct platform_device *pdev);
+int pci_host_common_init(struct platform_device *pdev,
+			 const struct pci_ecam_ops *ops);
+void pci_host_common_remove(struct platform_device *pdev);
+
+#endif
diff --git a/drivers/pci/controller/pci-host-generic.c b/drivers/pci/controller/pci-host-generic.c
index 4051b9b61dac..c1bc0d34348f 100644
--- a/drivers/pci/controller/pci-host-generic.c
+++ b/drivers/pci/controller/pci-host-generic.c
@@ -14,6 +14,8 @@
 #include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
 
+#include "pci-host-common.h"
+
 static const struct pci_ecam_ops gen_pci_cfg_cam_bus_ops = {
 	.bus_shift	= 16,
 	.pci_ops	= {
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index e1eaa24559a2..ef5d655a0052 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -50,6 +50,7 @@
 #include <linux/irqdomain.h>
 #include <linux/acpi.h>
 #include <linux/sizes.h>
+#include <linux/of_irq.h>
 #include <asm/mshyperv.h>
 
 /*
@@ -309,8 +310,6 @@ struct pci_packet {
 	void (*completion_func)(void *context, struct pci_response *resp,
 				int resp_packet_size);
 	void *compl_ctxt;
-
-	struct pci_message message[];
 };
 
 /*
@@ -817,9 +816,17 @@ static int hv_pci_vec_irq_gic_domain_alloc(struct irq_domain *domain,
 	int ret;
 
 	fwspec.fwnode = domain->parent->fwnode;
-	fwspec.param_count = 2;
-	fwspec.param[0] = hwirq;
-	fwspec.param[1] = IRQ_TYPE_EDGE_RISING;
+	if (is_of_node(fwspec.fwnode)) {
+		/* SPI lines for OF translations start at offset 32 */
+		fwspec.param_count = 3;
+		fwspec.param[0] = 0;
+		fwspec.param[1] = hwirq - 32;
+		fwspec.param[2] = IRQ_TYPE_EDGE_RISING;
+	} else {
+		fwspec.param_count = 2;
+		fwspec.param[0] = hwirq;
+		fwspec.param[1] = IRQ_TYPE_EDGE_RISING;
+	}
 
 	ret = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec);
 	if (ret)
@@ -887,10 +894,44 @@ static const struct irq_domain_ops hv_pci_domain_ops = {
 	.activate = hv_pci_vec_irq_domain_activate,
 };
 
+#ifdef CONFIG_OF
+
+static struct irq_domain *hv_pci_of_irq_domain_parent(void)
+{
+	struct device_node *parent;
+	struct irq_domain *domain;
+
+	parent = of_irq_find_parent(hv_get_vmbus_root_device()->of_node);
+	if (!parent)
+		return NULL;
+	domain = irq_find_host(parent);
+	of_node_put(parent);
+
+	return domain;
+}
+
+#endif
+
+#ifdef CONFIG_ACPI
+
+static struct irq_domain *hv_pci_acpi_irq_domain_parent(void)
+{
+	acpi_gsi_domain_disp_fn gsi_domain_disp_fn;
+
+	gsi_domain_disp_fn = acpi_get_gsi_dispatcher();
+	if (!gsi_domain_disp_fn)
+		return NULL;
+	return irq_find_matching_fwnode(gsi_domain_disp_fn(0),
+				     DOMAIN_BUS_ANY);
+}
+
+#endif
+
 static int hv_pci_irqchip_init(void)
 {
 	static struct hv_pci_chip_data *chip_data;
 	struct fwnode_handle *fn = NULL;
+	struct irq_domain *irq_domain_parent = NULL;
 	int ret = -ENOMEM;
 
 	chip_data = kzalloc(sizeof(*chip_data), GFP_KERNEL);
@@ -907,9 +948,24 @@ static int hv_pci_irqchip_init(void)
 	 * way to ensure that all the corresponding devices are also gone and
 	 * no interrupts will be generated.
 	 */
-	hv_msi_gic_irq_domain = acpi_irq_create_hierarchy(0, HV_PCI_MSI_SPI_NR,
-							  fn, &hv_pci_domain_ops,
-							  chip_data);
+#ifdef CONFIG_ACPI
+	if (!acpi_disabled)
+		irq_domain_parent = hv_pci_acpi_irq_domain_parent();
+#endif
+#ifdef CONFIG_OF
+	if (!irq_domain_parent)
+		irq_domain_parent = hv_pci_of_irq_domain_parent();
+#endif
+	if (!irq_domain_parent) {
+		WARN_ONCE(1, "Invalid firmware configuration for VMBus interrupts\n");
+		ret = -EINVAL;
+		goto free_chip;
+	}
+
+	hv_msi_gic_irq_domain = irq_domain_create_hierarchy(irq_domain_parent, 0,
+		HV_PCI_MSI_SPI_NR,
+		fn, &hv_pci_domain_ops,
+		chip_data);
 
 	if (!hv_msi_gic_irq_domain) {
 		pr_err("Failed to create Hyper-V arm64 vPCI MSI IRQ domain\n");
@@ -1438,7 +1494,7 @@ static int hv_read_config_block(struct pci_dev *pdev, void *buf,
 	memset(&pkt, 0, sizeof(pkt));
 	pkt.pkt.completion_func = hv_pci_read_config_compl;
 	pkt.pkt.compl_ctxt = &comp_pkt;
-	read_blk = (struct pci_read_block *)&pkt.pkt.message;
+	read_blk = (struct pci_read_block *)pkt.buf;
 	read_blk->message_type.type = PCI_READ_BLOCK;
 	read_blk->wslot.slot = devfn_to_wslot(pdev->devfn);
 	read_blk->block_id = block_id;
@@ -1518,7 +1574,7 @@ static int hv_write_config_block(struct pci_dev *pdev, void *buf,
 	memset(&pkt, 0, sizeof(pkt));
 	pkt.pkt.completion_func = hv_pci_write_config_compl;
 	pkt.pkt.compl_ctxt = &comp_pkt;
-	write_blk = (struct pci_write_block *)&pkt.pkt.message;
+	write_blk = (struct pci_write_block *)pkt.buf;
 	write_blk->message_type.type = PCI_WRITE_BLOCK;
 	write_blk->wslot.slot = devfn_to_wslot(pdev->devfn);
 	write_blk->block_id = block_id;
@@ -1599,7 +1655,7 @@ static void hv_int_desc_free(struct hv_pci_dev *hpdev,
 		return;
 	}
 	memset(&ctxt, 0, sizeof(ctxt));
-	int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message;
+	int_pkt = (struct pci_delete_interrupt *)ctxt.buffer;
 	int_pkt->message_type.type =
 		PCI_DELETE_INTERRUPT_MESSAGE;
 	int_pkt->wslot.slot = hpdev->desc.win_slot.slot;
@@ -2482,7 +2538,7 @@ static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus,
 	comp_pkt.hpdev = hpdev;
 	pkt.init_packet.compl_ctxt = &comp_pkt;
 	pkt.init_packet.completion_func = q_resource_requirements;
-	res_req = (struct pci_child_message *)&pkt.init_packet.message;
+	res_req = (struct pci_child_message *)pkt.buffer;
 	res_req->message_type.type = PCI_QUERY_RESOURCE_REQUIREMENTS;
 	res_req->wslot.slot = desc->win_slot.slot;
 
@@ -2860,7 +2916,7 @@ static void hv_eject_device_work(struct work_struct *work)
 		pci_destroy_slot(hpdev->pci_slot);
 
 	memset(&ctxt, 0, sizeof(ctxt));
-	ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message;
+	ejct_pkt = (struct pci_eject_response *)ctxt.buffer;
 	ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE;
 	ejct_pkt->wslot.slot = hpdev->desc.win_slot.slot;
 	vmbus_sendpacket(hbus->hdev->channel, ejct_pkt,
@@ -3118,7 +3174,7 @@ static int hv_pci_protocol_negotiation(struct hv_device *hdev,
 	init_completion(&comp_pkt.host_event);
 	pkt->completion_func = hv_pci_generic_compl;
 	pkt->compl_ctxt = &comp_pkt;
-	version_req = (struct pci_version_request *)&pkt->message;
+	version_req = (struct pci_version_request *)(pkt + 1);
 	version_req->message_type.type = PCI_QUERY_PROTOCOL_VERSION;
 
 	for (i = 0; i < num_version; i++) {
@@ -3340,7 +3396,7 @@ enter_d0_retry:
 	init_completion(&comp_pkt.host_event);
 	pkt->completion_func = hv_pci_generic_compl;
 	pkt->compl_ctxt = &comp_pkt;
-	d0_entry = (struct pci_bus_d0_entry *)&pkt->message;
+	d0_entry = (struct pci_bus_d0_entry *)(pkt + 1);
 	d0_entry->message_type.type = PCI_BUS_D0ENTRY;
 	d0_entry->mmio_base = hbus->mem_config->start;
 
@@ -3498,20 +3554,20 @@ static int hv_send_resources_allocated(struct hv_device *hdev)
 
 		if (hbus->protocol_version < PCI_PROTOCOL_VERSION_1_2) {
 			res_assigned =
-				(struct pci_resources_assigned *)&pkt->message;
+				(struct pci_resources_assigned *)(pkt + 1);
 			res_assigned->message_type.type =
 				PCI_RESOURCES_ASSIGNED;
 			res_assigned->wslot.slot = hpdev->desc.win_slot.slot;
 		} else {
 			res_assigned2 =
-				(struct pci_resources_assigned2 *)&pkt->message;
+				(struct pci_resources_assigned2 *)(pkt + 1);
 			res_assigned2->message_type.type =
 				PCI_RESOURCES_ASSIGNED2;
 			res_assigned2->wslot.slot = hpdev->desc.win_slot.slot;
 		}
 		put_pcichild(hpdev);
 
-		ret = vmbus_sendpacket(hdev->channel, &pkt->message,
+		ret = vmbus_sendpacket(hdev->channel, pkt + 1,
 				size_res, (unsigned long)pkt,
 				VM_PKT_DATA_INBAND,
 				VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
@@ -3809,6 +3865,7 @@ static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs)
 		struct pci_packet teardown_packet;
 		u8 buffer[sizeof(struct pci_message)];
 	} pkt;
+	struct pci_message *msg;
 	struct hv_pci_compl comp_pkt;
 	struct hv_pci_dev *hpdev, *tmp;
 	unsigned long flags;
@@ -3854,10 +3911,10 @@ static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs)
 	init_completion(&comp_pkt.host_event);
 	pkt.teardown_packet.completion_func = hv_pci_generic_compl;
 	pkt.teardown_packet.compl_ctxt = &comp_pkt;
-	pkt.teardown_packet.message[0].type = PCI_BUS_D0EXIT;
+	msg = (struct pci_message *)pkt.buffer;
+	msg->type = PCI_BUS_D0EXIT;
 
-	ret = vmbus_sendpacket_getid(chan, &pkt.teardown_packet.message,
-				     sizeof(struct pci_message),
+	ret = vmbus_sendpacket_getid(chan, msg, sizeof(*msg),
 				     (unsigned long)&pkt.teardown_packet,
 				     &trans_id, VM_PKT_DATA_INBAND,
 				     VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index 60da24ba0a19..a4a2bac4f4b2 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -1179,37 +1179,29 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn,
 			      unsigned int *tgt,
 			      unsigned int *attr)
 {
-	const int na = 3, ns = 2;
-	const __be32 *range;
-	int rlen, nranges, rangesz, pna, i;
+	struct of_range range;
+	struct of_range_parser parser;
 
 	*tgt = -1;
 	*attr = -1;
 
-	range = of_get_property(np, "ranges", &rlen);
-	if (!range)
+	if (of_pci_range_parser_init(&parser, np))
 		return -EINVAL;
 
-	pna = of_n_addr_cells(np);
-	rangesz = pna + na + ns;
-	nranges = rlen / sizeof(__be32) / rangesz;
-
-	for (i = 0; i < nranges; i++, range += rangesz) {
-		u32 flags = of_read_number(range, 1);
-		u32 slot = of_read_number(range + 1, 1);
-		u64 cpuaddr = of_read_number(range + na, pna);
+	for_each_of_range(&parser, &range) {
 		unsigned long rtype;
+		u32 slot = upper_32_bits(range.bus_addr);
 
-		if (DT_FLAGS_TO_TYPE(flags) == DT_TYPE_IO)
+		if (DT_FLAGS_TO_TYPE(range.flags) == DT_TYPE_IO)
 			rtype = IORESOURCE_IO;
-		else if (DT_FLAGS_TO_TYPE(flags) == DT_TYPE_MEM32)
+		else if (DT_FLAGS_TO_TYPE(range.flags) == DT_TYPE_MEM32)
 			rtype = IORESOURCE_MEM;
 		else
 			continue;
 
 		if (slot == PCI_SLOT(devfn) && type == rtype) {
-			*tgt = DT_CPUADDR_TO_TARGET(cpuaddr);
-			*attr = DT_CPUADDR_TO_ATTR(cpuaddr);
+			*tgt = DT_CPUADDR_TO_TARGET(range.cpu_addr);
+			*attr = DT_CPUADDR_TO_ATTR(range.cpu_addr);
 			return 0;
 		}
 	}
diff --git a/drivers/pci/controller/pci-thunder-ecam.c b/drivers/pci/controller/pci-thunder-ecam.c
index 08161065a89c..b5b4a958e6a2 100644
--- a/drivers/pci/controller/pci-thunder-ecam.c
+++ b/drivers/pci/controller/pci-thunder-ecam.c
@@ -11,6 +11,8 @@
 #include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
 
+#include "pci-host-common.h"
+
 #if defined(CONFIG_PCI_HOST_THUNDER_ECAM) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS))
 
 static void set_val(u32 v, int where, int size, u32 *val)
diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c
index f1bd5de67997..5fa037fb61dc 100644
--- a/drivers/pci/controller/pci-thunder-pem.c
+++ b/drivers/pci/controller/pci-thunder-pem.c
@@ -14,6 +14,7 @@
 #include <linux/platform_device.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include "../pci.h"
+#include "pci-host-common.h"
 
 #if defined(CONFIG_PCI_HOST_THUNDER_PEM) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS))
 
diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c
index 3d412a931774..77fe73976654 100644
--- a/drivers/pci/controller/pcie-apple.c
+++ b/drivers/pci/controller/pcie-apple.c
@@ -18,6 +18,7 @@
  * Author: Marc Zyngier <maz@kernel.org>
  */
 
+#include <linux/bitfield.h>
 #include <linux/gpio/consumer.h>
 #include <linux/kernel.h>
 #include <linux/iopoll.h>
@@ -30,6 +31,9 @@
 #include <linux/of_irq.h>
 #include <linux/pci-ecam.h>
 
+#include "pci-host-common.h"
+
+/* T8103 (original M1) and related SoCs */
 #define CORE_RC_PHYIF_CTL		0x00024
 #define   CORE_RC_PHYIF_CTL_RUN		BIT(0)
 #define CORE_RC_PHYIF_STAT		0x00028
@@ -40,14 +44,18 @@
 #define   CORE_RC_STAT_READY		BIT(0)
 #define CORE_FABRIC_STAT		0x04000
 #define   CORE_FABRIC_STAT_MASK		0x001F001F
-#define CORE_LANE_CFG(port)		(0x84000 + 0x4000 * (port))
-#define   CORE_LANE_CFG_REFCLK0REQ	BIT(0)
-#define   CORE_LANE_CFG_REFCLK1REQ	BIT(1)
-#define   CORE_LANE_CFG_REFCLK0ACK	BIT(2)
-#define   CORE_LANE_CFG_REFCLK1ACK	BIT(3)
-#define   CORE_LANE_CFG_REFCLKEN	(BIT(9) | BIT(10))
-#define CORE_LANE_CTL(port)		(0x84004 + 0x4000 * (port))
-#define   CORE_LANE_CTL_CFGACC		BIT(15)
+
+#define CORE_PHY_DEFAULT_BASE(port)	(0x84000 + 0x4000 * (port))
+
+#define PHY_LANE_CFG			0x00000
+#define   PHY_LANE_CFG_REFCLK0REQ	BIT(0)
+#define   PHY_LANE_CFG_REFCLK1REQ	BIT(1)
+#define   PHY_LANE_CFG_REFCLK0ACK	BIT(2)
+#define   PHY_LANE_CFG_REFCLK1ACK	BIT(3)
+#define   PHY_LANE_CFG_REFCLKEN		(BIT(9) | BIT(10))
+#define   PHY_LANE_CFG_REFCLKCGEN	(BIT(30) | BIT(31))
+#define PHY_LANE_CTL			0x00004
+#define   PHY_LANE_CTL_CFGACC		BIT(15)
 
 #define PORT_LTSSMCTL			0x00080
 #define   PORT_LTSSMCTL_START		BIT(0)
@@ -101,7 +109,7 @@
 #define   PORT_REFCLK_CGDIS		BIT(8)
 #define PORT_PERST			0x00814
 #define   PORT_PERST_OFF		BIT(0)
-#define PORT_RID2SID(i16)		(0x00828 + 4 * (i16))
+#define PORT_RID2SID			0x00828
 #define   PORT_RID2SID_VALID		BIT(31)
 #define   PORT_RID2SID_SID_SHIFT	16
 #define   PORT_RID2SID_BUS_SHIFT	8
@@ -119,7 +127,15 @@
 #define   PORT_TUNSTAT_PERST_ACK_PEND	BIT(1)
 #define PORT_PREFMEM_ENABLE		0x00994
 
-#define MAX_RID2SID			64
+/* T602x (M2-pro and co) */
+#define PORT_T602X_MSIADDR	0x016c
+#define PORT_T602X_MSIADDR_HI	0x0170
+#define PORT_T602X_PERST	0x082c
+#define PORT_T602X_RID2SID	0x3000
+#define PORT_T602X_MSIMAP	0x3800
+
+#define PORT_MSIMAP_ENABLE	BIT(31)
+#define PORT_MSIMAP_TARGET	GENMASK(7, 0)
 
 /*
  * The doorbell address is set to 0xfffff000, which by convention
@@ -130,10 +146,45 @@
  */
 #define DOORBELL_ADDR		CONFIG_PCIE_APPLE_MSI_DOORBELL_ADDR
 
+struct hw_info {
+	u32 phy_lane_ctl;
+	u32 port_msiaddr;
+	u32 port_msiaddr_hi;
+	u32 port_refclk;
+	u32 port_perst;
+	u32 port_rid2sid;
+	u32 port_msimap;
+	u32 max_rid2sid;
+};
+
+static const struct hw_info t8103_hw = {
+	.phy_lane_ctl		= PHY_LANE_CTL,
+	.port_msiaddr		= PORT_MSIADDR,
+	.port_msiaddr_hi	= 0,
+	.port_refclk		= PORT_REFCLK,
+	.port_perst		= PORT_PERST,
+	.port_rid2sid		= PORT_RID2SID,
+	.port_msimap		= 0,
+	.max_rid2sid		= 64,
+};
+
+static const struct hw_info t602x_hw = {
+	.phy_lane_ctl		= 0,
+	.port_msiaddr		= PORT_T602X_MSIADDR,
+	.port_msiaddr_hi	= PORT_T602X_MSIADDR_HI,
+	.port_refclk		= 0,
+	.port_perst		= PORT_T602X_PERST,
+	.port_rid2sid		= PORT_T602X_RID2SID,
+	.port_msimap		= PORT_T602X_MSIMAP,
+	/* 16 on t602x, guess for autodetect on future HW */
+	.max_rid2sid		= 512,
+};
+
 struct apple_pcie {
 	struct mutex		lock;
 	struct device		*dev;
 	void __iomem            *base;
+	const struct hw_info	*hw;
 	unsigned long		*bitmap;
 	struct list_head	ports;
 	struct completion	event;
@@ -142,12 +193,14 @@ struct apple_pcie {
 };
 
 struct apple_pcie_port {
+	raw_spinlock_t		lock;
 	struct apple_pcie	*pcie;
 	struct device_node	*np;
 	void __iomem		*base;
+	void __iomem		*phy;
 	struct irq_domain	*domain;
 	struct list_head	entry;
-	DECLARE_BITMAP(sid_map, MAX_RID2SID);
+	unsigned long		*sid_map;
 	int			sid_map_sz;
 	int			idx;
 };
@@ -233,14 +286,16 @@ static void apple_port_irq_mask(struct irq_data *data)
 {
 	struct apple_pcie_port *port = irq_data_get_irq_chip_data(data);
 
-	writel_relaxed(BIT(data->hwirq), port->base + PORT_INTMSKSET);
+	guard(raw_spinlock_irqsave)(&port->lock);
+	rmw_set(BIT(data->hwirq), port->base + PORT_INTMSK);
 }
 
 static void apple_port_irq_unmask(struct irq_data *data)
 {
 	struct apple_pcie_port *port = irq_data_get_irq_chip_data(data);
 
-	writel_relaxed(BIT(data->hwirq), port->base + PORT_INTMSKCLR);
+	guard(raw_spinlock_irqsave)(&port->lock);
+	rmw_clear(BIT(data->hwirq), port->base + PORT_INTMSK);
 }
 
 static bool hwirq_is_intx(unsigned int hwirq)
@@ -344,7 +399,9 @@ static void apple_port_irq_handler(struct irq_desc *desc)
 static int apple_pcie_port_setup_irq(struct apple_pcie_port *port)
 {
 	struct fwnode_handle *fwnode = &port->np->fwnode;
+	struct apple_pcie *pcie = port->pcie;
 	unsigned int irq;
+	u32 val = 0;
 
 	/* FIXME: consider moving each interrupt under each port */
 	irq = irq_of_parse_and_map(to_of_node(dev_fwnode(port->pcie->dev)),
@@ -359,20 +416,31 @@ static int apple_pcie_port_setup_irq(struct apple_pcie_port *port)
 		return -ENOMEM;
 
 	/* Disable all interrupts */
-	writel_relaxed(~0, port->base + PORT_INTMSKSET);
+	writel_relaxed(~0, port->base + PORT_INTMSK);
 	writel_relaxed(~0, port->base + PORT_INTSTAT);
+	writel_relaxed(~0, port->base + PORT_LINKCMDSTS);
 
 	irq_set_chained_handler_and_data(irq, apple_port_irq_handler, port);
 
 	/* Configure MSI base address */
 	BUILD_BUG_ON(upper_32_bits(DOORBELL_ADDR));
-	writel_relaxed(lower_32_bits(DOORBELL_ADDR), port->base + PORT_MSIADDR);
+	writel_relaxed(lower_32_bits(DOORBELL_ADDR),
+		       port->base + pcie->hw->port_msiaddr);
+	if (pcie->hw->port_msiaddr_hi)
+		writel_relaxed(0, port->base + pcie->hw->port_msiaddr_hi);
 
 	/* Enable MSIs, shared between all ports */
-	writel_relaxed(0, port->base + PORT_MSIBASE);
-	writel_relaxed((ilog2(port->pcie->nvecs) << PORT_MSICFG_L2MSINUM_SHIFT) |
-		       PORT_MSICFG_EN, port->base + PORT_MSICFG);
+	if (pcie->hw->port_msimap) {
+		for (int i = 0; i < pcie->nvecs; i++)
+			writel_relaxed(FIELD_PREP(PORT_MSIMAP_TARGET, i) |
+				       PORT_MSIMAP_ENABLE,
+				       port->base + pcie->hw->port_msimap + 4 * i);
+	} else {
+		writel_relaxed(0, port->base + PORT_MSIBASE);
+		val = ilog2(pcie->nvecs) << PORT_MSICFG_L2MSINUM_SHIFT;
+	}
 
+	writel_relaxed(val | PORT_MSICFG_EN, port->base + PORT_MSICFG);
 	return 0;
 }
 
@@ -439,43 +507,47 @@ static int apple_pcie_setup_refclk(struct apple_pcie *pcie,
 	u32 stat;
 	int res;
 
-	res = readl_relaxed_poll_timeout(pcie->base + CORE_RC_PHYIF_STAT, stat,
-					 stat & CORE_RC_PHYIF_STAT_REFCLK,
-					 100, 50000);
-	if (res < 0)
-		return res;
+	if (pcie->hw->phy_lane_ctl)
+		rmw_set(PHY_LANE_CTL_CFGACC, port->phy + pcie->hw->phy_lane_ctl);
 
-	rmw_set(CORE_LANE_CTL_CFGACC, pcie->base + CORE_LANE_CTL(port->idx));
-	rmw_set(CORE_LANE_CFG_REFCLK0REQ, pcie->base + CORE_LANE_CFG(port->idx));
+	rmw_set(PHY_LANE_CFG_REFCLK0REQ, port->phy + PHY_LANE_CFG);
 
-	res = readl_relaxed_poll_timeout(pcie->base + CORE_LANE_CFG(port->idx),
-					 stat, stat & CORE_LANE_CFG_REFCLK0ACK,
+	res = readl_relaxed_poll_timeout(port->phy + PHY_LANE_CFG,
+					 stat, stat & PHY_LANE_CFG_REFCLK0ACK,
 					 100, 50000);
 	if (res < 0)
 		return res;
 
-	rmw_set(CORE_LANE_CFG_REFCLK1REQ, pcie->base + CORE_LANE_CFG(port->idx));
-	res = readl_relaxed_poll_timeout(pcie->base + CORE_LANE_CFG(port->idx),
-					 stat, stat & CORE_LANE_CFG_REFCLK1ACK,
+	rmw_set(PHY_LANE_CFG_REFCLK1REQ, port->phy + PHY_LANE_CFG);
+	res = readl_relaxed_poll_timeout(port->phy + PHY_LANE_CFG,
+					 stat, stat & PHY_LANE_CFG_REFCLK1ACK,
 					 100, 50000);
 
 	if (res < 0)
 		return res;
 
-	rmw_clear(CORE_LANE_CTL_CFGACC, pcie->base + CORE_LANE_CTL(port->idx));
+	if (pcie->hw->phy_lane_ctl)
+		rmw_clear(PHY_LANE_CTL_CFGACC, port->phy + pcie->hw->phy_lane_ctl);
+
+	rmw_set(PHY_LANE_CFG_REFCLKEN, port->phy + PHY_LANE_CFG);
 
-	rmw_set(CORE_LANE_CFG_REFCLKEN, pcie->base + CORE_LANE_CFG(port->idx));
-	rmw_set(PORT_REFCLK_EN, port->base + PORT_REFCLK);
+	if (pcie->hw->port_refclk)
+		rmw_set(PORT_REFCLK_EN, port->base + pcie->hw->port_refclk);
 
 	return 0;
 }
 
+static void __iomem *port_rid2sid_addr(struct apple_pcie_port *port, int idx)
+{
+	return port->base + port->pcie->hw->port_rid2sid + 4 * idx;
+}
+
 static u32 apple_pcie_rid2sid_write(struct apple_pcie_port *port,
 				    int idx, u32 val)
 {
-	writel_relaxed(val, port->base + PORT_RID2SID(idx));
+	writel_relaxed(val, port_rid2sid_addr(port, idx));
 	/* Read back to ensure completion of the write */
-	return readl_relaxed(port->base + PORT_RID2SID(idx));
+	return readl_relaxed(port_rid2sid_addr(port, idx));
 }
 
 static int apple_pcie_setup_port(struct apple_pcie *pcie,
@@ -484,6 +556,8 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie,
 	struct platform_device *platform = to_platform_device(pcie->dev);
 	struct apple_pcie_port *port;
 	struct gpio_desc *reset;
+	struct resource *res;
+	char name[16];
 	u32 stat, idx;
 	int ret, i;
 
@@ -496,6 +570,10 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie,
 	if (!port)
 		return -ENOMEM;
 
+	port->sid_map = devm_bitmap_zalloc(pcie->dev, pcie->hw->max_rid2sid, GFP_KERNEL);
+	if (!port->sid_map)
+		return -ENOMEM;
+
 	ret = of_property_read_u32_index(np, "reg", 0, &idx);
 	if (ret)
 		return ret;
@@ -505,14 +583,28 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie,
 	port->pcie = pcie;
 	port->np = np;
 
-	port->base = devm_platform_ioremap_resource(platform, port->idx + 2);
+	raw_spin_lock_init(&port->lock);
+
+	snprintf(name, sizeof(name), "port%d", port->idx);
+	res = platform_get_resource_byname(platform, IORESOURCE_MEM, name);
+	if (!res)
+		res = platform_get_resource(platform, IORESOURCE_MEM, port->idx + 2);
+
+	port->base = devm_ioremap_resource(&platform->dev, res);
 	if (IS_ERR(port->base))
 		return PTR_ERR(port->base);
 
+	snprintf(name, sizeof(name), "phy%d", port->idx);
+	res = platform_get_resource_byname(platform, IORESOURCE_MEM, name);
+	if (res)
+		port->phy = devm_ioremap_resource(&platform->dev, res);
+	else
+		port->phy = pcie->base + CORE_PHY_DEFAULT_BASE(port->idx);
+
 	rmw_set(PORT_APPCLK_EN, port->base + PORT_APPCLK);
 
 	/* Assert PERST# before setting up the clock */
-	gpiod_set_value(reset, 1);
+	gpiod_set_value_cansleep(reset, 1);
 
 	ret = apple_pcie_setup_refclk(pcie, port);
 	if (ret < 0)
@@ -522,8 +614,8 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie,
 	usleep_range(100, 200);
 
 	/* Deassert PERST# */
-	rmw_set(PORT_PERST_OFF, port->base + PORT_PERST);
-	gpiod_set_value(reset, 0);
+	rmw_set(PORT_PERST_OFF, port->base + pcie->hw->port_perst);
+	gpiod_set_value_cansleep(reset, 0);
 
 	/* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */
 	msleep(100);
@@ -535,7 +627,11 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie,
 		return ret;
 	}
 
-	rmw_clear(PORT_REFCLK_CGDIS, port->base + PORT_REFCLK);
+	if (pcie->hw->port_refclk)
+		rmw_clear(PORT_REFCLK_CGDIS, port->base + pcie->hw->port_refclk);
+	else
+		rmw_set(PHY_LANE_CFG_REFCLKCGEN, port->phy + PHY_LANE_CFG);
+
 	rmw_clear(PORT_APPCLK_CGDIS, port->base + PORT_APPCLK);
 
 	ret = apple_pcie_port_setup_irq(port);
@@ -543,7 +639,7 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie,
 		return ret;
 
 	/* Reset all RID/SID mappings, and check for RAZ/WI registers */
-	for (i = 0; i < MAX_RID2SID; i++) {
+	for (i = 0; i < pcie->hw->max_rid2sid; i++) {
 		if (apple_pcie_rid2sid_write(port, i, 0xbad1d) != 0xbad1d)
 			break;
 		apple_pcie_rid2sid_write(port, i, 0);
@@ -556,6 +652,9 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie,
 	list_add_tail(&port->entry, &pcie->ports);
 	init_completion(&pcie->event);
 
+	/* In the success path, we keep a reference to np around */
+	of_node_get(np);
+
 	ret = apple_pcie_port_register_irqs(port);
 	WARN_ON(ret);
 
@@ -693,7 +792,7 @@ static void apple_pcie_disable_device(struct pci_host_bridge *bridge, struct pci
 	for_each_set_bit(idx, port->sid_map, port->sid_map_sz) {
 		u32 val;
 
-		val = readl_relaxed(port->base + PORT_RID2SID(idx));
+		val = readl_relaxed(port_rid2sid_addr(port, idx));
 		if ((val & 0xffff) == rid) {
 			apple_pcie_rid2sid_write(port, idx, 0);
 			bitmap_release_region(port->sid_map, idx, 0);
@@ -707,34 +806,14 @@ static void apple_pcie_disable_device(struct pci_host_bridge *bridge, struct pci
 
 static int apple_pcie_init(struct pci_config_window *cfg)
 {
+	struct apple_pcie *pcie = cfg->priv;
 	struct device *dev = cfg->parent;
-	struct platform_device *platform = to_platform_device(dev);
-	struct apple_pcie *pcie;
 	int ret;
 
-	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
-	if (!pcie)
-		return -ENOMEM;
-
-	pcie->dev = dev;
-
-	mutex_init(&pcie->lock);
-
-	pcie->base = devm_platform_ioremap_resource(platform, 1);
-	if (IS_ERR(pcie->base))
-		return PTR_ERR(pcie->base);
-
-	cfg->priv = pcie;
-	INIT_LIST_HEAD(&pcie->ports);
-
-	ret = apple_msi_init(pcie);
-	if (ret)
-		return ret;
-
-	for_each_child_of_node_scoped(dev->of_node, of_port) {
+	for_each_available_child_of_node_scoped(dev->of_node, of_port) {
 		ret = apple_pcie_setup_port(pcie, of_port);
 		if (ret) {
-			dev_err(pcie->dev, "Port %pOF setup fail: %d\n", of_port, ret);
+			dev_err(dev, "Port %pOF setup fail: %d\n", of_port, ret);
 			return ret;
 		}
 	}
@@ -753,14 +832,44 @@ static const struct pci_ecam_ops apple_pcie_cfg_ecam_ops = {
 	}
 };
 
+static int apple_pcie_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct apple_pcie *pcie;
+	int ret;
+
+	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
+	if (!pcie)
+		return -ENOMEM;
+
+	pcie->dev = dev;
+	pcie->hw = of_device_get_match_data(dev);
+	if (!pcie->hw)
+		return -ENODEV;
+	pcie->base = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(pcie->base))
+		return PTR_ERR(pcie->base);
+
+	mutex_init(&pcie->lock);
+	INIT_LIST_HEAD(&pcie->ports);
+	dev_set_drvdata(dev, pcie);
+
+	ret = apple_msi_init(pcie);
+	if (ret)
+		return ret;
+
+	return pci_host_common_init(pdev, &apple_pcie_cfg_ecam_ops);
+}
+
 static const struct of_device_id apple_pcie_of_match[] = {
-	{ .compatible = "apple,pcie", .data = &apple_pcie_cfg_ecam_ops },
+	{ .compatible = "apple,t6020-pcie",	.data = &t602x_hw },
+	{ .compatible = "apple,pcie",		.data = &t8103_hw },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, apple_pcie_of_match);
 
 static struct platform_driver apple_pcie_driver = {
-	.probe	= pci_host_common_probe,
+	.probe	= apple_pcie_probe,
 	.driver	= {
 		.name			= "pcie-apple",
 		.of_match_table		= apple_pcie_of_match,
diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c
index c5e0d025bc43..a8a966844cf3 100644
--- a/drivers/pci/controller/pcie-rcar-ep.c
+++ b/drivers/pci/controller/pcie-rcar-ep.c
@@ -256,15 +256,15 @@ static void rcar_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn,
 	clear_bit(atu_index + 1, ep->ib_window_map);
 }
 
-static int rcar_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn,
-				u8 interrupts)
+static int rcar_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 nr_irqs)
 {
 	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
 	struct rcar_pcie *pcie = &ep->pcie;
+	u8 mmc = order_base_2(nr_irqs);
 	u32 flags;
 
 	flags = rcar_pci_read_reg(pcie, MSICAP(fn));
-	flags |= interrupts << MSICAP0_MMESCAP_OFFSET;
+	flags |= mmc << MSICAP0_MMESCAP_OFFSET;
 	rcar_pci_write_reg(pcie, flags, MSICAP(fn));
 
 	return 0;
@@ -280,7 +280,7 @@ static int rcar_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn)
 	if (!(flags & MSICAP0_MSIE))
 		return -EINVAL;
 
-	return ((flags & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET);
+	return 1 << ((flags & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET);
 }
 
 static int rcar_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn,
diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 85ea36df2f59..55416b8311dd 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -308,10 +308,11 @@ static void rockchip_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn,
 }
 
 static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn,
-				    u8 multi_msg_cap)
+				    u8 nr_irqs)
 {
 	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
 	struct rockchip_pcie *rockchip = &ep->rockchip;
+	u8 mmc = order_base_2(nr_irqs);
 	u32 flags;
 
 	flags = rockchip_pcie_read(rockchip,
@@ -319,7 +320,7 @@ static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn,
 				   ROCKCHIP_PCIE_EP_MSI_CTRL_REG);
 	flags &= ~ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_MASK;
 	flags |=
-	   (multi_msg_cap << ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET) |
+	   (mmc << ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET) |
 	   (PCI_MSI_FLAGS_64BIT << ROCKCHIP_PCIE_EP_MSI_FLAGS_OFFSET);
 	flags &= ~ROCKCHIP_PCIE_EP_MSI_CTRL_MASK_MSI_CAP;
 	rockchip_pcie_write(rockchip, flags,
@@ -340,8 +341,8 @@ static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn)
 	if (!(flags & ROCKCHIP_PCIE_EP_MSI_CTRL_ME))
 		return -EINVAL;
 
-	return ((flags & ROCKCHIP_PCIE_EP_MSI_CTRL_MME_MASK) >>
-			ROCKCHIP_PCIE_EP_MSI_CTRL_MME_OFFSET);
+	return 1 << ((flags & ROCKCHIP_PCIE_EP_MSI_CTRL_MME_MASK) >>
+		     ROCKCHIP_PCIE_EP_MSI_CTRL_MME_OFFSET);
 }
 
 static void rockchip_pcie_ep_assert_intx(struct rockchip_pcie_ep *ep, u8 fn,
@@ -694,6 +695,7 @@ static const struct pci_epc_features rockchip_pcie_epc_features = {
 	.linkup_notifier = true,
 	.msi_capable = true,
 	.msix_capable = false,
+	.intx_capable = true,
 	.align = ROCKCHIP_PCIE_AT_SIZE_ALIGN,
 };
 
diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h
index 14954f43e5e9..5864a20323f2 100644
--- a/drivers/pci/controller/pcie-rockchip.h
+++ b/drivers/pci/controller/pcie-rockchip.h
@@ -319,11 +319,12 @@ static const char * const rockchip_pci_pm_rsts[] = {
 	"aclk",
 };
 
+/* NOTE: Do not reorder the deassert sequence of the following reset pins */
 static const char * const rockchip_pci_core_rsts[] = {
-	"mgmt-sticky",
-	"core",
-	"mgmt",
 	"pipe",
+	"mgmt",
+	"core",
+	"mgmt-sticky",
 };
 
 struct rockchip_pcie {
diff --git a/drivers/pci/controller/plda/pcie-microchip-host.c b/drivers/pci/controller/plda/pcie-microchip-host.c
index 3fdfffdf0270..24bbf93b8051 100644
--- a/drivers/pci/controller/plda/pcie-microchip-host.c
+++ b/drivers/pci/controller/plda/pcie-microchip-host.c
@@ -23,6 +23,7 @@
 #include <linux/wordpart.h>
 
 #include "../../pci.h"
+#include "../pci-host-common.h"
 #include "pcie-plda.h"
 
 #define MC_MAX_NUM_INBOUND_WINDOWS		8
diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c
index 73047316889e..9f4190501395 100644
--- a/drivers/pci/devres.c
+++ b/drivers/pci/devres.c
@@ -6,30 +6,13 @@
 /*
  * On the state of PCI's devres implementation:
  *
- * The older devres API for PCI has two significant problems:
+ * The older PCI devres API has one significant problem:
  *
- * 1. It is very strongly tied to the statically allocated mapping table in
- *    struct pcim_iomap_devres below. This is mostly solved in the sense of the
- *    pcim_ functions in this file providing things like ranged mapping by
- *    bypassing this table, whereas the functions that were present in the old
- *    API still enter the mapping addresses into the table for users of the old
- *    API.
- *
- * 2. The region-request-functions in pci.c do become managed IF the device has
- *    been enabled with pcim_enable_device() instead of pci_enable_device().
- *    This resulted in the API becoming inconsistent: Some functions have an
- *    obviously managed counter-part (e.g., pci_iomap() <-> pcim_iomap()),
- *    whereas some don't and are never managed, while others don't and are
- *    _sometimes_ managed (e.g. pci_request_region()).
- *
- *    Consequently, in the new API, region requests performed by the pcim_
- *    functions are automatically cleaned up through the devres callback
- *    pcim_addr_resource_release().
- *
- *    Users of pcim_enable_device() + pci_*region*() are redirected in
- *    pci.c to the managed functions here in this file. This isn't exactly
- *    perfect, but the only alternative way would be to port ALL drivers
- *    using said combination to pcim_ functions.
+ * It is very strongly tied to the statically allocated mapping table in struct
+ * pcim_iomap_devres below. This is mostly solved in the sense of the pcim_
+ * functions in this file providing things like ranged mapping by bypassing
+ * this table, whereas the functions that were present in the old API still
+ * enter the mapping addresses into the table for users of the old API.
  *
  * TODO:
  * Remove the legacy table entirely once all calls to pcim_iomap_table() in
@@ -87,104 +70,6 @@ static inline void pcim_addr_devres_clear(struct pcim_addr_devres *res)
 	res->bar = -1;
 }
 
-/*
- * The following functions, __pcim_*_region*, exist as counterparts to the
- * versions from pci.c - which, unfortunately, can be in "hybrid mode", i.e.,
- * sometimes managed, sometimes not.
- *
- * To separate the APIs cleanly, we define our own, simplified versions here.
- */
-
-/**
- * __pcim_request_region_range - Request a ranged region
- * @pdev: PCI device the region belongs to
- * @bar: BAR the range is within
- * @offset: offset from the BAR's start address
- * @maxlen: length in bytes, beginning at @offset
- * @name: name of the driver requesting the resource
- * @req_flags: flags for the request, e.g., for kernel-exclusive requests
- *
- * Returns: 0 on success, a negative error code on failure.
- *
- * Request a range within a device's PCI BAR.  Sanity check the input.
- */
-static int __pcim_request_region_range(struct pci_dev *pdev, int bar,
-				       unsigned long offset,
-				       unsigned long maxlen,
-				       const char *name, int req_flags)
-{
-	resource_size_t start = pci_resource_start(pdev, bar);
-	resource_size_t len = pci_resource_len(pdev, bar);
-	unsigned long dev_flags = pci_resource_flags(pdev, bar);
-
-	if (start == 0 || len == 0) /* Unused BAR. */
-		return 0;
-	if (len <= offset)
-		return -EINVAL;
-
-	start += offset;
-	len -= offset;
-
-	if (len > maxlen && maxlen != 0)
-		len = maxlen;
-
-	if (dev_flags & IORESOURCE_IO) {
-		if (!request_region(start, len, name))
-			return -EBUSY;
-	} else if (dev_flags & IORESOURCE_MEM) {
-		if (!__request_mem_region(start, len, name, req_flags))
-			return -EBUSY;
-	} else {
-		/* That's not a device we can request anything on. */
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
-static void __pcim_release_region_range(struct pci_dev *pdev, int bar,
-					unsigned long offset,
-					unsigned long maxlen)
-{
-	resource_size_t start = pci_resource_start(pdev, bar);
-	resource_size_t len = pci_resource_len(pdev, bar);
-	unsigned long flags = pci_resource_flags(pdev, bar);
-
-	if (len <= offset || start == 0)
-		return;
-
-	if (len == 0 || maxlen == 0) /* This an unused BAR. Do nothing. */
-		return;
-
-	start += offset;
-	len -= offset;
-
-	if (len > maxlen)
-		len = maxlen;
-
-	if (flags & IORESOURCE_IO)
-		release_region(start, len);
-	else if (flags & IORESOURCE_MEM)
-		release_mem_region(start, len);
-}
-
-static int __pcim_request_region(struct pci_dev *pdev, int bar,
-				 const char *name, int flags)
-{
-	unsigned long offset = 0;
-	unsigned long len = pci_resource_len(pdev, bar);
-
-	return __pcim_request_region_range(pdev, bar, offset, len, name, flags);
-}
-
-static void __pcim_release_region(struct pci_dev *pdev, int bar)
-{
-	unsigned long offset = 0;
-	unsigned long len = pci_resource_len(pdev, bar);
-
-	__pcim_release_region_range(pdev, bar, offset, len);
-}
-
 static void pcim_addr_resource_release(struct device *dev, void *resource_raw)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -192,11 +77,11 @@ static void pcim_addr_resource_release(struct device *dev, void *resource_raw)
 
 	switch (res->type) {
 	case PCIM_ADDR_DEVRES_TYPE_REGION:
-		__pcim_release_region(pdev, res->bar);
+		pci_release_region(pdev, res->bar);
 		break;
 	case PCIM_ADDR_DEVRES_TYPE_REGION_MAPPING:
 		pci_iounmap(pdev, res->baseaddr);
-		__pcim_release_region(pdev, res->bar);
+		pci_release_region(pdev, res->bar);
 		break;
 	case PCIM_ADDR_DEVRES_TYPE_MAPPING:
 		pci_iounmap(pdev, res->baseaddr);
@@ -735,7 +620,7 @@ void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar,
 	res->type = PCIM_ADDR_DEVRES_TYPE_REGION_MAPPING;
 	res->bar = bar;
 
-	ret = __pcim_request_region(pdev, bar, name, 0);
+	ret = pci_request_region(pdev, bar, name);
 	if (ret != 0)
 		goto err_region;
 
@@ -749,7 +634,7 @@ void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar,
 	return res->baseaddr;
 
 err_iomap:
-	__pcim_release_region(pdev, bar);
+	pci_release_region(pdev, bar);
 err_region:
 	pcim_addr_devres_free(res);
 
@@ -823,8 +708,20 @@ err:
 }
 EXPORT_SYMBOL(pcim_iomap_regions);
 
-static int _pcim_request_region(struct pci_dev *pdev, int bar, const char *name,
-				int request_flags)
+/**
+ * pcim_request_region - Request a PCI BAR
+ * @pdev: PCI device to request region for
+ * @bar: Index of BAR to request
+ * @name: Name of the driver requesting the resource
+ *
+ * Returns: 0 on success, a negative error code on failure.
+ *
+ * Request region specified by @bar.
+ *
+ * The region will automatically be released on driver detach. If desired,
+ * release manually only with pcim_release_region().
+ */
+int pcim_request_region(struct pci_dev *pdev, int bar, const char *name)
 {
 	int ret;
 	struct pcim_addr_devres *res;
@@ -838,7 +735,7 @@ static int _pcim_request_region(struct pci_dev *pdev, int bar, const char *name,
 	res->type = PCIM_ADDR_DEVRES_TYPE_REGION;
 	res->bar = bar;
 
-	ret = __pcim_request_region(pdev, bar, name, request_flags);
+	ret = pci_request_region(pdev, bar, name);
 	if (ret != 0) {
 		pcim_addr_devres_free(res);
 		return ret;
@@ -847,45 +744,9 @@ static int _pcim_request_region(struct pci_dev *pdev, int bar, const char *name,
 	devres_add(&pdev->dev, res);
 	return 0;
 }
-
-/**
- * pcim_request_region - Request a PCI BAR
- * @pdev: PCI device to request region for
- * @bar: Index of BAR to request
- * @name: Name of the driver requesting the resource
- *
- * Returns: 0 on success, a negative error code on failure.
- *
- * Request region specified by @bar.
- *
- * The region will automatically be released on driver detach. If desired,
- * release manually only with pcim_release_region().
- */
-int pcim_request_region(struct pci_dev *pdev, int bar, const char *name)
-{
-	return _pcim_request_region(pdev, bar, name, 0);
-}
 EXPORT_SYMBOL(pcim_request_region);
 
 /**
- * pcim_request_region_exclusive - Request a PCI BAR exclusively
- * @pdev: PCI device to request region for
- * @bar: Index of BAR to request
- * @name: Name of the driver requesting the resource
- *
- * Returns: 0 on success, a negative error code on failure.
- *
- * Request region specified by @bar exclusively.
- *
- * The region will automatically be released on driver detach. If desired,
- * release manually only with pcim_release_region().
- */
-int pcim_request_region_exclusive(struct pci_dev *pdev, int bar, const char *name)
-{
-	return _pcim_request_region(pdev, bar, name, IORESOURCE_EXCLUSIVE);
-}
-
-/**
  * pcim_release_region - Release a PCI BAR
  * @pdev: PCI device to operate on
  * @bar: Index of BAR to release
@@ -893,7 +754,7 @@ int pcim_request_region_exclusive(struct pci_dev *pdev, int bar, const char *nam
  * Release a region manually that was previously requested by
  * pcim_request_region().
  */
-void pcim_release_region(struct pci_dev *pdev, int bar)
+static void pcim_release_region(struct pci_dev *pdev, int bar)
 {
 	struct pcim_addr_devres res_searched;
 
@@ -956,30 +817,6 @@ err:
 EXPORT_SYMBOL(pcim_request_all_regions);
 
 /**
- * pcim_iounmap_regions - Unmap and release PCI BARs (DEPRECATED)
- * @pdev: PCI device to map IO resources for
- * @mask: Mask of BARs to unmap and release
- *
- * Unmap and release regions specified by @mask.
- *
- * This function is DEPRECATED. Do not use it in new code.
- * Use pcim_iounmap_region() instead.
- */
-void pcim_iounmap_regions(struct pci_dev *pdev, int mask)
-{
-	int i;
-
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		if (!mask_contains_bar(mask, i))
-			continue;
-
-		pcim_iounmap_region(pdev, i);
-		pcim_remove_bar_from_legacy_table(pdev, i);
-	}
-}
-EXPORT_SYMBOL(pcim_iounmap_regions);
-
-/**
  * pcim_iomap_range - Create a ranged __iomap mapping within a PCI BAR
  * @pdev: PCI device to map IO resources for
  * @bar: Index of the BAR
diff --git a/drivers/pci/ecam.c b/drivers/pci/ecam.c
index 260b7de2dbd5..2c5e6446e00e 100644
--- a/drivers/pci/ecam.c
+++ b/drivers/pci/ecam.c
@@ -84,6 +84,8 @@ struct pci_config_window *pci_ecam_create(struct device *dev,
 			goto err_exit_iomap;
 	}
 
+	cfg->priv = dev_get_drvdata(dev);
+
 	if (ops->init) {
 		err = ops->init(cfg);
 		if (err)
diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
index 874cb097b093..e4da3fdb0007 100644
--- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
@@ -408,11 +408,9 @@ static void epf_ntb_config_spad_bar_free(struct epf_ntb *ntb)
  */
 static int epf_ntb_config_spad_bar_alloc(struct epf_ntb *ntb)
 {
-	size_t align;
 	enum pci_barno barno;
 	struct epf_ntb_ctrl *ctrl;
 	u32 spad_size, ctrl_size;
-	u64 size;
 	struct pci_epf *epf = ntb->epf;
 	struct device *dev = &epf->dev;
 	u32 spad_count;
@@ -422,31 +420,13 @@ static int epf_ntb_config_spad_bar_alloc(struct epf_ntb *ntb)
 								epf->func_no,
 								epf->vfunc_no);
 	barno = ntb->epf_ntb_bar[BAR_CONFIG];
-	size = epc_features->bar[barno].fixed_size;
-	align = epc_features->align;
-
-	if ((!IS_ALIGNED(size, align)))
-		return -EINVAL;
-
 	spad_count = ntb->spad_count;
 
-	ctrl_size = sizeof(struct epf_ntb_ctrl);
+	ctrl_size = ALIGN(sizeof(struct epf_ntb_ctrl), sizeof(u32));
 	spad_size = 2 * spad_count * sizeof(u32);
 
-	if (!align) {
-		ctrl_size = roundup_pow_of_two(ctrl_size);
-		spad_size = roundup_pow_of_two(spad_size);
-	} else {
-		ctrl_size = ALIGN(ctrl_size, align);
-		spad_size = ALIGN(spad_size, align);
-	}
-
-	if (!size)
-		size = ctrl_size + spad_size;
-	else if (size < ctrl_size + spad_size)
-		return -EINVAL;
-
-	base = pci_epf_alloc_space(epf, size, barno, epc_features, 0);
+	base = pci_epf_alloc_space(epf, ctrl_size + spad_size,
+				   barno, epc_features, 0);
 	if (!base) {
 		dev_err(dev, "Config/Status/SPAD alloc region fail\n");
 		return -ENOMEM;
diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index beabea00af91..ca7f19cc973a 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -293,8 +293,6 @@ int pci_epc_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 	if (interrupt < 0)
 		return 0;
 
-	interrupt = 1 << interrupt;
-
 	return interrupt;
 }
 EXPORT_SYMBOL_GPL(pci_epc_get_msi);
@@ -304,28 +302,25 @@ EXPORT_SYMBOL_GPL(pci_epc_get_msi);
  * @epc: the EPC device on which MSI has to be configured
  * @func_no: the physical endpoint function number in the EPC device
  * @vfunc_no: the virtual endpoint function number in the physical function
- * @interrupts: number of MSI interrupts required by the EPF
+ * @nr_irqs: number of MSI interrupts required by the EPF
  *
  * Invoke to set the required number of MSI interrupts.
  */
-int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u8 interrupts)
+int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u8 nr_irqs)
 {
 	int ret;
-	u8 encode_int;
 
 	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return -EINVAL;
 
-	if (interrupts < 1 || interrupts > 32)
+	if (nr_irqs < 1 || nr_irqs > 32)
 		return -EINVAL;
 
 	if (!epc->ops->set_msi)
 		return 0;
 
-	encode_int = order_base_2(interrupts);
-
 	mutex_lock(&epc->lock);
-	ret = epc->ops->set_msi(epc, func_no, vfunc_no, encode_int);
+	ret = epc->ops->set_msi(epc, func_no, vfunc_no, nr_irqs);
 	mutex_unlock(&epc->lock);
 
 	return ret;
@@ -357,7 +352,7 @@ int pci_epc_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 	if (interrupt < 0)
 		return 0;
 
-	return interrupt + 1;
+	return interrupt;
 }
 EXPORT_SYMBOL_GPL(pci_epc_get_msix);
 
@@ -366,29 +361,28 @@ EXPORT_SYMBOL_GPL(pci_epc_get_msix);
  * @epc: the EPC device on which MSI-X has to be configured
  * @func_no: the physical endpoint function number in the EPC device
  * @vfunc_no: the virtual endpoint function number in the physical function
- * @interrupts: number of MSI-X interrupts required by the EPF
+ * @nr_irqs: number of MSI-X interrupts required by the EPF
  * @bir: BAR where the MSI-X table resides
  * @offset: Offset pointing to the start of MSI-X table
  *
  * Invoke to set the required number of MSI-X interrupts.
  */
-int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-		     u16 interrupts, enum pci_barno bir, u32 offset)
+int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u16 nr_irqs,
+		     enum pci_barno bir, u32 offset)
 {
 	int ret;
 
 	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return -EINVAL;
 
-	if (interrupts < 1 || interrupts > 2048)
+	if (nr_irqs < 1 || nr_irqs > 2048)
 		return -EINVAL;
 
 	if (!epc->ops->set_msix)
 		return 0;
 
 	mutex_lock(&epc->lock);
-	ret = epc->ops->set_msix(epc, func_no, vfunc_no, interrupts - 1, bir,
-				 offset);
+	ret = epc->ops->set_msix(epc, func_no, vfunc_no, nr_irqs, bir, offset);
 	mutex_unlock(&epc->lock);
 
 	return ret;
diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c
index 394395c7f8de..577a9e490115 100644
--- a/drivers/pci/endpoint/pci-epf-core.c
+++ b/drivers/pci/endpoint/pci-epf-core.c
@@ -236,12 +236,13 @@ void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar,
 	}
 
 	dev = epc->dev.parent;
-	dma_free_coherent(dev, epf_bar[bar].size, addr,
+	dma_free_coherent(dev, epf_bar[bar].aligned_size, addr,
 			  epf_bar[bar].phys_addr);
 
 	epf_bar[bar].phys_addr = 0;
 	epf_bar[bar].addr = NULL;
 	epf_bar[bar].size = 0;
+	epf_bar[bar].aligned_size = 0;
 	epf_bar[bar].barno = 0;
 	epf_bar[bar].flags = 0;
 }
@@ -264,7 +265,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 			  enum pci_epc_interface_type type)
 {
 	u64 bar_fixed_size = epc_features->bar[bar].fixed_size;
-	size_t align = epc_features->align;
+	size_t aligned_size, align = epc_features->align;
 	struct pci_epf_bar *epf_bar;
 	dma_addr_t phys_addr;
 	struct pci_epc *epc;
@@ -285,12 +286,18 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 			return NULL;
 		}
 		size = bar_fixed_size;
+	} else {
+		/* BAR size must be power of two */
+		size = roundup_pow_of_two(size);
 	}
 
-	if (align)
-		size = ALIGN(size, align);
-	else
-		size = roundup_pow_of_two(size);
+	/*
+	 * Allocate enough memory to accommodate the iATU alignment
+	 * requirement.  In most cases, this will be the same as .size but
+	 * it might be different if, for example, the fixed size of a BAR
+	 * is smaller than align.
+	 */
+	aligned_size = align ? ALIGN(size, align) : size;
 
 	if (type == PRIMARY_INTERFACE) {
 		epc = epf->epc;
@@ -301,7 +308,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 	}
 
 	dev = epc->dev.parent;
-	space = dma_alloc_coherent(dev, size, &phys_addr, GFP_KERNEL);
+	space = dma_alloc_coherent(dev, aligned_size, &phys_addr, GFP_KERNEL);
 	if (!space) {
 		dev_err(dev, "failed to allocate mem space\n");
 		return NULL;
@@ -310,6 +317,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 	epf_bar[bar].phys_addr = phys_addr;
 	epf_bar[bar].addr = space;
 	epf_bar[bar].size = size;
+	epf_bar[bar].aligned_size = aligned_size;
 	epf_bar[bar].barno = bar;
 	if (upper_32_bits(size) || epc_features->bar[bar].only_64bit)
 		epf_bar[bar].flags |= PCI_BASE_ADDRESS_MEM_TYPE_64;
diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index d30f1316c98e..fadcf98a8a66 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -20,13 +20,9 @@
 #include <linux/types.h>
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
-#include <linux/pagemap.h>
 #include <linux/init.h>
-#include <linux/mount.h>
-#include <linux/namei.h>
 #include <linux/pci.h>
 #include <linux/pci_hotplug.h>
-#include <linux/uaccess.h>
 #include "../pci.h"
 #include "cpci_hotplug.h"
 
@@ -492,6 +488,75 @@ void pci_hp_destroy(struct hotplug_slot *slot)
 }
 EXPORT_SYMBOL_GPL(pci_hp_destroy);
 
+static DECLARE_WAIT_QUEUE_HEAD(pci_hp_link_change_wq);
+
+/**
+ * pci_hp_ignore_link_change - begin code section causing spurious link changes
+ * @pdev: PCI hotplug bridge
+ *
+ * Mark the beginning of a code section causing spurious link changes on the
+ * Secondary Bus of @pdev, e.g. as a side effect of a Secondary Bus Reset,
+ * D3cold transition, firmware update or FPGA reconfiguration.
+ *
+ * Hotplug drivers can thus check whether such a code section is executing
+ * concurrently, await it with pci_hp_spurious_link_change() and ignore the
+ * resulting link change events.
+ *
+ * Must be paired with pci_hp_unignore_link_change().  May be called both
+ * from the PCI core and from Endpoint drivers.  May be called for bridges
+ * which are not hotplug-capable, in which case it has no effect because
+ * no hotplug driver is bound to the bridge.
+ */
+void pci_hp_ignore_link_change(struct pci_dev *pdev)
+{
+	set_bit(PCI_LINK_CHANGING, &pdev->priv_flags);
+	smp_mb__after_atomic(); /* pairs with implied barrier of wait_event() */
+}
+
+/**
+ * pci_hp_unignore_link_change - end code section causing spurious link changes
+ * @pdev: PCI hotplug bridge
+ *
+ * Mark the end of a code section causing spurious link changes on the
+ * Secondary Bus of @pdev.  Must be paired with pci_hp_ignore_link_change().
+ */
+void pci_hp_unignore_link_change(struct pci_dev *pdev)
+{
+	set_bit(PCI_LINK_CHANGED, &pdev->priv_flags);
+	mb(); /* ensure pci_hp_spurious_link_change() sees either bit set */
+	clear_bit(PCI_LINK_CHANGING, &pdev->priv_flags);
+	wake_up_all(&pci_hp_link_change_wq);
+}
+
+/**
+ * pci_hp_spurious_link_change - check for spurious link changes
+ * @pdev: PCI hotplug bridge
+ *
+ * Check whether a code section is executing concurrently which is causing
+ * spurious link changes on the Secondary Bus of @pdev.  Await the end of the
+ * code section if so.
+ *
+ * May be called by hotplug drivers to check whether a link change is spurious
+ * and can be ignored.
+ *
+ * Because a genuine link change may have occurred in-between a spurious link
+ * change and the invocation of this function, hotplug drivers should perform
+ * sanity checks such as retrieving the current link state and bringing down
+ * the slot if the link is down.
+ *
+ * Return: %true if such a code section has been executing concurrently,
+ * otherwise %false.  Also return %true if such a code section has not been
+ * executing concurrently, but at least once since the last invocation of this
+ * function.
+ */
+bool pci_hp_spurious_link_change(struct pci_dev *pdev)
+{
+	wait_event(pci_hp_link_change_wq,
+		   !test_bit(PCI_LINK_CHANGING, &pdev->priv_flags));
+
+	return test_and_clear_bit(PCI_LINK_CHANGED, &pdev->priv_flags);
+}
+
 static int __init pci_hotplug_init(void)
 {
 	int result;
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 273dd8c66f4e..debc79b0adfb 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -187,6 +187,7 @@ int pciehp_card_present(struct controller *ctrl);
 int pciehp_card_present_or_link_active(struct controller *ctrl);
 int pciehp_check_link_status(struct controller *ctrl);
 int pciehp_check_link_active(struct controller *ctrl);
+bool pciehp_device_replaced(struct controller *ctrl);
 void pciehp_release_ctrl(struct controller *ctrl);
 
 int pciehp_sysfs_enable_slot(struct hotplug_slot *hotplug_slot);
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 997841c69893..f59baa912970 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -284,35 +284,6 @@ static int pciehp_suspend(struct pcie_device *dev)
 	return 0;
 }
 
-static bool pciehp_device_replaced(struct controller *ctrl)
-{
-	struct pci_dev *pdev __free(pci_dev_put) = NULL;
-	u32 reg;
-
-	if (pci_dev_is_disconnected(ctrl->pcie->port))
-		return false;
-
-	pdev = pci_get_slot(ctrl->pcie->port->subordinate, PCI_DEVFN(0, 0));
-	if (!pdev)
-		return true;
-
-	if (pci_read_config_dword(pdev, PCI_VENDOR_ID, &reg) ||
-	    reg != (pdev->vendor | (pdev->device << 16)) ||
-	    pci_read_config_dword(pdev, PCI_CLASS_REVISION, &reg) ||
-	    reg != (pdev->revision | (pdev->class << 8)))
-		return true;
-
-	if (pdev->hdr_type == PCI_HEADER_TYPE_NORMAL &&
-	    (pci_read_config_dword(pdev, PCI_SUBSYSTEM_VENDOR_ID, &reg) ||
-	     reg != (pdev->subsystem_vendor | (pdev->subsystem_device << 16))))
-		return true;
-
-	if (pci_get_dsn(pdev) != ctrl->dsn)
-		return true;
-
-	return false;
-}
-
 static int pciehp_resume_noirq(struct pcie_device *dev)
 {
 	struct controller *ctrl = get_service_data(dev);
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index d603a7aa7483..bcc938d4420f 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -131,7 +131,7 @@ static void remove_board(struct controller *ctrl, bool safe_removal)
 			      INDICATOR_NOOP);
 
 	/* Don't carry LBMS indications across */
-	pcie_reset_lbms_count(ctrl->pcie->port);
+	pcie_reset_lbms(ctrl->pcie->port);
 }
 
 static int pciehp_enable_slot(struct controller *ctrl);
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 8a09fb6083e2..ebd342bda235 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -563,20 +563,50 @@ void pciehp_power_off_slot(struct controller *ctrl)
 		 PCI_EXP_SLTCTL_PWR_OFF);
 }
 
-static void pciehp_ignore_dpc_link_change(struct controller *ctrl,
-					  struct pci_dev *pdev, int irq)
+bool pciehp_device_replaced(struct controller *ctrl)
+{
+	struct pci_dev *pdev __free(pci_dev_put) = NULL;
+	u32 reg;
+
+	if (pci_dev_is_disconnected(ctrl->pcie->port))
+		return false;
+
+	pdev = pci_get_slot(ctrl->pcie->port->subordinate, PCI_DEVFN(0, 0));
+	if (!pdev)
+		return true;
+
+	if (pci_read_config_dword(pdev, PCI_VENDOR_ID, &reg) ||
+	    reg != (pdev->vendor | (pdev->device << 16)) ||
+	    pci_read_config_dword(pdev, PCI_CLASS_REVISION, &reg) ||
+	    reg != (pdev->revision | (pdev->class << 8)))
+		return true;
+
+	if (pdev->hdr_type == PCI_HEADER_TYPE_NORMAL &&
+	    (pci_read_config_dword(pdev, PCI_SUBSYSTEM_VENDOR_ID, &reg) ||
+	     reg != (pdev->subsystem_vendor | (pdev->subsystem_device << 16))))
+		return true;
+
+	if (pci_get_dsn(pdev) != ctrl->dsn)
+		return true;
+
+	return false;
+}
+
+static void pciehp_ignore_link_change(struct controller *ctrl,
+				      struct pci_dev *pdev, int irq,
+				      u16 ignored_events)
 {
 	/*
 	 * Ignore link changes which occurred while waiting for DPC recovery.
 	 * Could be several if DPC triggered multiple times consecutively.
+	 * Also ignore link changes caused by Secondary Bus Reset, etc.
 	 */
 	synchronize_hardirq(irq);
-	atomic_and(~PCI_EXP_SLTSTA_DLLSC, &ctrl->pending_events);
+	atomic_and(~ignored_events, &ctrl->pending_events);
 	if (pciehp_poll_mode)
 		pcie_capability_write_word(pdev, PCI_EXP_SLTSTA,
-					   PCI_EXP_SLTSTA_DLLSC);
-	ctrl_info(ctrl, "Slot(%s): Link Down/Up ignored (recovered by DPC)\n",
-		  slot_name(ctrl));
+					   ignored_events);
+	ctrl_info(ctrl, "Slot(%s): Link Down/Up ignored\n", slot_name(ctrl));
 
 	/*
 	 * If the link is unexpectedly down after successful recovery,
@@ -584,8 +614,8 @@ static void pciehp_ignore_dpc_link_change(struct controller *ctrl,
 	 * Synthesize it to ensure that it is acted on.
 	 */
 	down_read_nested(&ctrl->reset_lock, ctrl->depth);
-	if (!pciehp_check_link_active(ctrl))
-		pciehp_request(ctrl, PCI_EXP_SLTSTA_DLLSC);
+	if (!pciehp_check_link_active(ctrl) || pciehp_device_replaced(ctrl))
+		pciehp_request(ctrl, ignored_events);
 	up_read(&ctrl->reset_lock);
 }
 
@@ -732,12 +762,19 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 
 	/*
 	 * Ignore Link Down/Up events caused by Downstream Port Containment
-	 * if recovery from the error succeeded.
+	 * if recovery succeeded, or caused by Secondary Bus Reset,
+	 * suspend to D3cold, firmware update, FPGA reconfiguration, etc.
 	 */
-	if ((events & PCI_EXP_SLTSTA_DLLSC) && pci_dpc_recovered(pdev) &&
+	if ((events & (PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC)) &&
+	    (pci_dpc_recovered(pdev) || pci_hp_spurious_link_change(pdev)) &&
 	    ctrl->state == ON_STATE) {
-		events &= ~PCI_EXP_SLTSTA_DLLSC;
-		pciehp_ignore_dpc_link_change(ctrl, pdev, irq);
+		u16 ignored_events = PCI_EXP_SLTSTA_DLLSC;
+
+		if (!ctrl->inband_presence_disabled)
+			ignored_events |= events & PCI_EXP_SLTSTA_PDC;
+
+		events &= ~ignored_events;
+		pciehp_ignore_link_change(ctrl, pdev, irq, ignored_events);
 	}
 
 	/*
@@ -902,7 +939,6 @@ int pciehp_reset_slot(struct hotplug_slot *hotplug_slot, bool probe)
 {
 	struct controller *ctrl = to_ctrl(hotplug_slot);
 	struct pci_dev *pdev = ctrl_dev(ctrl);
-	u16 stat_mask = 0, ctrl_mask = 0;
 	int rc;
 
 	if (probe)
@@ -910,23 +946,11 @@ int pciehp_reset_slot(struct hotplug_slot *hotplug_slot, bool probe)
 
 	down_write_nested(&ctrl->reset_lock, ctrl->depth);
 
-	if (!ATTN_BUTTN(ctrl)) {
-		ctrl_mask |= PCI_EXP_SLTCTL_PDCE;
-		stat_mask |= PCI_EXP_SLTSTA_PDC;
-	}
-	ctrl_mask |= PCI_EXP_SLTCTL_DLLSCE;
-	stat_mask |= PCI_EXP_SLTSTA_DLLSC;
-
-	pcie_write_cmd(ctrl, 0, ctrl_mask);
-	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
-		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, 0);
+	pci_hp_ignore_link_change(pdev);
 
 	rc = pci_bridge_secondary_bus_reset(ctrl->pcie->port);
 
-	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, stat_mask);
-	pcie_write_cmd_nowait(ctrl, ctrl_mask, ctrl_mask);
-	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
-		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, ctrl_mask);
+	pci_hp_unignore_link_change(pdev);
 
 	up_write(&ctrl->reset_lock);
 	return rc;
diff --git a/drivers/pci/iomap.c b/drivers/pci/iomap.c
index fe706ed946df..ea86c282a386 100644
--- a/drivers/pci/iomap.c
+++ b/drivers/pci/iomap.c
@@ -25,10 +25,6 @@
  *
  * @maxlen specifies the maximum length to map. If you want to get access to
  * the complete BAR from offset to the end, pass %0 here.
- *
- * NOTE:
- * This function is never managed, even if you initialized with
- * pcim_enable_device().
  * */
 void __iomem *pci_iomap_range(struct pci_dev *dev,
 			      int bar,
@@ -76,10 +72,6 @@ EXPORT_SYMBOL(pci_iomap_range);
  *
  * @maxlen specifies the maximum length to map. If you want to get access to
  * the complete BAR from offset to the end, pass %0 here.
- *
- * NOTE:
- * This function is never managed, even if you initialized with
- * pcim_enable_device().
  * */
 void __iomem *pci_iomap_wc_range(struct pci_dev *dev,
 				 int bar,
@@ -127,10 +119,6 @@ EXPORT_SYMBOL_GPL(pci_iomap_wc_range);
  *
  * @maxlen specifies the maximum length to map. If you want to get access to
  * the complete BAR without checking for its length first, pass %0 here.
- *
- * NOTE:
- * This function is never managed, even if you initialized with
- * pcim_enable_device(). If you need automatic cleanup, use pcim_iomap().
  * */
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
@@ -152,10 +140,6 @@ EXPORT_SYMBOL(pci_iomap);
  *
  * @maxlen specifies the maximum length to map. If you want to get access to
  * the complete BAR without checking for its length first, pass %0 here.
- *
- * NOTE:
- * This function is never managed, even if you initialized with
- * pcim_enable_device().
  * */
 void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index ab7a8252bf41..3579265f1198 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -966,3 +966,47 @@ u32 of_pci_get_slot_power_limit(struct device_node *node,
 	return slot_power_limit_mw;
 }
 EXPORT_SYMBOL_GPL(of_pci_get_slot_power_limit);
+
+/**
+ * of_pci_get_equalization_presets - Parses the "eq-presets-Ngts" property.
+ *
+ * @dev: Device containing the properties.
+ * @presets: Pointer to store the parsed data.
+ * @num_lanes: Maximum number of lanes supported.
+ *
+ * If the property is present, read and store the data in the @presets structure.
+ * Else, assign a default value of PCI_EQ_RESV.
+ *
+ * Return: 0 if the property is not available or successfully parsed else
+ * errno otherwise.
+ */
+int of_pci_get_equalization_presets(struct device *dev,
+				    struct pci_eq_presets *presets,
+				    int num_lanes)
+{
+	char name[20];
+	int ret;
+
+	presets->eq_presets_8gts[0] = PCI_EQ_RESV;
+	ret = of_property_read_u16_array(dev->of_node, "eq-presets-8gts",
+					 presets->eq_presets_8gts, num_lanes);
+	if (ret && ret != -EINVAL) {
+		dev_err(dev, "Error reading eq-presets-8gts: %d\n", ret);
+		return ret;
+	}
+
+	for (int i = 0; i < EQ_PRESET_TYPE_MAX - 1; i++) {
+		presets->eq_presets_Ngts[i][0] = PCI_EQ_RESV;
+		snprintf(name, sizeof(name), "eq-presets-%dgts", 8 << (i + 1));
+		ret = of_property_read_u8_array(dev->of_node, name,
+						presets->eq_presets_Ngts[i],
+						num_lanes);
+		if (ret && ret != -EINVAL) {
+			dev_err(dev, "Error reading %s: %d\n", name, ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_pci_get_equalization_presets);
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index af370628e583..b78e0e417324 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -1676,24 +1676,19 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 		return NULL;
 
 	root_ops = kzalloc(sizeof(*root_ops), GFP_KERNEL);
-	if (!root_ops) {
-		kfree(ri);
-		return NULL;
-	}
+	if (!root_ops)
+		goto free_ri;
 
 	ri->cfg = pci_acpi_setup_ecam_mapping(root);
-	if (!ri->cfg) {
-		kfree(ri);
-		kfree(root_ops);
-		return NULL;
-	}
+	if (!ri->cfg)
+		goto free_root_ops;
 
 	root_ops->release_info = pci_acpi_generic_release_info;
 	root_ops->prepare_resources = pci_acpi_root_prepare_resources;
 	root_ops->pci_ops = (struct pci_ops *)&ri->cfg->ops->pci_ops;
 	bus = acpi_pci_root_create(root, root_ops, &ri->common, ri->cfg);
 	if (!bus)
-		return NULL;
+		goto free_cfg;
 
 	/* If we must preserve the resource configuration, claim now */
 	host = pci_find_host_bridge(bus);
@@ -1710,6 +1705,14 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 		pcie_bus_configure_settings(child);
 
 	return bus;
+
+free_cfg:
+	pci_ecam_free(ri->cfg);
+free_root_ops:
+	kfree(root_ops);
+free_ri:
+	kfree(ri);
+	return NULL;
 }
 
 void pcibios_add_bus(struct pci_bus *bus)
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index c8bd71a739f7..67db34fd10ee 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -555,12 +555,6 @@ static void pci_pm_default_resume(struct pci_dev *pci_dev)
 	pci_enable_wake(pci_dev, PCI_D0, false);
 }
 
-static void pci_pm_power_up_and_verify_state(struct pci_dev *pci_dev)
-{
-	pci_power_up(pci_dev);
-	pci_update_current_state(pci_dev, PCI_D0);
-}
-
 static void pci_pm_default_resume_early(struct pci_dev *pci_dev)
 {
 	pci_pm_power_up_and_verify_state(pci_dev);
@@ -1507,7 +1501,7 @@ static int pci_bus_match(struct device *dev, const struct device_driver *drv)
 	struct pci_driver *pci_drv;
 	const struct pci_device_id *found_id;
 
-	if (!pci_dev->match_driver)
+	if (pci_dev_binding_disallowed(pci_dev))
 		return 0;
 
 	pci_drv = (struct pci_driver *)to_pci_driver(drv);
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index c6cda56ca52c..268c69daa4d5 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1475,6 +1475,9 @@ static ssize_t reset_method_store(struct device *dev,
 		return count;
 	}
 
+	pm_runtime_get_sync(dev);
+	struct device *pmdev __free(pm_runtime_put) = dev;
+
 	if (sysfs_streq(buf, "default")) {
 		pci_init_reset_methods(pdev);
 		return count;
@@ -1805,6 +1808,7 @@ const struct attribute_group *pci_dev_attr_groups[] = {
 	&pcie_dev_attr_group,
 #ifdef CONFIG_PCIEAER
 	&aer_stats_attr_group,
+	&aer_attr_group,
 #endif
 #ifdef CONFIG_PCIEASPM
 	&aspm_ctrl_attr_group,
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e77d5b53c0ce..e9448d55113b 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3192,6 +3192,12 @@ void pci_d3cold_disable(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_d3cold_disable);
 
+void pci_pm_power_up_and_verify_state(struct pci_dev *pci_dev)
+{
+	pci_power_up(pci_dev);
+	pci_update_current_state(pci_dev, PCI_D0);
+}
+
 /**
  * pci_pm_init - Initialize PM functions of given PCI device
  * @dev: PCI device to handle.
@@ -3202,9 +3208,6 @@ void pci_pm_init(struct pci_dev *dev)
 	u16 status;
 	u16 pmc;
 
-	pm_runtime_forbid(&dev->dev);
-	pm_runtime_set_active(&dev->dev);
-	pm_runtime_enable(&dev->dev);
 	device_enable_async_suspend(&dev->dev);
 	dev->wakeup_prepared = false;
 
@@ -3266,6 +3269,10 @@ void pci_pm_init(struct pci_dev *dev)
 	pci_read_config_word(dev, PCI_STATUS, &status);
 	if (status & PCI_STATUS_IMM_READY)
 		dev->imm_ready = 1;
+	pci_pm_power_up_and_verify_state(dev);
+	pm_runtime_forbid(&dev->dev);
+	pm_runtime_set_active(&dev->dev);
+	pm_runtime_enable(&dev->dev);
 }
 
 static unsigned long pci_ea_flags(struct pci_dev *dev, u8 prop)
@@ -3937,16 +3944,6 @@ void pci_release_region(struct pci_dev *pdev, int bar)
 	if (!pci_bar_index_is_valid(bar))
 		return;
 
-	/*
-	 * This is done for backwards compatibility, because the old PCI devres
-	 * API had a mode in which the function became managed if it had been
-	 * enabled with pcim_enable_device() instead of pci_enable_device().
-	 */
-	if (pci_is_managed(pdev)) {
-		pcim_release_region(pdev, bar);
-		return;
-	}
-
 	if (pci_resource_len(pdev, bar) == 0)
 		return;
 	if (pci_resource_flags(pdev, bar) & IORESOURCE_IO)
@@ -3984,13 +3981,6 @@ static int __pci_request_region(struct pci_dev *pdev, int bar,
 	if (!pci_bar_index_is_valid(bar))
 		return -EINVAL;
 
-	if (pci_is_managed(pdev)) {
-		if (exclusive == IORESOURCE_EXCLUSIVE)
-			return pcim_request_region_exclusive(pdev, bar, name);
-
-		return pcim_request_region(pdev, bar, name);
-	}
-
 	if (pci_resource_len(pdev, bar) == 0)
 		return 0;
 
@@ -4027,11 +4017,6 @@ err_out:
  *
  * Returns 0 on success, or %EBUSY on error.  A warning
  * message is also printed on failure.
- *
- * NOTE:
- * This is a "hybrid" function: It's normally unmanaged, but becomes managed
- * when pcim_enable_device() has been called in advance. This hybrid feature is
- * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead.
  */
 int pci_request_region(struct pci_dev *pdev, int bar, const char *name)
 {
@@ -4084,11 +4069,6 @@ err_out:
  * @name: Name of the driver requesting the resources
  *
  * Returns: 0 on success, negative error code on failure.
- *
- * NOTE:
- * This is a "hybrid" function: It's normally unmanaged, but becomes managed
- * when pcim_enable_device() has been called in advance. This hybrid feature is
- * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead.
  */
 int pci_request_selected_regions(struct pci_dev *pdev, int bars,
 				 const char *name)
@@ -4104,11 +4084,6 @@ EXPORT_SYMBOL(pci_request_selected_regions);
  * @name: name of the driver requesting the resources
  *
  * Returns: 0 on success, negative error code on failure.
- *
- * NOTE:
- * This is a "hybrid" function: It's normally unmanaged, but becomes managed
- * when pcim_enable_device() has been called in advance. This hybrid feature is
- * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead.
  */
 int pci_request_selected_regions_exclusive(struct pci_dev *pdev, int bars,
 					   const char *name)
@@ -4144,11 +4119,6 @@ EXPORT_SYMBOL(pci_release_regions);
  *
  * Returns 0 on success, or %EBUSY on error.  A warning
  * message is also printed on failure.
- *
- * NOTE:
- * This is a "hybrid" function: It's normally unmanaged, but becomes managed
- * when pcim_enable_device() has been called in advance. This hybrid feature is
- * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead.
  */
 int pci_request_regions(struct pci_dev *pdev, const char *name)
 {
@@ -4173,11 +4143,6 @@ EXPORT_SYMBOL(pci_request_regions);
  *
  * Returns 0 on success, or %EBUSY on error.  A warning message is also
  * printed on failure.
- *
- * NOTE:
- * This is a "hybrid" function: It's normally unmanaged, but becomes managed
- * when pcim_enable_device() has been called in advance. This hybrid feature is
- * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead.
  */
 int pci_request_regions_exclusive(struct pci_dev *pdev, const char *name)
 {
@@ -4257,7 +4222,7 @@ unsigned long __weak pci_address_to_pio(phys_addr_t address)
 #ifndef pci_remap_iospace
 int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
 {
-#if defined(PCI_IOBASE) && defined(CONFIG_MMU)
+#if defined(PCI_IOBASE)
 	unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start;
 
 	if (!(res->flags & IORESOURCE_IO))
@@ -4290,7 +4255,7 @@ EXPORT_SYMBOL(pci_remap_iospace);
  */
 void pci_unmap_iospace(struct resource *res)
 {
-#if defined(PCI_IOBASE) && defined(CONFIG_MMU)
+#if defined(PCI_IOBASE)
 	unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start;
 
 	vunmap_range(vaddr, vaddr + resource_size(res));
@@ -4718,6 +4683,11 @@ static int pcie_wait_for_link_status(struct pci_dev *pdev,
  * @pdev: Device whose link to retrain.
  * @use_lt: Use the LT bit if TRUE, or the DLLLA bit if FALSE, for status.
  *
+ * Trigger retraining of the PCIe Link and wait for the completion of the
+ * retraining. As link retraining is known to asserts LBMS and may change
+ * the Link Speed, LBMS is cleared after the retraining and the Link Speed
+ * of the subordinate bus is updated.
+ *
  * Retrain completion status is retrieved from the Link Status Register
  * according to @use_lt.  It is not verified whether the use of the DLLLA
  * bit is valid.
@@ -4757,7 +4727,19 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt)
 	 * to track link speed or width changes made by hardware itself
 	 * in attempt to correct unreliable link operation.
 	 */
-	pcie_reset_lbms_count(pdev);
+	pcie_reset_lbms(pdev);
+
+	/*
+	 * Ensure the Link Speed updates after retraining in case the Link
+	 * Speed was changed because of the retraining. While the bwctrl's
+	 * IRQ handler normally picks up the new Link Speed, clearing LBMS
+	 * races with the IRQ handler reading the Link Status register and
+	 * can result in the handler returning early without updating the
+	 * Link Speed.
+	 */
+	if (pdev->subordinate)
+		pcie_update_link_speed(pdev->subordinate);
+
 	return rc;
 }
 
@@ -4954,7 +4936,7 @@ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type)
 		delay);
 	if (!pcie_wait_for_link_delay(dev, true, delay)) {
 		/* Did not train, no need to wait any further */
-		pci_info(dev, "Data Link Layer Link Active not set in 1000 msec\n");
+		pci_info(dev, "Data Link Layer Link Active not set in %d msec\n", delay);
 		return -ENOTTY;
 	}
 
@@ -5538,7 +5520,8 @@ static void pci_slot_unlock(struct pci_slot *slot)
 			continue;
 		if (dev->subordinate)
 			pci_bus_unlock(dev->subordinate);
-		pci_dev_unlock(dev);
+		else
+			pci_dev_unlock(dev);
 	}
 }
 
@@ -6802,11 +6785,6 @@ int __weak pci_ext_cfg_avail(void)
 	return 1;
 }
 
-void __weak pci_fixup_cardbus(struct pci_bus *bus)
-{
-}
-EXPORT_SYMBOL(pci_fixup_cardbus);
-
 static int __init pci_setup(char *str)
 {
 	while (str) {
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 39f368d2f26d..12215ee72afb 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -9,6 +9,8 @@ struct pcie_tlp_log;
 /* Number of possible devfns: 0.0 to 1f.7 inclusive */
 #define MAX_NR_DEVFNS 256
 
+#define MAX_NR_LANES 16
+
 #define PCI_FIND_CAP_TTL	48
 
 #define PCI_VSEC_ID_INTEL_TBT	0x1234	/* Thunderbolt */
@@ -148,6 +150,7 @@ void pci_dev_adjust_pme(struct pci_dev *dev);
 void pci_dev_complete_resume(struct pci_dev *pci_dev);
 void pci_config_pm_runtime_get(struct pci_dev *dev);
 void pci_config_pm_runtime_put(struct pci_dev *dev);
+void pci_pm_power_up_and_verify_state(struct pci_dev *pci_dev);
 void pci_pm_init(struct pci_dev *dev);
 void pci_ea_init(struct pci_dev *dev);
 void pci_msi_init(struct pci_dev *dev);
@@ -227,6 +230,7 @@ static inline int pci_proc_detach_bus(struct pci_bus *bus) { return 0; }
 
 /* Functions for PCI Hotplug drivers to use */
 int pci_hp_add_bridge(struct pci_dev *dev);
+bool pci_hp_spurious_link_change(struct pci_dev *pdev);
 
 #if defined(CONFIG_SYSFS) && defined(HAVE_PCI_LEGACY)
 void pci_create_legacy_files(struct pci_bus *bus);
@@ -557,6 +561,10 @@ static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused)
 #define PCI_DPC_RECOVERED 1
 #define PCI_DPC_RECOVERING 2
 #define PCI_DEV_REMOVED 3
+#define PCI_LINK_CHANGED 4
+#define PCI_LINK_CHANGING 5
+#define PCI_LINK_LBMS_SEEN	6
+#define PCI_DEV_ALLOW_BINDING 7
 
 static inline void pci_dev_assign_added(struct pci_dev *dev)
 {
@@ -580,6 +588,16 @@ static inline bool pci_dev_test_and_set_removed(struct pci_dev *dev)
 	return test_and_set_bit(PCI_DEV_REMOVED, &dev->priv_flags);
 }
 
+static inline void pci_dev_allow_binding(struct pci_dev *dev)
+{
+	set_bit(PCI_DEV_ALLOW_BINDING, &dev->priv_flags);
+}
+
+static inline bool pci_dev_binding_disallowed(struct pci_dev *dev)
+{
+	return !test_bit(PCI_DEV_ALLOW_BINDING, &dev->priv_flags);
+}
+
 #ifdef CONFIG_PCIEAER
 #include <linux/aer.h>
 
@@ -587,12 +605,15 @@ static inline bool pci_dev_test_and_set_removed(struct pci_dev *dev)
 
 struct aer_err_info {
 	struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
+	int ratelimit_print[AER_MAX_MULTI_ERR_DEVICES];
 	int error_dev_num;
+	const char *level;		/* printk level */
 
 	unsigned int id:16;
 
 	unsigned int severity:2;	/* 0:NONFATAL | 1:FATAL | 2:COR */
-	unsigned int __pad1:5;
+	unsigned int root_ratelimit_print:1;	/* 0=skip, 1=print */
+	unsigned int __pad1:4;
 	unsigned int multi_error_valid:1;
 
 	unsigned int first_error:5;
@@ -604,15 +625,16 @@ struct aer_err_info {
 	struct pcie_tlp_log tlp;	/* TLP Header */
 };
 
-int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info);
-void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
+int aer_get_device_error_info(struct aer_err_info *info, int i);
+void aer_print_error(struct aer_err_info *info, int i);
 
 int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2,
 		      unsigned int tlp_len, bool flit,
 		      struct pcie_tlp_log *log);
 unsigned int aer_tlp_log_len(struct pci_dev *dev, u32 aercc);
 void pcie_print_tlp_log(const struct pci_dev *dev,
-			const struct pcie_tlp_log *log, const char *pfx);
+			const struct pcie_tlp_log *log, const char *level,
+			const char *pfx);
 #endif	/* CONFIG_PCIEAER */
 
 #ifdef CONFIG_PCIEPORTBUS
@@ -824,14 +846,9 @@ static inline void pcie_ecrc_get_policy(char *str) { }
 #endif
 
 #ifdef CONFIG_PCIEPORTBUS
-void pcie_reset_lbms_count(struct pci_dev *port);
-int pcie_lbms_count(struct pci_dev *port, unsigned long *val);
+void pcie_reset_lbms(struct pci_dev *port);
 #else
-static inline void pcie_reset_lbms_count(struct pci_dev *port) {}
-static inline int pcie_lbms_count(struct pci_dev *port, unsigned long *val)
-{
-	return -EOPNOTSUPP;
-}
+static inline void pcie_reset_lbms(struct pci_dev *port) {}
 #endif
 
 struct pci_dev_reset_methods {
@@ -876,6 +893,21 @@ static inline u64 pci_rebar_size_to_bytes(int size)
 
 struct device_node;
 
+#define PCI_EQ_RESV	0xff
+
+enum equalization_preset_type {
+	EQ_PRESET_TYPE_8GTS,
+	EQ_PRESET_TYPE_16GTS,
+	EQ_PRESET_TYPE_32GTS,
+	EQ_PRESET_TYPE_64GTS,
+	EQ_PRESET_TYPE_MAX
+};
+
+struct pci_eq_presets {
+	u16 eq_presets_8gts[MAX_NR_LANES];
+	u8 eq_presets_Ngts[EQ_PRESET_TYPE_MAX - 1][MAX_NR_LANES];
+};
+
 #ifdef CONFIG_OF
 int of_get_pci_domain_nr(struct device_node *node);
 int of_pci_get_max_link_speed(struct device_node *node);
@@ -890,7 +922,9 @@ void pci_release_bus_of_node(struct pci_bus *bus);
 
 int devm_of_pci_bridge_init(struct device *dev, struct pci_host_bridge *bridge);
 bool of_pci_supply_present(struct device_node *np);
-
+int of_pci_get_equalization_presets(struct device *dev,
+				    struct pci_eq_presets *presets,
+				    int num_lanes);
 #else
 static inline int
 of_get_pci_domain_nr(struct device_node *node)
@@ -935,6 +969,17 @@ static inline bool of_pci_supply_present(struct device_node *np)
 {
 	return false;
 }
+
+static inline int of_pci_get_equalization_presets(struct device *dev,
+						  struct pci_eq_presets *presets,
+						  int num_lanes)
+{
+	presets->eq_presets_8gts[0] = PCI_EQ_RESV;
+	for (int i = 0; i < EQ_PRESET_TYPE_MAX - 1; i++)
+		presets->eq_presets_Ngts[i][0] = PCI_EQ_RESV;
+
+	return 0;
+}
 #endif /* CONFIG_OF */
 
 struct of_changeset;
@@ -961,6 +1006,7 @@ void pci_no_aer(void);
 void pci_aer_init(struct pci_dev *dev);
 void pci_aer_exit(struct pci_dev *dev);
 extern const struct attribute_group aer_stats_attr_group;
+extern const struct attribute_group aer_attr_group;
 void pci_aer_clear_fatal_status(struct pci_dev *dev);
 int pci_aer_clear_status(struct pci_dev *dev);
 int pci_aer_raw_clear_status(struct pci_dev *dev);
@@ -1059,11 +1105,6 @@ static inline pci_power_t mid_pci_get_power_state(struct pci_dev *pdev)
 }
 #endif
 
-int pcim_intx(struct pci_dev *dev, int enable);
-int pcim_request_region_exclusive(struct pci_dev *pdev, int bar,
-				  const char *name);
-void pcim_release_region(struct pci_dev *pdev, int bar);
-
 #ifdef CONFIG_PCI_MSI
 int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag);
 #else
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index a1cf8c7ef628..70ac66188367 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -28,6 +28,7 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/kfifo.h>
+#include <linux/ratelimit.h>
 #include <linux/slab.h>
 #include <acpi/apei.h>
 #include <acpi/ghes.h>
@@ -54,8 +55,8 @@ struct aer_rpc {
 	DECLARE_KFIFO(aer_fifo, struct aer_err_source, AER_ERROR_SOURCES_MAX);
 };
 
-/* AER stats for the device */
-struct aer_stats {
+/* AER info for the device */
+struct aer_info {
 
 	/*
 	 * Fields for all AER capable devices. They indicate the errors
@@ -88,6 +89,10 @@ struct aer_stats {
 	u64 rootport_total_cor_errs;
 	u64 rootport_total_fatal_errs;
 	u64 rootport_total_nonfatal_errs;
+
+	/* Ratelimits for errors */
+	struct ratelimit_state correctable_ratelimit;
+	struct ratelimit_state nonfatal_ratelimit;
 };
 
 #define AER_LOG_TLP_MASKS		(PCI_ERR_UNC_POISON_TLP|	\
@@ -377,7 +382,12 @@ void pci_aer_init(struct pci_dev *dev)
 	if (!dev->aer_cap)
 		return;
 
-	dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL);
+	dev->aer_info = kzalloc(sizeof(*dev->aer_info), GFP_KERNEL);
+
+	ratelimit_state_init(&dev->aer_info->correctable_ratelimit,
+			     DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST);
+	ratelimit_state_init(&dev->aer_info->nonfatal_ratelimit,
+			     DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST);
 
 	/*
 	 * We save/restore PCI_ERR_UNCOR_MASK, PCI_ERR_UNCOR_SEVER,
@@ -398,8 +408,8 @@ void pci_aer_init(struct pci_dev *dev)
 
 void pci_aer_exit(struct pci_dev *dev)
 {
-	kfree(dev->aer_stats);
-	dev->aer_stats = NULL;
+	kfree(dev->aer_info);
+	dev->aer_info = NULL;
 }
 
 #define AER_AGENT_RECEIVER		0
@@ -537,10 +547,10 @@ static const char *aer_agent_string[] = {
 {									\
 	unsigned int i;							\
 	struct pci_dev *pdev = to_pci_dev(dev);				\
-	u64 *stats = pdev->aer_stats->stats_array;			\
+	u64 *stats = pdev->aer_info->stats_array;			\
 	size_t len = 0;							\
 									\
-	for (i = 0; i < ARRAY_SIZE(pdev->aer_stats->stats_array); i++) {\
+	for (i = 0; i < ARRAY_SIZE(pdev->aer_info->stats_array); i++) {	\
 		if (strings_array[i])					\
 			len += sysfs_emit_at(buf, len, "%s %llu\n",	\
 					     strings_array[i],		\
@@ -551,7 +561,7 @@ static const char *aer_agent_string[] = {
 					     i, stats[i]);		\
 	}								\
 	len += sysfs_emit_at(buf, len, "TOTAL_%s %llu\n", total_string,	\
-			     pdev->aer_stats->total_field);		\
+			     pdev->aer_info->total_field);		\
 	return len;							\
 }									\
 static DEVICE_ATTR_RO(name)
@@ -572,7 +582,7 @@ aer_stats_dev_attr(aer_dev_nonfatal, dev_nonfatal_errs,
 		     char *buf)						\
 {									\
 	struct pci_dev *pdev = to_pci_dev(dev);				\
-	return sysfs_emit(buf, "%llu\n", pdev->aer_stats->field);	\
+	return sysfs_emit(buf, "%llu\n", pdev->aer_info->field);	\
 }									\
 static DEVICE_ATTR_RO(name)
 
@@ -599,7 +609,7 @@ static umode_t aer_stats_attrs_are_visible(struct kobject *kobj,
 	struct device *dev = kobj_to_dev(kobj);
 	struct pci_dev *pdev = to_pci_dev(dev);
 
-	if (!pdev->aer_stats)
+	if (!pdev->aer_info)
 		return 0;
 
 	if ((a == &dev_attr_aer_rootport_total_err_cor.attr ||
@@ -617,31 +627,136 @@ const struct attribute_group aer_stats_attr_group = {
 	.is_visible = aer_stats_attrs_are_visible,
 };
 
+/*
+ * Ratelimit interval
+ * <=0: disabled with ratelimit.interval = 0
+ * >0: enabled with ratelimit.interval in ms
+ */
+#define aer_ratelimit_interval_attr(name, ratelimit)			\
+	static ssize_t							\
+	name##_show(struct device *dev, struct device_attribute *attr,	\
+					 char *buf)			\
+	{								\
+		struct pci_dev *pdev = to_pci_dev(dev);			\
+									\
+		return sysfs_emit(buf, "%d\n",				\
+				  pdev->aer_info->ratelimit.interval);	\
+	}								\
+									\
+	static ssize_t							\
+	name##_store(struct device *dev, struct device_attribute *attr, \
+		     const char *buf, size_t count) 			\
+	{								\
+		struct pci_dev *pdev = to_pci_dev(dev);			\
+		int interval;						\
+									\
+		if (!capable(CAP_SYS_ADMIN))				\
+			return -EPERM;					\
+									\
+		if (kstrtoint(buf, 0, &interval) < 0)			\
+			return -EINVAL;					\
+									\
+		if (interval <= 0)					\
+			interval = 0;					\
+		else							\
+			interval = msecs_to_jiffies(interval); 		\
+									\
+		pdev->aer_info->ratelimit.interval = interval;		\
+									\
+		return count;						\
+	}								\
+	static DEVICE_ATTR_RW(name);
+
+#define aer_ratelimit_burst_attr(name, ratelimit)			\
+	static ssize_t							\
+	name##_show(struct device *dev, struct device_attribute *attr,	\
+		    char *buf)						\
+	{								\
+		struct pci_dev *pdev = to_pci_dev(dev);			\
+									\
+		return sysfs_emit(buf, "%d\n",				\
+				  pdev->aer_info->ratelimit.burst);	\
+	}								\
+									\
+	static ssize_t							\
+	name##_store(struct device *dev, struct device_attribute *attr,	\
+		     const char *buf, size_t count)			\
+	{								\
+		struct pci_dev *pdev = to_pci_dev(dev);			\
+		int burst;						\
+									\
+		if (!capable(CAP_SYS_ADMIN))				\
+			return -EPERM;					\
+									\
+		if (kstrtoint(buf, 0, &burst) < 0)			\
+			return -EINVAL;					\
+									\
+		pdev->aer_info->ratelimit.burst = burst;		\
+									\
+		return count;						\
+	}								\
+	static DEVICE_ATTR_RW(name);
+
+#define aer_ratelimit_attrs(name)					\
+	aer_ratelimit_interval_attr(name##_ratelimit_interval_ms,	\
+				    name##_ratelimit)			\
+	aer_ratelimit_burst_attr(name##_ratelimit_burst,		\
+				 name##_ratelimit)
+
+aer_ratelimit_attrs(correctable)
+aer_ratelimit_attrs(nonfatal)
+
+static struct attribute *aer_attrs[] = {
+	&dev_attr_correctable_ratelimit_interval_ms.attr,
+	&dev_attr_correctable_ratelimit_burst.attr,
+	&dev_attr_nonfatal_ratelimit_interval_ms.attr,
+	&dev_attr_nonfatal_ratelimit_burst.attr,
+	NULL
+};
+
+static umode_t aer_attrs_are_visible(struct kobject *kobj,
+				     struct attribute *a, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (!pdev->aer_info)
+		return 0;
+
+	return a->mode;
+}
+
+const struct attribute_group aer_attr_group = {
+	.name = "aer",
+	.attrs = aer_attrs,
+	.is_visible = aer_attrs_are_visible,
+};
+
 static void pci_dev_aer_stats_incr(struct pci_dev *pdev,
 				   struct aer_err_info *info)
 {
 	unsigned long status = info->status & ~info->mask;
 	int i, max = -1;
 	u64 *counter = NULL;
-	struct aer_stats *aer_stats = pdev->aer_stats;
+	struct aer_info *aer_info = pdev->aer_info;
 
-	if (!aer_stats)
+	if (!aer_info)
 		return;
 
 	switch (info->severity) {
 	case AER_CORRECTABLE:
-		aer_stats->dev_total_cor_errs++;
-		counter = &aer_stats->dev_cor_errs[0];
+		aer_info->dev_total_cor_errs++;
+		counter = &aer_info->dev_cor_errs[0];
 		max = AER_MAX_TYPEOF_COR_ERRS;
 		break;
 	case AER_NONFATAL:
-		aer_stats->dev_total_nonfatal_errs++;
-		counter = &aer_stats->dev_nonfatal_errs[0];
+		aer_info->dev_total_nonfatal_errs++;
+		counter = &aer_info->dev_nonfatal_errs[0];
 		max = AER_MAX_TYPEOF_UNCOR_ERRS;
 		break;
 	case AER_FATAL:
-		aer_stats->dev_total_fatal_errs++;
-		counter = &aer_stats->dev_fatal_errs[0];
+		aer_info->dev_total_fatal_errs++;
+		counter = &aer_info->dev_fatal_errs[0];
 		max = AER_MAX_TYPEOF_UNCOR_ERRS;
 		break;
 	}
@@ -653,37 +768,46 @@ static void pci_dev_aer_stats_incr(struct pci_dev *pdev,
 static void pci_rootport_aer_stats_incr(struct pci_dev *pdev,
 				 struct aer_err_source *e_src)
 {
-	struct aer_stats *aer_stats = pdev->aer_stats;
+	struct aer_info *aer_info = pdev->aer_info;
 
-	if (!aer_stats)
+	if (!aer_info)
 		return;
 
 	if (e_src->status & PCI_ERR_ROOT_COR_RCV)
-		aer_stats->rootport_total_cor_errs++;
+		aer_info->rootport_total_cor_errs++;
 
 	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
 		if (e_src->status & PCI_ERR_ROOT_FATAL_RCV)
-			aer_stats->rootport_total_fatal_errs++;
+			aer_info->rootport_total_fatal_errs++;
 		else
-			aer_stats->rootport_total_nonfatal_errs++;
+			aer_info->rootport_total_nonfatal_errs++;
+	}
+}
+
+static int aer_ratelimit(struct pci_dev *dev, unsigned int severity)
+{
+	switch (severity) {
+	case AER_NONFATAL:
+		return __ratelimit(&dev->aer_info->nonfatal_ratelimit);
+	case AER_CORRECTABLE:
+		return __ratelimit(&dev->aer_info->correctable_ratelimit);
+	default:
+		return 1;	/* Don't ratelimit fatal errors */
 	}
 }
 
-static void __aer_print_error(struct pci_dev *dev,
-			      struct aer_err_info *info)
+static void __aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 {
 	const char **strings;
 	unsigned long status = info->status & ~info->mask;
-	const char *level, *errmsg;
+	const char *level = info->level;
+	const char *errmsg;
 	int i;
 
-	if (info->severity == AER_CORRECTABLE) {
+	if (info->severity == AER_CORRECTABLE)
 		strings = aer_correctable_error_string;
-		level = KERN_WARNING;
-	} else {
+	else
 		strings = aer_uncorrectable_error_string;
-		level = KERN_ERR;
-	}
 
 	for_each_set_bit(i, &status, 32) {
 		errmsg = strings[i];
@@ -693,14 +817,39 @@ static void __aer_print_error(struct pci_dev *dev,
 		aer_printk(level, dev, "   [%2d] %-22s%s\n", i, errmsg,
 				info->first_error == i ? " (First)" : "");
 	}
-	pci_dev_aer_stats_incr(dev, info);
 }
 
-void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
+static void aer_print_source(struct pci_dev *dev, struct aer_err_info *info,
+			     bool found)
+{
+	u16 source = info->id;
+
+	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d%s\n",
+		 info->multi_error_valid ? "Multiple " : "",
+		 aer_error_severity_string[info->severity],
+		 pci_domain_nr(dev->bus), PCI_BUS_NUM(source),
+		 PCI_SLOT(source), PCI_FUNC(source),
+		 found ? "" : " (no details found");
+}
+
+void aer_print_error(struct aer_err_info *info, int i)
 {
-	int layer, agent;
-	int id = pci_dev_id(dev);
-	const char *level;
+	struct pci_dev *dev;
+	int layer, agent, id;
+	const char *level = info->level;
+
+	if (WARN_ON_ONCE(i >= AER_MAX_MULTI_ERR_DEVICES))
+		return;
+
+	dev = info->dev[i];
+	id = pci_dev_id(dev);
+
+	pci_dev_aer_stats_incr(dev, info);
+	trace_aer_event(pci_name(dev), (info->status & ~info->mask),
+			info->severity, info->tlp_header_valid, &info->tlp);
+
+	if (!info->ratelimit_print[i])
+		return;
 
 	if (!info->status) {
 		pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
@@ -711,8 +860,6 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 	layer = AER_GET_LAYER_ERROR(info->severity, info->status);
 	agent = AER_GET_AGENT(info->severity, info->status);
 
-	level = (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR;
-
 	aer_printk(level, dev, "PCIe Bus Error: severity=%s, type=%s, (%s)\n",
 		   aer_error_severity_string[info->severity],
 		   aer_error_layer[layer], aer_agent_string[agent]);
@@ -723,26 +870,11 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 	__aer_print_error(dev, info);
 
 	if (info->tlp_header_valid)
-		pcie_print_tlp_log(dev, &info->tlp, dev_fmt("  "));
+		pcie_print_tlp_log(dev, &info->tlp, level, dev_fmt("  "));
 
 out:
 	if (info->id && info->error_dev_num > 1 && info->id == id)
 		pci_err(dev, "  Error of this Agent is reported first\n");
-
-	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
-			info->severity, info->tlp_header_valid, &info->tlp);
-}
-
-static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
-{
-	u8 bus = info->id >> 8;
-	u8 devfn = info->id & 0xff;
-
-	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d\n",
-		 info->multi_error_valid ? "Multiple " : "",
-		 aer_error_severity_string[info->severity],
-		 pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn),
-		 PCI_FUNC(devfn));
 }
 
 #ifdef CONFIG_ACPI_APEI_PCIEAER
@@ -765,40 +897,48 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
 {
 	int layer, agent, tlp_header_valid = 0;
 	u32 status, mask;
-	struct aer_err_info info;
+	struct aer_err_info info = {
+		.severity = aer_severity,
+		.first_error = PCI_ERR_CAP_FEP(aer->cap_control),
+	};
 
 	if (aer_severity == AER_CORRECTABLE) {
 		status = aer->cor_status;
 		mask = aer->cor_mask;
+		info.level = KERN_WARNING;
 	} else {
 		status = aer->uncor_status;
 		mask = aer->uncor_mask;
+		info.level = KERN_ERR;
 		tlp_header_valid = status & AER_LOG_TLP_MASKS;
 	}
 
-	layer = AER_GET_LAYER_ERROR(aer_severity, status);
-	agent = AER_GET_AGENT(aer_severity, status);
-
-	memset(&info, 0, sizeof(info));
-	info.severity = aer_severity;
 	info.status = status;
 	info.mask = mask;
-	info.first_error = PCI_ERR_CAP_FEP(aer->cap_control);
 
-	pci_err(dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask);
+	pci_dev_aer_stats_incr(dev, &info);
+	trace_aer_event(pci_name(dev), (status & ~mask),
+			aer_severity, tlp_header_valid, &aer->header_log);
+
+	if (!aer_ratelimit(dev, info.severity))
+		return;
+
+	layer = AER_GET_LAYER_ERROR(aer_severity, status);
+	agent = AER_GET_AGENT(aer_severity, status);
+
+	aer_printk(info.level, dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n",
+		   status, mask);
 	__aer_print_error(dev, &info);
-	pci_err(dev, "aer_layer=%s, aer_agent=%s\n",
-		aer_error_layer[layer], aer_agent_string[agent]);
+	aer_printk(info.level, dev, "aer_layer=%s, aer_agent=%s\n",
+		   aer_error_layer[layer], aer_agent_string[agent]);
 
 	if (aer_severity != AER_CORRECTABLE)
-		pci_err(dev, "aer_uncor_severity: 0x%08x\n",
-			aer->uncor_severity);
+		aer_printk(info.level, dev, "aer_uncor_severity: 0x%08x\n",
+			   aer->uncor_severity);
 
 	if (tlp_header_valid)
-		pcie_print_tlp_log(dev, &aer->header_log, dev_fmt("  "));
-
-	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
-			aer_severity, tlp_header_valid, &aer->header_log);
+		pcie_print_tlp_log(dev, &aer->header_log, info.level,
+				   dev_fmt("  "));
 }
 EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL");
 
@@ -809,12 +949,27 @@ EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL");
  */
 static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)
 {
-	if (e_info->error_dev_num < AER_MAX_MULTI_ERR_DEVICES) {
-		e_info->dev[e_info->error_dev_num] = pci_dev_get(dev);
-		e_info->error_dev_num++;
-		return 0;
+	int i = e_info->error_dev_num;
+
+	if (i >= AER_MAX_MULTI_ERR_DEVICES)
+		return -ENOSPC;
+
+	e_info->dev[i] = pci_dev_get(dev);
+	e_info->error_dev_num++;
+
+	/*
+	 * Ratelimit AER log messages.  "dev" is either the source
+	 * identified by the root's Error Source ID or it has an unmasked
+	 * error logged in its own AER Capability.  Messages are emitted
+	 * when "ratelimit_print[i]" is non-zero.  If we will print detail
+	 * for a downstream device, make sure we print the Error Source ID
+	 * from the root as well.
+	 */
+	if (aer_ratelimit(dev, e_info->severity)) {
+		e_info->ratelimit_print[i] = 1;
+		e_info->root_ratelimit_print = 1;
 	}
-	return -ENOSPC;
+	return 0;
 }
 
 /**
@@ -908,7 +1063,7 @@ static int find_device_iter(struct pci_dev *dev, void *data)
  * e_info->error_dev_num and e_info->dev[], based on the given information.
  */
 static bool find_source_device(struct pci_dev *parent,
-		struct aer_err_info *e_info)
+			       struct aer_err_info *e_info)
 {
 	struct pci_dev *dev = parent;
 	int result;
@@ -926,15 +1081,8 @@ static bool find_source_device(struct pci_dev *parent,
 	else
 		pci_walk_bus(parent->subordinate, find_device_iter, e_info);
 
-	if (!e_info->error_dev_num) {
-		u8 bus = e_info->id >> 8;
-		u8 devfn = e_info->id & 0xff;
-
-		pci_info(parent, "found no error details for %04x:%02x:%02x.%d\n",
-			 pci_domain_nr(parent->bus), bus, PCI_SLOT(devfn),
-			 PCI_FUNC(devfn));
+	if (!e_info->error_dev_num)
 		return false;
-	}
 	return true;
 }
 
@@ -1141,9 +1289,10 @@ static void aer_recover_work_func(struct work_struct *work)
 		pdev = pci_get_domain_bus_and_slot(entry.domain, entry.bus,
 						   entry.devfn);
 		if (!pdev) {
-			pr_err("no pci_dev for %04x:%02x:%02x.%x\n",
-			       entry.domain, entry.bus,
-			       PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn));
+			pr_err_ratelimited("%04x:%02x:%02x.%x: no pci_dev found\n",
+					   entry.domain, entry.bus,
+					   PCI_SLOT(entry.devfn),
+					   PCI_FUNC(entry.devfn));
 			continue;
 		}
 		pci_print_aer(pdev, entry.severity, entry.regs);
@@ -1199,19 +1348,26 @@ EXPORT_SYMBOL_GPL(aer_recover_queue);
 
 /**
  * aer_get_device_error_info - read error status from dev and store it to info
- * @dev: pointer to the device expected to have an error record
  * @info: pointer to structure to store the error record
+ * @i: index into info->dev[]
  *
  * Return: 1 on success, 0 on error.
  *
  * Note that @info is reused among all error devices. Clear fields properly.
  */
-int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
+int aer_get_device_error_info(struct aer_err_info *info, int i)
 {
-	int type = pci_pcie_type(dev);
-	int aer = dev->aer_cap;
+	struct pci_dev *dev;
+	int type, aer;
 	u32 aercc;
 
+	if (i >= AER_MAX_MULTI_ERR_DEVICES)
+		return 0;
+
+	dev = info->dev[i];
+	aer = dev->aer_cap;
+	type = pci_pcie_type(dev);
+
 	/* Must reset in this function */
 	info->status = 0;
 	info->tlp_header_valid = 0;
@@ -1263,63 +1419,87 @@ static inline void aer_process_err_devices(struct aer_err_info *e_info)
 
 	/* Report all before handling them, to not lose records by reset etc. */
 	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
-		if (aer_get_device_error_info(e_info->dev[i], e_info))
-			aer_print_error(e_info->dev[i], e_info);
+		if (aer_get_device_error_info(e_info, i))
+			aer_print_error(e_info, i);
 	}
 	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
-		if (aer_get_device_error_info(e_info->dev[i], e_info))
+		if (aer_get_device_error_info(e_info, i))
 			handle_error_source(e_info->dev[i], e_info);
 	}
 }
 
 /**
- * aer_isr_one_error - consume an error detected by Root Port
- * @rpc: pointer to the Root Port which holds an error
- * @e_src: pointer to an error source
+ * aer_isr_one_error_type - consume a Correctable or Uncorrectable Error
+ *			    detected by Root Port or RCEC
+ * @root: pointer to Root Port or RCEC that signaled AER interrupt
+ * @info: pointer to AER error info
  */
-static void aer_isr_one_error(struct aer_rpc *rpc,
-		struct aer_err_source *e_src)
+static void aer_isr_one_error_type(struct pci_dev *root,
+				   struct aer_err_info *info)
 {
-	struct pci_dev *pdev = rpc->rpd;
-	struct aer_err_info e_info;
+	bool found;
 
-	pci_rootport_aer_stats_incr(pdev, e_src);
+	found = find_source_device(root, info);
 
 	/*
-	 * There is a possibility that both correctable error and
-	 * uncorrectable error being logged. Report correctable error first.
+	 * If we're going to log error messages, we've already set
+	 * "info->root_ratelimit_print" and "info->ratelimit_print[i]" to
+	 * non-zero (which enables printing) because this is either an
+	 * ERR_FATAL or we found a device with an error logged in its AER
+	 * Capability.
+	 *
+	 * If we didn't find the Error Source device, at least log the
+	 * Requester ID from the ERR_* Message received by the Root Port or
+	 * RCEC, ratelimited by the RP or RCEC.
 	 */
-	if (e_src->status & PCI_ERR_ROOT_COR_RCV) {
-		e_info.id = ERR_COR_ID(e_src->id);
-		e_info.severity = AER_CORRECTABLE;
-
-		if (e_src->status & PCI_ERR_ROOT_MULTI_COR_RCV)
-			e_info.multi_error_valid = 1;
-		else
-			e_info.multi_error_valid = 0;
-		aer_print_port_info(pdev, &e_info);
+	if (info->root_ratelimit_print ||
+	    (!found && aer_ratelimit(root, info->severity)))
+		aer_print_source(root, info, found);
 
-		if (find_source_device(pdev, &e_info))
-			aer_process_err_devices(&e_info);
-	}
-
-	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
-		e_info.id = ERR_UNCOR_ID(e_src->id);
+	if (found)
+		aer_process_err_devices(info);
+}
 
-		if (e_src->status & PCI_ERR_ROOT_FATAL_RCV)
-			e_info.severity = AER_FATAL;
-		else
-			e_info.severity = AER_NONFATAL;
+/**
+ * aer_isr_one_error - consume error(s) signaled by an AER interrupt from
+ *		       Root Port or RCEC
+ * @root: pointer to Root Port or RCEC that signaled AER interrupt
+ * @e_src: pointer to an error source
+ */
+static void aer_isr_one_error(struct pci_dev *root,
+			      struct aer_err_source *e_src)
+{
+	u32 status = e_src->status;
 
-		if (e_src->status & PCI_ERR_ROOT_MULTI_UNCOR_RCV)
-			e_info.multi_error_valid = 1;
-		else
-			e_info.multi_error_valid = 0;
+	pci_rootport_aer_stats_incr(root, e_src);
 
-		aer_print_port_info(pdev, &e_info);
+	/*
+	 * There is a possibility that both correctable error and
+	 * uncorrectable error being logged. Report correctable error first.
+	 */
+	if (status & PCI_ERR_ROOT_COR_RCV) {
+		int multi = status & PCI_ERR_ROOT_MULTI_COR_RCV;
+		struct aer_err_info e_info = {
+			.id = ERR_COR_ID(e_src->id),
+			.severity = AER_CORRECTABLE,
+			.level = KERN_WARNING,
+			.multi_error_valid = multi ? 1 : 0,
+		};
+
+		aer_isr_one_error_type(root, &e_info);
+	}
 
-		if (find_source_device(pdev, &e_info))
-			aer_process_err_devices(&e_info);
+	if (status & PCI_ERR_ROOT_UNCOR_RCV) {
+		int fatal = status & PCI_ERR_ROOT_FATAL_RCV;
+		int multi = status & PCI_ERR_ROOT_MULTI_UNCOR_RCV;
+		struct aer_err_info e_info = {
+			.id = ERR_UNCOR_ID(e_src->id),
+			.severity = fatal ? AER_FATAL : AER_NONFATAL,
+			.level = KERN_ERR,
+			.multi_error_valid = multi ? 1 : 0,
+		};
+
+		aer_isr_one_error_type(root, &e_info);
 	}
 }
 
@@ -1340,7 +1520,7 @@ static irqreturn_t aer_isr(int irq, void *context)
 		return IRQ_NONE;
 
 	while (kfifo_get(&rpc->aer_fifo, &e_src))
-		aer_isr_one_error(rpc, &e_src);
+		aer_isr_one_error(rpc->rpd, &e_src);
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c
index d8d2aa85a229..36f939f23d34 100644
--- a/drivers/pci/pcie/bwctrl.c
+++ b/drivers/pci/pcie/bwctrl.c
@@ -38,24 +38,14 @@
 /**
  * struct pcie_bwctrl_data - PCIe bandwidth controller
  * @set_speed_mutex:	Serializes link speed changes
- * @lbms_count:		Count for LBMS (since last reset)
  * @cdev:		Thermal cooling device associated with the port
  */
 struct pcie_bwctrl_data {
 	struct mutex set_speed_mutex;
-	atomic_t lbms_count;
 	struct thermal_cooling_device *cdev;
 };
 
-/*
- * Prevent port removal during LBMS count accessors and Link Speed changes.
- *
- * These have to be differentiated because pcie_bwctrl_change_speed() calls
- * pcie_retrain_link() which uses LBMS count reset accessor on success
- * (using just one rwsem triggers "possible recursive locking detected"
- * warning).
- */
-static DECLARE_RWSEM(pcie_bwctrl_lbms_rwsem);
+/* Prevent port removal during Link Speed changes. */
 static DECLARE_RWSEM(pcie_bwctrl_setspeed_rwsem);
 
 static bool pcie_valid_speed(enum pci_bus_speed speed)
@@ -127,18 +117,7 @@ static int pcie_bwctrl_change_speed(struct pci_dev *port, u16 target_speed, bool
 	if (ret != PCIBIOS_SUCCESSFUL)
 		return pcibios_err_to_errno(ret);
 
-	ret = pcie_retrain_link(port, use_lt);
-	if (ret < 0)
-		return ret;
-
-	/*
-	 * Ensure link speed updates also with platforms that have problems
-	 * with notifications.
-	 */
-	if (port->subordinate)
-		pcie_update_link_speed(port->subordinate);
-
-	return 0;
+	return pcie_retrain_link(port, use_lt);
 }
 
 /**
@@ -202,15 +181,14 @@ int pcie_set_target_speed(struct pci_dev *port, enum pci_bus_speed speed_req,
 
 static void pcie_bwnotif_enable(struct pcie_device *srv)
 {
-	struct pcie_bwctrl_data *data = srv->port->link_bwctrl;
 	struct pci_dev *port = srv->port;
 	u16 link_status;
 	int ret;
 
-	/* Count LBMS seen so far as one */
+	/* Note if LBMS has been seen so far */
 	ret = pcie_capability_read_word(port, PCI_EXP_LNKSTA, &link_status);
 	if (ret == PCIBIOS_SUCCESSFUL && link_status & PCI_EXP_LNKSTA_LBMS)
-		atomic_inc(&data->lbms_count);
+		set_bit(PCI_LINK_LBMS_SEEN, &port->priv_flags);
 
 	pcie_capability_set_word(port, PCI_EXP_LNKCTL,
 				 PCI_EXP_LNKCTL_LBMIE | PCI_EXP_LNKCTL_LABIE);
@@ -233,7 +211,6 @@ static void pcie_bwnotif_disable(struct pci_dev *port)
 static irqreturn_t pcie_bwnotif_irq(int irq, void *context)
 {
 	struct pcie_device *srv = context;
-	struct pcie_bwctrl_data *data = srv->port->link_bwctrl;
 	struct pci_dev *port = srv->port;
 	u16 link_status, events;
 	int ret;
@@ -247,7 +224,7 @@ static irqreturn_t pcie_bwnotif_irq(int irq, void *context)
 		return IRQ_NONE;
 
 	if (events & PCI_EXP_LNKSTA_LBMS)
-		atomic_inc(&data->lbms_count);
+		set_bit(PCI_LINK_LBMS_SEEN, &port->priv_flags);
 
 	pcie_capability_write_word(port, PCI_EXP_LNKSTA, events);
 
@@ -262,31 +239,10 @@ static irqreturn_t pcie_bwnotif_irq(int irq, void *context)
 	return IRQ_HANDLED;
 }
 
-void pcie_reset_lbms_count(struct pci_dev *port)
+void pcie_reset_lbms(struct pci_dev *port)
 {
-	struct pcie_bwctrl_data *data;
-
-	guard(rwsem_read)(&pcie_bwctrl_lbms_rwsem);
-	data = port->link_bwctrl;
-	if (data)
-		atomic_set(&data->lbms_count, 0);
-	else
-		pcie_capability_write_word(port, PCI_EXP_LNKSTA,
-					   PCI_EXP_LNKSTA_LBMS);
-}
-
-int pcie_lbms_count(struct pci_dev *port, unsigned long *val)
-{
-	struct pcie_bwctrl_data *data;
-
-	guard(rwsem_read)(&pcie_bwctrl_lbms_rwsem);
-	data = port->link_bwctrl;
-	if (!data)
-		return -ENOTTY;
-
-	*val = atomic_read(&data->lbms_count);
-
-	return 0;
+	clear_bit(PCI_LINK_LBMS_SEEN, &port->priv_flags);
+	pcie_capability_write_word(port, PCI_EXP_LNKSTA, PCI_EXP_LNKSTA_LBMS);
 }
 
 static int pcie_bwnotif_probe(struct pcie_device *srv)
@@ -308,18 +264,16 @@ static int pcie_bwnotif_probe(struct pcie_device *srv)
 		return ret;
 
 	scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) {
-		scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) {
-			port->link_bwctrl = data;
-
-			ret = request_irq(srv->irq, pcie_bwnotif_irq,
-					  IRQF_SHARED, "PCIe bwctrl", srv);
-			if (ret) {
-				port->link_bwctrl = NULL;
-				return ret;
-			}
+		port->link_bwctrl = data;
 
-			pcie_bwnotif_enable(srv);
+		ret = request_irq(srv->irq, pcie_bwnotif_irq,
+				  IRQF_SHARED, "PCIe bwctrl", srv);
+		if (ret) {
+			port->link_bwctrl = NULL;
+			return ret;
 		}
+
+		pcie_bwnotif_enable(srv);
 	}
 
 	pci_dbg(port, "enabled with IRQ %d\n", srv->irq);
@@ -339,13 +293,11 @@ static void pcie_bwnotif_remove(struct pcie_device *srv)
 	pcie_cooling_device_unregister(data->cdev);
 
 	scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) {
-		scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) {
-			pcie_bwnotif_disable(srv->port);
+		pcie_bwnotif_disable(srv->port);
 
-			free_irq(srv->irq, srv);
+		free_irq(srv->irq, srv);
 
-			srv->port->link_bwctrl = NULL;
-		}
+		srv->port->link_bwctrl = NULL;
 	}
 }
 
diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index df42f15c9829..fc18349614d7 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -222,7 +222,7 @@ static void dpc_process_rp_pio_error(struct pci_dev *pdev)
 			  dpc_tlp_log_len(pdev),
 			  pdev->subordinate->flit_mode,
 			  &tlp_log);
-	pcie_print_tlp_log(pdev, &tlp_log, dev_fmt(""));
+	pcie_print_tlp_log(pdev, &tlp_log, KERN_ERR, dev_fmt(""));
 
 	if (pdev->dpc_rp_log_size < PCIE_STD_NUM_TLP_HEADERLOG + 1)
 		goto clear_status;
@@ -252,46 +252,59 @@ static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev,
 	else
 		info->severity = AER_NONFATAL;
 
+	info->level = KERN_ERR;
+
+	info->dev[0] = dev;
+	info->error_dev_num = 1;
+
 	return 1;
 }
 
 void dpc_process_error(struct pci_dev *pdev)
 {
 	u16 cap = pdev->dpc_cap, status, source, reason, ext_reason;
-	struct aer_err_info info;
+	struct aer_err_info info = {};
 
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
-	pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, &source);
-
-	pci_info(pdev, "containment event, status:%#06x source:%#06x\n",
-		 status, source);
 
 	reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN;
-	ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT;
-	pci_warn(pdev, "%s detected\n",
-		 (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR) ?
-		 "unmasked uncorrectable error" :
-		 (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE) ?
-		 "ERR_NONFATAL" :
-		 (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ?
-		 "ERR_FATAL" :
-		 (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ?
-		 "RP PIO error" :
-		 (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ?
-		 "software trigger" :
-		 "reserved error");
-
-	/* show RP PIO error detail information */
-	if (pdev->dpc_rp_extensions &&
-	    reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT &&
-	    ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO)
-		dpc_process_rp_pio_error(pdev);
-	else if (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR &&
-		 dpc_get_aer_uncorrect_severity(pdev, &info) &&
-		 aer_get_device_error_info(pdev, &info)) {
-		aer_print_error(pdev, &info);
-		pci_aer_clear_nonfatal_status(pdev);
-		pci_aer_clear_fatal_status(pdev);
+
+	switch (reason) {
+	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR:
+		pci_warn(pdev, "containment event, status:%#06x: unmasked uncorrectable error detected\n",
+			 status);
+		if (dpc_get_aer_uncorrect_severity(pdev, &info) &&
+		    aer_get_device_error_info(&info, 0)) {
+			aer_print_error(&info, 0);
+			pci_aer_clear_nonfatal_status(pdev);
+			pci_aer_clear_fatal_status(pdev);
+		}
+		break;
+	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE:
+	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE:
+		pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID,
+				     &source);
+		pci_warn(pdev, "containment event, status:%#06x, %s received from %04x:%02x:%02x.%d\n",
+			 status,
+			 (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ?
+				"ERR_FATAL" : "ERR_NONFATAL",
+			 pci_domain_nr(pdev->bus), PCI_BUS_NUM(source),
+			 PCI_SLOT(source), PCI_FUNC(source));
+		break;
+	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT:
+		ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT;
+		pci_warn(pdev, "containment event, status:%#06x: %s detected\n",
+			 status,
+			 (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ?
+			 "RP PIO error" :
+			 (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ?
+			 "software trigger" :
+			 "reserved error");
+		/* show RP PIO error detail information */
+		if (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO &&
+		    pdev->dpc_rp_extensions)
+			dpc_process_rp_pio_error(pdev);
+		break;
 	}
 }
 
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 31090770fffc..de6381c690f5 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -271,7 +271,6 @@ failed:
 
 	pci_uevent_ers(bridge, PCI_ERS_RESULT_DISCONNECT);
 
-	/* TODO: Should kernel panic here? */
 	pci_info(bridge, "device recovery failed\n");
 
 	return status;
diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c
index 7cfb6c0d5dcb..ee5f615a9023 100644
--- a/drivers/pci/pcie/ptm.c
+++ b/drivers/pci/pcie/ptm.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/bitfield.h>
+#include <linux/debugfs.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/pci.h>
@@ -252,3 +253,302 @@ bool pcie_ptm_enabled(struct pci_dev *dev)
 	return dev->ptm_enabled;
 }
 EXPORT_SYMBOL(pcie_ptm_enabled);
+
+static ssize_t context_update_write(struct file *file, const char __user *ubuf,
+			     size_t count, loff_t *ppos)
+{
+	struct pci_ptm_debugfs *ptm_debugfs = file->private_data;
+	char buf[7];
+	int ret;
+	u8 mode;
+
+	if (!ptm_debugfs->ops->context_update_write)
+		return -EOPNOTSUPP;
+
+	if (count < 1 || count >= sizeof(buf))
+		return -EINVAL;
+
+	ret = copy_from_user(buf, ubuf, count);
+	if (ret)
+		return -EFAULT;
+
+	buf[count] = '\0';
+
+	if (sysfs_streq(buf, "auto"))
+		mode = PCIE_PTM_CONTEXT_UPDATE_AUTO;
+	else if (sysfs_streq(buf, "manual"))
+		mode = PCIE_PTM_CONTEXT_UPDATE_MANUAL;
+	else
+		return -EINVAL;
+
+	mutex_lock(&ptm_debugfs->lock);
+	ret = ptm_debugfs->ops->context_update_write(ptm_debugfs->pdata, mode);
+	mutex_unlock(&ptm_debugfs->lock);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static ssize_t context_update_read(struct file *file, char __user *ubuf,
+			     size_t count, loff_t *ppos)
+{
+	struct pci_ptm_debugfs *ptm_debugfs = file->private_data;
+	char buf[8]; /* Extra space for NULL termination at the end */
+	ssize_t pos;
+	u8 mode;
+
+	if (!ptm_debugfs->ops->context_update_read)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&ptm_debugfs->lock);
+	ptm_debugfs->ops->context_update_read(ptm_debugfs->pdata, &mode);
+	mutex_unlock(&ptm_debugfs->lock);
+
+	if (mode == PCIE_PTM_CONTEXT_UPDATE_AUTO)
+		pos = scnprintf(buf, sizeof(buf), "auto\n");
+	else
+		pos = scnprintf(buf, sizeof(buf), "manual\n");
+
+	return simple_read_from_buffer(ubuf, count, ppos, buf, pos);
+}
+
+static const struct file_operations context_update_fops = {
+	.open = simple_open,
+	.read = context_update_read,
+	.write = context_update_write,
+};
+
+static int context_valid_get(void *data, u64 *val)
+{
+	struct pci_ptm_debugfs *ptm_debugfs = data;
+	bool valid;
+	int ret;
+
+	if (!ptm_debugfs->ops->context_valid_read)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&ptm_debugfs->lock);
+	ret = ptm_debugfs->ops->context_valid_read(ptm_debugfs->pdata, &valid);
+	mutex_unlock(&ptm_debugfs->lock);
+	if (ret)
+		return ret;
+
+	*val = valid;
+
+	return 0;
+}
+
+static int context_valid_set(void *data, u64 val)
+{
+	struct pci_ptm_debugfs *ptm_debugfs = data;
+	int ret;
+
+	if (!ptm_debugfs->ops->context_valid_write)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&ptm_debugfs->lock);
+	ret = ptm_debugfs->ops->context_valid_write(ptm_debugfs->pdata, !!val);
+	mutex_unlock(&ptm_debugfs->lock);
+
+	return ret;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(context_valid_fops, context_valid_get,
+			 context_valid_set, "%llu\n");
+
+static int local_clock_get(void *data, u64 *val)
+{
+	struct pci_ptm_debugfs *ptm_debugfs = data;
+	u64 clock;
+	int ret;
+
+	if (!ptm_debugfs->ops->local_clock_read)
+		return -EOPNOTSUPP;
+
+	ret = ptm_debugfs->ops->local_clock_read(ptm_debugfs->pdata, &clock);
+	if (ret)
+		return ret;
+
+	*val = clock;
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(local_clock_fops, local_clock_get, NULL, "%llu\n");
+
+static int master_clock_get(void *data, u64 *val)
+{
+	struct pci_ptm_debugfs *ptm_debugfs = data;
+	u64 clock;
+	int ret;
+
+	if (!ptm_debugfs->ops->master_clock_read)
+		return -EOPNOTSUPP;
+
+	ret = ptm_debugfs->ops->master_clock_read(ptm_debugfs->pdata, &clock);
+	if (ret)
+		return ret;
+
+	*val = clock;
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(master_clock_fops, master_clock_get, NULL, "%llu\n");
+
+static int t1_get(void *data, u64 *val)
+{
+	struct pci_ptm_debugfs *ptm_debugfs = data;
+	u64 clock;
+	int ret;
+
+	if (!ptm_debugfs->ops->t1_read)
+		return -EOPNOTSUPP;
+
+	ret = ptm_debugfs->ops->t1_read(ptm_debugfs->pdata, &clock);
+	if (ret)
+		return ret;
+
+	*val = clock;
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(t1_fops, t1_get, NULL, "%llu\n");
+
+static int t2_get(void *data, u64 *val)
+{
+	struct pci_ptm_debugfs *ptm_debugfs = data;
+	u64 clock;
+	int ret;
+
+	if (!ptm_debugfs->ops->t2_read)
+		return -EOPNOTSUPP;
+
+	ret = ptm_debugfs->ops->t2_read(ptm_debugfs->pdata, &clock);
+	if (ret)
+		return ret;
+
+	*val = clock;
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(t2_fops, t2_get, NULL, "%llu\n");
+
+static int t3_get(void *data, u64 *val)
+{
+	struct pci_ptm_debugfs *ptm_debugfs = data;
+	u64 clock;
+	int ret;
+
+	if (!ptm_debugfs->ops->t3_read)
+		return -EOPNOTSUPP;
+
+	ret = ptm_debugfs->ops->t3_read(ptm_debugfs->pdata, &clock);
+	if (ret)
+		return ret;
+
+	*val = clock;
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(t3_fops, t3_get, NULL, "%llu\n");
+
+static int t4_get(void *data, u64 *val)
+{
+	struct pci_ptm_debugfs *ptm_debugfs = data;
+	u64 clock;
+	int ret;
+
+	if (!ptm_debugfs->ops->t4_read)
+		return -EOPNOTSUPP;
+
+	ret = ptm_debugfs->ops->t4_read(ptm_debugfs->pdata, &clock);
+	if (ret)
+		return ret;
+
+	*val = clock;
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(t4_fops, t4_get, NULL, "%llu\n");
+
+#define pcie_ptm_create_debugfs_file(pdata, mode, attr)			\
+	do {								\
+		if (ops->attr##_visible && ops->attr##_visible(pdata))	\
+			debugfs_create_file(#attr, mode, ptm_debugfs->debugfs, \
+					    ptm_debugfs, &attr##_fops);	\
+	} while (0)
+
+/*
+ * pcie_ptm_create_debugfs() - Create debugfs entries for the PTM context
+ * @dev: PTM capable component device
+ * @pdata: Private data of the PTM capable component device
+ * @ops: PTM callback structure
+ *
+ * Create debugfs entries for exposing the PTM context of the PTM capable
+ * components such as Root Complex and Endpoint controllers.
+ *
+ * Return: Pointer to 'struct pci_ptm_debugfs' if success, NULL otherwise.
+ */
+struct pci_ptm_debugfs *pcie_ptm_create_debugfs(struct device *dev, void *pdata,
+			  const struct pcie_ptm_ops *ops)
+{
+	struct pci_ptm_debugfs *ptm_debugfs;
+	char *dirname;
+	int ret;
+
+	/* Caller must provide check_capability() callback */
+	if (!ops->check_capability)
+		return NULL;
+
+	/* Check for PTM capability before creating debugfs attrbutes */
+	ret = ops->check_capability(pdata);
+	if (!ret) {
+		dev_dbg(dev, "PTM capability not present\n");
+		return NULL;
+	}
+
+	ptm_debugfs = kzalloc(sizeof(*ptm_debugfs), GFP_KERNEL);
+	if (!ptm_debugfs)
+		return NULL;
+
+	dirname = devm_kasprintf(dev, GFP_KERNEL, "pcie_ptm_%s", dev_name(dev));
+	if (!dirname)
+		return NULL;
+
+	ptm_debugfs->debugfs = debugfs_create_dir(dirname, NULL);
+	ptm_debugfs->pdata = pdata;
+	ptm_debugfs->ops = ops;
+	mutex_init(&ptm_debugfs->lock);
+
+	pcie_ptm_create_debugfs_file(pdata, 0644, context_update);
+	pcie_ptm_create_debugfs_file(pdata, 0644, context_valid);
+	pcie_ptm_create_debugfs_file(pdata, 0444, local_clock);
+	pcie_ptm_create_debugfs_file(pdata, 0444, master_clock);
+	pcie_ptm_create_debugfs_file(pdata, 0444, t1);
+	pcie_ptm_create_debugfs_file(pdata, 0444, t2);
+	pcie_ptm_create_debugfs_file(pdata, 0444, t3);
+	pcie_ptm_create_debugfs_file(pdata, 0444, t4);
+
+	return ptm_debugfs;
+}
+EXPORT_SYMBOL_GPL(pcie_ptm_create_debugfs);
+
+/*
+ * pcie_ptm_destroy_debugfs() - Destroy debugfs entries for the PTM context
+ * @ptm_debugfs: Pointer to the PTM debugfs struct
+ */
+void pcie_ptm_destroy_debugfs(struct pci_ptm_debugfs *ptm_debugfs)
+{
+	if (!ptm_debugfs)
+		return;
+
+	mutex_destroy(&ptm_debugfs->lock);
+	debugfs_remove_recursive(ptm_debugfs->debugfs);
+}
+EXPORT_SYMBOL_GPL(pcie_ptm_destroy_debugfs);
diff --git a/drivers/pci/pcie/tlp.c b/drivers/pci/pcie/tlp.c
index 890d5391d7f5..71f8fc9ea2ed 100644
--- a/drivers/pci/pcie/tlp.c
+++ b/drivers/pci/pcie/tlp.c
@@ -98,12 +98,14 @@ int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2,
  * pcie_print_tlp_log - Print TLP Header / Prefix Log contents
  * @dev: PCIe device
  * @log: TLP Log structure
+ * @level: Printk log level
  * @pfx: String prefix
  *
  * Prints TLP Header and Prefix Log information held by @log.
  */
 void pcie_print_tlp_log(const struct pci_dev *dev,
-			const struct pcie_tlp_log *log, const char *pfx)
+			const struct pcie_tlp_log *log, const char *level,
+			const char *pfx)
 {
 	/* EE_PREFIX_STR fits the extended DW space needed for the Flit mode */
 	char buf[11 * PCIE_STD_MAX_TLP_HEADERLOG + 1];
@@ -130,6 +132,6 @@ void pcie_print_tlp_log(const struct pci_dev *dev,
 		}
 	}
 
-	pci_err(dev, "%sTLP Header%s: %s\n", pfx,
+	dev_printk(level, &dev->dev, "%sTLP Header%s: %s\n", pfx,
 		log->flit ? " (Flit)" : "", buf);
 }
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 364fa2a514f8..4b8693ec9e4c 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2058,7 +2058,7 @@ int pci_setup_device(struct pci_dev *dev)
 		if (class == PCI_CLASS_BRIDGE_PCI)
 			goto bad;
 		pci_read_irq(dev);
-		pci_read_bases(dev, 6, PCI_ROM_ADDRESS);
+		pci_read_bases(dev, PCI_STD_NUM_BARS, PCI_ROM_ADDRESS);
 
 		pci_subsystem_ids(dev, &dev->subsystem_vendor, &dev->subsystem_device);
 
@@ -2711,7 +2711,6 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus)
 	pci_set_msi_domain(dev);
 
 	/* Notifier could use PCI capabilities */
-	dev->match_driver = false;
 	ret = device_add(&dev->dev);
 	WARN_ON(ret < 0);
 
diff --git a/drivers/pci/pwrctrl/Kconfig b/drivers/pci/pwrctrl/Kconfig
index 990cab67d413..6956c1854811 100644
--- a/drivers/pci/pwrctrl/Kconfig
+++ b/drivers/pci/pwrctrl/Kconfig
@@ -1,19 +1,19 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-config HAVE_PWRCTL
+config HAVE_PWRCTRL
 	bool
 
-config PCI_PWRCTL
+config PCI_PWRCTRL
 	tristate
 
-config PCI_PWRCTL_PWRSEQ
+config PCI_PWRCTRL_PWRSEQ
 	tristate
 	select POWER_SEQUENCING
-	select PCI_PWRCTL
+	select PCI_PWRCTRL
 
-config PCI_PWRCTL_SLOT
+config PCI_PWRCTRL_SLOT
 	tristate "PCI Power Control driver for PCI slots"
-	select PCI_PWRCTL
+	select PCI_PWRCTRL
 	help
 	  Say Y here to enable the PCI Power Control driver to control the power
 	  state of PCI slots.
@@ -21,3 +21,13 @@ config PCI_PWRCTL_SLOT
 	  This is a generic driver that controls the power state of different
 	  PCI slots. The voltage regulators powering the rails of the PCI slots
 	  are expected to be defined in the devicetree node of the PCI bridge.
+
+# deprecated
+config HAVE_PWRCTL
+	bool
+	select HAVE_PWRCTRL
+
+# deprecated
+config PCI_PWRCTL_PWRSEQ
+	tristate
+	select PCI_PWRCTRL_PWRSEQ
diff --git a/drivers/pci/pwrctrl/Makefile b/drivers/pci/pwrctrl/Makefile
index ddfb12c5aadf..a4e5808d7850 100644
--- a/drivers/pci/pwrctrl/Makefile
+++ b/drivers/pci/pwrctrl/Makefile
@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-obj-$(CONFIG_PCI_PWRCTL)		+= pci-pwrctrl-core.o
+obj-$(CONFIG_PCI_PWRCTRL)		+= pci-pwrctrl-core.o
 pci-pwrctrl-core-y			:= core.o
 
-obj-$(CONFIG_PCI_PWRCTL_PWRSEQ)		+= pci-pwrctrl-pwrseq.o
+obj-$(CONFIG_PCI_PWRCTRL_PWRSEQ)	+= pci-pwrctrl-pwrseq.o
 
-obj-$(CONFIG_PCI_PWRCTL_SLOT)		+= pci-pwrctl-slot.o
-pci-pwrctl-slot-y			:= slot.o
+obj-$(CONFIG_PCI_PWRCTRL_SLOT)		+= pci-pwrctrl-slot.o
+pci-pwrctrl-slot-y			:= slot.o
diff --git a/drivers/pci/pwrctrl/core.c b/drivers/pci/pwrctrl/core.c
index 9cc7e2b7f2b5..6bdbfed584d6 100644
--- a/drivers/pci/pwrctrl/core.c
+++ b/drivers/pci/pwrctrl/core.c
@@ -101,6 +101,8 @@ EXPORT_SYMBOL_GPL(pci_pwrctrl_device_set_ready);
  */
 void pci_pwrctrl_device_unset_ready(struct pci_pwrctrl *pwrctrl)
 {
+	cancel_work_sync(&pwrctrl->work);
+
 	/*
 	 * We don't have to delete the link here. Typically, this function
 	 * is only called when the power control device is being detached. If
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 94daca15a096..d7f4ee634263 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -38,14 +38,10 @@
 
 static bool pcie_lbms_seen(struct pci_dev *dev, u16 lnksta)
 {
-	unsigned long count;
-	int ret;
-
-	ret = pcie_lbms_count(dev, &count);
-	if (ret < 0)
-		return lnksta & PCI_EXP_LNKSTA_LBMS;
+	if (test_bit(PCI_LINK_LBMS_SEEN, &dev->priv_flags))
+		return true;
 
-	return count > 0;
+	return lnksta & PCI_EXP_LNKSTA_LBMS;
 }
 
 /*
@@ -4995,6 +4991,18 @@ static int pci_quirk_brcm_acs(struct pci_dev *dev, u16 acs_flags)
 		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
 }
 
+static int pci_quirk_loongson_acs(struct pci_dev *dev, u16 acs_flags)
+{
+	/*
+	 * Loongson PCIe Root Ports don't advertise an ACS capability, but
+	 * they do not allow peer-to-peer transactions between Root Ports.
+	 * Allow each Root Port to be in a separate IOMMU group by masking
+	 * SV/RR/CR/UF bits.
+	 */
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
+}
+
 /*
  * Wangxun 40G/25G/10G/1G NICs have no ACS capability, but on
  * multi-function devices, the hardware isolates the functions by
@@ -5128,6 +5136,17 @@ static const struct pci_dev_acs_enabled {
 	{ PCI_VENDOR_ID_BROADCOM, 0x1762, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_BROADCOM, 0x1763, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs },
+	/* Loongson PCIe Root Ports */
+	{ PCI_VENDOR_ID_LOONGSON, 0x3C09, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x3C19, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x3C29, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A09, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A19, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A29, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A39, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A49, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A59, pci_quirk_loongson_acs },
+	{ PCI_VENDOR_ID_LOONGSON, 0x7A69, pci_quirk_loongson_acs },
 	/* Amazon Annapurna Labs */
 	{ PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, pci_quirk_al_acs },
 	/* Zhaoxin multi-function devices */
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index e994c546422c..07c3d021a47e 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -776,8 +776,7 @@ static void __pci_setup_bridge(struct pci_bus *bus, unsigned long type)
 {
 	struct pci_dev *bridge = bus->self;
 
-	pci_info(bridge, "PCI bridge to %pR\n",
-		 &bus->busn_res);
+	pci_info(bridge, "PCI bridge to %pR\n", &bus->busn_res);
 
 	if (type & IORESOURCE_IO)
 		pci_setup_bridge_io(bridge);
@@ -2302,8 +2301,8 @@ void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus)
 
 		/* Depth last, allocate resources and update the hardware. */
 		__pci_bus_assign_resources(bus, add_list, &fail_head);
-		if (add_list)
-			BUG_ON(!list_empty(add_list));
+		if (WARN_ON_ONCE(add_list && !list_empty(add_list)))
+			free_list(add_list);
 		tried_times++;
 
 		/* Any device complain? */
@@ -2365,7 +2364,8 @@ void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge)
 		pci_bridge_distribute_available_resources(bridge, &add_list);
 
 		__pci_bridge_assign_resources(bridge, &add_list, &fail_head);
-		BUG_ON(!list_empty(&add_list));
+		if (WARN_ON_ONCE(!list_empty(&add_list)))
+			free_list(&add_list);
 		tried_times++;
 
 		if (list_empty(&fail_head))
@@ -2441,7 +2441,8 @@ int pci_reassign_bridge_resources(struct pci_dev *bridge, unsigned long type)
 
 	__pci_bus_size_bridges(bridge->subordinate, &added);
 	__pci_bridge_assign_resources(bridge, &added, &failed);
-	BUG_ON(!list_empty(&added));
+	if (WARN_ON_ONCE(!list_empty(&added)))
+		free_list(&added);
 
 	if (!list_empty(&failed)) {
 		ret = -ENOSPC;
@@ -2497,6 +2498,7 @@ void pci_assign_unassigned_bus_resources(struct pci_bus *bus)
 			__pci_bus_size_bridges(dev->subordinate, &add_list);
 	up_read(&pci_bus_sem);
 	__pci_bus_assign_resources(bus, &add_list, NULL);
-	BUG_ON(!list_empty(&add_list));
+	if (WARN_ON_ONCE(!list_empty(&add_list)))
+		free_list(&add_list);
 }
 EXPORT_SYMBOL_GPL(pci_assign_unassigned_bus_resources);
diff --git a/drivers/pcmcia/cardbus.c b/drivers/pcmcia/cardbus.c
index 45c8252c8edc..5e5cf2c3e2c8 100644
--- a/drivers/pcmcia/cardbus.c
+++ b/drivers/pcmcia/cardbus.c
@@ -72,7 +72,6 @@ int __ref cb_alloc(struct pcmcia_socket *s)
 	pci_lock_rescan_remove();
 
 	s->functions = pci_scan_slot(bus, PCI_DEVFN(0, 0));
-	pci_fixup_cardbus(bus);
 
 	max = bus->busn_res.start;
 	for (pass = 0; pass < 2; pass++)
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index 8d58efe998ec..58c911e1b2d2 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -43,6 +43,14 @@ config PHY_PISTACHIO_USB
 	help
 	  Enable this to support the USB2.0 PHY on the IMG Pistachio SoC.
 
+config PHY_SNPS_EUSB2
+	tristate "SNPS eUSB2 PHY Driver"
+	depends on OF && (ARCH_EXYNOS || ARCH_QCOM || COMPILE_TEST)
+	select GENERIC_PHY
+	help
+	  Enable support for the USB high-speed SNPS eUSB2 phy on select
+	  SoCs. The PHY is usually paired with a Synopsys DWC3 USB controller.
+
 config PHY_XGENE
 	tristate "APM X-Gene 15Gbps PHY support"
 	depends on HAS_IOMEM && OF && (ARCH_XGENE || COMPILE_TEST)
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index e281442acc75..c670a8dac468 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_PHY_CAN_TRANSCEIVER)	+= phy-can-transceiver.o
 obj-$(CONFIG_PHY_LPC18XX_USB_OTG)	+= phy-lpc18xx-usb-otg.o
 obj-$(CONFIG_PHY_XGENE)			+= phy-xgene.o
 obj-$(CONFIG_PHY_PISTACHIO_USB)		+= phy-pistachio-usb.o
+obj-$(CONFIG_PHY_SNPS_EUSB2)		+= phy-snps-eusb2.o
 obj-$(CONFIG_USB_LGM_PHY)		+= phy-lgm-usb.o
 obj-$(CONFIG_PHY_AIROHA_PCIE)		+= phy-airoha-pcie.o
 obj-$(CONFIG_PHY_NXP_PTN3222)		+= phy-nxp-ptn3222.o
diff --git a/drivers/phy/amlogic/phy-meson-axg-mipi-dphy.c b/drivers/phy/amlogic/phy-meson-axg-mipi-dphy.c
index 08a86962d949..c4a56b9d3289 100644
--- a/drivers/phy/amlogic/phy-meson-axg-mipi-dphy.c
+++ b/drivers/phy/amlogic/phy-meson-axg-mipi-dphy.c
@@ -377,13 +377,9 @@ static int phy_meson_axg_mipi_dphy_probe(struct platform_device *pdev)
 		return ret;
 
 	phy = devm_phy_create(dev, NULL, &phy_meson_axg_mipi_dphy_ops);
-	if (IS_ERR(phy)) {
-		ret = PTR_ERR(phy);
-		if (ret != -EPROBE_DEFER)
-			dev_err(dev, "failed to create PHY\n");
-
-		return ret;
-	}
+	if (IS_ERR(phy))
+		return dev_err_probe(dev, PTR_ERR(phy),
+				     "failed to create PHY\n");
 
 	phy_set_drvdata(phy, priv);
 
diff --git a/drivers/phy/amlogic/phy-meson-axg-mipi-pcie-analog.c b/drivers/phy/amlogic/phy-meson-axg-mipi-pcie-analog.c
index ae898f93f97b..c0ba2852dbb8 100644
--- a/drivers/phy/amlogic/phy-meson-axg-mipi-pcie-analog.c
+++ b/drivers/phy/amlogic/phy-meson-axg-mipi-pcie-analog.c
@@ -200,7 +200,6 @@ static int phy_axg_mipi_pcie_analog_probe(struct platform_device *pdev)
 	struct phy_axg_mipi_pcie_analog_priv *priv;
 	struct device_node *np = dev->of_node, *parent_np;
 	struct regmap *map;
-	int ret;
 
 	priv = devm_kmalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -219,12 +218,9 @@ static int phy_axg_mipi_pcie_analog_probe(struct platform_device *pdev)
 	priv->regmap = map;
 
 	priv->phy = devm_phy_create(dev, np, &phy_axg_mipi_pcie_analog_ops);
-	if (IS_ERR(priv->phy)) {
-		ret = PTR_ERR(priv->phy);
-		if (ret != -EPROBE_DEFER)
-			dev_err(dev, "failed to create PHY\n");
-		return ret;
-	}
+	if (IS_ERR(priv->phy))
+		return dev_err_probe(dev, PTR_ERR(priv->phy),
+				     "failed to create PHY\n");
 
 	phy_set_drvdata(priv->phy, priv);
 	dev_set_drvdata(dev, priv);
diff --git a/drivers/phy/amlogic/phy-meson-axg-pcie.c b/drivers/phy/amlogic/phy-meson-axg-pcie.c
index 60be5cdc600b..14dee73f9cb5 100644
--- a/drivers/phy/amlogic/phy-meson-axg-pcie.c
+++ b/drivers/phy/amlogic/phy-meson-axg-pcie.c
@@ -131,20 +131,11 @@ static int phy_axg_pcie_probe(struct platform_device *pdev)
 	struct phy_axg_pcie_priv *priv;
 	struct device_node *np = dev->of_node;
 	void __iomem *base;
-	int ret;
 
 	priv = devm_kmalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
-	priv->phy = devm_phy_create(dev, np, &phy_axg_pcie_ops);
-	if (IS_ERR(priv->phy)) {
-		ret = PTR_ERR(priv->phy);
-		if (ret != -EPROBE_DEFER)
-			dev_err(dev, "failed to create PHY\n");
-		return ret;
-	}
-
 	base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
@@ -162,6 +153,11 @@ static int phy_axg_pcie_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->analog))
 		return PTR_ERR(priv->analog);
 
+	priv->phy = devm_phy_create(dev, np, &phy_axg_pcie_ops);
+	if (IS_ERR(priv->phy))
+		return dev_err_probe(dev, PTR_ERR(priv->phy),
+				     "failed to create PHY\n");
+
 	phy_set_drvdata(priv->phy, priv);
 	dev_set_drvdata(dev, priv);
 	pphy = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
diff --git a/drivers/phy/amlogic/phy-meson-g12a-usb2.c b/drivers/phy/amlogic/phy-meson-g12a-usb2.c
index 0e0b5c00b676..66bf0b7ef8ed 100644
--- a/drivers/phy/amlogic/phy-meson-g12a-usb2.c
+++ b/drivers/phy/amlogic/phy-meson-g12a-usb2.c
@@ -339,13 +339,9 @@ static int phy_meson_g12a_usb2_probe(struct platform_device *pdev)
 		return ret;
 
 	phy = devm_phy_create(dev, NULL, &phy_meson_g12a_usb2_ops);
-	if (IS_ERR(phy)) {
-		ret = PTR_ERR(phy);
-		if (ret != -EPROBE_DEFER)
-			dev_err(dev, "failed to create PHY\n");
-
-		return ret;
-	}
+	if (IS_ERR(phy))
+		return dev_err_probe(dev, PTR_ERR(phy),
+				     "failed to create PHY\n");
 
 	phy_set_bus_width(phy, 8);
 	phy_set_drvdata(phy, priv);
diff --git a/drivers/phy/amlogic/phy-meson-gxl-usb2.c b/drivers/phy/amlogic/phy-meson-gxl-usb2.c
index 14ea89927ab1..6b390304f723 100644
--- a/drivers/phy/amlogic/phy-meson-gxl-usb2.c
+++ b/drivers/phy/amlogic/phy-meson-gxl-usb2.c
@@ -237,7 +237,6 @@ static int phy_meson_gxl_usb2_probe(struct platform_device *pdev)
 	struct phy_meson_gxl_usb2_priv *priv;
 	struct phy *phy;
 	void __iomem *base;
-	int ret;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -266,13 +265,9 @@ static int phy_meson_gxl_usb2_probe(struct platform_device *pdev)
 		return PTR_ERR(priv->reset);
 
 	phy = devm_phy_create(dev, NULL, &phy_meson_gxl_usb2_ops);
-	if (IS_ERR(phy)) {
-		ret = PTR_ERR(phy);
-		if (ret != -EPROBE_DEFER)
-			dev_err(dev, "failed to create PHY\n");
-
-		return ret;
-	}
+	if (IS_ERR(phy))
+		return dev_err_probe(dev, PTR_ERR(phy),
+				     "failed to create PHY\n");
 
 	phy_set_drvdata(phy, priv);
 
diff --git a/drivers/phy/amlogic/phy-meson8b-usb2.c b/drivers/phy/amlogic/phy-meson8b-usb2.c
index d63147c41b8c..a553231a9f7c 100644
--- a/drivers/phy/amlogic/phy-meson8b-usb2.c
+++ b/drivers/phy/amlogic/phy-meson8b-usb2.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2016 Martin Blumenstingl <martin.blumenstingl@googlemail.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/io.h>
@@ -39,9 +40,7 @@
 	#define REG_CTRL_TX_BITSTUFF_ENN		BIT(18)
 	#define REG_CTRL_COMMON_ON			BIT(19)
 	#define REG_CTRL_REF_CLK_SEL_MASK		GENMASK(21, 20)
-	#define REG_CTRL_REF_CLK_SEL_SHIFT		20
 	#define REG_CTRL_FSEL_MASK			GENMASK(24, 22)
-	#define REG_CTRL_FSEL_SHIFT			22
 	#define REG_CTRL_PORT_RESET			BIT(25)
 	#define REG_CTRL_THREAD_ID_MASK			GENMASK(31, 26)
 
@@ -166,33 +165,29 @@ static int phy_meson8b_usb2_power_on(struct phy *phy)
 		return ret;
 	}
 
-	regmap_update_bits(priv->regmap, REG_CONFIG, REG_CONFIG_CLK_32k_ALTSEL,
-			   REG_CONFIG_CLK_32k_ALTSEL);
+	regmap_set_bits(priv->regmap, REG_CONFIG, REG_CONFIG_CLK_32k_ALTSEL);
 
 	regmap_update_bits(priv->regmap, REG_CTRL, REG_CTRL_REF_CLK_SEL_MASK,
-			   0x2 << REG_CTRL_REF_CLK_SEL_SHIFT);
+			   FIELD_PREP(REG_CTRL_REF_CLK_SEL_MASK, 0x2));
 
 	regmap_update_bits(priv->regmap, REG_CTRL, REG_CTRL_FSEL_MASK,
-			   0x5 << REG_CTRL_FSEL_SHIFT);
+			   FIELD_PREP(REG_CTRL_FSEL_MASK, 0x5));
 
 	/* reset the PHY */
-	regmap_update_bits(priv->regmap, REG_CTRL, REG_CTRL_POWER_ON_RESET,
-			   REG_CTRL_POWER_ON_RESET);
+	regmap_set_bits(priv->regmap, REG_CTRL, REG_CTRL_POWER_ON_RESET);
 	udelay(RESET_COMPLETE_TIME);
-	regmap_update_bits(priv->regmap, REG_CTRL, REG_CTRL_POWER_ON_RESET, 0);
+	regmap_clear_bits(priv->regmap, REG_CTRL, REG_CTRL_POWER_ON_RESET);
 	udelay(RESET_COMPLETE_TIME);
 
-	regmap_update_bits(priv->regmap, REG_CTRL, REG_CTRL_SOF_TOGGLE_OUT,
-			   REG_CTRL_SOF_TOGGLE_OUT);
+	regmap_set_bits(priv->regmap, REG_CTRL, REG_CTRL_SOF_TOGGLE_OUT);
 
 	if (priv->dr_mode == USB_DR_MODE_HOST) {
-		regmap_update_bits(priv->regmap, REG_DBG_UART,
-				   REG_DBG_UART_SET_IDDQ, 0);
+		regmap_clear_bits(priv->regmap, REG_DBG_UART,
+				  REG_DBG_UART_SET_IDDQ);
 
 		if (priv->match->host_enable_aca) {
-			regmap_update_bits(priv->regmap, REG_ADP_BC,
-					   REG_ADP_BC_ACA_ENABLE,
-					   REG_ADP_BC_ACA_ENABLE);
+			regmap_set_bits(priv->regmap, REG_ADP_BC,
+					REG_ADP_BC_ACA_ENABLE);
 
 			udelay(ACA_ENABLE_COMPLETE_TIME);
 
@@ -215,17 +210,15 @@ static int phy_meson8b_usb2_power_off(struct phy *phy)
 	struct phy_meson8b_usb2_priv *priv = phy_get_drvdata(phy);
 
 	if (priv->dr_mode == USB_DR_MODE_HOST)
-		regmap_update_bits(priv->regmap, REG_DBG_UART,
-				   REG_DBG_UART_SET_IDDQ,
-				   REG_DBG_UART_SET_IDDQ);
+		regmap_set_bits(priv->regmap, REG_DBG_UART,
+				REG_DBG_UART_SET_IDDQ);
 
 	clk_disable_unprepare(priv->clk_usb);
 	clk_disable_unprepare(priv->clk_usb_general);
 	reset_control_rearm(priv->reset);
 
 	/* power off the PHY by putting it into reset mode */
-	regmap_update_bits(priv->regmap, REG_CTRL, REG_CTRL_POWER_ON_RESET,
-			   REG_CTRL_POWER_ON_RESET);
+	regmap_set_bits(priv->regmap, REG_CTRL, REG_CTRL_POWER_ON_RESET);
 
 	return 0;
 }
diff --git a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c
index dc452610934a..8a5ed50f2da0 100644
--- a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c
+++ b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c
@@ -43,6 +43,8 @@
 #define   USB_CTRL_SETUP_tca_drv_sel_MASK		BIT(24)
 #define   USB_CTRL_SETUP_STRAP_IPP_SEL_MASK		BIT(25)
 #define USB_CTRL_USB_PM			0x04
+#define   USB_CTRL_USB_PM_REF_S2_CLK_SWITCH_EN_MASK	BIT(1)
+#define   USB_CTRL_USB_PM_UTMI_S2_CLK_SWITCH_EN_MASK	BIT(2)
 #define   USB_CTRL_USB_PM_XHC_S2_CLK_SWITCH_EN_MASK	BIT(3)
 #define   USB_CTRL_USB_PM_XHC_PME_EN_MASK		BIT(4)
 #define   USB_CTRL_USB_PM_XHC_SOFT_RESETB_MASK		BIT(22)
@@ -61,6 +63,13 @@
 #define   USB_CTRL_CTLR_CSHCR_ctl_pme_en_MASK		BIT(18)
 #define USB_CTRL_P0_U2PHY_CFG1		0x68
 #define   USB_CTRL_P0_U2PHY_CFG1_COMMONONN_MASK		BIT(10)
+#define USB_CTRL_P0_U2PHY_CFG2		0x6c
+#define   USB_CTRL_P0_U2PHY_CFG2_TXVREFTUNE0_MASK	GENMASK(20, 17)
+#define   USB_CTRL_P0_U2PHY_CFG2_TXVREFTUNE0_SHIFT	17
+#define   USB_CTRL_P0_U2PHY_CFG2_TXRESTUNE0_MASK	GENMASK(24, 23)
+#define   USB_CTRL_P0_U2PHY_CFG2_TXRESTUNE0_SHIFT	23
+#define   USB_CTRL_P0_U2PHY_CFG2_TXPREEMPAMPTUNE0_MASK	GENMASK(26, 25)
+#define   USB_CTRL_P0_U2PHY_CFG2_TXPREEMPAMPTUNE0_SHIFT	25
 
 /* Register definitions for the USB_PHY block in 7211b0 */
 #define USB_PHY_PLL_CTL			0x00
@@ -369,6 +378,42 @@ static void usb_uninit_common_7216(struct brcm_usb_init_params *params)
 	}
 }
 
+static void usb_init_common_74110(struct brcm_usb_init_params *params)
+{
+	void __iomem *ctrl = params->regs[BRCM_REGS_CTRL];
+	u32 reg;
+
+	reg = brcm_usb_readl(USB_CTRL_REG(ctrl, USB_PM));
+	reg &= ~(USB_CTRL_MASK(USB_PM, REF_S2_CLK_SWITCH_EN) |
+		USB_CTRL_MASK(USB_PM, UTMI_S2_CLK_SWITCH_EN));
+	brcm_usb_writel(reg, USB_CTRL_REG(ctrl, USB_PM));
+
+	usb_init_common_7216(params);
+
+	reg = brcm_usb_readl(USB_CTRL_REG(ctrl, P0_U2PHY_CFG2));
+	reg &= ~(USB_CTRL_P0_U2PHY_CFG2_TXVREFTUNE0_MASK |
+		 USB_CTRL_P0_U2PHY_CFG2_TXRESTUNE0_MASK |
+		 USB_CTRL_P0_U2PHY_CFG2_TXPREEMPAMPTUNE0_MASK);
+	reg |= (0x6 << USB_CTRL_P0_U2PHY_CFG2_TXVREFTUNE0_SHIFT) |
+		(0x3 << USB_CTRL_P0_U2PHY_CFG2_TXRESTUNE0_SHIFT) |
+		(0x2 << USB_CTRL_P0_U2PHY_CFG2_TXPREEMPAMPTUNE0_SHIFT);
+	brcm_usb_writel(reg, USB_CTRL_REG(ctrl, P0_U2PHY_CFG2));
+}
+
+static void usb_uninit_common_74110(struct brcm_usb_init_params *params)
+{
+	void __iomem *ctrl = params->regs[BRCM_REGS_CTRL];
+	u32 reg;
+
+	if (params->wake_enabled) {
+		reg = brcm_usb_readl(USB_CTRL_REG(ctrl, USB_PM));
+		reg |= (USB_CTRL_MASK(USB_PM, REF_S2_CLK_SWITCH_EN) |
+		       USB_CTRL_MASK(USB_PM, UTMI_S2_CLK_SWITCH_EN));
+		brcm_usb_writel(reg, USB_CTRL_REG(ctrl, USB_PM));
+	}
+	usb_uninit_common_7216(params);
+}
+
 static void usb_uninit_common_7211b0(struct brcm_usb_init_params *params)
 {
 	void __iomem *ctrl = params->regs[BRCM_REGS_CTRL];
@@ -426,6 +471,16 @@ static void usb_set_dual_select(struct brcm_usb_init_params *params)
 	brcm_usb_writel(reg, USB_CTRL_REG(ctrl, USB_DEVICE_CTL1));
 }
 
+static const struct brcm_usb_init_ops bcm74110_ops = {
+	.init_ipp = usb_init_ipp,
+	.init_common = usb_init_common_74110,
+	.init_xhci = usb_init_xhci,
+	.uninit_common = usb_uninit_common_74110,
+	.uninit_xhci = usb_uninit_xhci,
+	.get_dual_select = usb_get_dual_select,
+	.set_dual_select = usb_set_dual_select,
+};
+
 static const struct brcm_usb_init_ops bcm7216_ops = {
 	.init_ipp = usb_init_ipp,
 	.init_common = usb_init_common_7216,
@@ -446,6 +501,12 @@ static const struct brcm_usb_init_ops bcm7211b0_ops = {
 	.set_dual_select = usb_set_dual_select,
 };
 
+void brcm_usb_dvr_init_74110(struct brcm_usb_init_params *params)
+{
+	params->family_name = "74110";
+	params->ops = &bcm74110_ops;
+}
+
 void brcm_usb_dvr_init_7216(struct brcm_usb_init_params *params)
 {
 
diff --git a/drivers/phy/broadcom/phy-brcm-usb-init.h b/drivers/phy/broadcom/phy-brcm-usb-init.h
index c1a88f5cd4cd..4c7be78d0b14 100644
--- a/drivers/phy/broadcom/phy-brcm-usb-init.h
+++ b/drivers/phy/broadcom/phy-brcm-usb-init.h
@@ -72,6 +72,7 @@ struct  brcm_usb_init_params {
 	bool wake_enabled;
 };
 
+void brcm_usb_dvr_init_74110(struct brcm_usb_init_params *params);
 void brcm_usb_dvr_init_4908(struct brcm_usb_init_params *params);
 void brcm_usb_dvr_init_7445(struct brcm_usb_init_params *params);
 void brcm_usb_dvr_init_7216(struct brcm_usb_init_params *params);
diff --git a/drivers/phy/broadcom/phy-brcm-usb.c b/drivers/phy/broadcom/phy-brcm-usb.c
index 6362ca5b7fb6..0666864c2f77 100644
--- a/drivers/phy/broadcom/phy-brcm-usb.c
+++ b/drivers/phy/broadcom/phy-brcm-usb.c
@@ -283,6 +283,16 @@ static const struct attribute_group brcm_usb_phy_group = {
 	.attrs = brcm_usb_phy_attrs,
 };
 
+static const struct match_chip_info chip_info_74110 = {
+	.init_func = &brcm_usb_dvr_init_74110,
+	.required_regs = {
+		BRCM_REGS_CTRL,
+		BRCM_REGS_XHCI_EC,
+		BRCM_REGS_XHCI_GBL,
+		-1,
+	},
+};
+
 static const struct match_chip_info chip_info_4908 = {
 	.init_func = &brcm_usb_dvr_init_4908,
 	.required_regs = {
@@ -326,6 +336,10 @@ static const struct match_chip_info chip_info_7445 = {
 
 static const struct of_device_id brcm_usb_dt_ids[] = {
 	{
+		.compatible = "brcm,bcm74110-usb-phy",
+		.data = &chip_info_74110,
+	},
+	{
 		.compatible = "brcm,bcm4908-usb-phy",
 		.data = &chip_info_4908,
 	},
diff --git a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c
index 7355d9921b64..68fcc8114d75 100644
--- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c
+++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c
@@ -238,24 +238,21 @@ static int imx8_pcie_phy_probe(struct platform_device *pdev)
 		imx8_phy->clkreq_unused = false;
 
 	imx8_phy->clk = devm_clk_get(dev, "ref");
-	if (IS_ERR(imx8_phy->clk)) {
-		dev_err(dev, "failed to get imx pcie phy clock\n");
-		return PTR_ERR(imx8_phy->clk);
-	}
+	if (IS_ERR(imx8_phy->clk))
+		return dev_err_probe(dev, PTR_ERR(imx8_phy->clk),
+				     "failed to get imx pcie phy clock\n");
 
 	/* Grab GPR config register range */
 	imx8_phy->iomuxc_gpr =
 		 syscon_regmap_lookup_by_compatible(imx8_phy->drvdata->gpr);
-	if (IS_ERR(imx8_phy->iomuxc_gpr)) {
-		dev_err(dev, "unable to find iomuxc registers\n");
-		return PTR_ERR(imx8_phy->iomuxc_gpr);
-	}
+	if (IS_ERR(imx8_phy->iomuxc_gpr))
+		return dev_err_probe(dev, PTR_ERR(imx8_phy->iomuxc_gpr),
+				     "unable to find iomuxc registers\n");
 
 	imx8_phy->reset = devm_reset_control_get_exclusive(dev, "pciephy");
-	if (IS_ERR(imx8_phy->reset)) {
-		dev_err(dev, "Failed to get PCIEPHY reset control\n");
-		return PTR_ERR(imx8_phy->reset);
-	}
+	if (IS_ERR(imx8_phy->reset))
+		return dev_err_probe(dev, PTR_ERR(imx8_phy->reset),
+				     "Failed to get PCIEPHY reset control\n");
 
 	if (imx8_phy->drvdata->variant == IMX8MP) {
 		imx8_phy->perst =
diff --git a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c
index a974ef94de9a..b94f242420fc 100644
--- a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c
+++ b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c
@@ -293,6 +293,28 @@ static u32 phy_tx_vref_tune_from_property(u32 percent)
 	return DIV_ROUND_CLOSEST(percent - 94U, 2);
 }
 
+static u32 imx95_phy_tx_vref_tune_from_property(u32 percent)
+{
+	percent = clamp(percent, 90U, 108U);
+
+	switch (percent) {
+	case 90 ... 91:
+		percent = 0;
+		break;
+	case 92 ... 96:
+		percent -= 91;
+		break;
+	case 97 ... 104:
+		percent -= 92;
+		break;
+	case 105 ... 108:
+		percent -= 93;
+		break;
+	}
+
+	return percent;
+}
+
 static u32 phy_tx_rise_tune_from_property(u32 percent)
 {
 	switch (percent) {
@@ -307,6 +329,22 @@ static u32 phy_tx_rise_tune_from_property(u32 percent)
 	}
 }
 
+static u32 imx95_phy_tx_rise_tune_from_property(u32 percent)
+{
+	percent = clamp(percent, 90U, 120U);
+
+	switch (percent) {
+	case 90 ... 99:
+		return 3;
+	case 101 ... 115:
+		return 1;
+	case 116 ... 120:
+		return 0;
+	default:
+		return 2;
+	}
+}
+
 static u32 phy_tx_preemp_amp_tune_from_property(u32 microamp)
 {
 	microamp = min(microamp, 1800U);
@@ -317,12 +355,12 @@ static u32 phy_tx_preemp_amp_tune_from_property(u32 microamp)
 static u32 phy_tx_vboost_level_from_property(u32 microvolt)
 {
 	switch (microvolt) {
-	case 0 ... 960:
-		return 0;
-	case 961 ... 1160:
-		return 2;
-	default:
+	case 1156:
+		return 5;
+	case 844:
 		return 3;
+	default:
+		return 4;
 	}
 }
 
@@ -352,6 +390,29 @@ static u32 phy_comp_dis_tune_from_property(u32 percent)
 		return 7;
 	}
 }
+
+static u32 imx95_phy_comp_dis_tune_from_property(u32 percent)
+{
+	percent = clamp(percent, 94, 104);
+
+	switch (percent) {
+	case 94 ... 95:
+		percent = 0;
+		break;
+	case 96 ... 98:
+		percent -= 95;
+		break;
+	case 99 ... 102:
+		percent -= 96;
+		break;
+	case 103 ... 104:
+		percent -= 97;
+		break;
+	}
+
+	return percent;
+}
+
 static u32 phy_pcs_tx_swing_full_from_property(u32 percent)
 {
 	percent = min(percent, 100U);
@@ -362,10 +423,17 @@ static u32 phy_pcs_tx_swing_full_from_property(u32 percent)
 static void imx8m_get_phy_tuning_data(struct imx8mq_usb_phy *imx_phy)
 {
 	struct device *dev = imx_phy->phy->dev.parent;
+	bool is_imx95 = false;
+
+	if (device_is_compatible(dev, "fsl,imx95-usb-phy"))
+		is_imx95 = true;
 
 	if (device_property_read_u32(dev, "fsl,phy-tx-vref-tune-percent",
 				     &imx_phy->tx_vref_tune))
 		imx_phy->tx_vref_tune = PHY_TUNE_DEFAULT;
+	else if (is_imx95)
+		imx_phy->tx_vref_tune =
+			imx95_phy_tx_vref_tune_from_property(imx_phy->tx_vref_tune);
 	else
 		imx_phy->tx_vref_tune =
 			phy_tx_vref_tune_from_property(imx_phy->tx_vref_tune);
@@ -373,6 +441,9 @@ static void imx8m_get_phy_tuning_data(struct imx8mq_usb_phy *imx_phy)
 	if (device_property_read_u32(dev, "fsl,phy-tx-rise-tune-percent",
 				     &imx_phy->tx_rise_tune))
 		imx_phy->tx_rise_tune = PHY_TUNE_DEFAULT;
+	else if (is_imx95)
+		imx_phy->tx_rise_tune =
+			imx95_phy_tx_rise_tune_from_property(imx_phy->tx_rise_tune);
 	else
 		imx_phy->tx_rise_tune =
 			phy_tx_rise_tune_from_property(imx_phy->tx_rise_tune);
@@ -394,6 +465,9 @@ static void imx8m_get_phy_tuning_data(struct imx8mq_usb_phy *imx_phy)
 	if (device_property_read_u32(dev, "fsl,phy-comp-dis-tune-percent",
 				     &imx_phy->comp_dis_tune))
 		imx_phy->comp_dis_tune = PHY_TUNE_DEFAULT;
+	else if (is_imx95)
+		imx_phy->comp_dis_tune =
+			imx95_phy_comp_dis_tune_from_property(imx_phy->comp_dis_tune);
 	else
 		imx_phy->comp_dis_tune =
 			phy_comp_dis_tune_from_property(imx_phy->comp_dis_tune);
diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
index 10fbe8dee116..191c282246d9 100644
--- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
+++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
@@ -456,6 +456,8 @@ static int fsl_samsung_hdmi_phy_configure(struct fsl_samsung_hdmi_phy *phy,
 	int i, ret;
 	u8 val;
 
+	phy->cur_cfg = cfg;
+
 	/* HDMI PHY init */
 	writeb(REG33_FIX_DA, phy->regs + PHY_REG(33));
 
@@ -508,7 +510,14 @@ static const struct phy_config *fsl_samsung_hdmi_phy_lookup_rate(unsigned long r
 		if (phy_pll_cfg[i].pixclk <= rate)
 			break;
 
-	return &phy_pll_cfg[i];
+	/* If there is an exact match, or the array has been searched, return the value*/
+	if (phy_pll_cfg[i].pixclk == rate || i + 1 > ARRAY_SIZE(phy_pll_cfg) - 1)
+		return &phy_pll_cfg[i];
+
+	/* See if the next entry is closer to nominal than this one */
+	return (abs((long) rate - (long) phy_pll_cfg[i].pixclk) <
+		abs((long) rate - (long) phy_pll_cfg[i+1].pixclk) ?
+		&phy_pll_cfg[i] : &phy_pll_cfg[i+1]);
 }
 
 static void fsl_samsung_hdmi_calculate_phy(struct phy_config *cal_phy, unsigned long rate,
@@ -521,18 +530,9 @@ static void fsl_samsung_hdmi_calculate_phy(struct phy_config *cal_phy, unsigned
 	/* pll_div_regs 3-6 are fixed and pre-defined already */
 }
 
-static u32 fsl_samsung_hdmi_phy_get_closest_rate(unsigned long rate,
-						 u32 int_div_clk, u32 frac_div_clk)
-{
-	/* Calculate the absolute value of the differences and return whichever is closest */
-	if (abs((long)rate - (long)int_div_clk) < abs((long)(rate - (long)frac_div_clk)))
-		return int_div_clk;
-
-	return frac_div_clk;
-}
-
-static long phy_clk_round_rate(struct clk_hw *hw,
-			       unsigned long rate, unsigned long *parent_rate)
+static
+const struct phy_config *fsl_samsung_hdmi_phy_find_settings(struct fsl_samsung_hdmi_phy *phy,
+							    unsigned long rate)
 {
 	const struct phy_config *fract_div_phy;
 	u32 int_div_clk;
@@ -541,83 +541,66 @@ static long phy_clk_round_rate(struct clk_hw *hw,
 
 	/* If the clock is out of range return error instead of searching */
 	if (rate > 297000000 || rate < 22250000)
-		return -EINVAL;
+		return NULL;
 
 	/* Search the fractional divider lookup table */
 	fract_div_phy = fsl_samsung_hdmi_phy_lookup_rate(rate);
+	if (fract_div_phy->pixclk == rate) {
+		dev_dbg(phy->dev, "fractional divider match = %u\n", fract_div_phy->pixclk);
+		return fract_div_phy;
+	}
 
-	/* If the rate is an exact match, return that value */
-	if (rate == fract_div_phy->pixclk)
-		return fract_div_phy->pixclk;
-
-	/* If the exact match isn't found, calculate the integer divider */
+	/* Calculate the integer divider */
 	int_div_clk = fsl_samsung_hdmi_phy_find_pms(rate, &p, &m, &s);
+	fsl_samsung_hdmi_calculate_phy(&calculated_phy_pll_cfg, int_div_clk, p, m, s);
+	if (int_div_clk == rate) {
+		dev_dbg(phy->dev, "integer divider match = %u\n", calculated_phy_pll_cfg.pixclk);
+		return &calculated_phy_pll_cfg;
+	}
 
-	/* If the int_div_clk rate is an exact match, return that value */
-	if (int_div_clk == rate)
-		return int_div_clk;
+	/* Calculate the absolute value of the differences and return whichever is closest */
+	if (abs((long)rate - (long)int_div_clk) <
+	    abs((long)rate - (long)fract_div_phy->pixclk)) {
+		dev_dbg(phy->dev, "integer divider = %u\n", calculated_phy_pll_cfg.pixclk);
+		return &calculated_phy_pll_cfg;
+	}
 
-	/* If neither rate is an exact match, use the value from the LUT */
-	return fract_div_phy->pixclk;
-}
+	dev_dbg(phy->dev, "fractional divider = %u\n", phy->cur_cfg->pixclk);
 
-static int phy_use_fract_div(struct fsl_samsung_hdmi_phy *phy, const struct phy_config *fract_div_phy)
-{
-	phy->cur_cfg = fract_div_phy;
-	dev_dbg(phy->dev, "fsl_samsung_hdmi_phy: using fractional divider rate = %u\n",
-		phy->cur_cfg->pixclk);
-	return fsl_samsung_hdmi_phy_configure(phy, phy->cur_cfg);
+	return fract_div_phy;
 }
 
-static int phy_use_integer_div(struct fsl_samsung_hdmi_phy *phy,
-			       const struct phy_config *int_div_clk)
+static long fsl_samsung_hdmi_phy_clk_round_rate(struct clk_hw *hw,
+						unsigned long rate, unsigned long *parent_rate)
 {
-	phy->cur_cfg  = &calculated_phy_pll_cfg;
-	dev_dbg(phy->dev, "fsl_samsung_hdmi_phy: integer divider rate = %u\n",
-		phy->cur_cfg->pixclk);
-	return fsl_samsung_hdmi_phy_configure(phy, phy->cur_cfg);
+	struct fsl_samsung_hdmi_phy *phy = to_fsl_samsung_hdmi_phy(hw);
+	const struct phy_config *target_settings = fsl_samsung_hdmi_phy_find_settings(phy, rate);
+
+	if (target_settings == NULL)
+		return -EINVAL;
+
+	dev_dbg(phy->dev, "round_rate, closest rate = %u\n", target_settings->pixclk);
+	return target_settings->pixclk;
 }
 
-static int phy_clk_set_rate(struct clk_hw *hw,
+static int fsl_samsung_hdmi_phy_clk_set_rate(struct clk_hw *hw,
 			    unsigned long rate, unsigned long parent_rate)
 {
 	struct fsl_samsung_hdmi_phy *phy = to_fsl_samsung_hdmi_phy(hw);
-	const struct phy_config *fract_div_phy;
-	u32 int_div_clk;
-	u16 m;
-	u8 p, s;
+	const struct phy_config *target_settings = fsl_samsung_hdmi_phy_find_settings(phy, rate);
 
-	/* Search the fractional divider lookup table */
-	fract_div_phy = fsl_samsung_hdmi_phy_lookup_rate(rate);
-
-	/* If the rate is an exact match, use that value */
-	if (fract_div_phy->pixclk == rate)
-		return phy_use_fract_div(phy, fract_div_phy);
+	if (target_settings == NULL)
+		return -EINVAL;
 
-	/*
-	 * If the rate from the fractional divider is not exact, check the integer divider,
-	 * and use it if that value is an exact match.
-	 */
-	int_div_clk = fsl_samsung_hdmi_phy_find_pms(rate, &p, &m, &s);
-	fsl_samsung_hdmi_calculate_phy(&calculated_phy_pll_cfg, int_div_clk, p, m, s);
-	if (int_div_clk == rate)
-		return phy_use_integer_div(phy, &calculated_phy_pll_cfg);
+	dev_dbg(phy->dev,  "set_rate, closest rate = %u\n", target_settings->pixclk);
 
-	/*
-	 * Compare the difference between the integer clock and the fractional clock against
-	 * the desired clock and which whichever is closest.
-	 */
-	if (fsl_samsung_hdmi_phy_get_closest_rate(rate, int_div_clk,
-						  fract_div_phy->pixclk) == fract_div_phy->pixclk)
-		return phy_use_fract_div(phy, fract_div_phy);
-	else
-		return phy_use_integer_div(phy, &calculated_phy_pll_cfg);
+	return fsl_samsung_hdmi_phy_configure(phy, target_settings);
 }
 
 static const struct clk_ops phy_clk_ops = {
 	.recalc_rate = phy_clk_recalc_rate,
-	.round_rate = phy_clk_round_rate,
-	.set_rate = phy_clk_set_rate,
+	.round_rate = fsl_samsung_hdmi_phy_clk_round_rate,
+	.set_rate = fsl_samsung_hdmi_phy_clk_set_rate,
 };
 
 static int phy_clk_register(struct fsl_samsung_hdmi_phy *phy)
diff --git a/drivers/phy/marvell/Kconfig b/drivers/phy/marvell/Kconfig
index bdb87c976243..bccd72dccb77 100644
--- a/drivers/phy/marvell/Kconfig
+++ b/drivers/phy/marvell/Kconfig
@@ -29,7 +29,7 @@ config PHY_MVEBU_A3700_COMPHY
 	depends on ARCH_MVEBU || COMPILE_TEST
 	depends on OF
 	depends on HAVE_ARM_SMCCC
-	default y
+	default ARCH_MVEBU
 	select GENERIC_PHY
 	help
 	  This driver allows to control the comphy, a hardware block providing
@@ -40,7 +40,7 @@ config PHY_MVEBU_A3700_UTMI
 	tristate "Marvell A3700 UTMI driver"
 	depends on ARCH_MVEBU || COMPILE_TEST
 	depends on OF
-	default y
+	default ARCH_MVEBU
 	select GENERIC_PHY
 	help
 	  Enable this to support Marvell A3700 UTMI PHY driver.
diff --git a/drivers/phy/mediatek/phy-mtk-xsphy.c b/drivers/phy/mediatek/phy-mtk-xsphy.c
index 7c248f5cfca5..c0ddb9273cc3 100644
--- a/drivers/phy/mediatek/phy-mtk-xsphy.c
+++ b/drivers/phy/mediatek/phy-mtk-xsphy.c
@@ -11,10 +11,12 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/iopoll.h>
+#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
+#include <linux/regmap.h>
 
 #include "phy-mtk-io.h"
 
@@ -81,12 +83,22 @@
 #define XSP_SR_COEF_DIVISOR	1000
 #define XSP_FM_DET_CYCLE_CNT	1024
 
+/* PHY switch between pcie/usb3/sgmii */
+#define USB_PHY_SWITCH_CTRL	0x0
+#define RG_PHY_SW_TYPE		GENMASK(3, 0)
+#define RG_PHY_SW_PCIE		0x0
+#define RG_PHY_SW_USB3		0x1
+#define RG_PHY_SW_SGMII		0x2
+
 struct xsphy_instance {
 	struct phy *phy;
 	void __iomem *port_base;
 	struct clk *ref_clk;	/* reference clock of anolog phy */
 	u32 index;
 	u32 type;
+	struct regmap *type_sw;
+	u32 type_sw_reg;
+	u32 type_sw_index;
 	/* only for HQA test */
 	int efuse_intr;
 	int efuse_tx_imp;
@@ -259,6 +271,10 @@ static void phy_parse_property(struct mtk_xsphy *xsphy,
 			inst->efuse_intr, inst->efuse_tx_imp,
 			inst->efuse_rx_imp);
 		break;
+	case PHY_TYPE_PCIE:
+	case PHY_TYPE_SGMII:
+		/* nothing to do */
+		break;
 	default:
 		dev_err(xsphy->dev, "incompatible phy type\n");
 		return;
@@ -305,6 +321,62 @@ static void u3_phy_props_set(struct mtk_xsphy *xsphy,
 				     RG_XTP_LN0_RX_IMPSEL, inst->efuse_rx_imp);
 }
 
+/* type switch for usb3/pcie/sgmii */
+static int phy_type_syscon_get(struct xsphy_instance *instance,
+			       struct device_node *dn)
+{
+	struct of_phandle_args args;
+	int ret;
+
+	/* type switch function is optional */
+	if (!of_property_present(dn, "mediatek,syscon-type"))
+		return 0;
+
+	ret = of_parse_phandle_with_fixed_args(dn, "mediatek,syscon-type",
+					       2, 0, &args);
+	if (ret)
+		return ret;
+
+	instance->type_sw_reg = args.args[0];
+	instance->type_sw_index = args.args[1] & 0x3; /* <=3 */
+	instance->type_sw = syscon_node_to_regmap(args.np);
+	of_node_put(args.np);
+	dev_info(&instance->phy->dev, "type_sw - reg %#x, index %d\n",
+		 instance->type_sw_reg, instance->type_sw_index);
+
+	return PTR_ERR_OR_ZERO(instance->type_sw);
+}
+
+static int phy_type_set(struct xsphy_instance *instance)
+{
+	int type;
+	u32 offset;
+
+	if (!instance->type_sw)
+		return 0;
+
+	switch (instance->type) {
+	case PHY_TYPE_USB3:
+		type = RG_PHY_SW_USB3;
+		break;
+	case PHY_TYPE_PCIE:
+		type = RG_PHY_SW_PCIE;
+		break;
+	case PHY_TYPE_SGMII:
+		type = RG_PHY_SW_SGMII;
+		break;
+	case PHY_TYPE_USB2:
+	default:
+		return 0;
+	}
+
+	offset = instance->type_sw_index * BITS_PER_BYTE;
+	regmap_update_bits(instance->type_sw, instance->type_sw_reg,
+			   RG_PHY_SW_TYPE << offset, type << offset);
+
+	return 0;
+}
+
 static int mtk_phy_init(struct phy *phy)
 {
 	struct xsphy_instance *inst = phy_get_drvdata(phy);
@@ -325,6 +397,10 @@ static int mtk_phy_init(struct phy *phy)
 	case PHY_TYPE_USB3:
 		u3_phy_props_set(xsphy, inst);
 		break;
+	case PHY_TYPE_PCIE:
+	case PHY_TYPE_SGMII:
+		/* nothing to do, only used to set type */
+		break;
 	default:
 		dev_err(xsphy->dev, "incompatible phy type\n");
 		clk_disable_unprepare(inst->ref_clk);
@@ -403,12 +479,15 @@ static struct phy *mtk_phy_xlate(struct device *dev,
 
 	inst->type = args->args[0];
 	if (!(inst->type == PHY_TYPE_USB2 ||
-	      inst->type == PHY_TYPE_USB3)) {
+	      inst->type == PHY_TYPE_USB3 ||
+	      inst->type == PHY_TYPE_PCIE ||
+	      inst->type == PHY_TYPE_SGMII)) {
 		dev_err(dev, "unsupported phy type: %d\n", inst->type);
 		return ERR_PTR(-EINVAL);
 	}
 
 	phy_parse_property(xsphy, inst);
+	phy_type_set(inst);
 
 	return inst->phy;
 }
@@ -510,6 +589,10 @@ static int mtk_xsphy_probe(struct platform_device *pdev)
 			dev_err(dev, "failed to get ref_clk(id-%d)\n", port);
 			return PTR_ERR(inst->ref_clk);
 		}
+
+		retval = phy_type_syscon_get(inst, child_np);
+		if (retval)
+			return retval;
 	}
 
 	provider = devm_of_phy_provider_register(dev, mtk_phy_xlate);
diff --git a/drivers/phy/phy-snps-eusb2.c b/drivers/phy/phy-snps-eusb2.c
new file mode 100644
index 000000000000..b73a1d7e57b3
--- /dev/null
+++ b/drivers/phy/phy-snps-eusb2.c
@@ -0,0 +1,627 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/iopoll.h>
+#include <linux/mod_devicetable.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/reset.h>
+
+#define EXYNOS_USB_PHY_HS_PHY_CTRL_RST	(0x0)
+#define USB_PHY_RST_MASK		GENMASK(1, 0)
+#define UTMI_PORT_RST_MASK		GENMASK(5, 4)
+
+#define EXYNOS_USB_PHY_HS_PHY_CTRL_COMMON	(0x4)
+#define RPTR_MODE			BIT(10)
+#define FSEL_20_MHZ_VAL			(0x1)
+#define FSEL_24_MHZ_VAL			(0x2)
+#define FSEL_26_MHZ_VAL			(0x3)
+#define FSEL_48_MHZ_VAL			(0x2)
+
+#define EXYNOS_USB_PHY_CFG_PLLCFG0	(0x8)
+#define PHY_CFG_PLL_FB_DIV_19_8_MASK	GENMASK(19, 8)
+#define DIV_19_8_19_2_MHZ_VAL		(0x170)
+#define DIV_19_8_20_MHZ_VAL		(0x160)
+#define DIV_19_8_24_MHZ_VAL		(0x120)
+#define DIV_19_8_26_MHZ_VAL		(0x107)
+#define DIV_19_8_48_MHZ_VAL		(0x120)
+
+#define EXYNOS_USB_PHY_CFG_PLLCFG1	(0xc)
+#define EXYNOS_PHY_CFG_PLL_FB_DIV_11_8_MASK	GENMASK(11, 8)
+#define EXYNOS_DIV_11_8_19_2_MHZ_VAL	(0x0)
+#define EXYNOS_DIV_11_8_20_MHZ_VAL	(0x0)
+#define EXYNOS_DIV_11_8_24_MHZ_VAL	(0x0)
+#define EXYNOS_DIV_11_8_26_MHZ_VAL	(0x0)
+#define EXYNOS_DIV_11_8_48_MHZ_VAL	(0x1)
+
+#define EXYNOS_PHY_CFG_TX		(0x14)
+#define EXYNOS_PHY_CFG_TX_FSLS_VREF_TUNE_MASK	GENMASK(2, 1)
+
+#define EXYNOS_USB_PHY_UTMI_TESTSE	(0x20)
+#define TEST_IDDQ			BIT(6)
+
+#define QCOM_USB_PHY_UTMI_CTRL0		(0x3c)
+#define SLEEPM				BIT(0)
+#define OPMODE_MASK			GENMASK(4, 3)
+#define OPMODE_NONDRIVING		BIT(3)
+
+#define QCOM_USB_PHY_UTMI_CTRL5		(0x50)
+#define POR				BIT(1)
+
+#define QCOM_USB_PHY_HS_PHY_CTRL_COMMON0	(0x54)
+#define PHY_ENABLE			BIT(0)
+#define SIDDQ_SEL			BIT(1)
+#define SIDDQ				BIT(2)
+#define RETENABLEN			BIT(3)
+#define FSEL_MASK			GENMASK(6, 4)
+#define FSEL_19_2_MHZ_VAL		(0x0)
+#define FSEL_38_4_MHZ_VAL		(0x4)
+
+#define QCOM_USB_PHY_CFG_CTRL_1		(0x58)
+#define PHY_CFG_PLL_CPBIAS_CNTRL_MASK	GENMASK(7, 1)
+
+#define QCOM_USB_PHY_CFG_CTRL_2		(0x5c)
+#define PHY_CFG_PLL_FB_DIV_7_0_MASK	GENMASK(7, 0)
+#define DIV_7_0_19_2_MHZ_VAL		(0x90)
+#define DIV_7_0_38_4_MHZ_VAL		(0xc8)
+
+#define QCOM_USB_PHY_CFG_CTRL_3		(0x60)
+#define PHY_CFG_PLL_FB_DIV_11_8_MASK	GENMASK(3, 0)
+#define DIV_11_8_19_2_MHZ_VAL		(0x1)
+#define DIV_11_8_38_4_MHZ_VAL		(0x0)
+
+#define PHY_CFG_PLL_REF_DIV		GENMASK(7, 4)
+#define PLL_REF_DIV_VAL			(0x0)
+
+#define QCOM_USB_PHY_HS_PHY_CTRL2	(0x64)
+#define VBUSVLDEXT0			BIT(0)
+#define USB2_SUSPEND_N			BIT(2)
+#define USB2_SUSPEND_N_SEL		BIT(3)
+#define VBUS_DET_EXT_SEL		BIT(4)
+
+#define QCOM_USB_PHY_CFG_CTRL_4		(0x68)
+#define PHY_CFG_PLL_GMP_CNTRL_MASK	GENMASK(1, 0)
+#define PHY_CFG_PLL_INT_CNTRL_MASK	GENMASK(7, 2)
+
+#define QCOM_USB_PHY_CFG_CTRL_5		(0x6c)
+#define PHY_CFG_PLL_PROP_CNTRL_MASK	GENMASK(4, 0)
+#define PHY_CFG_PLL_VREF_TUNE_MASK	GENMASK(7, 6)
+
+#define QCOM_USB_PHY_CFG_CTRL_6		(0x70)
+#define PHY_CFG_PLL_VCO_CNTRL_MASK	GENMASK(2, 0)
+
+#define QCOM_USB_PHY_CFG_CTRL_7		(0x74)
+
+#define QCOM_USB_PHY_CFG_CTRL_8		(0x78)
+#define PHY_CFG_TX_FSLS_VREF_TUNE_MASK	GENMASK(1, 0)
+#define PHY_CFG_TX_FSLS_VREG_BYPASS	BIT(2)
+#define PHY_CFG_TX_HS_VREF_TUNE_MASK	GENMASK(5, 3)
+#define PHY_CFG_TX_HS_XV_TUNE_MASK	GENMASK(7, 6)
+
+#define QCOM_USB_PHY_CFG_CTRL_9		(0x7c)
+#define PHY_CFG_TX_PREEMP_TUNE_MASK	GENMASK(2, 0)
+#define PHY_CFG_TX_RES_TUNE_MASK	GENMASK(4, 3)
+#define PHY_CFG_TX_RISE_TUNE_MASK	GENMASK(6, 5)
+#define PHY_CFG_RCAL_BYPASS		BIT(7)
+
+#define QCOM_USB_PHY_CFG_CTRL_10	(0x80)
+
+#define QCOM_USB_PHY_CFG0		(0x94)
+#define DATAPATH_CTRL_OVERRIDE_EN	BIT(0)
+#define CMN_CTRL_OVERRIDE_EN		BIT(1)
+
+#define QCOM_UTMI_PHY_CMN_CTRL0		(0x98)
+#define TESTBURNIN			BIT(6)
+
+#define QCOM_USB_PHY_FSEL_SEL		(0xb8)
+#define FSEL_SEL			BIT(0)
+
+#define QCOM_USB_PHY_APB_ACCESS_CMD	(0x130)
+#define RW_ACCESS			BIT(0)
+#define APB_START_CMD			BIT(1)
+#define APB_LOGIC_RESET			BIT(2)
+
+#define QCOM_USB_PHY_APB_ACCESS_STATUS	(0x134)
+#define ACCESS_DONE			BIT(0)
+#define TIMED_OUT			BIT(1)
+#define ACCESS_ERROR			BIT(2)
+#define ACCESS_IN_PROGRESS		BIT(3)
+
+#define QCOM_USB_PHY_APB_ADDRESS	(0x138)
+#define APB_REG_ADDR_MASK		GENMASK(7, 0)
+
+#define QCOM_USB_PHY_APB_WRDATA_LSB	(0x13c)
+#define APB_REG_WRDATA_7_0_MASK		GENMASK(3, 0)
+
+#define QCOM_USB_PHY_APB_WRDATA_MSB	(0x140)
+#define APB_REG_WRDATA_15_8_MASK	GENMASK(7, 4)
+
+#define QCOM_USB_PHY_APB_RDDATA_LSB	(0x144)
+#define APB_REG_RDDATA_7_0_MASK		GENMASK(3, 0)
+
+#define QCOM_USB_PHY_APB_RDDATA_MSB	(0x148)
+#define APB_REG_RDDATA_15_8_MASK	GENMASK(7, 4)
+
+static const char * const eusb2_hsphy_vreg_names[] = {
+	"vdd", "vdda12",
+};
+
+#define EUSB2_NUM_VREGS		ARRAY_SIZE(eusb2_hsphy_vreg_names)
+
+struct snps_eusb2_phy_drvdata {
+	int (*phy_init)(struct phy *p);
+	const char * const *clk_names;
+	int num_clks;
+};
+
+struct snps_eusb2_hsphy {
+	struct phy *phy;
+	void __iomem *base;
+
+	struct clk *ref_clk;
+	struct clk_bulk_data *clks;
+	struct reset_control *phy_reset;
+
+	struct regulator_bulk_data vregs[EUSB2_NUM_VREGS];
+
+	enum phy_mode mode;
+
+	struct phy *repeater;
+
+	const struct snps_eusb2_phy_drvdata *data;
+};
+
+static int snps_eusb2_hsphy_set_mode(struct phy *p, enum phy_mode mode, int submode)
+{
+	struct snps_eusb2_hsphy *phy = phy_get_drvdata(p);
+
+	phy->mode = mode;
+
+	return phy_set_mode_ext(phy->repeater, mode, submode);
+}
+
+static void snps_eusb2_hsphy_write_mask(void __iomem *base, u32 offset,
+					u32 mask, u32 val)
+{
+	u32 reg;
+
+	reg = readl_relaxed(base + offset);
+	reg &= ~mask;
+	reg |= val & mask;
+	writel_relaxed(reg, base + offset);
+
+	/* Ensure above write is completed */
+	readl_relaxed(base + offset);
+}
+
+static void qcom_eusb2_default_parameters(struct snps_eusb2_hsphy *phy)
+{
+	/* default parameters: tx pre-emphasis */
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_9,
+				    PHY_CFG_TX_PREEMP_TUNE_MASK,
+				    FIELD_PREP(PHY_CFG_TX_PREEMP_TUNE_MASK, 0));
+
+	/* tx rise/fall time */
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_9,
+				    PHY_CFG_TX_RISE_TUNE_MASK,
+				    FIELD_PREP(PHY_CFG_TX_RISE_TUNE_MASK, 0x2));
+
+	/* source impedance adjustment */
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_9,
+				    PHY_CFG_TX_RES_TUNE_MASK,
+				    FIELD_PREP(PHY_CFG_TX_RES_TUNE_MASK, 0x1));
+
+	/* dc voltage level adjustement */
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_8,
+				    PHY_CFG_TX_HS_VREF_TUNE_MASK,
+				    FIELD_PREP(PHY_CFG_TX_HS_VREF_TUNE_MASK, 0x3));
+
+	/* transmitter HS crossover adjustement */
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_8,
+				    PHY_CFG_TX_HS_XV_TUNE_MASK,
+				    FIELD_PREP(PHY_CFG_TX_HS_XV_TUNE_MASK, 0x0));
+}
+
+struct snps_eusb2_ref_clk {
+	unsigned long freq;
+	u32 fsel_val;
+	u32 div_7_0_val;
+	u32 div_11_8_val;
+};
+
+static const struct snps_eusb2_ref_clk exynos_eusb2_ref_clk[] = {
+	{ 19200000, FSEL_19_2_MHZ_VAL, DIV_19_8_19_2_MHZ_VAL, EXYNOS_DIV_11_8_19_2_MHZ_VAL },
+	{ 20000000, FSEL_20_MHZ_VAL, DIV_19_8_20_MHZ_VAL, EXYNOS_DIV_11_8_20_MHZ_VAL },
+	{ 24000000, FSEL_24_MHZ_VAL, DIV_19_8_24_MHZ_VAL, EXYNOS_DIV_11_8_24_MHZ_VAL },
+	{ 26000000, FSEL_26_MHZ_VAL, DIV_19_8_26_MHZ_VAL, EXYNOS_DIV_11_8_26_MHZ_VAL },
+	{ 48000000, FSEL_48_MHZ_VAL, DIV_19_8_48_MHZ_VAL, EXYNOS_DIV_11_8_48_MHZ_VAL },
+};
+
+static int exynos_eusb2_ref_clk_init(struct snps_eusb2_hsphy *phy)
+{
+	const struct snps_eusb2_ref_clk *config = NULL;
+	unsigned long ref_clk_freq = clk_get_rate(phy->ref_clk);
+
+	for (int i = 0; i < ARRAY_SIZE(exynos_eusb2_ref_clk); i++) {
+		if (exynos_eusb2_ref_clk[i].freq == ref_clk_freq) {
+			config = &exynos_eusb2_ref_clk[i];
+			break;
+		}
+	}
+
+	if (!config) {
+		dev_err(&phy->phy->dev, "unsupported ref_clk_freq:%lu\n", ref_clk_freq);
+		return -EINVAL;
+	}
+
+	snps_eusb2_hsphy_write_mask(phy->base, EXYNOS_USB_PHY_HS_PHY_CTRL_COMMON,
+				    FSEL_MASK,
+				    FIELD_PREP(FSEL_MASK, config->fsel_val));
+
+	snps_eusb2_hsphy_write_mask(phy->base, EXYNOS_USB_PHY_CFG_PLLCFG0,
+				    PHY_CFG_PLL_FB_DIV_19_8_MASK,
+				    FIELD_PREP(PHY_CFG_PLL_FB_DIV_19_8_MASK,
+					       config->div_7_0_val));
+
+	snps_eusb2_hsphy_write_mask(phy->base, EXYNOS_USB_PHY_CFG_PLLCFG1,
+				    EXYNOS_PHY_CFG_PLL_FB_DIV_11_8_MASK,
+				    config->div_11_8_val);
+	return 0;
+}
+
+static const struct snps_eusb2_ref_clk qcom_eusb2_ref_clk[] = {
+	{ 19200000, FSEL_19_2_MHZ_VAL, DIV_7_0_19_2_MHZ_VAL, DIV_11_8_19_2_MHZ_VAL },
+	{ 38400000, FSEL_38_4_MHZ_VAL, DIV_7_0_38_4_MHZ_VAL, DIV_11_8_38_4_MHZ_VAL },
+};
+
+static int qcom_eusb2_ref_clk_init(struct snps_eusb2_hsphy *phy)
+{
+	const struct snps_eusb2_ref_clk *config = NULL;
+	unsigned long ref_clk_freq = clk_get_rate(phy->ref_clk);
+
+	for (int i = 0; i < ARRAY_SIZE(qcom_eusb2_ref_clk); i++) {
+		if (qcom_eusb2_ref_clk[i].freq == ref_clk_freq) {
+			config = &qcom_eusb2_ref_clk[i];
+			break;
+		}
+	}
+
+	if (!config) {
+		dev_err(&phy->phy->dev, "unsupported ref_clk_freq:%lu\n", ref_clk_freq);
+		return -EINVAL;
+	}
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_HS_PHY_CTRL_COMMON0,
+				    FSEL_MASK,
+				    FIELD_PREP(FSEL_MASK, config->fsel_val));
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_2,
+				    PHY_CFG_PLL_FB_DIV_7_0_MASK,
+				    config->div_7_0_val);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_3,
+				    PHY_CFG_PLL_FB_DIV_11_8_MASK,
+				    config->div_11_8_val);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_3,
+				    PHY_CFG_PLL_REF_DIV, PLL_REF_DIV_VAL);
+
+	return 0;
+}
+
+static int exynos_snps_eusb2_hsphy_init(struct phy *p)
+{
+	struct snps_eusb2_hsphy *phy = phy_get_drvdata(p);
+	int ret;
+
+	snps_eusb2_hsphy_write_mask(phy->base, EXYNOS_USB_PHY_HS_PHY_CTRL_RST,
+				    USB_PHY_RST_MASK | UTMI_PORT_RST_MASK,
+				    USB_PHY_RST_MASK | UTMI_PORT_RST_MASK);
+	fsleep(50); /* required after holding phy in reset */
+
+	snps_eusb2_hsphy_write_mask(phy->base, EXYNOS_USB_PHY_HS_PHY_CTRL_COMMON,
+				    RPTR_MODE, RPTR_MODE);
+
+	/* update ref_clk related registers */
+	ret = exynos_eusb2_ref_clk_init(phy);
+	if (ret)
+		return ret;
+
+	/* default parameter: tx fsls-vref */
+	snps_eusb2_hsphy_write_mask(phy->base, EXYNOS_PHY_CFG_TX,
+				    EXYNOS_PHY_CFG_TX_FSLS_VREF_TUNE_MASK,
+				    FIELD_PREP(EXYNOS_PHY_CFG_TX_FSLS_VREF_TUNE_MASK, 0x0));
+
+	snps_eusb2_hsphy_write_mask(phy->base, EXYNOS_USB_PHY_UTMI_TESTSE,
+				    TEST_IDDQ, 0);
+	fsleep(10); /* required after releasing test_iddq */
+
+	snps_eusb2_hsphy_write_mask(phy->base, EXYNOS_USB_PHY_HS_PHY_CTRL_RST,
+				    USB_PHY_RST_MASK, 0);
+
+	snps_eusb2_hsphy_write_mask(phy->base, EXYNOS_USB_PHY_HS_PHY_CTRL_COMMON,
+				    PHY_ENABLE, PHY_ENABLE);
+
+	snps_eusb2_hsphy_write_mask(phy->base, EXYNOS_USB_PHY_HS_PHY_CTRL_RST,
+				    UTMI_PORT_RST_MASK, 0);
+
+	return 0;
+}
+
+static const char * const exynos_eusb2_hsphy_clock_names[] = {
+	"ref", "bus", "ctrl",
+};
+
+static const struct snps_eusb2_phy_drvdata exynos2200_snps_eusb2_phy = {
+	.phy_init	= exynos_snps_eusb2_hsphy_init,
+	.clk_names	= exynos_eusb2_hsphy_clock_names,
+	.num_clks	= ARRAY_SIZE(exynos_eusb2_hsphy_clock_names),
+};
+
+static int qcom_snps_eusb2_hsphy_init(struct phy *p)
+{
+	struct snps_eusb2_hsphy *phy = phy_get_drvdata(p);
+	int ret;
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG0,
+				    CMN_CTRL_OVERRIDE_EN, CMN_CTRL_OVERRIDE_EN);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_UTMI_CTRL5, POR, POR);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_HS_PHY_CTRL_COMMON0,
+				    PHY_ENABLE | RETENABLEN, PHY_ENABLE | RETENABLEN);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_APB_ACCESS_CMD,
+				    APB_LOGIC_RESET, APB_LOGIC_RESET);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_UTMI_PHY_CMN_CTRL0, TESTBURNIN, 0);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_FSEL_SEL,
+				    FSEL_SEL, FSEL_SEL);
+
+	/* update ref_clk related registers */
+	ret = qcom_eusb2_ref_clk_init(phy);
+	if (ret)
+		return ret;
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_1,
+				    PHY_CFG_PLL_CPBIAS_CNTRL_MASK,
+				    FIELD_PREP(PHY_CFG_PLL_CPBIAS_CNTRL_MASK, 0x1));
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_4,
+				    PHY_CFG_PLL_INT_CNTRL_MASK,
+				    FIELD_PREP(PHY_CFG_PLL_INT_CNTRL_MASK, 0x8));
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_4,
+				    PHY_CFG_PLL_GMP_CNTRL_MASK,
+				    FIELD_PREP(PHY_CFG_PLL_GMP_CNTRL_MASK, 0x1));
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_5,
+				    PHY_CFG_PLL_PROP_CNTRL_MASK,
+				    FIELD_PREP(PHY_CFG_PLL_PROP_CNTRL_MASK, 0x10));
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_6,
+				    PHY_CFG_PLL_VCO_CNTRL_MASK,
+				    FIELD_PREP(PHY_CFG_PLL_VCO_CNTRL_MASK, 0x0));
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_CFG_CTRL_5,
+				    PHY_CFG_PLL_VREF_TUNE_MASK,
+				    FIELD_PREP(PHY_CFG_PLL_VREF_TUNE_MASK, 0x1));
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_HS_PHY_CTRL2,
+				    VBUS_DET_EXT_SEL, VBUS_DET_EXT_SEL);
+
+	/* set default parameters */
+	qcom_eusb2_default_parameters(phy);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_HS_PHY_CTRL2,
+				    USB2_SUSPEND_N_SEL | USB2_SUSPEND_N,
+				    USB2_SUSPEND_N_SEL | USB2_SUSPEND_N);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_UTMI_CTRL0, SLEEPM, SLEEPM);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_HS_PHY_CTRL_COMMON0,
+				    SIDDQ_SEL, SIDDQ_SEL);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_HS_PHY_CTRL_COMMON0,
+				    SIDDQ, 0);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_UTMI_CTRL5, POR, 0);
+
+	snps_eusb2_hsphy_write_mask(phy->base, QCOM_USB_PHY_HS_PHY_CTRL2,
+				    USB2_SUSPEND_N_SEL, 0);
+
+	return 0;
+}
+
+static const char * const qcom_eusb2_hsphy_clock_names[] = {
+	"ref",
+};
+
+static const struct snps_eusb2_phy_drvdata sm8550_snps_eusb2_phy = {
+	.phy_init	= qcom_snps_eusb2_hsphy_init,
+	.clk_names      = qcom_eusb2_hsphy_clock_names,
+	.num_clks       = ARRAY_SIZE(qcom_eusb2_hsphy_clock_names),
+};
+
+static int snps_eusb2_hsphy_init(struct phy *p)
+{
+	struct snps_eusb2_hsphy *phy = phy_get_drvdata(p);
+	int ret;
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(phy->vregs), phy->vregs);
+	if (ret)
+		return ret;
+
+	ret = phy_init(phy->repeater);
+	if (ret) {
+		dev_err(&p->dev, "repeater init failed. %d\n", ret);
+		goto disable_vreg;
+	}
+
+	ret = clk_bulk_prepare_enable(phy->data->num_clks, phy->clks);
+	if (ret) {
+		dev_err(&p->dev, "failed to enable ref clock, %d\n", ret);
+		goto disable_vreg;
+	}
+
+	ret = reset_control_assert(phy->phy_reset);
+	if (ret) {
+		dev_err(&p->dev, "failed to assert phy_reset, %d\n", ret);
+		goto disable_ref_clk;
+	}
+
+	usleep_range(100, 150);
+
+	ret = reset_control_deassert(phy->phy_reset);
+	if (ret) {
+		dev_err(&p->dev, "failed to de-assert phy_reset, %d\n", ret);
+		goto disable_ref_clk;
+	}
+
+	ret = phy->data->phy_init(p);
+	if (ret)
+		goto disable_ref_clk;
+
+	return 0;
+
+disable_ref_clk:
+	clk_bulk_disable_unprepare(phy->data->num_clks, phy->clks);
+
+disable_vreg:
+	regulator_bulk_disable(ARRAY_SIZE(phy->vregs), phy->vregs);
+
+	return ret;
+}
+
+static int snps_eusb2_hsphy_exit(struct phy *p)
+{
+	struct snps_eusb2_hsphy *phy = phy_get_drvdata(p);
+
+	clk_disable_unprepare(phy->ref_clk);
+
+	regulator_bulk_disable(ARRAY_SIZE(phy->vregs), phy->vregs);
+
+	phy_exit(phy->repeater);
+
+	return 0;
+}
+
+static const struct phy_ops snps_eusb2_hsphy_ops = {
+	.init		= snps_eusb2_hsphy_init,
+	.exit		= snps_eusb2_hsphy_exit,
+	.set_mode	= snps_eusb2_hsphy_set_mode,
+	.owner		= THIS_MODULE,
+};
+
+static int snps_eusb2_hsphy_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct snps_eusb2_hsphy *phy;
+	struct phy_provider *phy_provider;
+	struct phy *generic_phy;
+	int ret, i;
+	int num;
+
+	phy = devm_kzalloc(dev, sizeof(*phy), GFP_KERNEL);
+	if (!phy)
+		return -ENOMEM;
+
+	phy->data = device_get_match_data(dev);
+	if (!phy->data)
+		return -EINVAL;
+
+	phy->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(phy->base))
+		return PTR_ERR(phy->base);
+
+	phy->phy_reset = devm_reset_control_get_optional_exclusive(dev, NULL);
+	if (IS_ERR(phy->phy_reset))
+		return PTR_ERR(phy->phy_reset);
+
+	phy->clks = devm_kcalloc(dev, phy->data->num_clks, sizeof(*phy->clks),
+				 GFP_KERNEL);
+	if (!phy->clks)
+		return -ENOMEM;
+
+	for (int i = 0; i < phy->data->num_clks; ++i)
+		phy->clks[i].id = phy->data->clk_names[i];
+
+	ret = devm_clk_bulk_get(dev, phy->data->num_clks, phy->clks);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "failed to get phy clock(s)\n");
+
+	phy->ref_clk = NULL;
+	for (int i = 0; i < phy->data->num_clks; ++i) {
+		if (!strcmp(phy->clks[i].id, "ref")) {
+			phy->ref_clk = phy->clks[i].clk;
+			break;
+		}
+	}
+
+	if (IS_ERR_OR_NULL(phy->ref_clk))
+		return dev_err_probe(dev, PTR_ERR(phy->ref_clk),
+				     "failed to get ref clk\n");
+
+	num = ARRAY_SIZE(phy->vregs);
+	for (i = 0; i < num; i++)
+		phy->vregs[i].supply = eusb2_hsphy_vreg_names[i];
+
+	ret = devm_regulator_bulk_get(dev, num, phy->vregs);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "failed to get regulator supplies\n");
+
+	phy->repeater = devm_of_phy_optional_get(dev, np, 0);
+	if (IS_ERR(phy->repeater))
+		return dev_err_probe(dev, PTR_ERR(phy->repeater),
+				     "failed to get repeater\n");
+
+	generic_phy = devm_phy_create(dev, NULL, &snps_eusb2_hsphy_ops);
+	if (IS_ERR(generic_phy)) {
+		dev_err(dev, "failed to create phy %d\n", ret);
+		return PTR_ERR(generic_phy);
+	}
+
+	dev_set_drvdata(dev, phy);
+	phy_set_drvdata(generic_phy, phy);
+
+	phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
+	if (IS_ERR(phy_provider))
+		return PTR_ERR(phy_provider);
+
+	dev_info(dev, "Registered Snps-eUSB2 phy\n");
+
+	return 0;
+}
+
+static const struct of_device_id snps_eusb2_hsphy_of_match_table[] = {
+	{
+		.compatible = "qcom,sm8550-snps-eusb2-phy",
+		.data = &sm8550_snps_eusb2_phy,
+	}, {
+		.compatible = "samsung,exynos2200-eusb2-phy",
+		.data = &exynos2200_snps_eusb2_phy,
+	}, { },
+};
+MODULE_DEVICE_TABLE(of, snps_eusb2_hsphy_of_match_table);
+
+static struct platform_driver snps_eusb2_hsphy_driver = {
+	.probe		= snps_eusb2_hsphy_probe,
+	.driver = {
+		.name	= "snps-eusb2-hsphy",
+		.of_match_table = snps_eusb2_hsphy_of_match_table,
+	},
+};
+
+module_platform_driver(snps_eusb2_hsphy_driver);
+MODULE_DESCRIPTION("Synopsys eUSB2 HS PHY driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/phy/qualcomm/Kconfig b/drivers/phy/qualcomm/Kconfig
index c1e0a11ddd76..ef14f4e33973 100644
--- a/drivers/phy/qualcomm/Kconfig
+++ b/drivers/phy/qualcomm/Kconfig
@@ -125,15 +125,6 @@ config PHY_QCOM_QUSB2
 	  PHY which is usually paired with either the ChipIdea or Synopsys DWC3
 	  USB IPs on MSM SOCs.
 
-config PHY_QCOM_SNPS_EUSB2
-	tristate "Qualcomm SNPS eUSB2 PHY Driver"
-	depends on OF && (ARCH_QCOM || COMPILE_TEST)
-	select GENERIC_PHY
-	help
-	  Enable support for the USB high-speed SNPS eUSB2 phy on Qualcomm
-	  chipsets. The PHY is paired with a Synopsys DWC3 USB controller
-	  on Qualcomm SOCs.
-
 config PHY_QCOM_EUSB2_REPEATER
 	tristate "Qualcomm SNPS eUSB2 Repeater Driver"
 	depends on OF && (ARCH_QCOM || COMPILE_TEST)
diff --git a/drivers/phy/qualcomm/Makefile b/drivers/phy/qualcomm/Makefile
index 42038bc30974..3851e28a212d 100644
--- a/drivers/phy/qualcomm/Makefile
+++ b/drivers/phy/qualcomm/Makefile
@@ -15,7 +15,6 @@ obj-$(CONFIG_PHY_QCOM_QMP_USB)		+= phy-qcom-qmp-usb.o
 obj-$(CONFIG_PHY_QCOM_QMP_USB_LEGACY)	+= phy-qcom-qmp-usb-legacy.o
 
 obj-$(CONFIG_PHY_QCOM_QUSB2)		+= phy-qcom-qusb2.o
-obj-$(CONFIG_PHY_QCOM_SNPS_EUSB2)	+= phy-qcom-snps-eusb2.o
 obj-$(CONFIG_PHY_QCOM_EUSB2_REPEATER)	+= phy-qcom-eusb2-repeater.o
 obj-$(CONFIG_PHY_QCOM_UNIPHY_PCIE_28LP)	+= phy-qcom-uniphy-pcie-28lp.o
 obj-$(CONFIG_PHY_QCOM_USB_HS) 		+= phy-qcom-usb-hs.o
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
index c232b8fe9846..461b9e0af610 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
@@ -3021,8 +3021,6 @@ struct qmp_phy_cfg {
 
 	bool skip_start_delay;
 
-	bool has_nocsr_reset;
-
 	/* QMP PHY pipe clock interface rate */
 	unsigned long pipe_clock_rate;
 
@@ -3035,6 +3033,7 @@ struct qmp_pcie {
 
 	const struct qmp_phy_cfg *cfg;
 	bool tcsr_4ln_config;
+	bool skip_init;
 
 	void __iomem *serdes;
 	void __iomem *pcs;
@@ -4020,7 +4019,6 @@ static const struct qmp_phy_cfg sm8550_qmp_gen4x2_pciephy_cfg = {
 
 	.pwrdn_ctrl		= SW_PWRDN | REFCLK_DRV_DSBL,
 	.phy_status		= PHYSTATUS_4_20,
-	.has_nocsr_reset	= true,
 
 	/* 20MHz PHY AUX Clock */
 	.aux_clock_rate		= 20000000,
@@ -4053,7 +4051,6 @@ static const struct qmp_phy_cfg sm8650_qmp_gen4x2_pciephy_cfg = {
 
 	.pwrdn_ctrl		= SW_PWRDN | REFCLK_DRV_DSBL,
 	.phy_status		= PHYSTATUS_4_20,
-	.has_nocsr_reset	= true,
 
 	/* 20MHz PHY AUX Clock */
 	.aux_clock_rate		= 20000000,
@@ -4173,7 +4170,6 @@ static const struct qmp_phy_cfg x1e80100_qmp_gen4x2_pciephy_cfg = {
 
 	.pwrdn_ctrl		= SW_PWRDN | REFCLK_DRV_DSBL,
 	.phy_status		= PHYSTATUS_4_20,
-	.has_nocsr_reset	= true,
 };
 
 static const struct qmp_phy_cfg x1e80100_qmp_gen4x4_pciephy_cfg = {
@@ -4207,7 +4203,6 @@ static const struct qmp_phy_cfg x1e80100_qmp_gen4x4_pciephy_cfg = {
 
 	.pwrdn_ctrl		= SW_PWRDN | REFCLK_DRV_DSBL,
 	.phy_status		= PHYSTATUS_4_20,
-	.has_nocsr_reset	= true,
 };
 
 static const struct qmp_phy_cfg x1e80100_qmp_gen4x8_pciephy_cfg = {
@@ -4233,13 +4228,12 @@ static const struct qmp_phy_cfg x1e80100_qmp_gen4x8_pciephy_cfg = {
 
 	.reset_list		= sdm845_pciephy_reset_l,
 	.num_resets		= ARRAY_SIZE(sdm845_pciephy_reset_l),
-	.vreg_list		= sm8550_qmp_phy_vreg_l,
-	.num_vregs		= ARRAY_SIZE(sm8550_qmp_phy_vreg_l),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
 	.regs			= pciephy_v6_regs_layout,
 
 	.pwrdn_ctrl		= SW_PWRDN | REFCLK_DRV_DSBL,
 	.phy_status		= PHYSTATUS_4_20,
-	.has_nocsr_reset	= true,
 };
 
 static const struct qmp_phy_cfg qmp_v6_gen4x4_pciephy_cfg = {
@@ -4337,18 +4331,38 @@ static int qmp_pcie_init(struct phy *phy)
 {
 	struct qmp_pcie *qmp = phy_get_drvdata(phy);
 	const struct qmp_phy_cfg *cfg = qmp->cfg;
+	void __iomem *pcs = qmp->pcs;
+	bool phy_initialized = !!(readl(pcs + cfg->regs[QPHY_START_CTRL]));
 	int ret;
 
+	qmp->skip_init = qmp->nocsr_reset && phy_initialized;
+	/*
+	 * We need to check the existence of init sequences in two cases:
+	 * 1. The PHY doesn't support no_csr reset.
+	 * 2. The PHY supports no_csr reset but isn't initialized by bootloader.
+	 * As we can't skip init in these two cases.
+	 */
+	if (!qmp->skip_init && !cfg->tbls.serdes_num) {
+		dev_err(qmp->dev, "Init sequence not available\n");
+		return -ENODATA;
+	}
+
 	ret = regulator_bulk_enable(cfg->num_vregs, qmp->vregs);
 	if (ret) {
 		dev_err(qmp->dev, "failed to enable regulators, err=%d\n", ret);
 		return ret;
 	}
 
-	ret = reset_control_bulk_assert(cfg->num_resets, qmp->resets);
-	if (ret) {
-		dev_err(qmp->dev, "reset assert failed\n");
-		goto err_disable_regulators;
+	/*
+	 * Toggle BCR reset for PHY that doesn't support no_csr reset or has not
+	 * been initialized.
+	 */
+	if (!qmp->skip_init) {
+		ret = reset_control_bulk_assert(cfg->num_resets, qmp->resets);
+		if (ret) {
+			dev_err(qmp->dev, "reset assert failed\n");
+			goto err_disable_regulators;
+		}
 	}
 
 	ret = reset_control_assert(qmp->nocsr_reset);
@@ -4359,10 +4373,12 @@ static int qmp_pcie_init(struct phy *phy)
 
 	usleep_range(200, 300);
 
-	ret = reset_control_bulk_deassert(cfg->num_resets, qmp->resets);
-	if (ret) {
-		dev_err(qmp->dev, "reset deassert failed\n");
-		goto err_assert_reset;
+	if (!qmp->skip_init) {
+		ret = reset_control_bulk_deassert(cfg->num_resets, qmp->resets);
+		if (ret) {
+			dev_err(qmp->dev, "reset deassert failed\n");
+			goto err_assert_reset;
+		}
 	}
 
 	ret = clk_bulk_prepare_enable(ARRAY_SIZE(qmp_pciephy_clk_l), qmp->clks);
@@ -4372,7 +4388,8 @@ static int qmp_pcie_init(struct phy *phy)
 	return 0;
 
 err_assert_reset:
-	reset_control_bulk_assert(cfg->num_resets, qmp->resets);
+	if (!qmp->skip_init)
+		reset_control_bulk_assert(cfg->num_resets, qmp->resets);
 err_disable_regulators:
 	regulator_bulk_disable(cfg->num_vregs, qmp->vregs);
 
@@ -4384,7 +4401,10 @@ static int qmp_pcie_exit(struct phy *phy)
 	struct qmp_pcie *qmp = phy_get_drvdata(phy);
 	const struct qmp_phy_cfg *cfg = qmp->cfg;
 
-	reset_control_bulk_assert(cfg->num_resets, qmp->resets);
+	if (qmp->nocsr_reset)
+		reset_control_assert(qmp->nocsr_reset);
+	else
+		reset_control_bulk_assert(cfg->num_resets, qmp->resets);
 
 	clk_bulk_disable_unprepare(ARRAY_SIZE(qmp_pciephy_clk_l), qmp->clks);
 
@@ -4403,6 +4423,13 @@ static int qmp_pcie_power_on(struct phy *phy)
 	unsigned int mask, val;
 	int ret;
 
+	/*
+	 * Write CSR register for PHY that doesn't support no_csr reset or has not
+	 * been initialized.
+	 */
+	if (qmp->skip_init)
+		goto skip_tbls_init;
+
 	qphy_setbits(pcs, cfg->regs[QPHY_PCS_POWER_DOWN_CONTROL],
 			cfg->pwrdn_ctrl);
 
@@ -4414,6 +4441,7 @@ static int qmp_pcie_power_on(struct phy *phy)
 	qmp_pcie_init_registers(qmp, &cfg->tbls);
 	qmp_pcie_init_registers(qmp, mode_tbls);
 
+skip_tbls_init:
 	ret = clk_bulk_prepare_enable(qmp->num_pipe_clks, qmp->pipe_clks);
 	if (ret)
 		return ret;
@@ -4424,6 +4452,9 @@ static int qmp_pcie_power_on(struct phy *phy)
 		goto err_disable_pipe_clk;
 	}
 
+	if (qmp->skip_init)
+		goto skip_serdes_start;
+
 	/* Pull PHY out of reset state */
 	qphy_clrbits(pcs, cfg->regs[QPHY_SW_RESET], SW_RESET);
 
@@ -4433,6 +4464,7 @@ static int qmp_pcie_power_on(struct phy *phy)
 	if (!cfg->skip_start_delay)
 		usleep_range(1000, 1200);
 
+skip_serdes_start:
 	status = pcs + cfg->regs[QPHY_PCS_STATUS];
 	mask = cfg->phy_status;
 	ret = readl_poll_timeout(status, val, !(val & mask), 200,
@@ -4457,6 +4489,15 @@ static int qmp_pcie_power_off(struct phy *phy)
 
 	clk_bulk_disable_unprepare(qmp->num_pipe_clks, qmp->pipe_clks);
 
+	/*
+	 * While powering off the PHY, only qmp->nocsr_reset needs to be checked. In
+	 * this way, no matter whether the PHY settings were initially programmed by
+	 * bootloader or PHY driver itself, we can reuse them when PHY is powered on
+	 * next time.
+	 */
+	if (qmp->nocsr_reset)
+		goto skip_phy_deinit;
+
 	/* PHY reset */
 	qphy_setbits(qmp->pcs, cfg->regs[QPHY_SW_RESET], SW_RESET);
 
@@ -4468,6 +4509,7 @@ static int qmp_pcie_power_off(struct phy *phy)
 	qphy_clrbits(qmp->pcs, cfg->regs[QPHY_PCS_POWER_DOWN_CONTROL],
 			cfg->pwrdn_ctrl);
 
+skip_phy_deinit:
 	return 0;
 }
 
@@ -4557,12 +4599,10 @@ static int qmp_pcie_reset_init(struct qmp_pcie *qmp)
 	if (ret)
 		return dev_err_probe(dev, ret, "failed to get resets\n");
 
-	if (cfg->has_nocsr_reset) {
-		qmp->nocsr_reset = devm_reset_control_get_exclusive(dev, "phy_nocsr");
-		if (IS_ERR(qmp->nocsr_reset))
-			return dev_err_probe(dev, PTR_ERR(qmp->nocsr_reset),
-						"failed to get no-csr reset\n");
-	}
+	qmp->nocsr_reset = devm_reset_control_get_optional_exclusive(dev, "phy_nocsr");
+	if (IS_ERR(qmp->nocsr_reset))
+		return dev_err_probe(dev, PTR_ERR(qmp->nocsr_reset),
+							"failed to get no-csr reset\n");
 
 	return 0;
 }
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
index 787721570457..ed646a7e705b 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
@@ -2106,12 +2106,16 @@ static void __iomem *qmp_usb_iomap(struct device *dev, struct device_node *np,
 					int index, bool exclusive)
 {
 	struct resource res;
+	void __iomem *mem;
 
 	if (!exclusive) {
 		if (of_address_to_resource(np, index, &res))
 			return IOMEM_ERR_PTR(-EINVAL);
 
-		return devm_ioremap(dev, res.start, resource_size(&res));
+		mem = devm_ioremap(dev, res.start, resource_size(&res));
+		if (!mem)
+			return IOMEM_ERR_PTR(-ENOMEM);
+		return mem;
 	}
 
 	return devm_of_iomap(dev, np, index, NULL);
diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c
index 1f5f7df14d5a..49c37c53b38e 100644
--- a/drivers/phy/qualcomm/phy-qcom-qusb2.c
+++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c
@@ -151,21 +151,6 @@ static const struct qusb2_phy_init_tbl ipq6018_init_tbl[] = {
 	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_AUTOPGM_CTL1, 0x9F),
 };
 
-static const struct qusb2_phy_init_tbl ipq5424_init_tbl[] = {
-	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL, 0x14),
-	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE1, 0x00),
-	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE2, 0x53),
-	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE4, 0xc3),
-	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_TUNE, 0x30),
-	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL1, 0x79),
-	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL2, 0x21),
-	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE5, 0x00),
-	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_PWR_CTRL, 0x00),
-	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TEST2, 0x14),
-	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_TEST, 0x80),
-	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_AUTOPGM_CTL1, 0x9f),
-};
-
 static const struct qusb2_phy_init_tbl qcs615_init_tbl[] = {
 	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE1, 0xc8),
 	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE2, 0xb3),
@@ -359,16 +344,6 @@ static const struct qusb2_phy_cfg ipq6018_phy_cfg = {
 	.autoresume_en   = BIT(0),
 };
 
-static const struct qusb2_phy_cfg ipq5424_phy_cfg = {
-	.tbl            = ipq5424_init_tbl,
-	.tbl_num        = ARRAY_SIZE(ipq5424_init_tbl),
-	.regs           = ipq6018_regs_layout,
-
-	.disable_ctrl   = POWER_DOWN,
-	.mask_core_ready = PLL_LOCKED,
-	.autoresume_en   = BIT(0),
-};
-
 static const struct qusb2_phy_cfg qcs615_phy_cfg = {
 	.tbl            = qcs615_init_tbl,
 	.tbl_num        = ARRAY_SIZE(qcs615_init_tbl),
@@ -955,7 +930,7 @@ static const struct phy_ops qusb2_phy_gen_ops = {
 static const struct of_device_id qusb2_phy_of_match_table[] = {
 	{
 		.compatible	= "qcom,ipq5424-qusb2-phy",
-		.data		= &ipq5424_phy_cfg,
+		.data		= &ipq6018_phy_cfg,
 	}, {
 		.compatible	= "qcom,ipq6018-qusb2-phy",
 		.data		= &ipq6018_phy_cfg,
diff --git a/drivers/phy/qualcomm/phy-qcom-snps-eusb2.c b/drivers/phy/qualcomm/phy-qcom-snps-eusb2.c
deleted file mode 100644
index 1484691a41d5..000000000000
--- a/drivers/phy/qualcomm/phy-qcom-snps-eusb2.c
+++ /dev/null
@@ -1,442 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2023, Linaro Limited
- */
-
-#include <linux/bitfield.h>
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/iopoll.h>
-#include <linux/mod_devicetable.h>
-#include <linux/phy/phy.h>
-#include <linux/platform_device.h>
-#include <linux/regulator/consumer.h>
-#include <linux/reset.h>
-
-#define USB_PHY_UTMI_CTRL0		(0x3c)
-#define SLEEPM				BIT(0)
-#define OPMODE_MASK			GENMASK(4, 3)
-#define OPMODE_NONDRIVING		BIT(3)
-
-#define USB_PHY_UTMI_CTRL5		(0x50)
-#define POR				BIT(1)
-
-#define USB_PHY_HS_PHY_CTRL_COMMON0	(0x54)
-#define PHY_ENABLE			BIT(0)
-#define SIDDQ_SEL			BIT(1)
-#define SIDDQ				BIT(2)
-#define RETENABLEN			BIT(3)
-#define FSEL_MASK			GENMASK(6, 4)
-#define FSEL_19_2_MHZ_VAL		(0x0)
-#define FSEL_38_4_MHZ_VAL		(0x4)
-
-#define USB_PHY_CFG_CTRL_1		(0x58)
-#define PHY_CFG_PLL_CPBIAS_CNTRL_MASK	GENMASK(7, 1)
-
-#define USB_PHY_CFG_CTRL_2		(0x5c)
-#define PHY_CFG_PLL_FB_DIV_7_0_MASK	GENMASK(7, 0)
-#define DIV_7_0_19_2_MHZ_VAL		(0x90)
-#define DIV_7_0_38_4_MHZ_VAL		(0xc8)
-
-#define USB_PHY_CFG_CTRL_3		(0x60)
-#define PHY_CFG_PLL_FB_DIV_11_8_MASK	GENMASK(3, 0)
-#define DIV_11_8_19_2_MHZ_VAL		(0x1)
-#define DIV_11_8_38_4_MHZ_VAL		(0x0)
-
-#define PHY_CFG_PLL_REF_DIV		GENMASK(7, 4)
-#define PLL_REF_DIV_VAL			(0x0)
-
-#define USB_PHY_HS_PHY_CTRL2		(0x64)
-#define VBUSVLDEXT0			BIT(0)
-#define USB2_SUSPEND_N			BIT(2)
-#define USB2_SUSPEND_N_SEL		BIT(3)
-#define VBUS_DET_EXT_SEL		BIT(4)
-
-#define USB_PHY_CFG_CTRL_4		(0x68)
-#define PHY_CFG_PLL_GMP_CNTRL_MASK	GENMASK(1, 0)
-#define PHY_CFG_PLL_INT_CNTRL_MASK	GENMASK(7, 2)
-
-#define USB_PHY_CFG_CTRL_5		(0x6c)
-#define PHY_CFG_PLL_PROP_CNTRL_MASK	GENMASK(4, 0)
-#define PHY_CFG_PLL_VREF_TUNE_MASK	GENMASK(7, 6)
-
-#define USB_PHY_CFG_CTRL_6		(0x70)
-#define PHY_CFG_PLL_VCO_CNTRL_MASK	GENMASK(2, 0)
-
-#define USB_PHY_CFG_CTRL_7		(0x74)
-
-#define USB_PHY_CFG_CTRL_8		(0x78)
-#define PHY_CFG_TX_FSLS_VREF_TUNE_MASK	GENMASK(1, 0)
-#define PHY_CFG_TX_FSLS_VREG_BYPASS	BIT(2)
-#define PHY_CFG_TX_HS_VREF_TUNE_MASK	GENMASK(5, 3)
-#define PHY_CFG_TX_HS_XV_TUNE_MASK	GENMASK(7, 6)
-
-#define USB_PHY_CFG_CTRL_9		(0x7c)
-#define PHY_CFG_TX_PREEMP_TUNE_MASK	GENMASK(2, 0)
-#define PHY_CFG_TX_RES_TUNE_MASK	GENMASK(4, 3)
-#define PHY_CFG_TX_RISE_TUNE_MASK	GENMASK(6, 5)
-#define PHY_CFG_RCAL_BYPASS		BIT(7)
-
-#define USB_PHY_CFG_CTRL_10		(0x80)
-
-#define USB_PHY_CFG0			(0x94)
-#define DATAPATH_CTRL_OVERRIDE_EN	BIT(0)
-#define CMN_CTRL_OVERRIDE_EN		BIT(1)
-
-#define UTMI_PHY_CMN_CTRL0		(0x98)
-#define TESTBURNIN			BIT(6)
-
-#define USB_PHY_FSEL_SEL		(0xb8)
-#define FSEL_SEL			BIT(0)
-
-#define USB_PHY_APB_ACCESS_CMD		(0x130)
-#define RW_ACCESS			BIT(0)
-#define APB_START_CMD			BIT(1)
-#define APB_LOGIC_RESET			BIT(2)
-
-#define USB_PHY_APB_ACCESS_STATUS	(0x134)
-#define ACCESS_DONE			BIT(0)
-#define TIMED_OUT			BIT(1)
-#define ACCESS_ERROR			BIT(2)
-#define ACCESS_IN_PROGRESS		BIT(3)
-
-#define USB_PHY_APB_ADDRESS		(0x138)
-#define APB_REG_ADDR_MASK		GENMASK(7, 0)
-
-#define USB_PHY_APB_WRDATA_LSB		(0x13c)
-#define APB_REG_WRDATA_7_0_MASK		GENMASK(3, 0)
-
-#define USB_PHY_APB_WRDATA_MSB		(0x140)
-#define APB_REG_WRDATA_15_8_MASK	GENMASK(7, 4)
-
-#define USB_PHY_APB_RDDATA_LSB		(0x144)
-#define APB_REG_RDDATA_7_0_MASK		GENMASK(3, 0)
-
-#define USB_PHY_APB_RDDATA_MSB		(0x148)
-#define APB_REG_RDDATA_15_8_MASK	GENMASK(7, 4)
-
-static const char * const eusb2_hsphy_vreg_names[] = {
-	"vdd", "vdda12",
-};
-
-#define EUSB2_NUM_VREGS		ARRAY_SIZE(eusb2_hsphy_vreg_names)
-
-struct qcom_snps_eusb2_hsphy {
-	struct phy *phy;
-	void __iomem *base;
-
-	struct clk *ref_clk;
-	struct reset_control *phy_reset;
-
-	struct regulator_bulk_data vregs[EUSB2_NUM_VREGS];
-
-	enum phy_mode mode;
-
-	struct phy *repeater;
-};
-
-static int qcom_snps_eusb2_hsphy_set_mode(struct phy *p, enum phy_mode mode, int submode)
-{
-	struct qcom_snps_eusb2_hsphy *phy = phy_get_drvdata(p);
-
-	phy->mode = mode;
-
-	return phy_set_mode_ext(phy->repeater, mode, submode);
-}
-
-static void qcom_snps_eusb2_hsphy_write_mask(void __iomem *base, u32 offset,
-					     u32 mask, u32 val)
-{
-	u32 reg;
-
-	reg = readl_relaxed(base + offset);
-	reg &= ~mask;
-	reg |= val & mask;
-	writel_relaxed(reg, base + offset);
-
-	/* Ensure above write is completed */
-	readl_relaxed(base + offset);
-}
-
-static void qcom_eusb2_default_parameters(struct qcom_snps_eusb2_hsphy *phy)
-{
-	/* default parameters: tx pre-emphasis */
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_9,
-					 PHY_CFG_TX_PREEMP_TUNE_MASK,
-					 FIELD_PREP(PHY_CFG_TX_PREEMP_TUNE_MASK, 0));
-
-	/* tx rise/fall time */
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_9,
-					 PHY_CFG_TX_RISE_TUNE_MASK,
-					 FIELD_PREP(PHY_CFG_TX_RISE_TUNE_MASK, 0x2));
-
-	/* source impedance adjustment */
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_9,
-					 PHY_CFG_TX_RES_TUNE_MASK,
-					 FIELD_PREP(PHY_CFG_TX_RES_TUNE_MASK, 0x1));
-
-	/* dc voltage level adjustement */
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_8,
-					 PHY_CFG_TX_HS_VREF_TUNE_MASK,
-					 FIELD_PREP(PHY_CFG_TX_HS_VREF_TUNE_MASK, 0x3));
-
-	/* transmitter HS crossover adjustement */
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_8,
-					 PHY_CFG_TX_HS_XV_TUNE_MASK,
-					 FIELD_PREP(PHY_CFG_TX_HS_XV_TUNE_MASK, 0x0));
-}
-
-static int qcom_eusb2_ref_clk_init(struct qcom_snps_eusb2_hsphy *phy)
-{
-	unsigned long ref_clk_freq = clk_get_rate(phy->ref_clk);
-
-	switch (ref_clk_freq) {
-	case 19200000:
-		qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_HS_PHY_CTRL_COMMON0,
-						 FSEL_MASK,
-						 FIELD_PREP(FSEL_MASK, FSEL_19_2_MHZ_VAL));
-
-		qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_2,
-						 PHY_CFG_PLL_FB_DIV_7_0_MASK,
-						 DIV_7_0_19_2_MHZ_VAL);
-
-		qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_3,
-						 PHY_CFG_PLL_FB_DIV_11_8_MASK,
-						 DIV_11_8_19_2_MHZ_VAL);
-		break;
-
-	case 38400000:
-		qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_HS_PHY_CTRL_COMMON0,
-						 FSEL_MASK,
-						 FIELD_PREP(FSEL_MASK, FSEL_38_4_MHZ_VAL));
-
-		qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_2,
-						 PHY_CFG_PLL_FB_DIV_7_0_MASK,
-						 DIV_7_0_38_4_MHZ_VAL);
-
-		qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_3,
-						 PHY_CFG_PLL_FB_DIV_11_8_MASK,
-						 DIV_11_8_38_4_MHZ_VAL);
-		break;
-
-	default:
-		dev_err(&phy->phy->dev, "unsupported ref_clk_freq:%lu\n", ref_clk_freq);
-		return -EINVAL;
-	}
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_3,
-					 PHY_CFG_PLL_REF_DIV, PLL_REF_DIV_VAL);
-
-	return 0;
-}
-
-static int qcom_snps_eusb2_hsphy_init(struct phy *p)
-{
-	struct qcom_snps_eusb2_hsphy *phy = phy_get_drvdata(p);
-	int ret;
-
-	ret = regulator_bulk_enable(ARRAY_SIZE(phy->vregs), phy->vregs);
-	if (ret)
-		return ret;
-
-	ret = phy_init(phy->repeater);
-	if (ret) {
-		dev_err(&p->dev, "repeater init failed. %d\n", ret);
-		goto disable_vreg;
-	}
-
-	ret = clk_prepare_enable(phy->ref_clk);
-	if (ret) {
-		dev_err(&p->dev, "failed to enable ref clock, %d\n", ret);
-		goto disable_vreg;
-	}
-
-	ret = reset_control_assert(phy->phy_reset);
-	if (ret) {
-		dev_err(&p->dev, "failed to assert phy_reset, %d\n", ret);
-		goto disable_ref_clk;
-	}
-
-	usleep_range(100, 150);
-
-	ret = reset_control_deassert(phy->phy_reset);
-	if (ret) {
-		dev_err(&p->dev, "failed to de-assert phy_reset, %d\n", ret);
-		goto disable_ref_clk;
-	}
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG0,
-					 CMN_CTRL_OVERRIDE_EN, CMN_CTRL_OVERRIDE_EN);
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_UTMI_CTRL5, POR, POR);
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_HS_PHY_CTRL_COMMON0,
-					 PHY_ENABLE | RETENABLEN, PHY_ENABLE | RETENABLEN);
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_APB_ACCESS_CMD,
-					 APB_LOGIC_RESET, APB_LOGIC_RESET);
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, UTMI_PHY_CMN_CTRL0, TESTBURNIN, 0);
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_FSEL_SEL,
-					 FSEL_SEL, FSEL_SEL);
-
-	/* update ref_clk related registers */
-	ret = qcom_eusb2_ref_clk_init(phy);
-	if (ret)
-		goto disable_ref_clk;
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_1,
-					 PHY_CFG_PLL_CPBIAS_CNTRL_MASK,
-					 FIELD_PREP(PHY_CFG_PLL_CPBIAS_CNTRL_MASK, 0x1));
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_4,
-					 PHY_CFG_PLL_INT_CNTRL_MASK,
-					 FIELD_PREP(PHY_CFG_PLL_INT_CNTRL_MASK, 0x8));
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_4,
-					 PHY_CFG_PLL_GMP_CNTRL_MASK,
-					 FIELD_PREP(PHY_CFG_PLL_GMP_CNTRL_MASK, 0x1));
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_5,
-					 PHY_CFG_PLL_PROP_CNTRL_MASK,
-					 FIELD_PREP(PHY_CFG_PLL_PROP_CNTRL_MASK, 0x10));
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_6,
-					 PHY_CFG_PLL_VCO_CNTRL_MASK,
-					 FIELD_PREP(PHY_CFG_PLL_VCO_CNTRL_MASK, 0x0));
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_CFG_CTRL_5,
-					 PHY_CFG_PLL_VREF_TUNE_MASK,
-					 FIELD_PREP(PHY_CFG_PLL_VREF_TUNE_MASK, 0x1));
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_HS_PHY_CTRL2,
-					 VBUS_DET_EXT_SEL, VBUS_DET_EXT_SEL);
-
-	/* set default parameters */
-	qcom_eusb2_default_parameters(phy);
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_HS_PHY_CTRL2,
-					 USB2_SUSPEND_N_SEL | USB2_SUSPEND_N,
-					 USB2_SUSPEND_N_SEL | USB2_SUSPEND_N);
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_UTMI_CTRL0, SLEEPM, SLEEPM);
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_HS_PHY_CTRL_COMMON0,
-					 SIDDQ_SEL, SIDDQ_SEL);
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_HS_PHY_CTRL_COMMON0,
-					 SIDDQ, 0);
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_UTMI_CTRL5, POR, 0);
-
-	qcom_snps_eusb2_hsphy_write_mask(phy->base, USB_PHY_HS_PHY_CTRL2,
-					 USB2_SUSPEND_N_SEL, 0);
-
-	return 0;
-
-disable_ref_clk:
-	clk_disable_unprepare(phy->ref_clk);
-
-disable_vreg:
-	regulator_bulk_disable(ARRAY_SIZE(phy->vregs), phy->vregs);
-
-	return ret;
-}
-
-static int qcom_snps_eusb2_hsphy_exit(struct phy *p)
-{
-	struct qcom_snps_eusb2_hsphy *phy = phy_get_drvdata(p);
-
-	clk_disable_unprepare(phy->ref_clk);
-
-	regulator_bulk_disable(ARRAY_SIZE(phy->vregs), phy->vregs);
-
-	phy_exit(phy->repeater);
-
-	return 0;
-}
-
-static const struct phy_ops qcom_snps_eusb2_hsphy_ops = {
-	.init		= qcom_snps_eusb2_hsphy_init,
-	.exit		= qcom_snps_eusb2_hsphy_exit,
-	.set_mode	= qcom_snps_eusb2_hsphy_set_mode,
-	.owner		= THIS_MODULE,
-};
-
-static int qcom_snps_eusb2_hsphy_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct device_node *np = dev->of_node;
-	struct qcom_snps_eusb2_hsphy *phy;
-	struct phy_provider *phy_provider;
-	struct phy *generic_phy;
-	int ret, i;
-	int num;
-
-	phy = devm_kzalloc(dev, sizeof(*phy), GFP_KERNEL);
-	if (!phy)
-		return -ENOMEM;
-
-	phy->base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(phy->base))
-		return PTR_ERR(phy->base);
-
-	phy->phy_reset = devm_reset_control_get_exclusive(dev, NULL);
-	if (IS_ERR(phy->phy_reset))
-		return PTR_ERR(phy->phy_reset);
-
-	phy->ref_clk = devm_clk_get(dev, "ref");
-	if (IS_ERR(phy->ref_clk))
-		return dev_err_probe(dev, PTR_ERR(phy->ref_clk),
-				     "failed to get ref clk\n");
-
-	num = ARRAY_SIZE(phy->vregs);
-	for (i = 0; i < num; i++)
-		phy->vregs[i].supply = eusb2_hsphy_vreg_names[i];
-
-	ret = devm_regulator_bulk_get(dev, num, phy->vregs);
-	if (ret)
-		return dev_err_probe(dev, ret,
-				     "failed to get regulator supplies\n");
-
-	phy->repeater = devm_of_phy_get_by_index(dev, np, 0);
-	if (IS_ERR(phy->repeater))
-		return dev_err_probe(dev, PTR_ERR(phy->repeater),
-				     "failed to get repeater\n");
-
-	generic_phy = devm_phy_create(dev, NULL, &qcom_snps_eusb2_hsphy_ops);
-	if (IS_ERR(generic_phy)) {
-		dev_err(dev, "failed to create phy %d\n", ret);
-		return PTR_ERR(generic_phy);
-	}
-
-	dev_set_drvdata(dev, phy);
-	phy_set_drvdata(generic_phy, phy);
-
-	phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
-	if (IS_ERR(phy_provider))
-		return PTR_ERR(phy_provider);
-
-	dev_info(dev, "Registered Qcom-eUSB2 phy\n");
-
-	return 0;
-}
-
-static const struct of_device_id qcom_snps_eusb2_hsphy_of_match_table[] = {
-	{ .compatible = "qcom,sm8550-snps-eusb2-phy", },
-	{ },
-};
-MODULE_DEVICE_TABLE(of, qcom_snps_eusb2_hsphy_of_match_table);
-
-static struct platform_driver qcom_snps_eusb2_hsphy_driver = {
-	.probe		= qcom_snps_eusb2_hsphy_probe,
-	.driver = {
-		.name	= "qcom-snps-eusb2-hsphy",
-		.of_match_table = qcom_snps_eusb2_hsphy_of_match_table,
-	},
-};
-
-module_platform_driver(qcom_snps_eusb2_hsphy_driver);
-MODULE_DESCRIPTION("Qualcomm SNPS eUSB2 HS PHY driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/phy/qualcomm/phy-qcom-uniphy-pcie-28lp.c b/drivers/phy/qualcomm/phy-qcom-uniphy-pcie-28lp.c
index c8b2a3818880..324c0a5d658e 100644
--- a/drivers/phy/qualcomm/phy-qcom-uniphy-pcie-28lp.c
+++ b/drivers/phy/qualcomm/phy-qcom-uniphy-pcie-28lp.c
@@ -75,6 +75,40 @@ struct qcom_uniphy_pcie {
 
 #define phy_to_dw_phy(x)	container_of((x), struct qca_uni_pcie_phy, phy)
 
+static const struct qcom_uniphy_pcie_regs ipq5018_regs[] = {
+	{
+		.offset = SSCG_CTRL_REG_4,
+		.val = 0x1cb9,
+	}, {
+		.offset = SSCG_CTRL_REG_5,
+		.val = 0x023a,
+	}, {
+		.offset = SSCG_CTRL_REG_3,
+		.val = 0xd360,
+	}, {
+		.offset = SSCG_CTRL_REG_1,
+		.val = 0x1,
+	}, {
+		.offset = SSCG_CTRL_REG_2,
+		.val = 0xeb,
+	}, {
+		.offset = CDR_CTRL_REG_4,
+		.val = 0x3f9,
+	}, {
+		.offset = CDR_CTRL_REG_5,
+		.val = 0x1c9,
+	}, {
+		.offset = CDR_CTRL_REG_2,
+		.val = 0x419,
+	}, {
+		.offset = CDR_CTRL_REG_1,
+		.val = 0x200,
+	}, {
+		.offset = PCS_INTERNAL_CONTROL_2,
+		.val = 0xf101,
+	},
+};
+
 static const struct qcom_uniphy_pcie_regs ipq5332_regs[] = {
 	{
 		.offset = PHY_CFG_PLLCFG,
@@ -88,6 +122,14 @@ static const struct qcom_uniphy_pcie_regs ipq5332_regs[] = {
 	},
 };
 
+static const struct qcom_uniphy_pcie_data ipq5018_data = {
+	.lane_offset	= 0x800,
+	.phy_type	= PHY_TYPE_PCIE_GEN2,
+	.init_seq	= ipq5018_regs,
+	.init_seq_num	= ARRAY_SIZE(ipq5018_regs),
+	.pipe_clk_rate	= 125 * MEGA,
+};
+
 static const struct qcom_uniphy_pcie_data ipq5332_data = {
 	.lane_offset	= 0x800,
 	.phy_type	= PHY_TYPE_PCIE_GEN3,
@@ -212,6 +254,9 @@ static inline int phy_pipe_clk_register(struct qcom_uniphy_pcie *phy, int id)
 
 static const struct of_device_id qcom_uniphy_pcie_id_table[] = {
 	{
+		.compatible = "qcom,ipq5018-uniphy-pcie-phy",
+		.data = &ipq5018_data,
+	}, {
 		.compatible = "qcom,ipq5332-uniphy-pcie-phy",
 		.data = &ipq5332_data,
 	}, {
diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index 9fdf17e0848a..47beb94cd424 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -29,8 +29,10 @@
 #define USB2_INT_ENABLE		0x000
 #define USB2_AHB_BUS_CTR	0x008
 #define USB2_USBCTR		0x00c
+#define USB2_REGEN_CG_CTRL	0x104	/* RZ/V2H(P) only */
 #define USB2_SPD_RSM_TIMSET	0x10c
 #define USB2_OC_TIMSET		0x110
+#define USB2_UTMI_CTRL		0x118	/* RZ/V2H(P) only */
 #define USB2_COMMCTRL		0x600
 #define USB2_OBINTSTA		0x604
 #define USB2_OBINTEN		0x608
@@ -51,12 +53,18 @@
 #define USB2_USBCTR_DIRPD	BIT(2)
 #define USB2_USBCTR_PLL_RST	BIT(1)
 
+/* REGEN_CG_CTRL*/
+#define USB2_REGEN_CG_CTRL_UPHY_WEN	BIT(0)
+
 /* SPD_RSM_TIMSET */
 #define USB2_SPD_RSM_TIMSET_INIT	0x014e029b
 
 /* OC_TIMSET */
 #define USB2_OC_TIMSET_INIT		0x000209ab
 
+/* UTMI_CTRL */
+#define USB2_UTMI_CTRL_INIT		0x8000018f
+
 /* COMMCTRL */
 #define USB2_COMMCTRL_OTG_PERI		BIT(31)	/* 1 = Peripheral mode */
 
@@ -126,12 +134,14 @@ struct rcar_gen3_chan {
 	bool is_otg_channel;
 	bool uses_otg_pins;
 	bool soc_no_adp_ctrl;
+	bool utmi_ctrl;
 };
 
 struct rcar_gen3_phy_drv_data {
 	const struct phy_ops *phy_usb2_ops;
 	bool no_adp_ctrl;
 	bool init_bus;
+	bool utmi_ctrl;
 };
 
 /*
@@ -477,6 +487,14 @@ static int rcar_gen3_phy_usb2_init(struct phy *p)
 	if (rphy->int_enable_bits)
 		rcar_gen3_init_otg(channel);
 
+	if (channel->utmi_ctrl) {
+		val = readl(usb2_base + USB2_REGEN_CG_CTRL) | USB2_REGEN_CG_CTRL_UPHY_WEN;
+		writel(val, usb2_base + USB2_REGEN_CG_CTRL);
+
+		writel(USB2_UTMI_CTRL_INIT, usb2_base + USB2_UTMI_CTRL);
+		writel(val & ~USB2_REGEN_CG_CTRL_UPHY_WEN, usb2_base + USB2_REGEN_CG_CTRL);
+	}
+
 	rphy->initialized = true;
 
 	return 0;
@@ -592,6 +610,12 @@ static const struct rcar_gen3_phy_drv_data rz_g3s_phy_usb2_data = {
 	.init_bus = true,
 };
 
+static const struct rcar_gen3_phy_drv_data rz_v2h_phy_usb2_data = {
+	.phy_usb2_ops = &rcar_gen3_phy_usb2_ops,
+	.no_adp_ctrl = true,
+	.utmi_ctrl = true,
+};
+
 static const struct of_device_id rcar_gen3_phy_usb2_match_table[] = {
 	{
 		.compatible = "renesas,usb2-phy-r8a77470",
@@ -610,14 +634,18 @@ static const struct of_device_id rcar_gen3_phy_usb2_match_table[] = {
 		.data = &rcar_gen3_phy_usb2_data,
 	},
 	{
-		.compatible = "renesas,rzg2l-usb2-phy",
-		.data = &rz_g2l_phy_usb2_data,
-	},
-	{
 		.compatible = "renesas,usb2-phy-r9a08g045",
 		.data = &rz_g3s_phy_usb2_data,
 	},
 	{
+		.compatible = "renesas,usb2-phy-r9a09g057",
+		.data = &rz_v2h_phy_usb2_data,
+	},
+	{
+		.compatible = "renesas,rzg2l-usb2-phy",
+		.data = &rz_g2l_phy_usb2_data,
+	},
+	{
 		.compatible = "renesas,rcar-gen3-usb2-phy",
 		.data = &rcar_gen3_phy_usb2_data,
 	},
@@ -764,6 +792,8 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 	if (phy_data->no_adp_ctrl)
 		channel->obint_enable_bits = USB2_OBINT_IDCHG_EN;
 
+	channel->utmi_ctrl = phy_data->utmi_ctrl;
+
 	spin_lock_init(&channel->lock);
 	for (i = 0; i < NUM_OF_PHYS; i++) {
 		channel->rphys[i].phy = devm_phy_create(dev, NULL,
diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
index b5e6a864deeb..b0f23690ec30 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
@@ -1583,6 +1583,37 @@ static int rk3588_usb2phy_tuning(struct rockchip_usb2phy *rphy)
 	return ret;
 }
 
+static const struct rockchip_usb2phy_cfg rk3036_phy_cfgs[] = {
+	{
+		.reg = 0x17c,
+		.num_ports	= 2,
+		.phy_tuning	= rk3128_usb2phy_tuning,
+		.clkout_ctl	= { 0x017c, 11, 11, 1, 0 },
+		.port_cfgs	= {
+			[USB2PHY_PORT_OTG] = {
+				.phy_sus	= { 0x017c, 8, 0, 0, 0x1d1 },
+				.bvalid_det_en	= { 0x017c, 14, 14, 0, 1 },
+				.bvalid_det_st	= { 0x017c, 15, 15, 0, 1 },
+				.bvalid_det_clr	= { 0x017c, 15, 15, 0, 1 },
+				.ls_det_en	= { 0x017c, 12, 12, 0, 1 },
+				.ls_det_st	= { 0x017c, 13, 13, 0, 1 },
+				.ls_det_clr	= { 0x017c, 13, 13, 0, 1 },
+				.utmi_bvalid	= { 0x014c, 8, 8, 0, 1 },
+				.utmi_id	= { 0x014c, 11, 11, 0, 1 },
+				.utmi_ls	= { 0x014c, 10, 9, 0, 1 },
+
+			},
+			[USB2PHY_PORT_HOST] = {
+				.phy_sus	= { 0x0194, 8, 0, 0, 0x1d1 },
+				.ls_det_en	= { 0x0194, 14, 14, 0, 1 },
+				.ls_det_st	= { 0x0194, 15, 15, 0, 1 },
+				.ls_det_clr	= { 0x0194, 15, 15, 0, 1 }
+			}
+		},
+	},
+	{ /* sentinel */ }
+};
+
 static const struct rockchip_usb2phy_cfg rk3128_phy_cfgs[] = {
 	{
 		.reg = 0x17c,
@@ -1892,6 +1923,54 @@ static const struct rockchip_usb2phy_cfg rk3399_phy_cfgs[] = {
 	{ /* sentinel */ }
 };
 
+static const struct rockchip_usb2phy_cfg rk3562_phy_cfgs[] = {
+	{
+		.reg = 0xff740000,
+		.num_ports	= 2,
+		.clkout_ctl	= { 0x0108, 4, 4, 1, 0 },
+		.port_cfgs	= {
+			[USB2PHY_PORT_OTG] = {
+				.phy_sus	= { 0x0100, 8, 0, 0, 0x1d1 },
+				.bvalid_det_en	= { 0x0110, 2, 2, 0, 1 },
+				.bvalid_det_st	= { 0x0114, 2, 2, 0, 1 },
+				.bvalid_det_clr = { 0x0118, 2, 2, 0, 1 },
+				.idfall_det_en	= { 0x0110, 5, 5, 0, 1 },
+				.idfall_det_st	= { 0x0114, 5, 5, 0, 1 },
+				.idfall_det_clr = { 0x0118, 5, 5, 0, 1 },
+				.idrise_det_en	= { 0x0110, 4, 4, 0, 1 },
+				.idrise_det_st	= { 0x0114, 4, 4, 0, 1 },
+				.idrise_det_clr = { 0x0118, 4, 4, 0, 1 },
+				.ls_det_en	= { 0x0110, 0, 0, 0, 1 },
+				.ls_det_st	= { 0x0114, 0, 0, 0, 1 },
+				.ls_det_clr	= { 0x0118, 0, 0, 0, 1 },
+				.utmi_avalid	= { 0x0120, 10, 10, 0, 1 },
+				.utmi_bvalid	= { 0x0120, 9, 9, 0, 1 },
+				.utmi_ls	= { 0x0120, 5, 4, 0, 1 },
+			},
+			[USB2PHY_PORT_HOST] = {
+				.phy_sus	= { 0x0104, 8, 0, 0x1d2, 0x1d1 },
+				.ls_det_en	= { 0x0110, 1, 1, 0, 1 },
+				.ls_det_st	= { 0x0114, 1, 1, 0, 1 },
+				.ls_det_clr	= { 0x0118, 1, 1, 0, 1 },
+				.utmi_ls	= { 0x0120, 17, 16, 0, 1 },
+				.utmi_hstdet	= { 0x0120, 19, 19, 0, 1 }
+			}
+		},
+		.chg_det = {
+			.cp_det		= { 0x0120, 24, 24, 0, 1 },
+			.dcp_det	= { 0x0120, 23, 23, 0, 1 },
+			.dp_det		= { 0x0120, 25, 25, 0, 1 },
+			.idm_sink_en	= { 0x0108, 8, 8, 0, 1 },
+			.idp_sink_en	= { 0x0108, 7, 7, 0, 1 },
+			.idp_src_en	= { 0x0108, 9, 9, 0, 1 },
+			.rdm_pdwn_en	= { 0x0108, 10, 10, 0, 1 },
+			.vdm_src_en	= { 0x0108, 12, 12, 0, 1 },
+			.vdp_src_en	= { 0x0108, 11, 11, 0, 1 },
+		},
+	},
+	{ /* sentinel */ }
+};
+
 static const struct rockchip_usb2phy_cfg rk3568_phy_cfgs[] = {
 	{
 		.reg = 0xfe8a0000,
@@ -2204,12 +2283,14 @@ static const struct rockchip_usb2phy_cfg rv1108_phy_cfgs[] = {
 
 static const struct of_device_id rockchip_usb2phy_dt_match[] = {
 	{ .compatible = "rockchip,px30-usb2phy", .data = &rk3328_phy_cfgs },
+	{ .compatible = "rockchip,rk3036-usb2phy", .data = &rk3036_phy_cfgs },
 	{ .compatible = "rockchip,rk3128-usb2phy", .data = &rk3128_phy_cfgs },
 	{ .compatible = "rockchip,rk3228-usb2phy", .data = &rk3228_phy_cfgs },
 	{ .compatible = "rockchip,rk3308-usb2phy", .data = &rk3308_phy_cfgs },
 	{ .compatible = "rockchip,rk3328-usb2phy", .data = &rk3328_phy_cfgs },
 	{ .compatible = "rockchip,rk3366-usb2phy", .data = &rk3366_phy_cfgs },
 	{ .compatible = "rockchip,rk3399-usb2phy", .data = &rk3399_phy_cfgs },
+	{ .compatible = "rockchip,rk3562-usb2phy", .data = &rk3562_phy_cfgs },
 	{ .compatible = "rockchip,rk3568-usb2phy", .data = &rk3568_phy_cfgs },
 	{ .compatible = "rockchip,rk3576-usb2phy", .data = &rk3576_phy_cfgs },
 	{ .compatible = "rockchip,rk3588-usb2phy", .data = &rk3588_phy_cfgs },
diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
index 77236f012a1f..79db57ee90d1 100644
--- a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
+++ b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
@@ -320,6 +320,7 @@
 #define LN3_TX_SER_RATE_SEL_HBR2_MASK	BIT(3)
 #define LN3_TX_SER_RATE_SEL_HBR3_MASK	BIT(2)
 
+#define HDMI14_MAX_RATE			340000000
 #define HDMI20_MAX_RATE			600000000
 
 enum dp_link_rate {
@@ -328,39 +329,8 @@ enum dp_link_rate {
 	DP_BW_HBR2,
 };
 
-struct lcpll_config {
-	u32 bit_rate;
-	u8 lcvco_mode_en;
-	u8 pi_en;
-	u8 clk_en_100m;
-	u8 pms_mdiv;
-	u8 pms_mdiv_afc;
-	u8 pms_pdiv;
-	u8 pms_refdiv;
-	u8 pms_sdiv;
-	u8 pi_cdiv_rstn;
-	u8 pi_cdiv_sel;
-	u8 sdm_en;
-	u8 sdm_rstn;
-	u8 sdc_frac_en;
-	u8 sdc_rstn;
-	u8 sdm_deno;
-	u8 sdm_num_sign;
-	u8 sdm_num;
-	u8 sdc_n;
-	u8 sdc_n2;
-	u8 sdc_num;
-	u8 sdc_deno;
-	u8 sdc_ndiv_rstn;
-	u8 ssc_en;
-	u8 ssc_fm_dev;
-	u8 ssc_fm_freq;
-	u8 ssc_clk_div_sel;
-	u8 cd_tx_ser_rate_sel;
-};
-
 struct ropll_config {
-	u32 bit_rate;
+	unsigned long long rate;
 	u8 pms_mdiv;
 	u8 pms_mdiv_afc;
 	u8 pms_pdiv;
@@ -422,19 +392,17 @@ struct rk_hdptx_phy {
 	struct regmap *regmap;
 	struct regmap *grf;
 
-	/* PHY const config */
-	const struct rk_hdptx_phy_cfg *cfgs;
 	int phy_id;
-
 	struct phy *phy;
-	struct phy_config *phy_cfg;
+	struct phy_configure_opts_hdmi hdmi_cfg;
 	struct clk_bulk_data *clks;
 	int nr_clks;
 	struct reset_control_bulk_data rsts[RST_MAX];
 
 	/* clk provider */
 	struct clk_hw hw;
-	unsigned long rate;
+	unsigned long hw_rate;
+	bool restrict_rate_change;
 
 	atomic_t usage_count;
 
@@ -444,47 +412,47 @@ struct rk_hdptx_phy {
 };
 
 static const struct ropll_config ropll_tmds_cfg[] = {
-	{ 5940000, 124, 124, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0,
+	{ 594000000ULL, 124, 124, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0,
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 3712500, 155, 155, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0,
+	{ 371250000ULL, 155, 155, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0,
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 2970000, 124, 124, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0,
+	{ 297000000ULL, 124, 124, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0,
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 1620000, 135, 135, 1, 1, 3, 1, 1, 0, 1, 1, 1, 1, 4, 0, 3, 5, 5, 0x10,
+	{ 162000000ULL, 135, 135, 1, 1, 3, 1, 1, 0, 1, 1, 1, 1, 4, 0, 3, 5, 5, 0x10,
 	  1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 1856250, 155, 155, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0,
+	{ 185625000ULL, 155, 155, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0,
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 1540000, 193, 193, 1, 1, 5, 1, 1, 1, 1, 1, 1, 1, 193, 1, 32, 2, 1,
+	{ 154000000ULL, 193, 193, 1, 1, 5, 1, 1, 1, 1, 1, 1, 1, 193, 1, 32, 2, 1,
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 1485000, 0x7b, 0x7b, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 4, 0, 3, 5, 5,
+	{ 148500000ULL, 0x7b, 0x7b, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 4, 0, 3, 5, 5,
 	  0x10, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 1462500, 122, 122, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 244, 1, 16, 2, 1, 1,
+	{ 146250000ULL, 122, 122, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 244, 1, 16, 2, 1, 1,
 	  1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 1190000, 149, 149, 1, 1, 5, 1, 1, 1, 1, 1, 1, 1, 149, 1, 16, 2, 1, 1,
+	{ 119000000ULL, 149, 149, 1, 1, 5, 1, 1, 1, 1, 1, 1, 1, 149, 1, 16, 2, 1, 1,
 	  1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 1065000, 89, 89, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 89, 1, 16, 1, 0, 1,
+	{ 106500000ULL, 89, 89, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 89, 1, 16, 1, 0, 1,
 	  1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 1080000, 135, 135, 1, 1, 5, 1, 1, 0, 1, 0, 1, 1, 0x9, 0, 0x05, 0,
+	{ 108000000ULL, 135, 135, 1, 1, 5, 1, 1, 0, 1, 0, 1, 1, 0x9, 0, 0x05, 0,
 	  0x14, 0x18, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 855000, 214, 214, 1, 1, 11, 1, 1, 1, 1, 1, 1, 1, 214, 1, 16, 2, 1,
+	{ 85500000ULL, 214, 214, 1, 1, 11, 1, 1, 1, 1, 1, 1, 1, 214, 1, 16, 2, 1,
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 835000, 105, 105, 1, 1, 5, 1, 1, 1, 1, 1, 1, 1, 42, 1, 16, 1, 0,
+	{ 83500000ULL, 105, 105, 1, 1, 5, 1, 1, 1, 1, 1, 1, 1, 42, 1, 16, 1, 0,
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 928125, 155, 155, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0,
+	{ 92812500ULL, 155, 155, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0,
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 742500, 124, 124, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0,
+	{ 74250000ULL, 124, 124, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0,
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 650000, 162, 162, 1, 1, 11, 1, 1, 1, 1, 1, 1, 1, 54, 0, 16, 4, 1,
+	{ 65000000ULL, 162, 162, 1, 1, 11, 1, 1, 1, 1, 1, 1, 1, 54, 0, 16, 4, 1,
 	  1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 502500, 84, 84, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 11, 1, 4, 5,
+	{ 50250000ULL, 84, 84, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 11, 1, 4, 5,
 	  4, 11, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 337500, 0x70, 0x70, 1, 1, 0xf, 1, 1, 1, 1, 1, 1, 1, 0x2, 0, 0x01, 5,
+	{ 33750000ULL, 0x70, 0x70, 1, 1, 0xf, 1, 1, 1, 1, 1, 1, 1, 0x2, 0, 0x01, 5,
 	  1, 1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 400000, 100, 100, 1, 1, 11, 1, 1, 0, 1, 0, 1, 1, 0x9, 0, 0x05, 0,
+	{ 40000000ULL, 100, 100, 1, 1, 11, 1, 1, 0, 1, 0, 1, 1, 0x9, 0, 0x05, 0,
 	  0x14, 0x18, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 270000, 0x5a, 0x5a, 1, 1, 0xf, 1, 1, 0, 1, 0, 1, 1, 0x9, 0, 0x05, 0,
+	{ 27000000ULL, 0x5a, 0x5a, 1, 1, 0xf, 1, 1, 0, 1, 0, 1, 1, 0x9, 0, 0x05, 0,
 	  0x14, 0x18, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
-	{ 251750, 84, 84, 1, 1, 0xf, 1, 1, 1, 1, 1, 1, 1, 168, 1, 16, 4, 1, 1,
+	{ 25175000ULL, 84, 84, 1, 1, 0xf, 1, 1, 1, 1, 1, 1, 1, 168, 1, 16, 4, 1, 1,
 	  1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, },
 };
 
@@ -930,10 +898,10 @@ static void rk_hdptx_phy_disable(struct rk_hdptx_phy *hdptx)
 	regmap_write(hdptx->grf, GRF_HDPTX_CON0, val);
 }
 
-static bool rk_hdptx_phy_clk_pll_calc(unsigned int data_rate,
+static bool rk_hdptx_phy_clk_pll_calc(unsigned long long rate,
 				      struct ropll_config *cfg)
 {
-	const unsigned int fout = data_rate / 2, fref = 24000;
+	const unsigned int fout = div_u64(rate, 200), fref = 24000;
 	unsigned long k = 0, lc, k_sub, lc_sub;
 	unsigned int fvco, sdc;
 	u32 mdiv, sdiv, n = 8;
@@ -1002,33 +970,34 @@ static bool rk_hdptx_phy_clk_pll_calc(unsigned int data_rate,
 	return true;
 }
 
-static int rk_hdptx_ropll_tmds_cmn_config(struct rk_hdptx_phy *hdptx,
-					  unsigned int rate)
+static int rk_hdptx_ropll_tmds_cmn_config(struct rk_hdptx_phy *hdptx)
 {
 	const struct ropll_config *cfg = NULL;
 	struct ropll_config rc = {0};
-	int i;
+	int ret, i;
 
-	hdptx->rate = rate * 100;
+	if (!hdptx->hdmi_cfg.tmds_char_rate)
+		return 0;
 
 	for (i = 0; i < ARRAY_SIZE(ropll_tmds_cfg); i++)
-		if (rate == ropll_tmds_cfg[i].bit_rate) {
+		if (hdptx->hdmi_cfg.tmds_char_rate == ropll_tmds_cfg[i].rate) {
 			cfg = &ropll_tmds_cfg[i];
 			break;
 		}
 
 	if (!cfg) {
-		if (rk_hdptx_phy_clk_pll_calc(rate, &rc)) {
-			cfg = &rc;
-		} else {
-			dev_err(hdptx->dev, "%s cannot find pll cfg\n", __func__);
+		if (!rk_hdptx_phy_clk_pll_calc(hdptx->hdmi_cfg.tmds_char_rate, &rc)) {
+			dev_err(hdptx->dev, "%s cannot find pll cfg for rate=%llu\n",
+				__func__, hdptx->hdmi_cfg.tmds_char_rate);
 			return -EINVAL;
 		}
+
+		cfg = &rc;
 	}
 
-	dev_dbg(hdptx->dev, "mdiv=%u, sdiv=%u, sdm_en=%u, k_sign=%u, k=%u, lc=%u\n",
-		cfg->pms_mdiv, cfg->pms_sdiv + 1, cfg->sdm_en,
-		cfg->sdm_num_sign, cfg->sdm_num, cfg->sdm_deno);
+	dev_dbg(hdptx->dev, "%s rate=%llu mdiv=%u sdiv=%u sdm_en=%u k_sign=%u k=%u lc=%u\n",
+		__func__, hdptx->hdmi_cfg.tmds_char_rate, cfg->pms_mdiv, cfg->pms_sdiv + 1,
+		cfg->sdm_en, cfg->sdm_num_sign, cfg->sdm_num, cfg->sdm_deno);
 
 	rk_hdptx_pre_power_up(hdptx);
 
@@ -1061,20 +1030,26 @@ static int rk_hdptx_ropll_tmds_cmn_config(struct rk_hdptx_phy *hdptx,
 	regmap_update_bits(hdptx->regmap, CMN_REG(0086), PLL_PCG_POSTDIV_SEL_MASK,
 			   FIELD_PREP(PLL_PCG_POSTDIV_SEL_MASK, cfg->pms_sdiv));
 
+	regmap_update_bits(hdptx->regmap, CMN_REG(0086), PLL_PCG_CLK_SEL_MASK,
+			   FIELD_PREP(PLL_PCG_CLK_SEL_MASK, (hdptx->hdmi_cfg.bpc - 8) >> 1));
+
 	regmap_update_bits(hdptx->regmap, CMN_REG(0086), PLL_PCG_CLK_EN_MASK,
 			   FIELD_PREP(PLL_PCG_CLK_EN_MASK, 0x1));
 
-	return rk_hdptx_post_enable_pll(hdptx);
+	ret = rk_hdptx_post_enable_pll(hdptx);
+	if (!ret)
+		hdptx->hw_rate = hdptx->hdmi_cfg.tmds_char_rate;
+
+	return ret;
 }
 
-static int rk_hdptx_ropll_tmds_mode_config(struct rk_hdptx_phy *hdptx,
-					   unsigned int rate)
+static int rk_hdptx_ropll_tmds_mode_config(struct rk_hdptx_phy *hdptx)
 {
 	rk_hdptx_multi_reg_write(hdptx, rk_hdtpx_common_sb_init_seq);
 
 	regmap_write(hdptx->regmap, LNTOP_REG(0200), 0x06);
 
-	if (rate >= 3400000) {
+	if (hdptx->hdmi_cfg.tmds_char_rate > HDMI14_MAX_RATE) {
 		/* For 1/40 bitrate clk */
 		rk_hdptx_multi_reg_write(hdptx, rk_hdtpx_tmds_lntop_highbr_seq);
 	} else {
@@ -1126,8 +1101,7 @@ static void rk_hdptx_dp_reset(struct rk_hdptx_phy *hdptx)
 		     HDPTX_I_BGR_EN << 16 | FIELD_PREP(HDPTX_I_BGR_EN, 0x0));
 }
 
-static int rk_hdptx_phy_consumer_get(struct rk_hdptx_phy *hdptx,
-				     unsigned int rate)
+static int rk_hdptx_phy_consumer_get(struct rk_hdptx_phy *hdptx)
 {
 	enum phy_mode mode = phy_get_mode(hdptx->phy);
 	u32 status;
@@ -1146,11 +1120,9 @@ static int rk_hdptx_phy_consumer_get(struct rk_hdptx_phy *hdptx,
 	if (mode == PHY_MODE_DP) {
 		rk_hdptx_dp_reset(hdptx);
 	} else {
-		if (rate) {
-			ret = rk_hdptx_ropll_tmds_cmn_config(hdptx, rate);
-			if (ret)
-				goto dec_usage;
-		}
+		ret = rk_hdptx_ropll_tmds_cmn_config(hdptx);
+		if (ret)
+			goto dec_usage;
 	}
 
 	return 0;
@@ -1445,21 +1417,26 @@ static int rk_hdptx_dp_aux_init(struct rk_hdptx_phy *hdptx)
 static int rk_hdptx_phy_power_on(struct phy *phy)
 {
 	struct rk_hdptx_phy *hdptx = phy_get_drvdata(phy);
-	int bus_width = phy_get_bus_width(hdptx->phy);
 	enum phy_mode mode = phy_get_mode(phy);
 	int ret, lane;
 
-	/*
-	 * FIXME: Temporary workaround to pass pixel_clk_rate
-	 * from the HDMI bridge driver until phy_configure_opts_hdmi
-	 * becomes available in the PHY API.
-	 */
-	unsigned int rate = bus_width & 0xfffffff;
+	if (mode != PHY_MODE_DP) {
+		if (!hdptx->hdmi_cfg.tmds_char_rate) {
+			/*
+			 * FIXME: Temporary workaround to setup TMDS char rate
+			 * from the RK DW HDMI QP bridge driver.
+			 * Will be removed as soon the switch to the HDMI PHY
+			 * configuration API has been completed on both ends.
+			 */
+			hdptx->hdmi_cfg.tmds_char_rate = phy_get_bus_width(hdptx->phy) & 0xfffffff;
+			hdptx->hdmi_cfg.tmds_char_rate *= 100;
+		}
 
-	dev_dbg(hdptx->dev, "%s bus_width=%x rate=%u\n",
-		__func__, bus_width, rate);
+		dev_dbg(hdptx->dev, "%s rate=%llu bpc=%u\n", __func__,
+			hdptx->hdmi_cfg.tmds_char_rate, hdptx->hdmi_cfg.bpc);
+	}
 
-	ret = rk_hdptx_phy_consumer_get(hdptx, rate);
+	ret = rk_hdptx_phy_consumer_get(hdptx);
 	if (ret)
 		return ret;
 
@@ -1490,7 +1467,7 @@ static int rk_hdptx_phy_power_on(struct phy *phy)
 		regmap_write(hdptx->grf, GRF_HDPTX_CON0,
 			     HDPTX_MODE_SEL << 16 | FIELD_PREP(HDPTX_MODE_SEL, 0x0));
 
-		ret = rk_hdptx_ropll_tmds_mode_config(hdptx, rate);
+		ret = rk_hdptx_ropll_tmds_mode_config(hdptx);
 		if (ret)
 			rk_hdptx_phy_consumer_put(hdptx, true);
 	}
@@ -1505,8 +1482,40 @@ static int rk_hdptx_phy_power_off(struct phy *phy)
 	return rk_hdptx_phy_consumer_put(hdptx, false);
 }
 
-static int rk_hdptx_phy_verify_config(struct rk_hdptx_phy *hdptx,
-				      struct phy_configure_opts_dp *dp)
+static int rk_hdptx_phy_verify_hdmi_config(struct rk_hdptx_phy *hdptx,
+					   struct phy_configure_opts_hdmi *hdmi)
+{
+	int i;
+
+	if (!hdmi->tmds_char_rate || hdmi->tmds_char_rate > HDMI20_MAX_RATE)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(ropll_tmds_cfg); i++)
+		if (hdmi->tmds_char_rate == ropll_tmds_cfg[i].rate)
+			break;
+
+	if (i == ARRAY_SIZE(ropll_tmds_cfg) &&
+	    !rk_hdptx_phy_clk_pll_calc(hdmi->tmds_char_rate, NULL))
+		return -EINVAL;
+
+	if (!hdmi->bpc)
+		hdmi->bpc = 8;
+
+	switch (hdmi->bpc) {
+	case 8:
+	case 10:
+	case 12:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rk_hdptx_phy_verify_dp_config(struct rk_hdptx_phy *hdptx,
+					 struct phy_configure_opts_dp *dp)
 {
 	int i;
 
@@ -1766,12 +1775,23 @@ static int rk_hdptx_phy_configure(struct phy *phy, union phy_configure_opts *opt
 	enum phy_mode mode = phy_get_mode(phy);
 	int ret;
 
-	if (mode != PHY_MODE_DP)
-		return 0;
+	if (mode != PHY_MODE_DP) {
+		ret = rk_hdptx_phy_verify_hdmi_config(hdptx, &opts->hdmi);
+		if (ret) {
+			dev_err(hdptx->dev, "invalid hdmi params for phy configure\n");
+		} else {
+			hdptx->hdmi_cfg = opts->hdmi;
+			hdptx->restrict_rate_change = true;
+		}
 
-	ret = rk_hdptx_phy_verify_config(hdptx, &opts->dp);
+		dev_dbg(hdptx->dev, "%s rate=%llu bpc=%u\n", __func__,
+			hdptx->hdmi_cfg.tmds_char_rate, hdptx->hdmi_cfg.bpc);
+		return ret;
+	}
+
+	ret = rk_hdptx_phy_verify_dp_config(hdptx, &opts->dp);
 	if (ret) {
-		dev_err(hdptx->dev, "invalid params for phy configure\n");
+		dev_err(hdptx->dev, "invalid dp params for phy configure\n");
 		return ret;
 	}
 
@@ -1803,10 +1823,22 @@ static int rk_hdptx_phy_configure(struct phy *phy, union phy_configure_opts *opt
 	return 0;
 }
 
+static int rk_hdptx_phy_validate(struct phy *phy, enum phy_mode mode,
+				 int submode, union phy_configure_opts *opts)
+{
+	struct rk_hdptx_phy *hdptx = phy_get_drvdata(phy);
+
+	if (mode != PHY_MODE_DP)
+		return rk_hdptx_phy_verify_hdmi_config(hdptx, &opts->hdmi);
+
+	return rk_hdptx_phy_verify_dp_config(hdptx, &opts->dp);
+}
+
 static const struct phy_ops rk_hdptx_phy_ops = {
 	.power_on  = rk_hdptx_phy_power_on,
 	.power_off = rk_hdptx_phy_power_off,
 	.configure = rk_hdptx_phy_configure,
+	.validate  = rk_hdptx_phy_validate,
 	.owner	   = THIS_MODULE,
 };
 
@@ -1819,7 +1851,7 @@ static int rk_hdptx_phy_clk_prepare(struct clk_hw *hw)
 {
 	struct rk_hdptx_phy *hdptx = to_rk_hdptx_phy(hw);
 
-	return rk_hdptx_phy_consumer_get(hdptx, hdptx->rate / 100);
+	return rk_hdptx_phy_consumer_get(hdptx);
 }
 
 static void rk_hdptx_phy_clk_unprepare(struct clk_hw *hw)
@@ -1834,27 +1866,37 @@ static unsigned long rk_hdptx_phy_clk_recalc_rate(struct clk_hw *hw,
 {
 	struct rk_hdptx_phy *hdptx = to_rk_hdptx_phy(hw);
 
-	return hdptx->rate;
+	return hdptx->hw_rate;
 }
 
 static long rk_hdptx_phy_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 					unsigned long *parent_rate)
 {
-	u32 bit_rate = rate / 100;
-	int i;
+	struct rk_hdptx_phy *hdptx = to_rk_hdptx_phy(hw);
 
-	if (rate > HDMI20_MAX_RATE)
-		return rate;
+	/*
+	 * FIXME: Temporarily allow altering TMDS char rate via CCF.
+	 * To be dropped as soon as the RK DW HDMI QP bridge driver
+	 * switches to make use of phy_configure().
+	 */
+	if (!hdptx->restrict_rate_change && rate != hdptx->hdmi_cfg.tmds_char_rate) {
+		struct phy_configure_opts_hdmi hdmi = {
+			.tmds_char_rate = rate,
+		};
+		int ret = rk_hdptx_phy_verify_hdmi_config(hdptx, &hdmi);
 
-	for (i = 0; i < ARRAY_SIZE(ropll_tmds_cfg); i++)
-		if (bit_rate == ropll_tmds_cfg[i].bit_rate)
-			break;
+		if (ret)
+			return ret;
 
-	if (i == ARRAY_SIZE(ropll_tmds_cfg) &&
-	    !rk_hdptx_phy_clk_pll_calc(bit_rate, NULL))
-		return -EINVAL;
+		hdptx->hdmi_cfg = hdmi;
+	}
 
-	return rate;
+	/*
+	 * The TMDS char rate shall be adjusted via phy_configure() only,
+	 * hence ensure rk_hdptx_phy_clk_set_rate() won't be invoked with
+	 * a different rate argument.
+	 */
+	return hdptx->hdmi_cfg.tmds_char_rate;
 }
 
 static int rk_hdptx_phy_clk_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -1862,7 +1904,21 @@ static int rk_hdptx_phy_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 {
 	struct rk_hdptx_phy *hdptx = to_rk_hdptx_phy(hw);
 
-	return rk_hdptx_ropll_tmds_cmn_config(hdptx, rate / 100);
+	/* Revert any unlikely TMDS char rate change since round_rate() */
+	if (hdptx->hdmi_cfg.tmds_char_rate != rate) {
+		dev_warn(hdptx->dev, "Reverting unexpected rate change from %lu to %llu\n",
+			 rate, hdptx->hdmi_cfg.tmds_char_rate);
+		hdptx->hdmi_cfg.tmds_char_rate = rate;
+	}
+
+	/*
+	 * The TMDS char rate would be normally programmed in HW during
+	 * phy_ops.power_on() or clk_ops.prepare() callbacks, but it might
+	 * happen that the former gets fired too late, i.e. after this call,
+	 * while the latter being executed only once, i.e. when clock remains
+	 * in the prepared state during rate changes.
+	 */
+	return rk_hdptx_ropll_tmds_cmn_config(hdptx);
 }
 
 static const struct clk_ops hdptx_phy_clk_ops = {
@@ -1925,6 +1981,7 @@ static int rk_hdptx_phy_runtime_resume(struct device *dev)
 
 static int rk_hdptx_phy_probe(struct platform_device *pdev)
 {
+	const struct rk_hdptx_phy_cfg *cfgs;
 	struct phy_provider *phy_provider;
 	struct device *dev = &pdev->dev;
 	struct rk_hdptx_phy *hdptx;
@@ -1937,20 +1994,21 @@ static int rk_hdptx_phy_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	hdptx->dev = dev;
+	hdptx->hdmi_cfg.bpc = 8;
 
 	regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(regs))
 		return dev_err_probe(dev, PTR_ERR(regs),
 				     "Failed to ioremap resource\n");
 
-	hdptx->cfgs = device_get_match_data(dev);
-	if (!hdptx->cfgs)
+	cfgs = device_get_match_data(dev);
+	if (!cfgs)
 		return dev_err_probe(dev, -EINVAL, "missing match data\n");
 
 	/* find the phy-id from the io address */
 	hdptx->phy_id = -ENODEV;
-	for (id = 0; id < hdptx->cfgs->num_phys; id++) {
-		if (res->start == hdptx->cfgs->phy_ids[id]) {
+	for (id = 0; id < cfgs->num_phys; id++) {
+		if (res->start == cfgs->phy_ids[id]) {
 			hdptx->phy_id = id;
 			break;
 		}
diff --git a/drivers/phy/samsung/Kconfig b/drivers/phy/samsung/Kconfig
index 6566100441d6..b7ab402909a8 100644
--- a/drivers/phy/samsung/Kconfig
+++ b/drivers/phy/samsung/Kconfig
@@ -85,7 +85,7 @@ config PHY_EXYNOS5_USBDRD
 	depends on USB_DWC3_EXYNOS
 	select GENERIC_PHY
 	select MFD_SYSCON
-	default y
+	default ARCH_EXYNOS
 	help
 	  Enable USB DRD PHY support for Exynos 5 SoC series.
 	  This driver provides PHY interface for USB 3.0 DRD controller
diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c
index 817fddee0392..917a76d584f0 100644
--- a/drivers/phy/samsung/phy-exynos5-usbdrd.c
+++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c
@@ -36,14 +36,40 @@
 #define EXYNOS5_FSEL_26MHZ		0x6
 #define EXYNOS5_FSEL_50MHZ		0x7
 
+/* USB 3.2 DRD 4nm PHY link controller registers */
+#define EXYNOS2200_DRD_CLKRST			0x0c
+#define EXYNOS2200_CLKRST_LINK_PCLK_SEL		BIT(1)
+
+#define EXYNOS2200_DRD_UTMI			0x10
+#define EXYNOS2200_UTMI_FORCE_VBUSVALID		BIT(1)
+#define EXYNOS2200_UTMI_FORCE_BVALID		BIT(0)
+
+#define EXYNOS2200_DRD_HSP_MISC			0x114
+#define HSP_MISC_SET_REQ_IN2			BIT(4)
+#define HSP_MISC_RES_TUNE			GENMASK(1, 0)
+#define RES_TUNE_PHY1_PHY2			0x1
+#define RES_TUNE_PHY1				0x2
+#define RES_TUNE_PHY2				0x3
+
 /* Exynos5: USB 3.0 DRD PHY registers */
 #define EXYNOS5_DRD_LINKSYSTEM			0x04
 #define LINKSYSTEM_XHCI_VERSION_CONTROL		BIT(27)
-#define LINKSYSTEM_FLADJ_MASK			(0x3f << 1)
-#define LINKSYSTEM_FLADJ(_x)			((_x) << 1)
+#define LINKSYSTEM_FORCE_VBUSVALID		BIT(8)
+#define LINKSYSTEM_FORCE_BVALID			BIT(7)
+#define LINKSYSTEM_FLADJ			GENMASK(6, 1)
 
 #define EXYNOS5_DRD_PHYUTMI			0x08
+#define PHYUTMI_UTMI_SUSPEND_COM_N		BIT(12)
+#define PHYUTMI_UTMI_L1_SUSPEND_COM_N		BIT(11)
+#define PHYUTMI_VBUSVLDEXTSEL			BIT(10)
+#define PHYUTMI_VBUSVLDEXT			BIT(9)
+#define PHYUTMI_TXBITSTUFFENH			BIT(8)
+#define PHYUTMI_TXBITSTUFFEN			BIT(7)
 #define PHYUTMI_OTGDISABLE			BIT(6)
+#define PHYUTMI_IDPULLUP			BIT(5)
+#define PHYUTMI_DRVVBUS				BIT(4)
+#define PHYUTMI_DPPULLDOWN			BIT(3)
+#define PHYUTMI_DMPULLDOWN			BIT(2)
 #define PHYUTMI_FORCESUSPEND			BIT(1)
 #define PHYUTMI_FORCESLEEP			BIT(0)
 
@@ -51,30 +77,27 @@
 
 #define EXYNOS5_DRD_PHYCLKRST			0x10
 #define PHYCLKRST_EN_UTMISUSPEND		BIT(31)
-#define PHYCLKRST_SSC_REFCLKSEL_MASK		(0xff << 23)
-#define PHYCLKRST_SSC_REFCLKSEL(_x)		((_x) << 23)
-#define PHYCLKRST_SSC_RANGE_MASK		(0x03 << 21)
-#define PHYCLKRST_SSC_RANGE(_x)			((_x) << 21)
+#define PHYCLKRST_SSC_REFCLKSEL			GENMASK(30, 23)
+#define PHYCLKRST_SSC_RANGE			GENMASK(22, 21)
 #define PHYCLKRST_SSC_EN			BIT(20)
 #define PHYCLKRST_REF_SSP_EN			BIT(19)
 #define PHYCLKRST_REF_CLKDIV2			BIT(18)
-#define PHYCLKRST_MPLL_MULTIPLIER_MASK		(0x7f << 11)
-#define PHYCLKRST_MPLL_MULTIPLIER_100MHZ_REF	(0x19 << 11)
-#define PHYCLKRST_MPLL_MULTIPLIER_50M_REF	(0x32 << 11)
-#define PHYCLKRST_MPLL_MULTIPLIER_24MHZ_REF	(0x68 << 11)
-#define PHYCLKRST_MPLL_MULTIPLIER_20MHZ_REF	(0x7d << 11)
-#define PHYCLKRST_MPLL_MULTIPLIER_19200KHZ_REF	(0x02 << 11)
-#define PHYCLKRST_FSEL_PIPE_MASK		(0x7 << 8)
-#define PHYCLKRST_FSEL_UTMI_MASK		(0x7 << 5)
-#define PHYCLKRST_FSEL(_x)			((_x) << 5)
-#define PHYCLKRST_FSEL_PAD_100MHZ		(0x27 << 5)
-#define PHYCLKRST_FSEL_PAD_24MHZ		(0x2a << 5)
-#define PHYCLKRST_FSEL_PAD_20MHZ		(0x31 << 5)
-#define PHYCLKRST_FSEL_PAD_19_2MHZ		(0x38 << 5)
+#define PHYCLKRST_MPLL_MULTIPLIER		GENMASK(17, 11)
+#define PHYCLKRST_MPLL_MULTIPLIER_100MHZ_REF	0x19
+#define PHYCLKRST_MPLL_MULTIPLIER_50M_REF	0x32
+#define PHYCLKRST_MPLL_MULTIPLIER_24MHZ_REF	0x68
+#define PHYCLKRST_MPLL_MULTIPLIER_20MHZ_REF	0x7d
+#define PHYCLKRST_MPLL_MULTIPLIER_19200KHZ_REF	0x02
+#define PHYCLKRST_FSEL_PIPE			GENMASK(10, 8)
+#define PHYCLKRST_FSEL_UTMI			GENMASK(7, 5)
+#define PHYCLKRST_FSEL_PAD_100MHZ		0x27
+#define PHYCLKRST_FSEL_PAD_24MHZ		0x2a
+#define PHYCLKRST_FSEL_PAD_20MHZ		0x31
+#define PHYCLKRST_FSEL_PAD_19_2MHZ		0x38
 #define PHYCLKRST_RETENABLEN			BIT(4)
-#define PHYCLKRST_REFCLKSEL_MASK		(0x03 << 2)
-#define PHYCLKRST_REFCLKSEL_PAD_REFCLK		(0x2 << 2)
-#define PHYCLKRST_REFCLKSEL_EXT_REFCLK		(0x3 << 2)
+#define PHYCLKRST_REFCLKSEL			GENMASK(3, 2)
+#define PHYCLKRST_REFCLKSEL_PAD_REFCLK		0x2
+#define PHYCLKRST_REFCLKSEL_EXT_REFCLK		0x3
 #define PHYCLKRST_PORTRESET			BIT(1)
 #define PHYCLKRST_COMMONONN			BIT(0)
 
@@ -83,22 +106,32 @@
 #define PHYREG0_SSC_RANGE			BIT(20)
 #define PHYREG0_CR_WRITE			BIT(19)
 #define PHYREG0_CR_READ				BIT(18)
-#define PHYREG0_CR_DATA_IN(_x)			((_x) << 2)
+#define PHYREG0_CR_DATA_IN			GENMASK(17, 2)
 #define PHYREG0_CR_CAP_DATA			BIT(1)
 #define PHYREG0_CR_CAP_ADDR			BIT(0)
 
 #define EXYNOS5_DRD_PHYREG1			0x18
-#define PHYREG1_CR_DATA_OUT(_x)			((_x) << 1)
+#define PHYREG0_CR_DATA_OUT			GENMASK(16, 1)
 #define PHYREG1_CR_ACK				BIT(0)
 
 #define EXYNOS5_DRD_PHYPARAM0			0x1c
 #define PHYPARAM0_REF_USE_PAD			BIT(31)
-#define PHYPARAM0_REF_LOSLEVEL_MASK		(0x1f << 26)
-#define PHYPARAM0_REF_LOSLEVEL			(0x9 << 26)
+#define PHYPARAM0_REF_LOSLEVEL			GENMASK(30, 26)
+#define PHYPARAM0_REF_LOSLEVEL_VAL		0x9
+#define PHYPARAM0_TXVREFTUNE			GENMASK(25, 22)
+#define PHYPARAM0_TXRISETUNE			GENMASK(21, 20)
+#define PHYPARAM0_TXRESTUNE			GENMASK(19, 18)
+#define PHYPARAM0_TXPREEMPPULSETUNE		BIT(17)
+#define PHYPARAM0_TXPREEMPAMPTUNE		GENMASK(16, 15)
+#define PHYPARAM0_TXHSXVTUNE			GENMASK(14, 13)
+#define PHYPARAM0_TXFSLSTUNE			GENMASK(12, 9)
+#define PHYPARAM0_SQRXTUNE			GENMASK(8, 6)
+#define PHYPARAM0_OTGTUNE			GENMASK(5, 3)
+#define PHYPARAM0_COMPDISTUNE			GENMASK(2, 0)
 
 #define EXYNOS5_DRD_PHYPARAM1			0x20
-#define PHYPARAM1_PCS_TXDEEMPH_MASK		(0x1f << 0)
-#define PHYPARAM1_PCS_TXDEEMPH			(0x1c)
+#define PHYPARAM1_PCS_TXDEEMPH			GENMASK(4, 0)
+#define PHYPARAM1_PCS_TXDEEMPH_VAL		0x1c
 
 #define EXYNOS5_DRD_PHYTERM			0x24
 
@@ -114,6 +147,12 @@
 #define EXYNOS5_DRD_PHYRESUME			0x34
 
 #define EXYNOS5_DRD_LINKPORT			0x44
+#define LINKPORT_HOST_U3_PORT_DISABLE		BIT(8)
+#define LINKPORT_HOST_U2_PORT_DISABLE		BIT(7)
+#define LINKPORT_HOST_PORT_OVCR_U3		BIT(5)
+#define LINKPORT_HOST_PORT_OVCR_U2		BIT(4)
+#define LINKPORT_HOST_PORT_OVCR_U3_SEL		BIT(3)
+#define LINKPORT_HOST_PORT_OVCR_U2_SEL		BIT(2)
 
 /* USB 3.0 DRD PHY SS Function Control Reg; accessed by CR_PORT */
 #define EXYNOS5_DRD_PHYSS_LOSLEVEL_OVRD_IN		(0x15)
@@ -134,13 +173,31 @@
 #define LANE0_TX_DEBUG_RXDET_MEAS_TIME_62M5		(0x20 << 4)
 #define LANE0_TX_DEBUG_RXDET_MEAS_TIME_96M_100M		(0x40 << 4)
 
+/* Exynos7870: USB DRD PHY registers */
+#define EXYNOS7870_DRD_PHYPCSVAL		0x3C
+#define PHYPCSVAL_PCS_RX_LOS_MASK		GENMASK(9, 0)
+
+#define EXYNOS7870_DRD_PHYPARAM2		0x50
+#define PHYPARAM2_TX_VBOOST_LVL		        GENMASK(6, 4)
+#define PHYPARAM2_LOS_BIAS			GENMASK(2, 0)
+
+#define EXYNOS7870_DRD_HSPHYCTRL		0x54
+#define HSPHYCTRL_PHYSWRSTALL			BIT(31)
+#define HSPHYCTRL_SIDDQ				BIT(6)
+#define HSPHYCTRL_PHYSWRST			BIT(0)
+
+#define EXYNOS7870_DRD_HSPHYPLLTUNE		0x70
+#define HSPHYPLLTUNE_PLL_B_TUNE			BIT(6)
+#define HSPHYPLLTUNE_PLL_I_TUNE			GENMASK(5, 4)
+#define HSPHYPLLTUNE_PLL_P_TUNE			GENMASK(3, 0)
+
 /* Exynos850: USB DRD PHY registers */
 #define EXYNOS850_DRD_LINKCTRL			0x04
 #define LINKCTRL_FORCE_RXELECIDLE		BIT(18)
 #define LINKCTRL_FORCE_PHYSTATUS		BIT(17)
 #define LINKCTRL_FORCE_PIPE_EN			BIT(16)
 #define LINKCTRL_FORCE_QACT			BIT(8)
-#define LINKCTRL_BUS_FILTER_BYPASS(_x)		((_x) << 4)
+#define LINKCTRL_BUS_FILTER_BYPASS		GENMASK(7, 4)
 
 #define EXYNOS850_DRD_LINKPORT			0x08
 #define LINKPORT_HOST_NUM_U3			GENMASK(19, 16)
@@ -389,6 +446,7 @@ struct exynos5_usbdrd_phy_drvdata {
  * @clks: clocks for register access
  * @core_clks: core clocks for phy (ref, pipe3, utmi+, ITP, etc. as required)
  * @drv_data: pointer to SoC level driver data structure
+ * @hs_phy: pointer to non-Samsung IP high-speed phy controller
  * @phy_mutex: mutex protecting phy_init/exit & TCPC callbacks
  * @phys: array for 'EXYNOS5_DRDPHYS_NUM' number of PHY
  *	    instances each with its 'phy' and 'phy_cfg'.
@@ -406,6 +464,7 @@ struct exynos5_usbdrd_phy {
 	struct clk_bulk_data *clks;
 	struct clk_bulk_data *core_clks;
 	const struct exynos5_usbdrd_phy_drvdata *drv_data;
+	struct phy *hs_phy;
 	struct mutex phy_mutex;
 	struct phy_usb_instance {
 		struct phy *phy;
@@ -497,29 +556,33 @@ exynos5_usbdrd_pipe3_set_refclk(struct phy_usb_instance *inst)
 	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_PHYCLKRST);
 
 	/* Use EXTREFCLK as ref clock */
-	reg &= ~PHYCLKRST_REFCLKSEL_MASK;
-	reg |=	PHYCLKRST_REFCLKSEL_EXT_REFCLK;
+	reg &= ~PHYCLKRST_REFCLKSEL;
+	reg |= FIELD_PREP(PHYCLKRST_REFCLKSEL, PHYCLKRST_REFCLKSEL_EXT_REFCLK);
 
 	/* FSEL settings corresponding to reference clock */
-	reg &= ~(PHYCLKRST_FSEL_PIPE_MASK |
-		 PHYCLKRST_MPLL_MULTIPLIER_MASK |
-		 PHYCLKRST_SSC_REFCLKSEL_MASK);
+	reg &= ~(PHYCLKRST_FSEL_PIPE |
+		 PHYCLKRST_MPLL_MULTIPLIER |
+		 PHYCLKRST_SSC_REFCLKSEL);
 	switch (phy_drd->extrefclk) {
 	case EXYNOS5_FSEL_50MHZ:
-		reg |= (PHYCLKRST_MPLL_MULTIPLIER_50M_REF |
-			PHYCLKRST_SSC_REFCLKSEL(0x00));
+		reg |= (FIELD_PREP(PHYCLKRST_SSC_REFCLKSEL, 0x00) |
+			FIELD_PREP(PHYCLKRST_MPLL_MULTIPLIER,
+				   PHYCLKRST_MPLL_MULTIPLIER_50M_REF));
 		break;
 	case EXYNOS5_FSEL_24MHZ:
-		reg |= (PHYCLKRST_MPLL_MULTIPLIER_24MHZ_REF |
-			PHYCLKRST_SSC_REFCLKSEL(0x88));
+		reg |= (FIELD_PREP(PHYCLKRST_SSC_REFCLKSEL, 0x88) |
+			FIELD_PREP(PHYCLKRST_MPLL_MULTIPLIER,
+				   PHYCLKRST_MPLL_MULTIPLIER_24MHZ_REF));
 		break;
 	case EXYNOS5_FSEL_20MHZ:
-		reg |= (PHYCLKRST_MPLL_MULTIPLIER_20MHZ_REF |
-			PHYCLKRST_SSC_REFCLKSEL(0x00));
+		reg |= (FIELD_PREP(PHYCLKRST_SSC_REFCLKSEL, 0x00) |
+			FIELD_PREP(PHYCLKRST_MPLL_MULTIPLIER,
+				   PHYCLKRST_MPLL_MULTIPLIER_20MHZ_REF));
 		break;
 	case EXYNOS5_FSEL_19MHZ2:
-		reg |= (PHYCLKRST_MPLL_MULTIPLIER_19200KHZ_REF |
-			PHYCLKRST_SSC_REFCLKSEL(0x88));
+		reg |= (FIELD_PREP(PHYCLKRST_SSC_REFCLKSEL, 0x88) |
+			FIELD_PREP(PHYCLKRST_MPLL_MULTIPLIER,
+				   PHYCLKRST_MPLL_MULTIPLIER_19200KHZ_REF));
 		break;
 	default:
 		dev_dbg(phy_drd->dev, "unsupported ref clk\n");
@@ -542,13 +605,13 @@ exynos5_usbdrd_utmi_set_refclk(struct phy_usb_instance *inst)
 	/* restore any previous reference clock settings */
 	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_PHYCLKRST);
 
-	reg &= ~PHYCLKRST_REFCLKSEL_MASK;
-	reg |=	PHYCLKRST_REFCLKSEL_EXT_REFCLK;
+	reg &= ~PHYCLKRST_REFCLKSEL;
+	reg |= FIELD_PREP(PHYCLKRST_REFCLKSEL, PHYCLKRST_REFCLKSEL_EXT_REFCLK);
 
-	reg &= ~(PHYCLKRST_FSEL_UTMI_MASK |
-		 PHYCLKRST_MPLL_MULTIPLIER_MASK |
-		 PHYCLKRST_SSC_REFCLKSEL_MASK);
-	reg |= PHYCLKRST_FSEL(phy_drd->extrefclk);
+	reg &= ~(PHYCLKRST_FSEL_UTMI |
+		 PHYCLKRST_MPLL_MULTIPLIER |
+		 PHYCLKRST_SSC_REFCLKSEL);
+	reg |= FIELD_PREP(PHYCLKRST_FSEL_UTMI, phy_drd->extrefclk);
 
 	return reg;
 }
@@ -598,8 +661,8 @@ static void exynos5_usbdrd_pipe3_init(struct exynos5_usbdrd_phy *phy_drd)
 
 	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_PHYPARAM1);
 	/* Set Tx De-Emphasis level */
-	reg &= ~PHYPARAM1_PCS_TXDEEMPH_MASK;
-	reg |=	PHYPARAM1_PCS_TXDEEMPH;
+	reg &= ~PHYPARAM1_PCS_TXDEEMPH;
+	reg |= FIELD_PREP(PHYPARAM1_PCS_TXDEEMPH, PHYPARAM1_PCS_TXDEEMPH_VAL);
 	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_PHYPARAM1);
 
 	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_PHYTEST);
@@ -749,14 +812,14 @@ static void exynos5_usbdrd_utmi_init(struct exynos5_usbdrd_phy *phy_drd)
 
 	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_PHYPARAM0);
 	/* Set Loss-of-Signal Detector sensitivity */
-	reg &= ~PHYPARAM0_REF_LOSLEVEL_MASK;
-	reg |=	PHYPARAM0_REF_LOSLEVEL;
+	reg &= ~PHYPARAM0_REF_LOSLEVEL;
+	reg |= FIELD_PREP(PHYPARAM0_REF_LOSLEVEL, PHYPARAM0_REF_LOSLEVEL_VAL);
 	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_PHYPARAM0);
 
 	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_PHYPARAM1);
 	/* Set Tx De-Emphasis level */
-	reg &= ~PHYPARAM1_PCS_TXDEEMPH_MASK;
-	reg |=	PHYPARAM1_PCS_TXDEEMPH;
+	reg &= ~PHYPARAM1_PCS_TXDEEMPH;
+	reg |= FIELD_PREP(PHYPARAM1_PCS_TXDEEMPH, PHYPARAM1_PCS_TXDEEMPH_VAL);
 	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_PHYPARAM1);
 
 	/* UTMI Power Control */
@@ -787,7 +850,7 @@ static int exynos5_usbdrd_phy_init(struct phy *phy)
 	 * See xHCI 1.0 spec, 5.2.4
 	 */
 	reg =	LINKSYSTEM_XHCI_VERSION_CONTROL |
-		LINKSYSTEM_FLADJ(0x20);
+		FIELD_PREP(LINKSYSTEM_FLADJ, 0x20);
 	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_LINKSYSTEM);
 
 	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_PHYPARAM0);
@@ -946,26 +1009,24 @@ static int crport_handshake(struct exynos5_usbdrd_phy *phy_drd,
 static int crport_ctrl_write(struct exynos5_usbdrd_phy *phy_drd,
 			     u32 addr, u32 data)
 {
+	u32 val;
 	int ret;
 
 	/* Write Address */
-	writel(PHYREG0_CR_DATA_IN(addr),
-	       phy_drd->reg_phy + EXYNOS5_DRD_PHYREG0);
-	ret = crport_handshake(phy_drd, PHYREG0_CR_DATA_IN(addr),
-			       PHYREG0_CR_CAP_ADDR);
+	val = FIELD_PREP(PHYREG0_CR_DATA_IN, addr);
+	writel(val, phy_drd->reg_phy + EXYNOS5_DRD_PHYREG0);
+	ret = crport_handshake(phy_drd, val, PHYREG0_CR_CAP_ADDR);
 	if (ret)
 		return ret;
 
 	/* Write Data */
-	writel(PHYREG0_CR_DATA_IN(data),
-	       phy_drd->reg_phy + EXYNOS5_DRD_PHYREG0);
-	ret = crport_handshake(phy_drd, PHYREG0_CR_DATA_IN(data),
-			       PHYREG0_CR_CAP_DATA);
+	val = FIELD_PREP(PHYREG0_CR_DATA_IN, data);
+	writel(val, phy_drd->reg_phy + EXYNOS5_DRD_PHYREG0);
+	ret = crport_handshake(phy_drd, val, PHYREG0_CR_CAP_DATA);
 	if (ret)
 		return ret;
 
-	ret = crport_handshake(phy_drd, PHYREG0_CR_DATA_IN(data),
-			       PHYREG0_CR_WRITE);
+	ret = crport_handshake(phy_drd, val, PHYREG0_CR_WRITE);
 
 	return ret;
 }
@@ -1075,6 +1136,315 @@ static const struct phy_ops exynos5_usbdrd_phy_ops = {
 	.owner		= THIS_MODULE,
 };
 
+static void exynos7870_usbdrd_phy_isol(struct phy_usb_instance *inst,
+				       bool isolate)
+{
+	unsigned int val;
+
+	if (!inst->reg_pmu)
+		return;
+
+	val = isolate ? 0 : EXYNOS7870_USB2PHY_ENABLE;
+
+	regmap_update_bits(inst->reg_pmu, inst->pmu_offset,
+			   EXYNOS7870_USB2PHY_ENABLE, val);
+}
+
+static void exynos7870_usbdrd_utmi_init(struct exynos5_usbdrd_phy *phy_drd)
+{
+	u32 reg;
+
+	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_PHYCLKRST);
+	/* Use PADREFCLK as ref clock */
+	reg &= ~PHYCLKRST_REFCLKSEL;
+	reg |= FIELD_PREP(PHYCLKRST_REFCLKSEL, PHYCLKRST_REFCLKSEL_PAD_REFCLK);
+	/* Select ref clock rate */
+	reg &= ~PHYCLKRST_FSEL_UTMI;
+	reg &= ~PHYCLKRST_FSEL_PIPE;
+	reg |= FIELD_PREP(PHYCLKRST_FSEL_UTMI, phy_drd->extrefclk);
+	/* Enable suspend and reset the port */
+	reg |= PHYCLKRST_EN_UTMISUSPEND;
+	reg |= PHYCLKRST_COMMONONN;
+	reg |= PHYCLKRST_PORTRESET;
+	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_PHYCLKRST);
+	udelay(10);
+
+	/* Clear the port reset bit */
+	reg &= ~PHYCLKRST_PORTRESET;
+	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_PHYCLKRST);
+
+	/* Change PHY PLL tune value */
+	reg = readl(phy_drd->reg_phy + EXYNOS7870_DRD_HSPHYPLLTUNE);
+	if (phy_drd->extrefclk == EXYNOS5_FSEL_24MHZ)
+		reg |= HSPHYPLLTUNE_PLL_B_TUNE;
+	else
+		reg &= ~HSPHYPLLTUNE_PLL_B_TUNE;
+	reg &= ~HSPHYPLLTUNE_PLL_P_TUNE;
+	reg |= FIELD_PREP(HSPHYPLLTUNE_PLL_P_TUNE, 14);
+	writel(reg, phy_drd->reg_phy + EXYNOS7870_DRD_HSPHYPLLTUNE);
+
+	/* High-Speed PHY control */
+	reg = readl(phy_drd->reg_phy + EXYNOS7870_DRD_HSPHYCTRL);
+	reg &= ~HSPHYCTRL_SIDDQ;
+	reg &= ~HSPHYCTRL_PHYSWRST;
+	reg &= ~HSPHYCTRL_PHYSWRSTALL;
+	writel(reg, phy_drd->reg_phy + EXYNOS7870_DRD_HSPHYCTRL);
+	udelay(500);
+
+	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_LINKSYSTEM);
+	/*
+	 * Setting the Frame length Adj value[6:1] to default 0x20
+	 * See xHCI 1.0 spec, 5.2.4
+	 */
+	reg |= LINKSYSTEM_XHCI_VERSION_CONTROL;
+	reg &= ~LINKSYSTEM_FLADJ;
+	reg |= FIELD_PREP(LINKSYSTEM_FLADJ, 0x20);
+	/* Set VBUSVALID signal as the VBUS pad is not used */
+	reg |= LINKSYSTEM_FORCE_BVALID;
+	reg |= LINKSYSTEM_FORCE_VBUSVALID;
+	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_LINKSYSTEM);
+
+	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_PHYUTMI);
+	/* Release force_sleep & force_suspend */
+	reg &= ~PHYUTMI_FORCESLEEP;
+	reg &= ~PHYUTMI_FORCESUSPEND;
+	/* DP/DM pull down control */
+	reg &= ~PHYUTMI_DMPULLDOWN;
+	reg &= ~PHYUTMI_DPPULLDOWN;
+	reg &= ~PHYUTMI_DRVVBUS;
+	/* Set DP-pull up as the VBUS pad is not used */
+	reg |= PHYUTMI_VBUSVLDEXTSEL;
+	reg |= PHYUTMI_VBUSVLDEXT;
+	/* Disable OTG block and VBUS valid comparator */
+	reg |= PHYUTMI_OTGDISABLE;
+	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_PHYUTMI);
+
+	/* Configure OVC IO usage */
+	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_LINKPORT);
+	reg |= LINKPORT_HOST_PORT_OVCR_U3_SEL | LINKPORT_HOST_PORT_OVCR_U2_SEL;
+	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_LINKPORT);
+
+	/* High-Speed PHY swrst */
+	reg = readl(phy_drd->reg_phy + EXYNOS7870_DRD_HSPHYCTRL);
+	reg |= HSPHYCTRL_PHYSWRST;
+	writel(reg, phy_drd->reg_phy + EXYNOS7870_DRD_HSPHYCTRL);
+	udelay(20);
+
+	/* Clear the PHY swrst bit */
+	reg = readl(phy_drd->reg_phy + EXYNOS7870_DRD_HSPHYCTRL);
+	reg &= ~HSPHYCTRL_PHYSWRST;
+	writel(reg, phy_drd->reg_phy + EXYNOS7870_DRD_HSPHYCTRL);
+
+	if (phy_drd->drv_data->phy_tunes)
+		exynos5_usbdrd_apply_phy_tunes(phy_drd,
+					       PTS_UTMI_POSTINIT);
+}
+
+static int exynos7870_usbdrd_phy_init(struct phy *phy)
+{
+	struct phy_usb_instance *inst = phy_get_drvdata(phy);
+	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
+	int ret;
+
+	ret = clk_bulk_prepare_enable(phy_drd->drv_data->n_clks, phy_drd->clks);
+	if (ret)
+		return ret;
+
+	/* UTMI or PIPE3 specific init */
+	inst->phy_cfg->phy_init(phy_drd);
+
+	clk_bulk_disable_unprepare(phy_drd->drv_data->n_clks, phy_drd->clks);
+
+	return 0;
+}
+
+static int exynos7870_usbdrd_phy_exit(struct phy *phy)
+{
+	int ret;
+	u32 reg;
+	struct phy_usb_instance *inst = phy_get_drvdata(phy);
+	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
+
+	ret = clk_bulk_prepare_enable(phy_drd->drv_data->n_clks, phy_drd->clks);
+	if (ret)
+		return ret;
+
+	/*
+	 * Disable the VBUS signal and the ID pull-up resistor.
+	 * Enable force-suspend and force-sleep modes.
+	 */
+	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_PHYUTMI);
+	reg &= ~(PHYUTMI_DRVVBUS | PHYUTMI_VBUSVLDEXT | PHYUTMI_VBUSVLDEXTSEL);
+	reg &= ~PHYUTMI_IDPULLUP;
+	reg |= PHYUTMI_FORCESUSPEND | PHYUTMI_FORCESLEEP;
+	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_PHYUTMI);
+
+	/* Power down PHY analog blocks */
+	reg = readl(phy_drd->reg_phy + EXYNOS7870_DRD_HSPHYCTRL);
+	reg |= HSPHYCTRL_SIDDQ;
+	writel(reg, phy_drd->reg_phy + EXYNOS7870_DRD_HSPHYCTRL);
+
+	/* Clear VBUSVALID signal as the VBUS pad is not used */
+	reg = readl(phy_drd->reg_phy + EXYNOS5_DRD_LINKSYSTEM);
+	reg &= ~(LINKSYSTEM_FORCE_BVALID | LINKSYSTEM_FORCE_VBUSVALID);
+	writel(reg, phy_drd->reg_phy + EXYNOS5_DRD_LINKSYSTEM);
+
+	clk_bulk_disable_unprepare(phy_drd->drv_data->n_clks, phy_drd->clks);
+
+	return 0;
+}
+
+static const struct phy_ops exynos7870_usbdrd_phy_ops = {
+	.init		= exynos7870_usbdrd_phy_init,
+	.exit		= exynos7870_usbdrd_phy_exit,
+	.power_on	= exynos5_usbdrd_phy_power_on,
+	.power_off	= exynos5_usbdrd_phy_power_off,
+	.owner		= THIS_MODULE,
+};
+
+static void exynos2200_usbdrd_utmi_init(struct exynos5_usbdrd_phy *phy_drd)
+{
+	/* Configure non-Samsung IP PHY, responsible for UTMI */
+	phy_init(phy_drd->hs_phy);
+}
+
+static void exynos2200_usbdrd_link_init(struct exynos5_usbdrd_phy *phy_drd)
+{
+	void __iomem *regs_base = phy_drd->reg_phy;
+	u32 reg;
+
+	/*
+	 * Disable HWACG (hardware auto clock gating control). This will force
+	 * QACTIVE signal in Q-Channel interface to HIGH level, to make sure
+	 * the PHY clock is not gated by the hardware.
+	 */
+	reg = readl(regs_base + EXYNOS850_DRD_LINKCTRL);
+	reg |= LINKCTRL_FORCE_QACT;
+	writel(reg, regs_base + EXYNOS850_DRD_LINKCTRL);
+
+	/* De-assert link reset */
+	reg = readl(regs_base + EXYNOS2200_DRD_CLKRST);
+	reg &= ~CLKRST_LINK_SW_RST;
+	writel(reg, regs_base + EXYNOS2200_DRD_CLKRST);
+
+	/* Set link VBUS Valid */
+	reg = readl(regs_base + EXYNOS2200_DRD_UTMI);
+	reg |= EXYNOS2200_UTMI_FORCE_BVALID | EXYNOS2200_UTMI_FORCE_VBUSVALID;
+	writel(reg, regs_base + EXYNOS2200_DRD_UTMI);
+}
+
+static void
+exynos2200_usbdrd_link_attach_detach_pipe3_phy(struct phy_usb_instance *inst)
+{
+	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
+	void __iomem *regs_base = phy_drd->reg_phy;
+	u32 reg;
+
+	reg = readl(regs_base + EXYNOS850_DRD_LINKCTRL);
+	if (inst->phy_cfg->id == EXYNOS5_DRDPHY_UTMI) {
+		/* force pipe3 signal for link */
+		reg &= ~LINKCTRL_FORCE_PHYSTATUS;
+		reg |= LINKCTRL_FORCE_PIPE_EN | LINKCTRL_FORCE_RXELECIDLE;
+	} else {
+		/* disable forcing pipe interface */
+		reg &= ~LINKCTRL_FORCE_PIPE_EN;
+	}
+	writel(reg, regs_base + EXYNOS850_DRD_LINKCTRL);
+
+	reg = readl(regs_base + EXYNOS2200_DRD_HSP_MISC);
+	if (inst->phy_cfg->id == EXYNOS5_DRDPHY_UTMI) {
+		/* calibrate only eUSB phy */
+		reg |= FIELD_PREP(HSP_MISC_RES_TUNE, RES_TUNE_PHY1);
+		reg |= HSP_MISC_SET_REQ_IN2;
+	} else {
+		/* calibrate for dual phy */
+		reg |= FIELD_PREP(HSP_MISC_RES_TUNE, RES_TUNE_PHY1_PHY2);
+		reg &= ~HSP_MISC_SET_REQ_IN2;
+	}
+	writel(reg, regs_base + EXYNOS2200_DRD_HSP_MISC);
+
+	reg = readl(regs_base + EXYNOS2200_DRD_CLKRST);
+	if (inst->phy_cfg->id == EXYNOS5_DRDPHY_UTMI)
+		reg &= ~EXYNOS2200_CLKRST_LINK_PCLK_SEL;
+	else
+		reg |= EXYNOS2200_CLKRST_LINK_PCLK_SEL;
+
+	writel(reg, regs_base + EXYNOS2200_DRD_CLKRST);
+}
+
+static int exynos2200_usbdrd_phy_init(struct phy *phy)
+{
+	struct phy_usb_instance *inst = phy_get_drvdata(phy);
+	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
+	int ret;
+
+	if (inst->phy_cfg->id == EXYNOS5_DRDPHY_UTMI) {
+		/* Power-on PHY ... */
+		ret = regulator_bulk_enable(phy_drd->drv_data->n_regulators,
+					    phy_drd->regulators);
+		if (ret) {
+			dev_err(phy_drd->dev,
+				"Failed to enable PHY regulator(s)\n");
+			return ret;
+		}
+	}
+	/*
+	 * ... and ungate power via PMU. Without this here, we get an SError
+	 * trying to access PMA registers
+	 */
+	exynos5_usbdrd_phy_isol(inst, false);
+
+	ret = clk_bulk_prepare_enable(phy_drd->drv_data->n_clks, phy_drd->clks);
+	if (ret)
+		return ret;
+
+	/* Set up the link controller */
+	exynos2200_usbdrd_link_init(phy_drd);
+
+	/* UTMI or PIPE3 link preparation */
+	exynos2200_usbdrd_link_attach_detach_pipe3_phy(inst);
+
+	/* UTMI or PIPE3 specific init */
+	inst->phy_cfg->phy_init(phy_drd);
+
+	clk_bulk_disable_unprepare(phy_drd->drv_data->n_clks, phy_drd->clks);
+
+	return 0;
+}
+
+static int exynos2200_usbdrd_phy_exit(struct phy *phy)
+{
+	struct phy_usb_instance *inst = phy_get_drvdata(phy);
+	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
+	void __iomem *regs_base = phy_drd->reg_phy;
+	u32 reg;
+	int ret;
+
+	ret = clk_bulk_prepare_enable(phy_drd->drv_data->n_clks, phy_drd->clks);
+	if (ret)
+		return ret;
+
+	reg = readl(regs_base + EXYNOS2200_DRD_UTMI);
+	reg &= ~(EXYNOS2200_UTMI_FORCE_BVALID | EXYNOS2200_UTMI_FORCE_VBUSVALID);
+	writel(reg, regs_base + EXYNOS2200_DRD_UTMI);
+
+	reg = readl(regs_base + EXYNOS2200_DRD_CLKRST);
+	reg |= CLKRST_LINK_SW_RST;
+	writel(reg, regs_base + EXYNOS2200_DRD_CLKRST);
+
+	clk_bulk_disable_unprepare(phy_drd->drv_data->n_clks, phy_drd->clks);
+
+	exynos5_usbdrd_phy_isol(inst, true);
+	return regulator_bulk_disable(phy_drd->drv_data->n_regulators,
+				      phy_drd->regulators);
+}
+
+static const struct phy_ops exynos2200_usbdrd_phy_ops = {
+	.init		= exynos2200_usbdrd_phy_init,
+	.exit		= exynos2200_usbdrd_phy_exit,
+	.owner		= THIS_MODULE,
+};
+
 static void
 exynos5_usbdrd_usb_v3p1_pipe_override(struct exynos5_usbdrd_phy *phy_drd)
 {
@@ -1134,7 +1504,7 @@ static void exynos850_usbdrd_utmi_init(struct exynos5_usbdrd_phy *phy_drd)
 
 	/* Set VBUS Valid and D+ pull-up control by VBUS pad usage */
 	reg = readl(regs_base + EXYNOS850_DRD_LINKCTRL);
-	reg |= LINKCTRL_BUS_FILTER_BYPASS(0xf);
+	reg |= FIELD_PREP(LINKCTRL_BUS_FILTER_BYPASS, 0xf);
 	writel(reg, regs_base + EXYNOS850_DRD_LINKCTRL);
 
 	if (!phy_drd->sw) {
@@ -1384,27 +1754,37 @@ static int exynos5_usbdrd_phy_clk_handle(struct exynos5_usbdrd_phy *phy_drd)
 		return dev_err_probe(phy_drd->dev, ret,
 				     "failed to get phy core clock(s)\n");
 
-	ref_clk = NULL;
-	for (int i = 0; i < phy_drd->drv_data->n_core_clks; ++i) {
-		if (!strcmp(phy_drd->core_clks[i].id, "ref")) {
-			ref_clk = phy_drd->core_clks[i].clk;
-			break;
+	if (phy_drd->drv_data->n_core_clks) {
+		ref_clk = NULL;
+		for (int i = 0; i < phy_drd->drv_data->n_core_clks; ++i) {
+			if (!strcmp(phy_drd->core_clks[i].id, "ref")) {
+				ref_clk = phy_drd->core_clks[i].clk;
+				break;
+			}
 		}
-	}
-	if (!ref_clk)
-		return dev_err_probe(phy_drd->dev, -ENODEV,
-				     "failed to find phy reference clock\n");
+		if (!ref_clk)
+			return dev_err_probe(phy_drd->dev, -ENODEV,
+					     "failed to find phy reference clock\n");
 
-	ref_rate = clk_get_rate(ref_clk);
-	ret = exynos5_rate_to_clk(ref_rate, &phy_drd->extrefclk);
-	if (ret)
-		return dev_err_probe(phy_drd->dev, ret,
-				     "clock rate (%ld) not supported\n",
-				     ref_rate);
+		ref_rate = clk_get_rate(ref_clk);
+		ret = exynos5_rate_to_clk(ref_rate, &phy_drd->extrefclk);
+		if (ret)
+			return dev_err_probe(phy_drd->dev, ret,
+					     "clock rate (%ld) not supported\n",
+					     ref_rate);
+	}
 
 	return 0;
 }
 
+static const struct exynos5_usbdrd_phy_config phy_cfg_exynos2200[] = {
+	{
+		.id		= EXYNOS5_DRDPHY_UTMI,
+		.phy_isol	= exynos5_usbdrd_phy_isol,
+		.phy_init	= exynos2200_usbdrd_utmi_init,
+	},
+};
+
 static int exynos5_usbdrd_orien_sw_set(struct typec_switch_dev *sw,
 				       enum typec_orientation orientation)
 {
@@ -1501,6 +1881,14 @@ static const struct exynos5_usbdrd_phy_config phy_cfg_exynos5[] = {
 	},
 };
 
+static const struct exynos5_usbdrd_phy_config phy_cfg_exynos7870[] = {
+	{
+		.id		= EXYNOS5_DRDPHY_UTMI,
+		.phy_isol	= exynos7870_usbdrd_phy_isol,
+		.phy_init	= exynos7870_usbdrd_utmi_init,
+	},
+};
+
 static const struct exynos5_usbdrd_phy_config phy_cfg_exynos850[] = {
 	{
 		.id		= EXYNOS5_DRDPHY_UTMI,
@@ -1509,6 +1897,30 @@ static const struct exynos5_usbdrd_phy_config phy_cfg_exynos850[] = {
 	},
 };
 
+static
+const struct exynos5_usbdrd_phy_tuning exynos7870_tunes_utmi_postinit[] = {
+	PHY_TUNING_ENTRY_PHY(EXYNOS5_DRD_PHYPARAM0,
+			     (PHYPARAM0_TXVREFTUNE | PHYPARAM0_TXRISETUNE |
+			      PHYPARAM0_TXRESTUNE | PHYPARAM0_TXPREEMPPULSETUNE |
+			      PHYPARAM0_TXPREEMPAMPTUNE | PHYPARAM0_TXHSXVTUNE |
+			      PHYPARAM0_TXFSLSTUNE | PHYPARAM0_SQRXTUNE |
+			      PHYPARAM0_OTGTUNE | PHYPARAM0_COMPDISTUNE),
+			     (FIELD_PREP_CONST(PHYPARAM0_TXVREFTUNE, 14) |
+			      FIELD_PREP_CONST(PHYPARAM0_TXRISETUNE, 1) |
+			      FIELD_PREP_CONST(PHYPARAM0_TXRESTUNE, 3) |
+			      FIELD_PREP_CONST(PHYPARAM0_TXPREEMPAMPTUNE, 0) |
+			      FIELD_PREP_CONST(PHYPARAM0_TXHSXVTUNE, 0) |
+			      FIELD_PREP_CONST(PHYPARAM0_TXFSLSTUNE, 3) |
+			      FIELD_PREP_CONST(PHYPARAM0_SQRXTUNE, 6) |
+			      FIELD_PREP_CONST(PHYPARAM0_OTGTUNE, 2) |
+			      FIELD_PREP_CONST(PHYPARAM0_COMPDISTUNE, 3))),
+	PHY_TUNING_ENTRY_LAST
+};
+
+static const struct exynos5_usbdrd_phy_tuning *exynos7870_tunes[PTS_MAX] = {
+	[PTS_UTMI_POSTINIT] = exynos7870_tunes_utmi_postinit,
+};
+
 static const char * const exynos5_clk_names[] = {
 	"phy",
 };
@@ -1525,6 +1937,19 @@ static const char * const exynos5_regulator_names[] = {
 	"vbus", "vbus-boost",
 };
 
+static const struct exynos5_usbdrd_phy_drvdata exynos2200_usb32drd_phy = {
+	.phy_cfg		= phy_cfg_exynos2200,
+	.phy_ops		= &exynos2200_usbdrd_phy_ops,
+	.pmu_offset_usbdrd0_phy	= EXYNOS2200_PHY_CTRL_USB20,
+	.clk_names		= exynos5_clk_names,
+	.n_clks			= ARRAY_SIZE(exynos5_clk_names),
+	/* clocks and regulators are specific to the underlying PHY blocks */
+	.core_clk_names		= NULL,
+	.n_core_clks		= 0,
+	.regulator_names	= NULL,
+	.n_regulators		= 0,
+};
+
 static const struct exynos5_usbdrd_phy_drvdata exynos5420_usbdrd_phy = {
 	.phy_cfg		= phy_cfg_exynos5,
 	.phy_ops		= &exynos5_usbdrd_phy_ops,
@@ -1575,6 +2000,19 @@ static const struct exynos5_usbdrd_phy_drvdata exynos7_usbdrd_phy = {
 	.n_regulators		= ARRAY_SIZE(exynos5_regulator_names),
 };
 
+static const struct exynos5_usbdrd_phy_drvdata exynos7870_usbdrd_phy = {
+	.phy_cfg		= phy_cfg_exynos7870,
+	.phy_tunes		= exynos7870_tunes,
+	.phy_ops		= &exynos7870_usbdrd_phy_ops,
+	.pmu_offset_usbdrd0_phy	= EXYNOS5_USBDRD_PHY_CONTROL,
+	.clk_names		= exynos5_clk_names,
+	.n_clks			= ARRAY_SIZE(exynos5_clk_names),
+	.core_clk_names		= exynos5_core_clk_names,
+	.n_core_clks		= ARRAY_SIZE(exynos5_core_clk_names),
+	.regulator_names	= exynos5_regulator_names,
+	.n_regulators		= ARRAY_SIZE(exynos5_regulator_names),
+};
+
 static const struct exynos5_usbdrd_phy_drvdata exynos850_usbdrd_phy = {
 	.phy_cfg		= phy_cfg_exynos850,
 	.phy_ops		= &exynos850_usbdrd_phy_ops,
@@ -1770,6 +2208,9 @@ static const struct of_device_id exynos5_usbdrd_phy_of_match[] = {
 		.compatible = "google,gs101-usb31drd-phy",
 		.data = &gs101_usbd31rd_phy
 	}, {
+		.compatible = "samsung,exynos2200-usb32drd-phy",
+		.data = &exynos2200_usb32drd_phy,
+	}, {
 		.compatible = "samsung,exynos5250-usbdrd-phy",
 		.data = &exynos5250_usbdrd_phy
 	}, {
@@ -1782,6 +2223,9 @@ static const struct of_device_id exynos5_usbdrd_phy_of_match[] = {
 		.compatible = "samsung,exynos7-usbdrd-phy",
 		.data = &exynos7_usbdrd_phy
 	}, {
+		.compatible = "samsung,exynos7870-usbdrd-phy",
+		.data = &exynos7870_usbdrd_phy
+	}, {
 		.compatible = "samsung,exynos850-usbdrd-phy",
 		.data = &exynos850_usbdrd_phy
 	},
@@ -1841,6 +2285,17 @@ static int exynos5_usbdrd_phy_probe(struct platform_device *pdev)
 			return PTR_ERR(phy_drd->reg_phy);
 	}
 
+	/*
+	 * USB32DRD 4nm controller implements Synopsys eUSB2.0 PHY
+	 * and Synopsys SS/USBDP COMBOPHY, managed by external code.
+	 */
+	if (of_property_present(dev->of_node, "phy-names")) {
+		phy_drd->hs_phy = devm_of_phy_get(dev, dev->of_node, "hs");
+		if (IS_ERR(phy_drd->hs_phy))
+			return dev_err_probe(dev, PTR_ERR(phy_drd->hs_phy),
+					     "failed to get hs_phy\n");
+	}
+
 	ret = exynos5_usbdrd_phy_clk_handle(phy_drd);
 	if (ret)
 		return ret;
diff --git a/drivers/phy/tegra/Kconfig b/drivers/phy/tegra/Kconfig
index f30cfb42b210..342fb736da4b 100644
--- a/drivers/phy/tegra/Kconfig
+++ b/drivers/phy/tegra/Kconfig
@@ -13,7 +13,7 @@ config PHY_TEGRA_XUSB
 
 config PHY_TEGRA194_P2U
 	tristate "NVIDIA Tegra194 PIPE2UPHY PHY driver"
-	depends on ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC || COMPILE_TEST
+	depends on ARCH_TEGRA || COMPILE_TEST
 	select GENERIC_PHY
 	help
 	  Enable this to support the P2U (PIPE to UPHY) that is part of Tegra 19x
diff --git a/drivers/phy/xilinx/phy-zynqmp.c b/drivers/phy/xilinx/phy-zynqmp.c
index 05a4a59f7c40..fe6b4925d166 100644
--- a/drivers/phy/xilinx/phy-zynqmp.c
+++ b/drivers/phy/xilinx/phy-zynqmp.c
@@ -222,7 +222,6 @@ struct xpsgtr_phy {
  * @siou: siou base address
  * @gtr_mutex: mutex for locking
  * @phys: PHY lanes
- * @refclk_sscs: spread spectrum settings for the reference clocks
  * @clk: reference clocks
  * @tx_term_fix: fix for GT issue
  * @saved_icm_cfg0: stored value of ICM CFG0 register
@@ -235,7 +234,6 @@ struct xpsgtr_dev {
 	void __iomem *siou;
 	struct mutex gtr_mutex; /* mutex for locking */
 	struct xpsgtr_phy phys[NUM_LANES];
-	const struct xpsgtr_ssc *refclk_sscs[NUM_LANES];
 	struct clk *clk[NUM_LANES];
 	bool tx_term_fix;
 	unsigned int saved_icm_cfg0;
@@ -398,13 +396,40 @@ got_phy:
 	return ret;
 }
 
+/* Get the spread spectrum (SSC) settings for the reference clock rate */
+static const struct xpsgtr_ssc *xpsgtr_find_sscs(struct xpsgtr_phy *gtr_phy)
+{
+	unsigned long rate;
+	struct clk *clk;
+	unsigned int i;
+
+	clk = gtr_phy->dev->clk[gtr_phy->refclk];
+	rate = clk_get_rate(clk);
+
+	for (i = 0 ; i < ARRAY_SIZE(ssc_lookup); i++) {
+		/* Allow an error of 100 ppm */
+		unsigned long error = ssc_lookup[i].refclk_rate / 10000;
+
+		if (abs(rate - ssc_lookup[i].refclk_rate) < error)
+			return &ssc_lookup[i];
+	}
+
+	dev_err(gtr_phy->dev->dev, "Invalid rate %lu for reference clock %u\n",
+		rate, gtr_phy->refclk);
+
+	return NULL;
+}
+
 /* Configure PLL and spread-sprectrum clock. */
-static void xpsgtr_configure_pll(struct xpsgtr_phy *gtr_phy)
+static int xpsgtr_configure_pll(struct xpsgtr_phy *gtr_phy)
 {
 	const struct xpsgtr_ssc *ssc;
 	u32 step_size;
 
-	ssc = gtr_phy->dev->refclk_sscs[gtr_phy->refclk];
+	ssc = xpsgtr_find_sscs(gtr_phy);
+	if (!ssc)
+		return -EINVAL;
+
 	step_size = ssc->step_size;
 
 	xpsgtr_clr_set(gtr_phy->dev, PLL_REF_SEL(gtr_phy->lane),
@@ -446,6 +471,8 @@ static void xpsgtr_configure_pll(struct xpsgtr_phy *gtr_phy)
 	xpsgtr_clr_set_phy(gtr_phy, L0_PLL_SS_STEP_SIZE_3_MSB,
 			   STEP_SIZE_3_MASK, (step_size & STEP_SIZE_3_MASK) |
 			   FORCE_STEP_SIZE | FORCE_STEPS);
+
+	return 0;
 }
 
 /* Configure the lane protocol. */
@@ -658,7 +685,10 @@ static int xpsgtr_phy_init(struct phy *phy)
 	 * Configure the PLL, the lane protocol, and perform protocol-specific
 	 * initialization.
 	 */
-	xpsgtr_configure_pll(gtr_phy);
+	ret = xpsgtr_configure_pll(gtr_phy);
+	if (ret)
+		goto out;
+
 	xpsgtr_lane_set_protocol(gtr_phy);
 
 	switch (gtr_phy->protocol) {
@@ -823,8 +853,7 @@ static struct phy *xpsgtr_xlate(struct device *dev,
 	}
 
 	refclk = args->args[3];
-	if (refclk >= ARRAY_SIZE(gtr_dev->refclk_sscs) ||
-	    !gtr_dev->refclk_sscs[refclk]) {
+	if (refclk >= ARRAY_SIZE(gtr_dev->clk)) {
 		dev_err(dev, "Invalid reference clock number %u\n", refclk);
 		return ERR_PTR(-EINVAL);
 	}
@@ -928,9 +957,7 @@ static int xpsgtr_get_ref_clocks(struct xpsgtr_dev *gtr_dev)
 {
 	unsigned int refclk;
 
-	for (refclk = 0; refclk < ARRAY_SIZE(gtr_dev->refclk_sscs); ++refclk) {
-		unsigned long rate;
-		unsigned int i;
+	for (refclk = 0; refclk < ARRAY_SIZE(gtr_dev->clk); ++refclk) {
 		struct clk *clk;
 		char name[8];
 
@@ -946,29 +973,6 @@ static int xpsgtr_get_ref_clocks(struct xpsgtr_dev *gtr_dev)
 			continue;
 
 		gtr_dev->clk[refclk] = clk;
-
-		/*
-		 * Get the spread spectrum (SSC) settings for the reference
-		 * clock rate.
-		 */
-		rate = clk_get_rate(clk);
-
-		for (i = 0 ; i < ARRAY_SIZE(ssc_lookup); i++) {
-			/* Allow an error of 100 ppm */
-			unsigned long error = ssc_lookup[i].refclk_rate / 10000;
-
-			if (abs(rate - ssc_lookup[i].refclk_rate) < error) {
-				gtr_dev->refclk_sscs[refclk] = &ssc_lookup[i];
-				break;
-			}
-		}
-
-		if (i == ARRAY_SIZE(ssc_lookup)) {
-			dev_err(gtr_dev->dev,
-				"Invalid rate %lu for reference clock %u\n",
-				rate, refclk);
-			return -EINVAL;
-		}
 	}
 
 	return 0;
diff --git a/drivers/pwm/pwm-stm32-lp.c b/drivers/pwm/pwm-stm32-lp.c
index 5832dce8ed9d..4789eafb8bac 100644
--- a/drivers/pwm/pwm-stm32-lp.c
+++ b/drivers/pwm/pwm-stm32-lp.c
@@ -20,6 +20,7 @@
 struct stm32_pwm_lp {
 	struct clk *clk;
 	struct regmap *regmap;
+	unsigned int num_cc_chans;
 };
 
 static inline struct stm32_pwm_lp *to_stm32_pwm_lp(struct pwm_chip *chip)
@@ -30,13 +31,101 @@ static inline struct stm32_pwm_lp *to_stm32_pwm_lp(struct pwm_chip *chip)
 /* STM32 Low-Power Timer is preceded by a configurable power-of-2 prescaler */
 #define STM32_LPTIM_MAX_PRESCALER	128
 
+static int stm32_pwm_lp_update_allowed(struct stm32_pwm_lp *priv, int channel)
+{
+	int ret;
+	u32 ccmr1;
+	unsigned long ccmr;
+
+	/* Only one PWM on this LPTIMER: enable, prescaler and reload value can be changed */
+	if (!priv->num_cc_chans)
+		return true;
+
+	ret = regmap_read(priv->regmap, STM32_LPTIM_CCMR1, &ccmr1);
+	if (ret)
+		return ret;
+	ccmr = ccmr1 & (STM32_LPTIM_CC1E | STM32_LPTIM_CC2E);
+
+	/* More than one channel enabled: enable, prescaler or ARR value can't be changed */
+	if (bitmap_weight(&ccmr, sizeof(u32) * BITS_PER_BYTE) > 1)
+		return false;
+
+	/*
+	 * Only one channel is enabled (or none): check status on the other channel, to
+	 * report if enable, prescaler or ARR value can be changed.
+	 */
+	if (channel)
+		return !(ccmr1 & STM32_LPTIM_CC1E);
+	else
+		return !(ccmr1 & STM32_LPTIM_CC2E);
+}
+
+static int stm32_pwm_lp_compare_channel_apply(struct stm32_pwm_lp *priv, int channel,
+					      bool enable, enum pwm_polarity polarity)
+{
+	u32 ccmr1, val, mask;
+	bool reenable;
+	int ret;
+
+	/* No dedicated CC channel: nothing to do */
+	if (!priv->num_cc_chans)
+		return 0;
+
+	ret = regmap_read(priv->regmap, STM32_LPTIM_CCMR1, &ccmr1);
+	if (ret)
+		return ret;
+
+	if (channel) {
+		/* Must disable CC channel (CCxE) to modify polarity (CCxP), then re-enable */
+		reenable = (enable && FIELD_GET(STM32_LPTIM_CC2E, ccmr1)) &&
+			(polarity != FIELD_GET(STM32_LPTIM_CC2P, ccmr1));
+
+		mask = STM32_LPTIM_CC2SEL | STM32_LPTIM_CC2E | STM32_LPTIM_CC2P;
+		val = FIELD_PREP(STM32_LPTIM_CC2P, polarity);
+		val |= FIELD_PREP(STM32_LPTIM_CC2E, enable);
+	} else {
+		reenable = (enable && FIELD_GET(STM32_LPTIM_CC1E, ccmr1)) &&
+			(polarity != FIELD_GET(STM32_LPTIM_CC1P, ccmr1));
+
+		mask = STM32_LPTIM_CC1SEL | STM32_LPTIM_CC1E | STM32_LPTIM_CC1P;
+		val = FIELD_PREP(STM32_LPTIM_CC1P, polarity);
+		val |= FIELD_PREP(STM32_LPTIM_CC1E, enable);
+	}
+
+	if (reenable) {
+		u32 cfgr, presc;
+		unsigned long rate;
+		unsigned int delay_us;
+
+		ret = regmap_update_bits(priv->regmap, STM32_LPTIM_CCMR1,
+					 channel ? STM32_LPTIM_CC2E : STM32_LPTIM_CC1E, 0);
+		if (ret)
+			return ret;
+		/*
+		 * After a write to the LPTIM_CCMRx register, a new write operation can only be
+		 * performed after a delay of at least (PRESC × 3) clock cycles
+		 */
+		ret = regmap_read(priv->regmap, STM32_LPTIM_CFGR, &cfgr);
+		if (ret)
+			return ret;
+		presc = FIELD_GET(STM32_LPTIM_PRESC, cfgr);
+		rate = clk_get_rate(priv->clk) >> presc;
+		if (!rate)
+			return -EINVAL;
+		delay_us = 3 * DIV_ROUND_UP(USEC_PER_SEC, rate);
+		usleep_range(delay_us, delay_us * 2);
+	}
+
+	return regmap_update_bits(priv->regmap, STM32_LPTIM_CCMR1, mask, val);
+}
+
 static int stm32_pwm_lp_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			      const struct pwm_state *state)
 {
 	struct stm32_pwm_lp *priv = to_stm32_pwm_lp(chip);
 	unsigned long long prd, div, dty;
 	struct pwm_state cstate;
-	u32 val, mask, cfgr, presc = 0;
+	u32 arr, val, mask, cfgr, presc = 0;
 	bool reenable;
 	int ret;
 
@@ -45,10 +134,28 @@ static int stm32_pwm_lp_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 
 	if (!state->enabled) {
 		if (cstate.enabled) {
-			/* Disable LP timer */
-			ret = regmap_write(priv->regmap, STM32_LPTIM_CR, 0);
+			/* Disable CC channel if any */
+			ret = stm32_pwm_lp_compare_channel_apply(priv, pwm->hwpwm, false,
+								 state->polarity);
 			if (ret)
 				return ret;
+			ret = regmap_write(priv->regmap, pwm->hwpwm ?
+					   STM32_LPTIM_CCR2 : STM32_LPTIM_CMP, 0);
+			if (ret)
+				return ret;
+
+			/* Check if the timer can be disabled */
+			ret = stm32_pwm_lp_update_allowed(priv, pwm->hwpwm);
+			if (ret < 0)
+				return ret;
+
+			if (ret) {
+				/* Disable LP timer */
+				ret = regmap_write(priv->regmap, STM32_LPTIM_CR, 0);
+				if (ret)
+					return ret;
+			}
+
 			/* disable clock to PWM counter */
 			clk_disable(priv->clk);
 		}
@@ -79,6 +186,23 @@ static int stm32_pwm_lp_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	dty = prd * state->duty_cycle;
 	do_div(dty, state->period);
 
+	ret = regmap_read(priv->regmap, STM32_LPTIM_CFGR, &cfgr);
+	if (ret)
+		return ret;
+
+	/*
+	 * When there are several channels, they share the same prescaler and reload value.
+	 * Check if this can be changed, or the values are the same for all channels.
+	 */
+	if (!stm32_pwm_lp_update_allowed(priv, pwm->hwpwm)) {
+		ret = regmap_read(priv->regmap, STM32_LPTIM_ARR, &arr);
+		if (ret)
+			return ret;
+
+		if ((FIELD_GET(STM32_LPTIM_PRESC, cfgr) != presc) || (arr != prd - 1))
+			return -EBUSY;
+	}
+
 	if (!cstate.enabled) {
 		/* enable clock to drive PWM counter */
 		ret = clk_enable(priv->clk);
@@ -86,15 +210,20 @@ static int stm32_pwm_lp_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			return ret;
 	}
 
-	ret = regmap_read(priv->regmap, STM32_LPTIM_CFGR, &cfgr);
-	if (ret)
-		goto err;
-
 	if ((FIELD_GET(STM32_LPTIM_PRESC, cfgr) != presc) ||
-	    (FIELD_GET(STM32_LPTIM_WAVPOL, cfgr) != state->polarity)) {
+	    ((FIELD_GET(STM32_LPTIM_WAVPOL, cfgr) != state->polarity) && !priv->num_cc_chans)) {
 		val = FIELD_PREP(STM32_LPTIM_PRESC, presc);
-		val |= FIELD_PREP(STM32_LPTIM_WAVPOL, state->polarity);
-		mask = STM32_LPTIM_PRESC | STM32_LPTIM_WAVPOL;
+		mask = STM32_LPTIM_PRESC;
+
+		if (!priv->num_cc_chans) {
+			/*
+			 * WAVPOL bit is only available when no capature compare channel is used,
+			 * e.g. on LPTIMER instances that have only one output channel. CCMR1 is
+			 * used otherwise.
+			 */
+			val |= FIELD_PREP(STM32_LPTIM_WAVPOL, state->polarity);
+			mask |= STM32_LPTIM_WAVPOL;
+		}
 
 		/* Must disable LP timer to modify CFGR */
 		reenable = true;
@@ -120,20 +249,27 @@ static int stm32_pwm_lp_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	if (ret)
 		goto err;
 
-	ret = regmap_write(priv->regmap, STM32_LPTIM_CMP, prd - (1 + dty));
+	/* Write CMP/CCRx register and ensure it's been properly written */
+	ret = regmap_write(priv->regmap, pwm->hwpwm ? STM32_LPTIM_CCR2 : STM32_LPTIM_CMP,
+			   prd - (1 + dty));
 	if (ret)
 		goto err;
 
-	/* ensure CMP & ARR registers are properly written */
-	ret = regmap_read_poll_timeout(priv->regmap, STM32_LPTIM_ISR, val,
+	/* ensure ARR and CMP/CCRx registers are properly written */
+	ret = regmap_read_poll_timeout(priv->regmap, STM32_LPTIM_ISR, val, pwm->hwpwm ?
+				       (val & STM32_LPTIM_CMP2_ARROK) == STM32_LPTIM_CMP2_ARROK :
 				       (val & STM32_LPTIM_CMPOK_ARROK) == STM32_LPTIM_CMPOK_ARROK,
 				       100, 1000);
 	if (ret) {
 		dev_err(pwmchip_parent(chip), "ARR/CMP registers write issue\n");
 		goto err;
 	}
-	ret = regmap_write(priv->regmap, STM32_LPTIM_ICR,
-			   STM32_LPTIM_CMPOKCF_ARROKCF);
+	ret = regmap_write(priv->regmap, STM32_LPTIM_ICR, pwm->hwpwm ?
+			   STM32_LPTIM_CMP2OKCF_ARROKCF : STM32_LPTIM_CMPOKCF_ARROKCF);
+	if (ret)
+		goto err;
+
+	ret = stm32_pwm_lp_compare_channel_apply(priv, pwm->hwpwm, true, state->polarity);
 	if (ret)
 		goto err;
 
@@ -161,11 +297,22 @@ static int stm32_pwm_lp_get_state(struct pwm_chip *chip,
 {
 	struct stm32_pwm_lp *priv = to_stm32_pwm_lp(chip);
 	unsigned long rate = clk_get_rate(priv->clk);
-	u32 val, presc, prd;
+	u32 val, presc, prd, ccmr1;
+	bool enabled;
 	u64 tmp;
 
 	regmap_read(priv->regmap, STM32_LPTIM_CR, &val);
-	state->enabled = !!FIELD_GET(STM32_LPTIM_ENABLE, val);
+	enabled = !!FIELD_GET(STM32_LPTIM_ENABLE, val);
+	if (priv->num_cc_chans) {
+		/* There's a CC chan, need to also check if it's enabled */
+		regmap_read(priv->regmap, STM32_LPTIM_CCMR1, &ccmr1);
+		if (pwm->hwpwm)
+			enabled &= !!FIELD_GET(STM32_LPTIM_CC2E, ccmr1);
+		else
+			enabled &= !!FIELD_GET(STM32_LPTIM_CC1E, ccmr1);
+	}
+	state->enabled = enabled;
+
 	/* Keep PWM counter clock refcount in sync with PWM initial state */
 	if (state->enabled) {
 		int ret = clk_enable(priv->clk);
@@ -176,14 +323,21 @@ static int stm32_pwm_lp_get_state(struct pwm_chip *chip,
 
 	regmap_read(priv->regmap, STM32_LPTIM_CFGR, &val);
 	presc = FIELD_GET(STM32_LPTIM_PRESC, val);
-	state->polarity = FIELD_GET(STM32_LPTIM_WAVPOL, val);
+	if (priv->num_cc_chans) {
+		if (pwm->hwpwm)
+			state->polarity = FIELD_GET(STM32_LPTIM_CC2P, ccmr1);
+		else
+			state->polarity = FIELD_GET(STM32_LPTIM_CC1P, ccmr1);
+	} else {
+		state->polarity = FIELD_GET(STM32_LPTIM_WAVPOL, val);
+	}
 
 	regmap_read(priv->regmap, STM32_LPTIM_ARR, &prd);
 	tmp = prd + 1;
 	tmp = (tmp << presc) * NSEC_PER_SEC;
 	state->period = DIV_ROUND_CLOSEST_ULL(tmp, rate);
 
-	regmap_read(priv->regmap, STM32_LPTIM_CMP, &val);
+	regmap_read(priv->regmap, pwm->hwpwm ? STM32_LPTIM_CCR2 : STM32_LPTIM_CMP, &val);
 	tmp = prd - val;
 	tmp = (tmp << presc) * NSEC_PER_SEC;
 	state->duty_cycle = DIV_ROUND_CLOSEST_ULL(tmp, rate);
@@ -201,15 +355,25 @@ static int stm32_pwm_lp_probe(struct platform_device *pdev)
 	struct stm32_lptimer *ddata = dev_get_drvdata(pdev->dev.parent);
 	struct stm32_pwm_lp *priv;
 	struct pwm_chip *chip;
+	unsigned int npwm;
 	int ret;
 
-	chip = devm_pwmchip_alloc(&pdev->dev, 1, sizeof(*priv));
+	if (!ddata->num_cc_chans) {
+		/* No dedicated CC channel, so there's only one PWM channel */
+		npwm = 1;
+	} else {
+		/* There are dedicated CC channels, each with one PWM output */
+		npwm = ddata->num_cc_chans;
+	}
+
+	chip = devm_pwmchip_alloc(&pdev->dev, npwm, sizeof(*priv));
 	if (IS_ERR(chip))
 		return PTR_ERR(chip);
 	priv = to_stm32_pwm_lp(chip);
 
 	priv->regmap = ddata->regmap;
 	priv->clk = ddata->clk;
+	priv->num_cc_chans = ddata->num_cc_chans;
 	chip->ops = &stm32_pwm_lp_ops;
 
 	ret = devm_pwmchip_add(&pdev->dev, chip);
@@ -225,12 +389,15 @@ static int stm32_pwm_lp_suspend(struct device *dev)
 {
 	struct pwm_chip *chip = dev_get_drvdata(dev);
 	struct pwm_state state;
-
-	pwm_get_state(&chip->pwms[0], &state);
-	if (state.enabled) {
-		dev_err(dev, "The consumer didn't stop us (%s)\n",
-			chip->pwms[0].label);
-		return -EBUSY;
+	unsigned int i;
+
+	for (i = 0; i < chip->npwm; i++) {
+		pwm_get_state(&chip->pwms[i], &state);
+		if (state.enabled) {
+			dev_err(dev, "The consumer didn't stop us (%s)\n",
+				chip->pwms[i].label);
+			return -EBUSY;
+		}
 	}
 
 	return pinctrl_pm_select_sleep_state(dev);
diff --git a/drivers/regulator/bcm590xx-regulator.c b/drivers/regulator/bcm590xx-regulator.c
index 9f0cda46b015..50414f4cb109 100644
--- a/drivers/regulator/bcm590xx-regulator.c
+++ b/drivers/regulator/bcm590xx-regulator.c
@@ -18,112 +18,236 @@
 #include <linux/regulator/of_regulator.h>
 #include <linux/slab.h>
 
-/* I2C slave 0 registers */
-#define BCM590XX_RFLDOPMCTRL1	0x60
-#define BCM590XX_IOSR1PMCTRL1	0x7a
-#define BCM590XX_IOSR2PMCTRL1	0x7c
-#define BCM590XX_CSRPMCTRL1	0x7e
-#define BCM590XX_SDSR1PMCTRL1	0x82
-#define BCM590XX_SDSR2PMCTRL1	0x86
-#define BCM590XX_MSRPMCTRL1	0x8a
-#define BCM590XX_VSRPMCTRL1	0x8e
-#define BCM590XX_RFLDOCTRL	0x96
-#define BCM590XX_CSRVOUT1	0xc0
-
-/* I2C slave 1 registers */
-#define BCM590XX_GPLDO5PMCTRL1	0x16
-#define BCM590XX_GPLDO6PMCTRL1	0x18
-#define BCM590XX_GPLDO1CTRL	0x1a
-#define BCM590XX_GPLDO2CTRL	0x1b
-#define BCM590XX_GPLDO3CTRL	0x1c
-#define BCM590XX_GPLDO4CTRL	0x1d
-#define BCM590XX_GPLDO5CTRL	0x1e
-#define BCM590XX_GPLDO6CTRL	0x1f
-#define BCM590XX_OTG_CTRL	0x40
-#define BCM590XX_GPLDO1PMCTRL1	0x57
-#define BCM590XX_GPLDO2PMCTRL1	0x59
-#define BCM590XX_GPLDO3PMCTRL1	0x5b
-#define BCM590XX_GPLDO4PMCTRL1	0x5d
-
 #define BCM590XX_REG_ENABLE	BIT(7)
 #define BCM590XX_VBUS_ENABLE	BIT(2)
 #define BCM590XX_LDO_VSEL_MASK	GENMASK(5, 3)
 #define BCM590XX_SR_VSEL_MASK	GENMASK(5, 0)
 
+enum bcm590xx_reg_type {
+	BCM590XX_REG_TYPE_LDO,
+	BCM590XX_REG_TYPE_GPLDO,
+	BCM590XX_REG_TYPE_SR,
+	BCM590XX_REG_TYPE_VBUS
+};
+
+struct bcm590xx_reg_data {
+	enum bcm590xx_reg_type type;
+	enum bcm590xx_regmap_type regmap;
+	const struct regulator_desc desc;
+};
+
+struct bcm590xx_reg {
+	struct bcm590xx *mfd;
+	unsigned int n_regulators;
+	const struct bcm590xx_reg_data *regs;
+};
+
+static const struct regulator_ops bcm590xx_ops_ldo = {
+	.is_enabled		= regulator_is_enabled_regmap,
+	.enable			= regulator_enable_regmap,
+	.disable		= regulator_disable_regmap,
+	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
+	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
+	.list_voltage		= regulator_list_voltage_table,
+	.map_voltage		= regulator_map_voltage_iterate,
+};
+
+/*
+ * LDO ops without voltage selection, used for MICLDO on BCM59054.
+ * (These are currently the same as VBUS ops, but will be different
+ * in the future once full PMMODE support is implemented.)
+ */
+static const struct regulator_ops bcm590xx_ops_ldo_novolt = {
+	.is_enabled		= regulator_is_enabled_regmap,
+	.enable			= regulator_enable_regmap,
+	.disable		= regulator_disable_regmap,
+};
+
+static const struct regulator_ops bcm590xx_ops_dcdc = {
+	.is_enabled		= regulator_is_enabled_regmap,
+	.enable			= regulator_enable_regmap,
+	.disable		= regulator_disable_regmap,
+	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
+	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
+	.list_voltage		= regulator_list_voltage_linear_range,
+	.map_voltage		= regulator_map_voltage_linear_range,
+};
+
+static const struct regulator_ops bcm590xx_ops_vbus = {
+	.is_enabled		= regulator_is_enabled_regmap,
+	.enable			= regulator_enable_regmap,
+	.disable		= regulator_disable_regmap,
+};
+
+#define BCM590XX_REG_DESC(_model, _name, _name_lower)			\
+	.id = _model##_REG_##_name,					\
+	.name = #_name_lower,						\
+	.of_match = of_match_ptr(#_name_lower),				\
+	.regulators_node = of_match_ptr("regulators"),			\
+	.type = REGULATOR_VOLTAGE,					\
+	.owner = THIS_MODULE						\
+
+#define BCM590XX_LDO_DESC(_model, _model_lower, _name, _name_lower, _table) \
+	BCM590XX_REG_DESC(_model, _name, _name_lower),			\
+	.ops = &bcm590xx_ops_ldo,					\
+	.n_voltages = ARRAY_SIZE(_model_lower##_##_table),		\
+	.volt_table = _model_lower##_##_table,				\
+	.vsel_reg = _model##_##_name##CTRL,				\
+	.vsel_mask = BCM590XX_LDO_VSEL_MASK,				\
+	.enable_reg = _model##_##_name##PMCTRL1,			\
+	.enable_mask = BCM590XX_REG_ENABLE,				\
+	.enable_is_inverted = true
+
+#define BCM590XX_SR_DESC(_model, _model_lower, _name, _name_lower, _ranges) \
+	BCM590XX_REG_DESC(_model, _name, _name_lower),			\
+	.ops = &bcm590xx_ops_dcdc,					\
+	.n_voltages = 64,						\
+	.linear_ranges = _model_lower##_##_ranges,			\
+	.n_linear_ranges = ARRAY_SIZE(_model_lower##_##_ranges),	\
+	.vsel_reg = _model##_##_name##VOUT1,				\
+	.vsel_mask = BCM590XX_SR_VSEL_MASK,				\
+	.enable_reg = _model##_##_name##PMCTRL1,			\
+	.enable_mask = BCM590XX_REG_ENABLE,				\
+	.enable_is_inverted = true
+
+#define BCM59056_REG_DESC(_name, _name_lower)				\
+	BCM590XX_REG_DESC(BCM59056, _name, _name_lower)
+#define BCM59056_LDO_DESC(_name, _name_lower, _table)			\
+	BCM590XX_LDO_DESC(BCM59056, bcm59056, _name, _name_lower, _table)
+#define BCM59056_SR_DESC(_name, _name_lower, _ranges)			\
+	BCM590XX_SR_DESC(BCM59056, bcm59056, _name, _name_lower, _ranges)
+
+#define BCM59054_REG_DESC(_name, _name_lower)				\
+	BCM590XX_REG_DESC(BCM59054, _name, _name_lower)
+#define BCM59054_LDO_DESC(_name, _name_lower, _table)			\
+	BCM590XX_LDO_DESC(BCM59054, bcm59054, _name, _name_lower, _table)
+#define BCM59054_SR_DESC(_name, _name_lower, _ranges)			\
+	BCM590XX_SR_DESC(BCM59054, bcm59054, _name, _name_lower, _ranges)
+
+/* BCM59056 data */
+
+/* I2C slave 0 registers */
+#define BCM59056_RFLDOPMCTRL1	0x60
+#define BCM59056_CAMLDO1PMCTRL1	0x62
+#define BCM59056_CAMLDO2PMCTRL1	0x64
+#define BCM59056_SIMLDO1PMCTRL1	0x66
+#define BCM59056_SIMLDO2PMCTRL1	0x68
+#define BCM59056_SDLDOPMCTRL1	0x6a
+#define BCM59056_SDXLDOPMCTRL1	0x6c
+#define BCM59056_MMCLDO1PMCTRL1	0x6e
+#define BCM59056_MMCLDO2PMCTRL1	0x70
+#define BCM59056_AUDLDOPMCTRL1	0x72
+#define BCM59056_MICLDOPMCTRL1	0x74
+#define BCM59056_USBLDOPMCTRL1	0x76
+#define BCM59056_VIBLDOPMCTRL1	0x78
+#define BCM59056_IOSR1PMCTRL1	0x7a
+#define BCM59056_IOSR2PMCTRL1	0x7c
+#define BCM59056_CSRPMCTRL1	0x7e
+#define BCM59056_SDSR1PMCTRL1	0x82
+#define BCM59056_SDSR2PMCTRL1	0x86
+#define BCM59056_MSRPMCTRL1	0x8a
+#define BCM59056_VSRPMCTRL1	0x8e
+#define BCM59056_RFLDOCTRL	0x96
+#define BCM59056_CAMLDO1CTRL	0x97
+#define BCM59056_CAMLDO2CTRL	0x98
+#define BCM59056_SIMLDO1CTRL	0x99
+#define BCM59056_SIMLDO2CTRL	0x9a
+#define BCM59056_SDLDOCTRL	0x9b
+#define BCM59056_SDXLDOCTRL	0x9c
+#define BCM59056_MMCLDO1CTRL	0x9d
+#define BCM59056_MMCLDO2CTRL	0x9e
+#define BCM59056_AUDLDOCTRL	0x9f
+#define BCM59056_MICLDOCTRL	0xa0
+#define BCM59056_USBLDOCTRL	0xa1
+#define BCM59056_VIBLDOCTRL	0xa2
+#define BCM59056_CSRVOUT1	0xc0
+#define BCM59056_IOSR1VOUT1	0xc3
+#define BCM59056_IOSR2VOUT1	0xc6
+#define BCM59056_MSRVOUT1	0xc9
+#define BCM59056_SDSR1VOUT1	0xcc
+#define BCM59056_SDSR2VOUT1	0xcf
+#define BCM59056_VSRVOUT1	0xd2
+
+/* I2C slave 1 registers */
+#define BCM59056_GPLDO5PMCTRL1	0x16
+#define BCM59056_GPLDO6PMCTRL1	0x18
+#define BCM59056_GPLDO1CTRL	0x1a
+#define BCM59056_GPLDO2CTRL	0x1b
+#define BCM59056_GPLDO3CTRL	0x1c
+#define BCM59056_GPLDO4CTRL	0x1d
+#define BCM59056_GPLDO5CTRL	0x1e
+#define BCM59056_GPLDO6CTRL	0x1f
+#define BCM59056_OTG_CTRL	0x40
+#define BCM59056_GPLDO1PMCTRL1	0x57
+#define BCM59056_GPLDO2PMCTRL1	0x59
+#define BCM59056_GPLDO3PMCTRL1	0x5b
+#define BCM59056_GPLDO4PMCTRL1	0x5d
+
 /*
  * RFLDO to VSR regulators are
  * accessed via I2C slave 0
  */
 
 /* LDO regulator IDs */
-#define BCM590XX_REG_RFLDO	0
-#define BCM590XX_REG_CAMLDO1	1
-#define BCM590XX_REG_CAMLDO2	2
-#define BCM590XX_REG_SIMLDO1	3
-#define BCM590XX_REG_SIMLDO2	4
-#define BCM590XX_REG_SDLDO	5
-#define BCM590XX_REG_SDXLDO	6
-#define BCM590XX_REG_MMCLDO1	7
-#define BCM590XX_REG_MMCLDO2	8
-#define BCM590XX_REG_AUDLDO	9
-#define BCM590XX_REG_MICLDO	10
-#define BCM590XX_REG_USBLDO	11
-#define BCM590XX_REG_VIBLDO	12
+#define BCM59056_REG_RFLDO	0
+#define BCM59056_REG_CAMLDO1	1
+#define BCM59056_REG_CAMLDO2	2
+#define BCM59056_REG_SIMLDO1	3
+#define BCM59056_REG_SIMLDO2	4
+#define BCM59056_REG_SDLDO	5
+#define BCM59056_REG_SDXLDO	6
+#define BCM59056_REG_MMCLDO1	7
+#define BCM59056_REG_MMCLDO2	8
+#define BCM59056_REG_AUDLDO	9
+#define BCM59056_REG_MICLDO	10
+#define BCM59056_REG_USBLDO	11
+#define BCM59056_REG_VIBLDO	12
 
 /* DCDC regulator IDs */
-#define BCM590XX_REG_CSR	13
-#define BCM590XX_REG_IOSR1	14
-#define BCM590XX_REG_IOSR2	15
-#define BCM590XX_REG_MSR	16
-#define BCM590XX_REG_SDSR1	17
-#define BCM590XX_REG_SDSR2	18
-#define BCM590XX_REG_VSR	19
+#define BCM59056_REG_CSR	13
+#define BCM59056_REG_IOSR1	14
+#define BCM59056_REG_IOSR2	15
+#define BCM59056_REG_MSR	16
+#define BCM59056_REG_SDSR1	17
+#define BCM59056_REG_SDSR2	18
+#define BCM59056_REG_VSR	19
 
 /*
  * GPLDO1 to VBUS regulators are
  * accessed via I2C slave 1
  */
 
-#define BCM590XX_REG_GPLDO1	20
-#define BCM590XX_REG_GPLDO2	21
-#define BCM590XX_REG_GPLDO3	22
-#define BCM590XX_REG_GPLDO4	23
-#define BCM590XX_REG_GPLDO5	24
-#define BCM590XX_REG_GPLDO6	25
-#define BCM590XX_REG_VBUS	26
+#define BCM59056_REG_GPLDO1	20
+#define BCM59056_REG_GPLDO2	21
+#define BCM59056_REG_GPLDO3	22
+#define BCM59056_REG_GPLDO4	23
+#define BCM59056_REG_GPLDO5	24
+#define BCM59056_REG_GPLDO6	25
+#define BCM59056_REG_VBUS	26
 
-#define BCM590XX_NUM_REGS	27
-
-#define BCM590XX_REG_IS_LDO(n)	(n < BCM590XX_REG_CSR)
-#define BCM590XX_REG_IS_GPLDO(n) \
-	((n > BCM590XX_REG_VSR) && (n < BCM590XX_REG_VBUS))
-#define BCM590XX_REG_IS_VBUS(n)	(n == BCM590XX_REG_VBUS)
+#define BCM59056_NUM_REGS	27
 
 /* LDO group A: supported voltages in microvolts */
-static const unsigned int ldo_a_table[] = {
+static const unsigned int bcm59056_ldo_a_table[] = {
 	1200000, 1800000, 2500000, 2700000, 2800000,
 	2900000, 3000000, 3300000,
 };
 
 /* LDO group C: supported voltages in microvolts */
-static const unsigned int ldo_c_table[] = {
+static const unsigned int bcm59056_ldo_c_table[] = {
 	3100000, 1800000, 2500000, 2700000, 2800000,
 	2900000, 3000000, 3300000,
 };
 
-static const unsigned int ldo_vbus[] = {
-	5000000,
-};
-
 /* DCDC group CSR: supported voltages in microvolts */
-static const struct linear_range dcdc_csr_ranges[] = {
+static const struct linear_range bcm59056_dcdc_csr_ranges[] = {
 	REGULATOR_LINEAR_RANGE(860000, 2, 50, 10000),
 	REGULATOR_LINEAR_RANGE(1360000, 51, 55, 20000),
 	REGULATOR_LINEAR_RANGE(900000, 56, 63, 0),
 };
 
 /* DCDC group IOSR1: supported voltages in microvolts */
-static const struct linear_range dcdc_iosr1_ranges[] = {
+static const struct linear_range bcm59056_dcdc_iosr1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(860000, 2, 51, 10000),
 	REGULATOR_LINEAR_RANGE(1500000, 52, 52, 0),
 	REGULATOR_LINEAR_RANGE(1800000, 53, 53, 0),
@@ -131,155 +255,854 @@ static const struct linear_range dcdc_iosr1_ranges[] = {
 };
 
 /* DCDC group SDSR1: supported voltages in microvolts */
-static const struct linear_range dcdc_sdsr1_ranges[] = {
+static const struct linear_range bcm59056_dcdc_sdsr1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(860000, 2, 50, 10000),
 	REGULATOR_LINEAR_RANGE(1340000, 51, 51, 0),
 	REGULATOR_LINEAR_RANGE(900000, 52, 63, 0),
 };
 
-struct bcm590xx_info {
-	const char *name;
-	const char *vin_name;
-	u8 n_voltages;
-	const unsigned int *volt_table;
-	u8 n_linear_ranges;
-	const struct linear_range *linear_ranges;
-};
+static const struct bcm590xx_reg_data bcm59056_regs[BCM59056_NUM_REGS] = {
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(RFLDO, rfldo, ldo_a_table),
+		},
+	},
 
-#define BCM590XX_REG_TABLE(_name, _table) \
-	{ \
-		.name = #_name, \
-		.n_voltages = ARRAY_SIZE(_table), \
-		.volt_table = _table, \
-	}
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(CAMLDO1, camldo1, ldo_c_table),
+		},
+	},
 
-#define BCM590XX_REG_RANGES(_name, _ranges) \
-	{ \
-		.name = #_name, \
-		.n_voltages = 64, \
-		.n_linear_ranges = ARRAY_SIZE(_ranges), \
-		.linear_ranges = _ranges, \
-	}
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(CAMLDO2, camldo2, ldo_c_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(SIMLDO1, simldo1, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(SIMLDO2, simldo2, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(SDLDO, sdldo, ldo_c_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(SDXLDO, sdxldo, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(MMCLDO1, mmcldo1, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(MMCLDO2, mmcldo2, ldo_a_table),
+		},
+	},
 
-static struct bcm590xx_info bcm590xx_regs[] = {
-	BCM590XX_REG_TABLE(rfldo, ldo_a_table),
-	BCM590XX_REG_TABLE(camldo1, ldo_c_table),
-	BCM590XX_REG_TABLE(camldo2, ldo_c_table),
-	BCM590XX_REG_TABLE(simldo1, ldo_a_table),
-	BCM590XX_REG_TABLE(simldo2, ldo_a_table),
-	BCM590XX_REG_TABLE(sdldo, ldo_c_table),
-	BCM590XX_REG_TABLE(sdxldo, ldo_a_table),
-	BCM590XX_REG_TABLE(mmcldo1, ldo_a_table),
-	BCM590XX_REG_TABLE(mmcldo2, ldo_a_table),
-	BCM590XX_REG_TABLE(audldo, ldo_a_table),
-	BCM590XX_REG_TABLE(micldo, ldo_a_table),
-	BCM590XX_REG_TABLE(usbldo, ldo_a_table),
-	BCM590XX_REG_TABLE(vibldo, ldo_c_table),
-	BCM590XX_REG_RANGES(csr, dcdc_csr_ranges),
-	BCM590XX_REG_RANGES(iosr1, dcdc_iosr1_ranges),
-	BCM590XX_REG_RANGES(iosr2, dcdc_iosr1_ranges),
-	BCM590XX_REG_RANGES(msr, dcdc_iosr1_ranges),
-	BCM590XX_REG_RANGES(sdsr1, dcdc_sdsr1_ranges),
-	BCM590XX_REG_RANGES(sdsr2, dcdc_iosr1_ranges),
-	BCM590XX_REG_RANGES(vsr, dcdc_iosr1_ranges),
-	BCM590XX_REG_TABLE(gpldo1, ldo_a_table),
-	BCM590XX_REG_TABLE(gpldo2, ldo_a_table),
-	BCM590XX_REG_TABLE(gpldo3, ldo_a_table),
-	BCM590XX_REG_TABLE(gpldo4, ldo_a_table),
-	BCM590XX_REG_TABLE(gpldo5, ldo_a_table),
-	BCM590XX_REG_TABLE(gpldo6, ldo_a_table),
-	BCM590XX_REG_TABLE(vbus, ldo_vbus),
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(AUDLDO, audldo, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(MICLDO, micldo, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(USBLDO, usbldo, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_LDO_DESC(VIBLDO, vibldo, ldo_c_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_SR_DESC(CSR, csr, dcdc_csr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_SR_DESC(IOSR1, iosr1, dcdc_iosr1_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_SR_DESC(IOSR2, iosr2, dcdc_iosr1_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_SR_DESC(MSR, msr, dcdc_iosr1_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_SR_DESC(SDSR1, sdsr1, dcdc_sdsr1_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_SR_DESC(SDSR2, sdsr2, dcdc_iosr1_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59056_SR_DESC(VSR, vsr, dcdc_iosr1_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59056_LDO_DESC(GPLDO1, gpldo1, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59056_LDO_DESC(GPLDO2, gpldo2, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59056_LDO_DESC(GPLDO3, gpldo3, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59056_LDO_DESC(GPLDO4, gpldo4, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59056_LDO_DESC(GPLDO5, gpldo5, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59056_LDO_DESC(GPLDO6, gpldo6, ldo_a_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_VBUS,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59056_REG_DESC(VBUS, vbus),
+			.ops = &bcm590xx_ops_vbus,
+			.n_voltages = 1,
+			.fixed_uV = 5000000,
+			.enable_reg = BCM59056_OTG_CTRL,
+			.enable_mask = BCM590XX_VBUS_ENABLE,
+		},
+	},
 };
 
-struct bcm590xx_reg {
-	struct regulator_desc *desc;
-	struct bcm590xx *mfd;
+/* BCM59054 data */
+
+/* I2C slave 0 registers */
+#define BCM59054_RFLDOPMCTRL1	0x60
+#define BCM59054_CAMLDO1PMCTRL1	0x62
+#define BCM59054_CAMLDO2PMCTRL1	0x64
+#define BCM59054_SIMLDO1PMCTRL1	0x66
+#define BCM59054_SIMLDO2PMCTRL1	0x68
+#define BCM59054_SDLDOPMCTRL1	0x6a
+#define BCM59054_SDXLDOPMCTRL1	0x6c
+#define BCM59054_MMCLDO1PMCTRL1	0x6e
+#define BCM59054_MMCLDO2PMCTRL1	0x70
+#define BCM59054_AUDLDOPMCTRL1	0x72
+#define BCM59054_MICLDOPMCTRL1	0x74
+#define BCM59054_USBLDOPMCTRL1	0x76
+#define BCM59054_VIBLDOPMCTRL1	0x78
+#define BCM59054_IOSR1PMCTRL1	0x7a
+#define BCM59054_IOSR2PMCTRL1	0x7c
+#define BCM59054_CSRPMCTRL1	0x7e
+#define BCM59054_SDSR1PMCTRL1	0x82
+#define BCM59054_SDSR2PMCTRL1	0x86
+#define BCM59054_MMSRPMCTRL1	0x8a
+#define BCM59054_VSRPMCTRL1	0x8e
+#define BCM59054_RFLDOCTRL	0x96
+#define BCM59054_CAMLDO1CTRL	0x97
+#define BCM59054_CAMLDO2CTRL	0x98
+#define BCM59054_SIMLDO1CTRL	0x99
+#define BCM59054_SIMLDO2CTRL	0x9a
+#define BCM59054_SDLDOCTRL	0x9b
+#define BCM59054_SDXLDOCTRL	0x9c
+#define BCM59054_MMCLDO1CTRL	0x9d
+#define BCM59054_MMCLDO2CTRL	0x9e
+#define BCM59054_AUDLDOCTRL	0x9f
+#define BCM59054_MICLDOCTRL	0xa0
+#define BCM59054_USBLDOCTRL	0xa1
+#define BCM59054_VIBLDOCTRL	0xa2
+#define BCM59054_CSRVOUT1	0xc0
+#define BCM59054_IOSR1VOUT1	0xc3
+#define BCM59054_IOSR2VOUT1	0xc6
+#define BCM59054_MMSRVOUT1	0xc9
+#define BCM59054_SDSR1VOUT1	0xcc
+#define BCM59054_SDSR2VOUT1	0xcf
+#define BCM59054_VSRVOUT1	0xd2
+
+/* I2C slave 1 registers */
+#define BCM59054_LVLDO1PMCTRL1	0x16
+#define BCM59054_LVLDO2PMCTRL1	0x18
+#define BCM59054_GPLDO1CTRL	0x1a
+#define BCM59054_GPLDO2CTRL	0x1b
+#define BCM59054_GPLDO3CTRL	0x1c
+#define BCM59054_TCXLDOCTRL	0x1d
+#define BCM59054_LVLDO1CTRL	0x1e
+#define BCM59054_LVLDO2CTRL	0x1f
+#define BCM59054_OTG_CTRL	0x40
+#define BCM59054_GPLDO1PMCTRL1	0x57
+#define BCM59054_GPLDO2PMCTRL1	0x59
+#define BCM59054_GPLDO3PMCTRL1	0x5b
+#define BCM59054_TCXLDOPMCTRL1	0x5d
+
+/*
+ * RFLDO to VSR regulators are
+ * accessed via I2C slave 0
+ */
+
+/* LDO regulator IDs */
+#define BCM59054_REG_RFLDO	0
+#define BCM59054_REG_CAMLDO1	1
+#define BCM59054_REG_CAMLDO2	2
+#define BCM59054_REG_SIMLDO1	3
+#define BCM59054_REG_SIMLDO2	4
+#define BCM59054_REG_SDLDO	5
+#define BCM59054_REG_SDXLDO	6
+#define BCM59054_REG_MMCLDO1	7
+#define BCM59054_REG_MMCLDO2	8
+#define BCM59054_REG_AUDLDO	9
+#define BCM59054_REG_MICLDO	10
+#define BCM59054_REG_USBLDO	11
+#define BCM59054_REG_VIBLDO	12
+
+/* DCDC regulator IDs */
+#define BCM59054_REG_CSR	13
+#define BCM59054_REG_IOSR1	14
+#define BCM59054_REG_IOSR2	15
+#define BCM59054_REG_MMSR	16
+#define BCM59054_REG_SDSR1	17
+#define BCM59054_REG_SDSR2	18
+#define BCM59054_REG_VSR	19
+
+/*
+ * GPLDO1 to VBUS regulators are
+ * accessed via I2C slave 1
+ */
+
+#define BCM59054_REG_GPLDO1	20
+#define BCM59054_REG_GPLDO2	21
+#define BCM59054_REG_GPLDO3	22
+#define BCM59054_REG_TCXLDO	23
+#define BCM59054_REG_LVLDO1	24
+#define BCM59054_REG_LVLDO2	25
+#define BCM59054_REG_VBUS	26
+
+#define BCM59054_NUM_REGS	27
+
+/* LDO group 1: supported voltages in microvolts */
+static const unsigned int bcm59054_ldo_1_table[] = {
+	1200000, 1800000, 2500000, 2700000, 2800000,
+	2900000, 3000000, 3300000,
 };
 
-static int bcm590xx_get_vsel_register(int id)
-{
-	if (BCM590XX_REG_IS_LDO(id))
-		return BCM590XX_RFLDOCTRL + id;
-	else if (BCM590XX_REG_IS_GPLDO(id))
-		return BCM590XX_GPLDO1CTRL + id;
-	else
-		return BCM590XX_CSRVOUT1 + (id - BCM590XX_REG_CSR) * 3;
-}
+/* LDO group 2: supported voltages in microvolts */
+static const unsigned int bcm59054_ldo_2_table[] = {
+	3100000, 1800000, 2500000, 2700000, 2800000,
+	2900000, 3000000, 3300000,
+};
 
-static int bcm590xx_get_enable_register(int id)
-{
-	int reg = 0;
-
-	if (BCM590XX_REG_IS_LDO(id))
-		reg = BCM590XX_RFLDOPMCTRL1 + id * 2;
-	else if (BCM590XX_REG_IS_GPLDO(id))
-		reg = BCM590XX_GPLDO1PMCTRL1 + id * 2;
-	else
-		switch (id) {
-		case BCM590XX_REG_CSR:
-			reg = BCM590XX_CSRPMCTRL1;
-			break;
-		case BCM590XX_REG_IOSR1:
-			reg = BCM590XX_IOSR1PMCTRL1;
-			break;
-		case BCM590XX_REG_IOSR2:
-			reg = BCM590XX_IOSR2PMCTRL1;
-			break;
-		case BCM590XX_REG_MSR:
-			reg = BCM590XX_MSRPMCTRL1;
-			break;
-		case BCM590XX_REG_SDSR1:
-			reg = BCM590XX_SDSR1PMCTRL1;
-			break;
-		case BCM590XX_REG_SDSR2:
-			reg = BCM590XX_SDSR2PMCTRL1;
-			break;
-		case BCM590XX_REG_VSR:
-			reg = BCM590XX_VSRPMCTRL1;
-			break;
-		case BCM590XX_REG_VBUS:
-			reg = BCM590XX_OTG_CTRL;
-			break;
-		}
+/* LDO group 3: supported voltages in microvolts */
+static const unsigned int bcm59054_ldo_3_table[] = {
+	1000000, 1107000, 1143000, 1214000, 1250000,
+	1464000, 1500000, 1786000,
+};
 
+/* DCDC group SR: supported voltages in microvolts */
+static const struct linear_range bcm59054_dcdc_sr_ranges[] = {
+	REGULATOR_LINEAR_RANGE(0, 0, 1, 0),
+	REGULATOR_LINEAR_RANGE(860000, 2, 60, 10000),
+	REGULATOR_LINEAR_RANGE(1500000, 61, 61, 0),
+	REGULATOR_LINEAR_RANGE(1800000, 62, 62, 0),
+	REGULATOR_LINEAR_RANGE(900000, 63, 63, 0),
+};
 
-	return reg;
-}
+/* DCDC group VSR (BCM59054A1): supported voltages in microvolts */
+static const struct linear_range bcm59054_dcdc_vsr_a1_ranges[] = {
+	REGULATOR_LINEAR_RANGE(0, 0, 1, 0),
+	REGULATOR_LINEAR_RANGE(860000, 2, 59, 10000),
+	REGULATOR_LINEAR_RANGE(1700000, 60, 60, 0),
+	REGULATOR_LINEAR_RANGE(1500000, 61, 61, 0),
+	REGULATOR_LINEAR_RANGE(1800000, 62, 62, 0),
+	REGULATOR_LINEAR_RANGE(1600000, 63, 63, 0),
+};
 
-static const struct regulator_ops bcm590xx_ops_ldo = {
-	.is_enabled		= regulator_is_enabled_regmap,
-	.enable			= regulator_enable_regmap,
-	.disable		= regulator_disable_regmap,
-	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
-	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
-	.list_voltage		= regulator_list_voltage_table,
-	.map_voltage		= regulator_map_voltage_iterate,
+/* DCDC group CSR: supported voltages in microvolts */
+static const struct linear_range bcm59054_dcdc_csr_ranges[] = {
+	REGULATOR_LINEAR_RANGE(700000, 0, 1, 100000),
+	REGULATOR_LINEAR_RANGE(860000, 2, 60, 10000),
+	REGULATOR_LINEAR_RANGE(900000, 61, 63, 0),
 };
 
-static const struct regulator_ops bcm590xx_ops_dcdc = {
-	.is_enabled		= regulator_is_enabled_regmap,
-	.enable			= regulator_enable_regmap,
-	.disable		= regulator_disable_regmap,
-	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
-	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
-	.list_voltage		= regulator_list_voltage_linear_range,
-	.map_voltage		= regulator_map_voltage_linear_range,
+static const struct bcm590xx_reg_data bcm59054_regs[BCM59054_NUM_REGS] = {
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(RFLDO, rfldo, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(CAMLDO1, camldo1, ldo_2_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(CAMLDO2, camldo2, ldo_2_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(SIMLDO1, simldo1, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(SIMLDO2, simldo2, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(SDLDO, sdldo, ldo_2_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(SDXLDO, sdxldo, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(MMCLDO1, mmcldo1, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(MMCLDO2, mmcldo2, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(AUDLDO, audldo, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_REG_DESC(MICLDO, micldo),
+			.ops = &bcm590xx_ops_ldo_novolt,
+			/* MICLDO is locked at 1.8V */
+			.n_voltages = 1,
+			.fixed_uV = 1800000,
+			.enable_reg = BCM59054_MICLDOPMCTRL1,
+			.enable_mask = BCM590XX_REG_ENABLE,
+			.enable_is_inverted = true,
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(USBLDO, usbldo, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(VIBLDO, vibldo, ldo_2_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(CSR, csr, dcdc_csr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(IOSR1, iosr1, dcdc_sr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(IOSR2, iosr2, dcdc_sr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(MMSR, mmsr, dcdc_sr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(SDSR1, sdsr1, dcdc_sr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(SDSR2, sdsr2, dcdc_sr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(VSR, vsr, dcdc_sr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_LDO_DESC(GPLDO1, gpldo1, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_LDO_DESC(GPLDO2, gpldo2, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_LDO_DESC(GPLDO3, gpldo3, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_LDO_DESC(TCXLDO, tcxldo, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_LDO_DESC(LVLDO1, lvldo1, ldo_3_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_LDO_DESC(LVLDO2, lvldo2, ldo_3_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_VBUS,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_REG_DESC(VBUS, vbus),
+			.ops = &bcm590xx_ops_vbus,
+			.n_voltages = 1,
+			.fixed_uV = 5000000,
+			.enable_reg = BCM59054_OTG_CTRL,
+			.enable_mask = BCM590XX_VBUS_ENABLE,
+		},
+	},
 };
 
-static const struct regulator_ops bcm590xx_ops_vbus = {
-	.is_enabled		= regulator_is_enabled_regmap,
-	.enable			= regulator_enable_regmap,
-	.disable		= regulator_disable_regmap,
+/*
+ * BCM59054A1 regulators; same as previous revision, but with different
+ * VSR voltage table.
+ */
+static const struct bcm590xx_reg_data bcm59054_a1_regs[BCM59054_NUM_REGS] = {
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(RFLDO, rfldo, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(CAMLDO1, camldo1, ldo_2_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(CAMLDO2, camldo2, ldo_2_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(SIMLDO1, simldo1, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(SIMLDO2, simldo2, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(SDLDO, sdldo, ldo_2_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(SDXLDO, sdxldo, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(MMCLDO1, mmcldo1, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(MMCLDO2, mmcldo2, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(AUDLDO, audldo, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_REG_DESC(MICLDO, micldo),
+			.ops = &bcm590xx_ops_ldo_novolt,
+			/* MICLDO is locked at 1.8V */
+			.n_voltages = 1,
+			.fixed_uV = 1800000,
+			.enable_reg = BCM59054_MICLDOPMCTRL1,
+			.enable_mask = BCM590XX_REG_ENABLE,
+			.enable_is_inverted = true,
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(USBLDO, usbldo, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_LDO,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_LDO_DESC(VIBLDO, vibldo, ldo_2_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(CSR, csr, dcdc_csr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(IOSR1, iosr1, dcdc_sr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(IOSR2, iosr2, dcdc_sr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(MMSR, mmsr, dcdc_sr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(SDSR1, sdsr1, dcdc_sr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(SDSR2, sdsr2, dcdc_sr_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_SR,
+		.regmap = BCM590XX_REGMAP_PRI,
+		.desc = {
+			BCM59054_SR_DESC(VSR, vsr, dcdc_vsr_a1_ranges),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_LDO_DESC(GPLDO1, gpldo1, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_LDO_DESC(GPLDO2, gpldo2, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_LDO_DESC(GPLDO3, gpldo3, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_LDO_DESC(TCXLDO, tcxldo, ldo_1_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_LDO_DESC(LVLDO1, lvldo1, ldo_3_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_GPLDO,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_LDO_DESC(LVLDO2, lvldo2, ldo_3_table),
+		},
+	},
+
+	{
+		.type = BCM590XX_REG_TYPE_VBUS,
+		.regmap = BCM590XX_REGMAP_SEC,
+		.desc = {
+			BCM59054_REG_DESC(VBUS, vbus),
+			.ops = &bcm590xx_ops_vbus,
+			.n_voltages = 1,
+			.fixed_uV = 5000000,
+			.enable_reg = BCM59054_OTG_CTRL,
+			.enable_mask = BCM590XX_VBUS_ENABLE,
+		},
+	},
 };
 
 static int bcm590xx_probe(struct platform_device *pdev)
 {
 	struct bcm590xx *bcm590xx = dev_get_drvdata(pdev->dev.parent);
 	struct bcm590xx_reg *pmu;
+	const struct bcm590xx_reg_data *info;
 	struct regulator_config config = { };
-	struct bcm590xx_info *info;
 	struct regulator_dev *rdev;
-	int i;
+	unsigned int i;
 
 	pmu = devm_kzalloc(&pdev->dev, sizeof(*pmu), GFP_KERNEL);
 	if (!pmu)
@@ -287,65 +1110,53 @@ static int bcm590xx_probe(struct platform_device *pdev)
 
 	pmu->mfd = bcm590xx;
 
-	platform_set_drvdata(pdev, pmu);
-
-	pmu->desc = devm_kcalloc(&pdev->dev,
-				 BCM590XX_NUM_REGS,
-				 sizeof(struct regulator_desc),
-				 GFP_KERNEL);
-	if (!pmu->desc)
-		return -ENOMEM;
+	switch (pmu->mfd->pmu_id) {
+	case BCM590XX_PMUID_BCM59054:
+		pmu->n_regulators = BCM59054_NUM_REGS;
+		if (pmu->mfd->rev_analog == BCM59054_REV_ANALOG_A1)
+			pmu->regs = bcm59054_a1_regs;
+		else
+			pmu->regs = bcm59054_regs;
+		break;
+	case BCM590XX_PMUID_BCM59056:
+		pmu->n_regulators = BCM59056_NUM_REGS;
+		pmu->regs = bcm59056_regs;
+		break;
+	default:
+		dev_err(bcm590xx->dev,
+			"unknown device type, could not initialize\n");
+		return -EINVAL;
+	}
 
-	info = bcm590xx_regs;
-
-	for (i = 0; i < BCM590XX_NUM_REGS; i++, info++) {
-		/* Register the regulators */
-		pmu->desc[i].name = info->name;
-		pmu->desc[i].of_match = of_match_ptr(info->name);
-		pmu->desc[i].regulators_node = of_match_ptr("regulators");
-		pmu->desc[i].supply_name = info->vin_name;
-		pmu->desc[i].id = i;
-		pmu->desc[i].volt_table = info->volt_table;
-		pmu->desc[i].n_voltages = info->n_voltages;
-		pmu->desc[i].linear_ranges = info->linear_ranges;
-		pmu->desc[i].n_linear_ranges = info->n_linear_ranges;
-
-		if ((BCM590XX_REG_IS_LDO(i)) || (BCM590XX_REG_IS_GPLDO(i))) {
-			pmu->desc[i].ops = &bcm590xx_ops_ldo;
-			pmu->desc[i].vsel_mask = BCM590XX_LDO_VSEL_MASK;
-		} else if (BCM590XX_REG_IS_VBUS(i))
-			pmu->desc[i].ops = &bcm590xx_ops_vbus;
-		else {
-			pmu->desc[i].ops = &bcm590xx_ops_dcdc;
-			pmu->desc[i].vsel_mask = BCM590XX_SR_VSEL_MASK;
-		}
+	platform_set_drvdata(pdev, pmu);
 
-		if (BCM590XX_REG_IS_VBUS(i))
-			pmu->desc[i].enable_mask = BCM590XX_VBUS_ENABLE;
-		else {
-			pmu->desc[i].vsel_reg = bcm590xx_get_vsel_register(i);
-			pmu->desc[i].enable_is_inverted = true;
-			pmu->desc[i].enable_mask = BCM590XX_REG_ENABLE;
-		}
-		pmu->desc[i].enable_reg = bcm590xx_get_enable_register(i);
-		pmu->desc[i].type = REGULATOR_VOLTAGE;
-		pmu->desc[i].owner = THIS_MODULE;
+	/* Register the regulators */
+	for (i = 0; i < pmu->n_regulators; i++) {
+		info = &pmu->regs[i];
 
 		config.dev = bcm590xx->dev;
 		config.driver_data = pmu;
-		if (BCM590XX_REG_IS_GPLDO(i) || BCM590XX_REG_IS_VBUS(i))
-			config.regmap = bcm590xx->regmap_sec;
-		else
-			config.regmap = bcm590xx->regmap_pri;
 
-		rdev = devm_regulator_register(&pdev->dev, &pmu->desc[i],
-					       &config);
-		if (IS_ERR(rdev)) {
+		switch (info->regmap) {
+		case BCM590XX_REGMAP_PRI:
+			config.regmap = bcm590xx->regmap_pri;
+			break;
+		case BCM590XX_REGMAP_SEC:
+			config.regmap = bcm590xx->regmap_sec;
+			break;
+		default:
 			dev_err(bcm590xx->dev,
-				"failed to register %s regulator\n",
+				"invalid regmap for %s regulator; this is a driver bug\n",
 				pdev->name);
-			return PTR_ERR(rdev);
+			return -EINVAL;
 		}
+
+		rdev = devm_regulator_register(&pdev->dev, &info->desc,
+					       &config);
+		if (IS_ERR(rdev))
+			return dev_err_probe(bcm590xx->dev, PTR_ERR(rdev),
+					     "failed to register %s regulator\n",
+					     pdev->name);
 	}
 
 	return 0;
diff --git a/drivers/regulator/bd96801-regulator.c b/drivers/regulator/bd96801-regulator.c
index 3a9d772491a8..24d21172298b 100644
--- a/drivers/regulator/bd96801-regulator.c
+++ b/drivers/regulator/bd96801-regulator.c
@@ -83,6 +83,7 @@ enum {
 #define BD96801_LDO6_VSEL_REG		0x26
 #define BD96801_LDO7_VSEL_REG		0x27
 #define BD96801_BUCK_VSEL_MASK		0x1F
+#define BD96805_BUCK_VSEL_MASK		0x3f
 #define BD96801_LDO_VSEL_MASK		0xff
 
 #define BD96801_MASK_RAMP_DELAY		0xc0
@@ -90,6 +91,7 @@ enum {
 #define BD96801_BUCK_INT_VOUT_MASK	0xff
 
 #define BD96801_BUCK_VOLTS		256
+#define BD96805_BUCK_VOLTS		64
 #define BD96801_LDO_VOLTS		256
 
 #define BD96801_OVP_MASK		0x03
@@ -160,6 +162,30 @@ static const struct linear_range bd96801_buck_init_volts[] = {
 	REGULATOR_LINEAR_RANGE(3300000 - 150000, 0xed, 0xff, 0),
 };
 
+/* BD96802 uses same voltage ranges for bucks as BD96801 */
+#define bd96802_tune_volts bd96801_tune_volts
+#define bd96802_buck_init_volts bd96801_buck_init_volts
+
+/*
+ * On BD96805 we have similar "negative tuning range" as on BD96801, except
+ * that the max tuning is -310 ... +310 mV (instead of the 150mV). We use same
+ * approach as with the BD96801 ranges.
+ */
+static const struct linear_range bd96805_tune_volts[] = {
+	REGULATOR_LINEAR_RANGE(310000, 0x00, 0x1F, 10000),
+	REGULATOR_LINEAR_RANGE(0, 0x20, 0x3F, 10000),
+};
+
+static const struct linear_range bd96805_buck_init_volts[] = {
+	REGULATOR_LINEAR_RANGE(500000 - 310000, 0x00, 0xc8, 5000),
+	REGULATOR_LINEAR_RANGE(1550000 - 310000, 0xc9, 0xec, 50000),
+	REGULATOR_LINEAR_RANGE(3300000 - 310000, 0xed, 0xff, 0),
+};
+
+/* BD96806 uses same voltage ranges for bucks as BD96805 */
+#define bd96806_tune_volts bd96805_tune_volts
+#define bd96806_buck_init_volts bd96805_buck_init_volts
+
 static const struct linear_range bd96801_ldo_int_volts[] = {
 	REGULATOR_LINEAR_RANGE(300000, 0x00, 0x78, 25000),
 	REGULATOR_LINEAR_RANGE(3300000, 0x79, 0xff, 0),
@@ -198,89 +224,89 @@ struct bd96801_irqinfo {
 
 static const struct bd96801_irqinfo buck1_irqinfo[] = {
 	BD96801_IRQINFO(BD96801_PROT_OCP, "buck1-over-curr-h", 500,
-			"bd96801-buck1-overcurr-h"),
+			"buck1-overcurr-h"),
 	BD96801_IRQINFO(BD96801_PROT_OCP, "buck1-over-curr-l", 500,
-			"bd96801-buck1-overcurr-l"),
+			"buck1-overcurr-l"),
 	BD96801_IRQINFO(BD96801_PROT_OCP, "buck1-over-curr-n", 500,
-			"bd96801-buck1-overcurr-n"),
+			"buck1-overcurr-n"),
 	BD96801_IRQINFO(BD96801_PROT_OVP, "buck1-over-voltage", 500,
-			"bd96801-buck1-overvolt"),
+			"buck1-overvolt"),
 	BD96801_IRQINFO(BD96801_PROT_UVP, "buck1-under-voltage", 500,
-			"bd96801-buck1-undervolt"),
+			"buck1-undervolt"),
 	BD96801_IRQINFO(BD96801_PROT_TEMP, "buck1-over-temp", 500,
-			"bd96801-buck1-thermal")
+			"buck1-thermal")
 };
 
 static const struct bd96801_irqinfo buck2_irqinfo[] = {
 	BD96801_IRQINFO(BD96801_PROT_OCP, "buck2-over-curr-h", 500,
-			"bd96801-buck2-overcurr-h"),
+			"buck2-overcurr-h"),
 	BD96801_IRQINFO(BD96801_PROT_OCP, "buck2-over-curr-l", 500,
-			"bd96801-buck2-overcurr-l"),
+			"buck2-overcurr-l"),
 	BD96801_IRQINFO(BD96801_PROT_OCP, "buck2-over-curr-n", 500,
-			"bd96801-buck2-overcurr-n"),
+			"buck2-overcurr-n"),
 	BD96801_IRQINFO(BD96801_PROT_OVP, "buck2-over-voltage", 500,
-			"bd96801-buck2-overvolt"),
+			"buck2-overvolt"),
 	BD96801_IRQINFO(BD96801_PROT_UVP, "buck2-under-voltage", 500,
-			"bd96801-buck2-undervolt"),
+			"buck2-undervolt"),
 	BD96801_IRQINFO(BD96801_PROT_TEMP, "buck2-over-temp", 500,
-			"bd96801-buck2-thermal")
+			"buck2-thermal")
 };
 
 static const struct bd96801_irqinfo buck3_irqinfo[] = {
 	BD96801_IRQINFO(BD96801_PROT_OCP, "buck3-over-curr-h", 500,
-			"bd96801-buck3-overcurr-h"),
+			"buck3-overcurr-h"),
 	BD96801_IRQINFO(BD96801_PROT_OCP, "buck3-over-curr-l", 500,
-			"bd96801-buck3-overcurr-l"),
+			"buck3-overcurr-l"),
 	BD96801_IRQINFO(BD96801_PROT_OCP, "buck3-over-curr-n", 500,
-			"bd96801-buck3-overcurr-n"),
+			"buck3-overcurr-n"),
 	BD96801_IRQINFO(BD96801_PROT_OVP, "buck3-over-voltage", 500,
-			"bd96801-buck3-overvolt"),
+			"buck3-overvolt"),
 	BD96801_IRQINFO(BD96801_PROT_UVP, "buck3-under-voltage", 500,
-			"bd96801-buck3-undervolt"),
+			"buck3-undervolt"),
 	BD96801_IRQINFO(BD96801_PROT_TEMP, "buck3-over-temp", 500,
-			"bd96801-buck3-thermal")
+			"buck3-thermal")
 };
 
 static const struct bd96801_irqinfo buck4_irqinfo[] = {
 	BD96801_IRQINFO(BD96801_PROT_OCP, "buck4-over-curr-h", 500,
-			"bd96801-buck4-overcurr-h"),
+			"buck4-overcurr-h"),
 	BD96801_IRQINFO(BD96801_PROT_OCP, "buck4-over-curr-l", 500,
-			"bd96801-buck4-overcurr-l"),
+			"buck4-overcurr-l"),
 	BD96801_IRQINFO(BD96801_PROT_OCP, "buck4-over-curr-n", 500,
-			"bd96801-buck4-overcurr-n"),
+			"buck4-overcurr-n"),
 	BD96801_IRQINFO(BD96801_PROT_OVP, "buck4-over-voltage", 500,
-			"bd96801-buck4-overvolt"),
+			"buck4-overvolt"),
 	BD96801_IRQINFO(BD96801_PROT_UVP, "buck4-under-voltage", 500,
-			"bd96801-buck4-undervolt"),
+			"buck4-undervolt"),
 	BD96801_IRQINFO(BD96801_PROT_TEMP, "buck4-over-temp", 500,
-			"bd96801-buck4-thermal")
+			"buck4-thermal")
 };
 
 static const struct bd96801_irqinfo ldo5_irqinfo[] = {
 	BD96801_IRQINFO(BD96801_PROT_OCP, "ldo5-overcurr", 500,
-			"bd96801-ldo5-overcurr"),
+			"ldo5-overcurr"),
 	BD96801_IRQINFO(BD96801_PROT_OVP, "ldo5-over-voltage", 500,
-			"bd96801-ldo5-overvolt"),
+			"ldo5-overvolt"),
 	BD96801_IRQINFO(BD96801_PROT_UVP, "ldo5-under-voltage", 500,
-			"bd96801-ldo5-undervolt"),
+			"ldo5-undervolt"),
 };
 
 static const struct bd96801_irqinfo ldo6_irqinfo[] = {
 	BD96801_IRQINFO(BD96801_PROT_OCP, "ldo6-overcurr", 500,
-			"bd96801-ldo6-overcurr"),
+			"ldo6-overcurr"),
 	BD96801_IRQINFO(BD96801_PROT_OVP, "ldo6-over-voltage", 500,
-			"bd96801-ldo6-overvolt"),
+			"ldo6-overvolt"),
 	BD96801_IRQINFO(BD96801_PROT_UVP, "ldo6-under-voltage", 500,
-			"bd96801-ldo6-undervolt"),
+			"ldo6-undervolt"),
 };
 
 static const struct bd96801_irqinfo ldo7_irqinfo[] = {
 	BD96801_IRQINFO(BD96801_PROT_OCP, "ldo7-overcurr", 500,
-			"bd96801-ldo7-overcurr"),
+			"ldo7-overcurr"),
 	BD96801_IRQINFO(BD96801_PROT_OVP, "ldo7-over-voltage", 500,
-			"bd96801-ldo7-overvolt"),
+			"ldo7-overvolt"),
 	BD96801_IRQINFO(BD96801_PROT_UVP, "ldo7-under-voltage", 500,
-			"bd96801-ldo7-undervolt"),
+			"ldo7-undervolt"),
 };
 
 struct bd96801_irq_desc {
@@ -302,6 +328,7 @@ struct bd96801_pmic_data {
 	struct bd96801_regulator_data regulator_data[BD96801_NUM_REGULATORS];
 	struct regmap *regmap;
 	int fatal_ind;
+	int num_regulators;
 };
 
 static int ldo_map_notif(int irq, struct regulator_irq_data *rid,
@@ -503,6 +530,70 @@ static int bd96801_walk_regulator_dt(struct device *dev, struct regmap *regmap,
  * case later. What we can easly do for preparing is to not use static global
  * data for regulators though.
  */
+static const struct bd96801_pmic_data bd96802_data = {
+	.regulator_data = {
+	{
+		.desc = {
+			.name = "buck1",
+			.of_match = of_match_ptr("buck1"),
+			.regulators_node = of_match_ptr("regulators"),
+			.id = BD96801_BUCK1,
+			.ops = &bd96801_buck_ops,
+			.type = REGULATOR_VOLTAGE,
+			.linear_ranges = bd96802_tune_volts,
+			.n_linear_ranges = ARRAY_SIZE(bd96802_tune_volts),
+			.n_voltages = BD96801_BUCK_VOLTS,
+			.enable_reg = BD96801_REG_ENABLE,
+			.enable_mask = BD96801_BUCK1_EN_MASK,
+			.enable_is_inverted = true,
+			.vsel_reg = BD96801_BUCK1_VSEL_REG,
+			.vsel_mask = BD96801_BUCK_VSEL_MASK,
+			.ramp_reg = BD96801_BUCK1_VSEL_REG,
+			.ramp_mask = BD96801_MASK_RAMP_DELAY,
+			.ramp_delay_table = &buck_ramp_table[0],
+			.n_ramp_values = ARRAY_SIZE(buck_ramp_table),
+			.owner = THIS_MODULE,
+		},
+		.init_ranges = bd96802_buck_init_volts,
+		.num_ranges = ARRAY_SIZE(bd96802_buck_init_volts),
+		.irq_desc = {
+			.irqinfo = (struct bd96801_irqinfo *)&buck1_irqinfo[0],
+			.num_irqs = ARRAY_SIZE(buck1_irqinfo),
+		},
+	},
+	{
+		.desc = {
+			.name = "buck2",
+			.of_match = of_match_ptr("buck2"),
+			.regulators_node = of_match_ptr("regulators"),
+			.id = BD96801_BUCK2,
+			.ops = &bd96801_buck_ops,
+			.type = REGULATOR_VOLTAGE,
+			.linear_ranges = bd96802_tune_volts,
+			.n_linear_ranges = ARRAY_SIZE(bd96802_tune_volts),
+			.n_voltages = BD96801_BUCK_VOLTS,
+			.enable_reg = BD96801_REG_ENABLE,
+			.enable_mask = BD96801_BUCK2_EN_MASK,
+			.enable_is_inverted = true,
+			.vsel_reg = BD96801_BUCK2_VSEL_REG,
+			.vsel_mask = BD96801_BUCK_VSEL_MASK,
+			.ramp_reg = BD96801_BUCK2_VSEL_REG,
+			.ramp_mask = BD96801_MASK_RAMP_DELAY,
+			.ramp_delay_table = &buck_ramp_table[0],
+			.n_ramp_values = ARRAY_SIZE(buck_ramp_table),
+			.owner = THIS_MODULE,
+		},
+		.irq_desc = {
+			.irqinfo = (struct bd96801_irqinfo *)&buck2_irqinfo[0],
+			.num_irqs = ARRAY_SIZE(buck2_irqinfo),
+		},
+		.init_ranges = bd96802_buck_init_volts,
+		.num_ranges = ARRAY_SIZE(bd96802_buck_init_volts),
+	},
+	},
+	.num_regulators = 2,
+};
+
 static const struct bd96801_pmic_data bd96801_data = {
 	.regulator_data = {
 	{
@@ -688,11 +779,265 @@ static const struct bd96801_pmic_data bd96801_data = {
 		.ldo_vol_lvl = BD96801_LDO7_VOL_LVL_REG,
 	},
 	},
+	.num_regulators = 7,
 };
 
-static int initialize_pmic_data(struct device *dev,
+static const struct bd96801_pmic_data bd96805_data = {
+	.regulator_data = {
+	{
+		.desc = {
+			.name = "buck1",
+			.of_match = of_match_ptr("buck1"),
+			.regulators_node = of_match_ptr("regulators"),
+			.id = BD96801_BUCK1,
+			.ops = &bd96801_buck_ops,
+			.type = REGULATOR_VOLTAGE,
+			.linear_ranges = bd96805_tune_volts,
+			.n_linear_ranges = ARRAY_SIZE(bd96805_tune_volts),
+			.n_voltages = BD96805_BUCK_VOLTS,
+			.enable_reg = BD96801_REG_ENABLE,
+			.enable_mask = BD96801_BUCK1_EN_MASK,
+			.enable_is_inverted = true,
+			.vsel_reg = BD96801_BUCK1_VSEL_REG,
+			.vsel_mask = BD96805_BUCK_VSEL_MASK,
+			.ramp_reg = BD96801_BUCK1_VSEL_REG,
+			.ramp_mask = BD96801_MASK_RAMP_DELAY,
+			.ramp_delay_table = &buck_ramp_table[0],
+			.n_ramp_values = ARRAY_SIZE(buck_ramp_table),
+			.owner = THIS_MODULE,
+		},
+		.init_ranges = bd96805_buck_init_volts,
+		.num_ranges = ARRAY_SIZE(bd96805_buck_init_volts),
+		.irq_desc = {
+			.irqinfo = (struct bd96801_irqinfo *)&buck1_irqinfo[0],
+			.num_irqs = ARRAY_SIZE(buck1_irqinfo),
+		},
+	}, {
+		.desc = {
+			.name = "buck2",
+			.of_match = of_match_ptr("buck2"),
+			.regulators_node = of_match_ptr("regulators"),
+			.id = BD96801_BUCK2,
+			.ops = &bd96801_buck_ops,
+			.type = REGULATOR_VOLTAGE,
+			.linear_ranges = bd96805_tune_volts,
+			.n_linear_ranges = ARRAY_SIZE(bd96805_tune_volts),
+			.n_voltages = BD96805_BUCK_VOLTS,
+			.enable_reg = BD96801_REG_ENABLE,
+			.enable_mask = BD96801_BUCK2_EN_MASK,
+			.enable_is_inverted = true,
+			.vsel_reg = BD96801_BUCK2_VSEL_REG,
+			.vsel_mask = BD96805_BUCK_VSEL_MASK,
+			.ramp_reg = BD96801_BUCK2_VSEL_REG,
+			.ramp_mask = BD96801_MASK_RAMP_DELAY,
+			.ramp_delay_table = &buck_ramp_table[0],
+			.n_ramp_values = ARRAY_SIZE(buck_ramp_table),
+			.owner = THIS_MODULE,
+		},
+		.irq_desc = {
+			.irqinfo = (struct bd96801_irqinfo *)&buck2_irqinfo[0],
+			.num_irqs = ARRAY_SIZE(buck2_irqinfo),
+		},
+		.init_ranges = bd96805_buck_init_volts,
+		.num_ranges = ARRAY_SIZE(bd96805_buck_init_volts),
+	}, {
+		.desc = {
+			.name = "buck3",
+			.of_match = of_match_ptr("buck3"),
+			.regulators_node = of_match_ptr("regulators"),
+			.id = BD96801_BUCK3,
+			.ops = &bd96801_buck_ops,
+			.type = REGULATOR_VOLTAGE,
+			.linear_ranges = bd96805_tune_volts,
+			.n_linear_ranges = ARRAY_SIZE(bd96805_tune_volts),
+			.n_voltages = BD96805_BUCK_VOLTS,
+			.enable_reg = BD96801_REG_ENABLE,
+			.enable_mask = BD96801_BUCK3_EN_MASK,
+			.enable_is_inverted = true,
+			.vsel_reg = BD96801_BUCK3_VSEL_REG,
+			.vsel_mask = BD96805_BUCK_VSEL_MASK,
+			.ramp_reg = BD96801_BUCK3_VSEL_REG,
+			.ramp_mask = BD96801_MASK_RAMP_DELAY,
+			.ramp_delay_table = &buck_ramp_table[0],
+			.n_ramp_values = ARRAY_SIZE(buck_ramp_table),
+			.owner = THIS_MODULE,
+		},
+		.irq_desc = {
+			.irqinfo = (struct bd96801_irqinfo *)&buck3_irqinfo[0],
+			.num_irqs = ARRAY_SIZE(buck3_irqinfo),
+		},
+		.init_ranges = bd96805_buck_init_volts,
+		.num_ranges = ARRAY_SIZE(bd96805_buck_init_volts),
+	}, {
+		.desc = {
+			.name = "buck4",
+			.of_match = of_match_ptr("buck4"),
+			.regulators_node = of_match_ptr("regulators"),
+			.id = BD96801_BUCK4,
+			.ops = &bd96801_buck_ops,
+			.type = REGULATOR_VOLTAGE,
+			.linear_ranges = bd96805_tune_volts,
+			.n_linear_ranges = ARRAY_SIZE(bd96805_tune_volts),
+			.n_voltages = BD96805_BUCK_VOLTS,
+			.enable_reg = BD96801_REG_ENABLE,
+			.enable_mask = BD96801_BUCK4_EN_MASK,
+			.enable_is_inverted = true,
+			.vsel_reg = BD96801_BUCK4_VSEL_REG,
+			.vsel_mask = BD96805_BUCK_VSEL_MASK,
+			.ramp_reg = BD96801_BUCK4_VSEL_REG,
+			.ramp_mask = BD96801_MASK_RAMP_DELAY,
+			.ramp_delay_table = &buck_ramp_table[0],
+			.n_ramp_values = ARRAY_SIZE(buck_ramp_table),
+			.owner = THIS_MODULE,
+		},
+		.irq_desc = {
+			.irqinfo = (struct bd96801_irqinfo *)&buck4_irqinfo[0],
+			.num_irqs = ARRAY_SIZE(buck4_irqinfo),
+		},
+		.init_ranges = bd96805_buck_init_volts,
+		.num_ranges = ARRAY_SIZE(bd96805_buck_init_volts),
+	}, {
+		.desc = {
+			.name = "ldo5",
+			.of_match = of_match_ptr("ldo5"),
+			.regulators_node = of_match_ptr("regulators"),
+			.id = BD96801_LDO5,
+			.ops = &bd96801_ldo_ops,
+			.type = REGULATOR_VOLTAGE,
+			.linear_ranges = bd96801_ldo_int_volts,
+			.n_linear_ranges = ARRAY_SIZE(bd96801_ldo_int_volts),
+			.n_voltages = BD96801_LDO_VOLTS,
+			.enable_reg = BD96801_REG_ENABLE,
+			.enable_mask = BD96801_LDO5_EN_MASK,
+			.enable_is_inverted = true,
+			.vsel_reg = BD96801_LDO5_VSEL_REG,
+			.vsel_mask = BD96801_LDO_VSEL_MASK,
+			.owner = THIS_MODULE,
+		},
+		.irq_desc = {
+			.irqinfo = (struct bd96801_irqinfo *)&ldo5_irqinfo[0],
+			.num_irqs = ARRAY_SIZE(ldo5_irqinfo),
+		},
+		.ldo_vol_lvl = BD96801_LDO5_VOL_LVL_REG,
+	}, {
+		.desc = {
+			.name = "ldo6",
+			.of_match = of_match_ptr("ldo6"),
+			.regulators_node = of_match_ptr("regulators"),
+			.id = BD96801_LDO6,
+			.ops = &bd96801_ldo_ops,
+			.type = REGULATOR_VOLTAGE,
+			.linear_ranges = bd96801_ldo_int_volts,
+			.n_linear_ranges = ARRAY_SIZE(bd96801_ldo_int_volts),
+			.n_voltages = BD96801_LDO_VOLTS,
+			.enable_reg = BD96801_REG_ENABLE,
+			.enable_mask = BD96801_LDO6_EN_MASK,
+			.enable_is_inverted = true,
+			.vsel_reg = BD96801_LDO6_VSEL_REG,
+			.vsel_mask = BD96801_LDO_VSEL_MASK,
+			.owner = THIS_MODULE,
+		},
+		.irq_desc = {
+			.irqinfo = (struct bd96801_irqinfo *)&ldo6_irqinfo[0],
+			.num_irqs = ARRAY_SIZE(ldo6_irqinfo),
+		},
+		.ldo_vol_lvl = BD96801_LDO6_VOL_LVL_REG,
+	}, {
+		.desc = {
+			.name = "ldo7",
+			.of_match = of_match_ptr("ldo7"),
+			.regulators_node = of_match_ptr("regulators"),
+			.id = BD96801_LDO7,
+			.ops = &bd96801_ldo_ops,
+			.type = REGULATOR_VOLTAGE,
+			.linear_ranges = bd96801_ldo_int_volts,
+			.n_linear_ranges = ARRAY_SIZE(bd96801_ldo_int_volts),
+			.n_voltages = BD96801_LDO_VOLTS,
+			.enable_reg = BD96801_REG_ENABLE,
+			.enable_mask = BD96801_LDO7_EN_MASK,
+			.enable_is_inverted = true,
+			.vsel_reg = BD96801_LDO7_VSEL_REG,
+			.vsel_mask = BD96801_LDO_VSEL_MASK,
+			.owner = THIS_MODULE,
+		},
+		.irq_desc = {
+			.irqinfo = (struct bd96801_irqinfo *)&ldo7_irqinfo[0],
+			.num_irqs = ARRAY_SIZE(ldo7_irqinfo),
+		},
+		.ldo_vol_lvl = BD96801_LDO7_VOL_LVL_REG,
+	},
+	},
+	.num_regulators = 7,
+};
+
+static const struct bd96801_pmic_data bd96806_data = {
+	.regulator_data = {
+	{
+		.desc = {
+			.name = "buck1",
+			.of_match = of_match_ptr("buck1"),
+			.regulators_node = of_match_ptr("regulators"),
+			.id = BD96801_BUCK1,
+			.ops = &bd96801_buck_ops,
+			.type = REGULATOR_VOLTAGE,
+			.linear_ranges = bd96806_tune_volts,
+			.n_linear_ranges = ARRAY_SIZE(bd96806_tune_volts),
+			.n_voltages = BD96805_BUCK_VOLTS,
+			.enable_reg = BD96801_REG_ENABLE,
+			.enable_mask = BD96801_BUCK1_EN_MASK,
+			.enable_is_inverted = true,
+			.vsel_reg = BD96801_BUCK1_VSEL_REG,
+			.vsel_mask = BD96805_BUCK_VSEL_MASK,
+			.ramp_reg = BD96801_BUCK1_VSEL_REG,
+			.ramp_mask = BD96801_MASK_RAMP_DELAY,
+			.ramp_delay_table = &buck_ramp_table[0],
+			.n_ramp_values = ARRAY_SIZE(buck_ramp_table),
+			.owner = THIS_MODULE,
+		},
+		.init_ranges = bd96806_buck_init_volts,
+		.num_ranges = ARRAY_SIZE(bd96806_buck_init_volts),
+		.irq_desc = {
+			.irqinfo = (struct bd96801_irqinfo *)&buck1_irqinfo[0],
+			.num_irqs = ARRAY_SIZE(buck1_irqinfo),
+		},
+	},
+	{
+		.desc = {
+			.name = "buck2",
+			.of_match = of_match_ptr("buck2"),
+			.regulators_node = of_match_ptr("regulators"),
+			.id = BD96801_BUCK2,
+			.ops = &bd96801_buck_ops,
+			.type = REGULATOR_VOLTAGE,
+			.linear_ranges = bd96806_tune_volts,
+			.n_linear_ranges = ARRAY_SIZE(bd96806_tune_volts),
+			.n_voltages = BD96805_BUCK_VOLTS,
+			.enable_reg = BD96801_REG_ENABLE,
+			.enable_mask = BD96801_BUCK2_EN_MASK,
+			.enable_is_inverted = true,
+			.vsel_reg = BD96801_BUCK2_VSEL_REG,
+			.vsel_mask = BD96805_BUCK_VSEL_MASK,
+			.ramp_reg = BD96801_BUCK2_VSEL_REG,
+			.ramp_mask = BD96801_MASK_RAMP_DELAY,
+			.ramp_delay_table = &buck_ramp_table[0],
+			.n_ramp_values = ARRAY_SIZE(buck_ramp_table),
+			.owner = THIS_MODULE,
+		},
+		.irq_desc = {
+			.irqinfo = (struct bd96801_irqinfo *)&buck2_irqinfo[0],
+			.num_irqs = ARRAY_SIZE(buck2_irqinfo),
+		},
+		.init_ranges = bd96806_buck_init_volts,
+		.num_ranges = ARRAY_SIZE(bd96806_buck_init_volts),
+	},
+	},
+	.num_regulators = 2,
+};
+
+static int initialize_pmic_data(struct platform_device *pdev,
 				struct bd96801_pmic_data *pdata)
 {
+	struct device *dev = &pdev->dev;
 	int r, i;
 
 	/*
@@ -700,7 +1045,7 @@ static int initialize_pmic_data(struct device *dev,
 	 * wish to modify IRQ information independently for each driver
 	 * instance.
 	 */
-	for (r = 0; r < BD96801_NUM_REGULATORS; r++) {
+	for (r = 0; r < pdata->num_regulators; r++) {
 		const struct bd96801_irqinfo *template;
 		struct bd96801_irqinfo *new;
 		int num_infos;
@@ -741,8 +1086,7 @@ static int bd96801_rdev_errb_irqs(struct platform_device *pdev,
 	int i;
 	void *retp;
 	static const char * const single_out_errb_irqs[] = {
-		"bd96801-%s-pvin-err", "bd96801-%s-ovp-err",
-		"bd96801-%s-uvp-err", "bd96801-%s-shdn-err",
+		"%s-pvin-err", "%s-ovp-err", "%s-uvp-err", "%s-shdn-err",
 	};
 
 	for (i = 0; i < ARRAY_SIZE(single_out_errb_irqs); i++) {
@@ -779,12 +1123,10 @@ static int bd96801_global_errb_irqs(struct platform_device *pdev,
 	int i, num_irqs;
 	void *retp;
 	static const char * const global_errb_irqs[] = {
-		"bd96801-otp-err", "bd96801-dbist-err", "bd96801-eep-err",
-		"bd96801-abist-err", "bd96801-prstb-err", "bd96801-drmoserr1",
-		"bd96801-drmoserr2", "bd96801-slave-err", "bd96801-vref-err",
-		"bd96801-tsd", "bd96801-uvlo-err", "bd96801-ovlo-err",
-		"bd96801-osc-err", "bd96801-pon-err", "bd96801-poff-err",
-		"bd96801-cmd-shdn-err", "bd96801-int-shdn-err"
+		"otp-err", "dbist-err", "eep-err", "abist-err", "prstb-err",
+		"drmoserr1", "drmoserr2", "slave-err", "vref-err", "tsd",
+		"uvlo-err", "ovlo-err", "osc-err", "pon-err", "poff-err",
+		"cmd-shdn-err", "int-shdn-err"
 	};
 
 	num_irqs = ARRAY_SIZE(global_errb_irqs);
@@ -869,6 +1211,7 @@ static int bd96801_probe(struct platform_device *pdev)
 {
 	struct regulator_dev *ldo_errs_rdev_arr[BD96801_NUM_LDOS];
 	struct regulator_dev *all_rdevs[BD96801_NUM_REGULATORS];
+	struct bd96801_pmic_data *pdata_template;
 	struct bd96801_regulator_data *rdesc;
 	struct regulator_config config = {};
 	int ldo_errs_arr[BD96801_NUM_LDOS];
@@ -881,12 +1224,16 @@ static int bd96801_probe(struct platform_device *pdev)
 
 	parent = pdev->dev.parent;
 
-	pdata = devm_kmemdup(&pdev->dev, &bd96801_data, sizeof(bd96801_data),
+	pdata_template = (struct bd96801_pmic_data *)platform_get_device_id(pdev)->driver_data;
+	if (!pdata_template)
+		return -ENODEV;
+
+	pdata = devm_kmemdup(&pdev->dev, pdata_template, sizeof(bd96801_data),
 			     GFP_KERNEL);
 	if (!pdata)
 		return -ENOMEM;
 
-	if (initialize_pmic_data(&pdev->dev, pdata))
+	if (initialize_pmic_data(pdev, pdata))
 		return -ENOMEM;
 
 	pdata->regmap = dev_get_regmap(parent, NULL);
@@ -909,11 +1256,11 @@ static int bd96801_probe(struct platform_device *pdev)
 		use_errb = true;
 
 	ret = bd96801_walk_regulator_dt(&pdev->dev, pdata->regmap, rdesc,
-					BD96801_NUM_REGULATORS);
+					pdata->num_regulators);
 	if (ret)
 		return ret;
 
-	for (i = 0; i < ARRAY_SIZE(pdata->regulator_data); i++) {
+	for (i = 0; i < pdata->num_regulators; i++) {
 		struct regulator_dev *rdev;
 		struct bd96801_irq_desc *idesc = &rdesc[i].irq_desc;
 		int j;
@@ -926,6 +1273,7 @@ static int bd96801_probe(struct platform_device *pdev)
 				rdesc[i].desc.name);
 			return PTR_ERR(rdev);
 		}
+
 		all_rdevs[i] = rdev;
 		/*
 		 * LDOs don't have own temperature monitoring. If temperature
@@ -956,12 +1304,12 @@ static int bd96801_probe(struct platform_device *pdev)
 	if (temp_notif_ldos) {
 		int irq;
 		struct regulator_irq_desc tw_desc = {
-			.name = "bd96801-core-thermal",
+			.name = "core-thermal",
 			.irq_off_ms = 500,
 			.map_event = ldo_map_notif,
 		};
 
-		irq = platform_get_irq_byname(pdev, "bd96801-core-thermal");
+		irq = platform_get_irq_byname(pdev, "core-thermal");
 		if (irq < 0)
 			return irq;
 
@@ -975,14 +1323,17 @@ static int bd96801_probe(struct platform_device *pdev)
 
 	if (use_errb)
 		return bd96801_global_errb_irqs(pdev, all_rdevs,
-						ARRAY_SIZE(all_rdevs));
+						pdata->num_regulators);
 
 	return 0;
 }
 
 static const struct platform_device_id bd96801_pmic_id[] = {
-	{ "bd96801-regulator", },
-	{ }
+	{ "bd96801-regulator", (kernel_ulong_t)&bd96801_data },
+	{ "bd96802-regulator", (kernel_ulong_t)&bd96802_data },
+	{ "bd96805-regulator", (kernel_ulong_t)&bd96805_data },
+	{ "bd96806-regulator", (kernel_ulong_t)&bd96806_data },
+	{ },
 };
 MODULE_DEVICE_TABLE(platform, bd96801_pmic_id);
 
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 838bdc138ffe..9aec922613ce 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -1388,6 +1388,18 @@ config RTC_DRV_ASM9260
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-asm9260.
 
+config RTC_DRV_CV1800
+	tristate "Sophgo CV1800 RTC"
+	depends on SOPHGO_CV1800_RTCSYS || COMPILE_TEST
+	select MFD_SYSCON
+	select REGMAP
+	help
+	  If you say yes here you get support the RTC driver for Sophgo CV1800
+	  series SoC.
+
+	  This driver can also be built as a module. If so, the module will be
+	  called rtc-cv1800.
+
 config RTC_DRV_DIGICOLOR
 	tristate "Conexant Digicolor RTC"
 	depends on ARCH_DIGICOLOR || COMPILE_TEST
@@ -2088,7 +2100,7 @@ config RTC_DRV_AMLOGIC_A4
 	tristate "Amlogic RTC"
 	depends on ARCH_MESON || COMPILE_TEST
 	select REGMAP_MMIO
-	default y
+	default ARCH_MESON
 	help
 	  If you say yes here you get support for the RTC block on the
 	  Amlogic A113L2(A4) and A113X2(A5) SoCs.
@@ -2096,4 +2108,15 @@ config RTC_DRV_AMLOGIC_A4
 	  This driver can also be built as a module. If so, the module
 	  will be called "rtc-amlogic-a4".
 
+config RTC_DRV_S32G
+	tristate "RTC driver for S32G2/S32G3 SoCs"
+	depends on ARCH_S32 || COMPILE_TEST
+	depends on COMMON_CLK
+	help
+	  Say yes to enable RTC driver for platforms based on the
+	  S32G2/S32G3 SoC family.
+
+	  This RTC module can be used as a wakeup source.
+	  Please note that it is not battery-powered.
+
 endif # RTC_CLASS
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 31473b3276d9..4619aa2ac469 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -44,6 +44,7 @@ obj-$(CONFIG_RTC_DRV_CADENCE)	+= rtc-cadence.o
 obj-$(CONFIG_RTC_DRV_CMOS)	+= rtc-cmos.o
 obj-$(CONFIG_RTC_DRV_CPCAP)	+= rtc-cpcap.o
 obj-$(CONFIG_RTC_DRV_CROS_EC)	+= rtc-cros-ec.o
+obj-$(CONFIG_RTC_DRV_CV1800)	+= rtc-cv1800.o
 obj-$(CONFIG_RTC_DRV_DA9052)	+= rtc-da9052.o
 obj-$(CONFIG_RTC_DRV_DA9055)	+= rtc-da9055.o
 obj-$(CONFIG_RTC_DRV_DA9063)	+= rtc-da9063.o
@@ -160,6 +161,7 @@ obj-$(CONFIG_RTC_DRV_RX8111)	+= rtc-rx8111.o
 obj-$(CONFIG_RTC_DRV_RX8581)	+= rtc-rx8581.o
 obj-$(CONFIG_RTC_DRV_RZN1)	+= rtc-rzn1.o
 obj-$(CONFIG_RTC_DRV_RENESAS_RTCA3)	+= rtc-renesas-rtca3.o
+obj-$(CONFIG_RTC_DRV_S32G)	+= rtc-s32g.o
 obj-$(CONFIG_RTC_DRV_S35390A)	+= rtc-s35390a.o
 obj-$(CONFIG_RTC_DRV_S3C)	+= rtc-s3c.o
 obj-$(CONFIG_RTC_DRV_S5M)	+= rtc-s5m.o
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index b88cd4fb295b..b1a2be1f9e3b 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -326,7 +326,7 @@ static void rtc_device_get_offset(struct rtc_device *rtc)
 	 *
 	 * Otherwise the offset seconds should be 0.
 	 */
-	if (rtc->start_secs > rtc->range_max ||
+	if ((rtc->start_secs >= 0 && rtc->start_secs > rtc->range_max) ||
 	    rtc->start_secs + range_secs - 1 < rtc->range_min)
 		rtc->offset_secs = rtc->start_secs - rtc->range_min;
 	else if (rtc->start_secs > rtc->range_min)
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index aaf76406cd7d..dc741ba29fa3 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -205,7 +205,7 @@ static int rtc_read_alarm_internal(struct rtc_device *rtc,
 
 	mutex_unlock(&rtc->ops_lock);
 
-	trace_rtc_read_alarm(rtc_tm_to_time64(&alarm->time), err);
+	trace_rtc_read_alarm(err?0:rtc_tm_to_time64(&alarm->time), err);
 	return err;
 }
 
diff --git a/drivers/rtc/lib.c b/drivers/rtc/lib.c
index fe361652727a..13b5b1f20465 100644
--- a/drivers/rtc/lib.c
+++ b/drivers/rtc/lib.c
@@ -46,24 +46,38 @@ EXPORT_SYMBOL(rtc_year_days);
  * rtc_time64_to_tm - converts time64_t to rtc_time.
  *
  * @time:	The number of seconds since 01-01-1970 00:00:00.
- *		(Must be positive.)
+ *		Works for values since at least 1900
  * @tm:		Pointer to the struct rtc_time.
  */
 void rtc_time64_to_tm(time64_t time, struct rtc_time *tm)
 {
-	unsigned int secs;
-	int days;
+	int days, secs;
 
 	u64 u64tmp;
 	u32 u32tmp, udays, century, day_of_century, year_of_century, year,
 		day_of_year, month, day;
 	bool is_Jan_or_Feb, is_leap_year;
 
-	/* time must be positive */
+	/*
+	 * Get days and seconds while preserving the sign to
+	 * handle negative time values (dates before 1970-01-01)
+	 */
 	days = div_s64_rem(time, 86400, &secs);
 
+	/*
+	 * We need 0 <= secs < 86400 which isn't given for negative
+	 * values of time. Fixup accordingly.
+	 */
+	if (secs < 0) {
+		days -= 1;
+		secs += 86400;
+	}
+
 	/* day of the week, 1970-01-01 was a Thursday */
 	tm->tm_wday = (days + 4) % 7;
+	/* Ensure tm_wday is always positive */
+	if (tm->tm_wday < 0)
+		tm->tm_wday += 7;
 
 	/*
 	 * The following algorithm is, basically, Proposition 6.3 of Neri
@@ -93,7 +107,7 @@ void rtc_time64_to_tm(time64_t time, struct rtc_time *tm)
 	 * thus, is slightly different from [1].
 	 */
 
-	udays		= ((u32) days) + 719468;
+	udays		= days + 719468;
 
 	u32tmp		= 4 * udays + 3;
 	century		= u32tmp / 146097;
diff --git a/drivers/rtc/lib_test.c b/drivers/rtc/lib_test.c
index c30c759662e3..0eebad1fe2a0 100644
--- a/drivers/rtc/lib_test.c
+++ b/drivers/rtc/lib_test.c
@@ -6,8 +6,10 @@
 /*
  * Advance a date by one day.
  */
-static void advance_date(int *year, int *month, int *mday, int *yday)
+static void advance_date(int *year, int *month, int *mday, int *yday, int *wday)
 {
+	*wday = (*wday + 1) % 7;
+
 	if (*mday != rtc_month_days(*month - 1, *year)) {
 		++*mday;
 		++*yday;
@@ -39,35 +41,38 @@ static void rtc_time64_to_tm_test_date_range(struct kunit *test, int years)
 	 */
 	time64_t total_secs = ((time64_t)years) / 400 * 146097 * 86400;
 
-	int year	= 1970;
+	int year	= 1900;
 	int month	= 1;
 	int mday	= 1;
 	int yday	= 1;
+	int wday	= 1; /* Jan 1st 1900 was a Monday */
 
 	struct rtc_time result;
 	time64_t secs;
-	s64 days;
+	const time64_t sec_offset = RTC_TIMESTAMP_BEGIN_1900 + ((1 * 60) + 2) * 60 + 3;
 
 	for (secs = 0; secs <= total_secs; secs += 86400) {
 
-		rtc_time64_to_tm(secs, &result);
-
-		days = div_s64(secs, 86400);
+		rtc_time64_to_tm(secs + sec_offset, &result);
 
-		#define FAIL_MSG "%d/%02d/%02d (%2d) : %lld", \
-			year, month, mday, yday, days
+		#define FAIL_MSG "%d/%02d/%02d (%2d, %d) : %lld", \
+			year, month, mday, yday, wday, secs + sec_offset
 
 		KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG);
 		KUNIT_ASSERT_EQ_MSG(test, month - 1, result.tm_mon, FAIL_MSG);
 		KUNIT_ASSERT_EQ_MSG(test, mday, result.tm_mday, FAIL_MSG);
 		KUNIT_ASSERT_EQ_MSG(test, yday, result.tm_yday, FAIL_MSG);
+		KUNIT_ASSERT_EQ_MSG(test, 1, result.tm_hour, FAIL_MSG);
+		KUNIT_ASSERT_EQ_MSG(test, 2, result.tm_min, FAIL_MSG);
+		KUNIT_ASSERT_EQ_MSG(test, 3, result.tm_sec, FAIL_MSG);
+		KUNIT_ASSERT_EQ_MSG(test, wday, result.tm_wday, FAIL_MSG);
 
-		advance_date(&year, &month, &mday, &yday);
+		advance_date(&year, &month, &mday, &yday, &wday);
 	}
 }
 
 /*
- * Checks every day in a 160000 years interval starting on 1970-01-01
+ * Checks every day in a 160000 years interval starting on 1900-01-01
  * against the expected result.
  */
 static void rtc_time64_to_tm_test_date_range_160000(struct kunit *test)
@@ -76,7 +81,7 @@ static void rtc_time64_to_tm_test_date_range_160000(struct kunit *test)
 }
 
 /*
- * Checks every day in a 1000 years interval starting on 1970-01-01
+ * Checks every day in a 1000 years interval starting on 1900-01-01
  * against the expected result.
  */
 static void rtc_time64_to_tm_test_date_range_1000(struct kunit *test)
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index f6b0102a843a..643734dbae33 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -654,4 +654,3 @@ module_platform_driver_probe(at91_rtc_driver, at91_rtc_probe);
 MODULE_AUTHOR("Rick Bronson");
 MODULE_DESCRIPTION("RTC driver for Atmel AT91RM9200");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:at91_rtc");
diff --git a/drivers/rtc/rtc-cpcap.c b/drivers/rtc/rtc-cpcap.c
index 568a89e79c11..c170345ac076 100644
--- a/drivers/rtc/rtc-cpcap.c
+++ b/drivers/rtc/rtc-cpcap.c
@@ -320,7 +320,6 @@ static struct platform_driver cpcap_rtc_driver = {
 
 module_platform_driver(cpcap_rtc_driver);
 
-MODULE_ALIAS("platform:cpcap-rtc");
 MODULE_DESCRIPTION("CPCAP RTC driver");
 MODULE_AUTHOR("Sebastian Reichel <sre@kernel.org>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-cv1800.c b/drivers/rtc/rtc-cv1800.c
new file mode 100644
index 000000000000..678c2c10bf58
--- /dev/null
+++ b/drivers/rtc/rtc-cv1800.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * rtc-cv1800.c: RTC driver for Sophgo cv1800 RTC
+ *
+ * Author: Jingbao Qiu <qiujingbao.dlmu@gmail.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/rtc.h>
+
+#define SEC_PULSE_GEN          0x1004
+#define ALARM_TIME             0x1008
+#define ALARM_ENABLE           0x100C
+#define SET_SEC_CNTR_VAL       0x1010
+#define SET_SEC_CNTR_TRIG      0x1014
+#define SEC_CNTR_VAL           0x1018
+
+/*
+ * When in VDDBKUP domain, this MACRO register
+ * does not power down
+ */
+#define MACRO_RO_T             0x14A8
+#define MACRO_RG_SET_T         0x1498
+
+#define ALARM_ENABLE_MASK      BIT(0)
+#define SEL_SEC_PULSE          BIT(31)
+
+struct cv1800_rtc_priv {
+	struct rtc_device *rtc_dev;
+	struct regmap *rtc_map;
+	struct clk *clk;
+	int irq;
+};
+
+static bool cv1800_rtc_enabled(struct device *dev)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+	u32 reg;
+
+	regmap_read(info->rtc_map, SEC_PULSE_GEN, &reg);
+
+	return (reg & SEL_SEC_PULSE) == 0;
+}
+
+static void cv1800_rtc_enable(struct device *dev)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+
+	/* Sec pulse generated internally */
+	regmap_update_bits(info->rtc_map, SEC_PULSE_GEN, SEL_SEC_PULSE, 0);
+}
+
+static int cv1800_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+
+	regmap_write(info->rtc_map, ALARM_ENABLE, enabled);
+
+	return 0;
+}
+
+static int cv1800_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+	unsigned long alarm_time;
+
+	alarm_time = rtc_tm_to_time64(&alrm->time);
+
+	cv1800_rtc_alarm_irq_enable(dev, 0);
+
+	regmap_write(info->rtc_map, ALARM_TIME, alarm_time);
+
+	cv1800_rtc_alarm_irq_enable(dev, alrm->enabled);
+
+	return 0;
+}
+
+static int cv1800_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+	u32 enabled;
+	u32 time;
+
+	if (!cv1800_rtc_enabled(dev)) {
+		alarm->enabled = 0;
+		return 0;
+	}
+
+	regmap_read(info->rtc_map, ALARM_ENABLE, &enabled);
+
+	alarm->enabled = enabled & ALARM_ENABLE_MASK;
+
+	regmap_read(info->rtc_map, ALARM_TIME, &time);
+
+	rtc_time64_to_tm(time, &alarm->time);
+
+	return 0;
+}
+
+static int cv1800_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+	u32 sec;
+
+	if (!cv1800_rtc_enabled(dev))
+		return -EINVAL;
+
+	regmap_read(info->rtc_map, SEC_CNTR_VAL, &sec);
+
+	rtc_time64_to_tm(sec, tm);
+
+	return 0;
+}
+
+static int cv1800_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct cv1800_rtc_priv *info = dev_get_drvdata(dev);
+	unsigned long sec;
+
+	sec = rtc_tm_to_time64(tm);
+
+	regmap_write(info->rtc_map, SET_SEC_CNTR_VAL, sec);
+	regmap_write(info->rtc_map, SET_SEC_CNTR_TRIG, 1);
+
+	regmap_write(info->rtc_map, MACRO_RG_SET_T, sec);
+
+	cv1800_rtc_enable(dev);
+
+	return 0;
+}
+
+static irqreturn_t cv1800_rtc_irq_handler(int irq, void *dev_id)
+{
+	struct cv1800_rtc_priv *info = dev_id;
+
+	rtc_update_irq(info->rtc_dev, 1, RTC_IRQF | RTC_AF);
+
+	regmap_write(info->rtc_map, ALARM_ENABLE, 0);
+
+	return IRQ_HANDLED;
+}
+
+static const struct rtc_class_ops cv1800_rtc_ops = {
+	.read_time = cv1800_rtc_read_time,
+	.set_time = cv1800_rtc_set_time,
+	.read_alarm = cv1800_rtc_read_alarm,
+	.set_alarm = cv1800_rtc_set_alarm,
+	.alarm_irq_enable = cv1800_rtc_alarm_irq_enable,
+};
+
+static int cv1800_rtc_probe(struct platform_device *pdev)
+{
+	struct cv1800_rtc_priv *rtc;
+	int ret;
+
+	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
+	if (!rtc)
+		return -ENOMEM;
+
+	rtc->rtc_map = device_node_to_regmap(pdev->dev.parent->of_node);
+	if (IS_ERR(rtc->rtc_map))
+		return dev_err_probe(&pdev->dev, PTR_ERR(rtc->rtc_map),
+				     "cannot get parent regmap\n");
+
+	rtc->irq = platform_get_irq(pdev, 0);
+	if (rtc->irq < 0)
+		return rtc->irq;
+
+	rtc->clk = devm_clk_get_enabled(pdev->dev.parent, "rtc");
+	if (IS_ERR(rtc->clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(rtc->clk),
+				     "rtc clk not found\n");
+
+	platform_set_drvdata(pdev, rtc);
+
+	device_init_wakeup(&pdev->dev, 1);
+
+	rtc->rtc_dev = devm_rtc_allocate_device(&pdev->dev);
+	if (IS_ERR(rtc->rtc_dev))
+		return PTR_ERR(rtc->rtc_dev);
+
+	rtc->rtc_dev->ops = &cv1800_rtc_ops;
+	rtc->rtc_dev->range_max = U32_MAX;
+
+	ret = devm_request_irq(&pdev->dev, rtc->irq, cv1800_rtc_irq_handler,
+			       IRQF_TRIGGER_HIGH, "rtc alarm", rtc);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret,
+				     "cannot register interrupt handler\n");
+
+	return devm_rtc_register_device(rtc->rtc_dev);
+}
+
+static const struct platform_device_id cv1800_rtc_id[] = {
+	{ .name = "cv1800b-rtc" },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(platform, cv1800_rtc_id);
+
+static struct platform_driver cv1800_rtc_driver = {
+	.driver = {
+		.name = "sophgo-cv1800-rtc",
+	},
+	.probe = cv1800_rtc_probe,
+	.id_table = cv1800_rtc_id,
+};
+
+module_platform_driver(cv1800_rtc_driver);
+MODULE_AUTHOR("Jingbao Qiu");
+MODULE_DESCRIPTION("Sophgo cv1800 RTC Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c
index 859397541f29..557c9b29dcc1 100644
--- a/drivers/rtc/rtc-da9063.c
+++ b/drivers/rtc/rtc-da9063.c
@@ -194,26 +194,17 @@ static void da9063_tm_to_data(struct rtc_time *tm, u8 *data,
 				config->rtc_count_year_mask;
 }
 
-static int da9063_rtc_stop_alarm(struct device *dev)
-{
-	struct da9063_compatible_rtc *rtc = dev_get_drvdata(dev);
-	const struct da9063_compatible_rtc_regmap *config = rtc->config;
-
-	return regmap_update_bits(rtc->regmap,
-				  config->rtc_alarm_year_reg,
-				  config->rtc_alarm_on_mask,
-				  0);
-}
-
-static int da9063_rtc_start_alarm(struct device *dev)
+static int da9063_rtc_alarm_irq_enable(struct device *dev,
+				       unsigned int enabled)
 {
 	struct da9063_compatible_rtc *rtc = dev_get_drvdata(dev);
 	const struct da9063_compatible_rtc_regmap *config = rtc->config;
+	u8 set_bit = enabled ? config->rtc_alarm_on_mask : 0;
 
 	return regmap_update_bits(rtc->regmap,
 				  config->rtc_alarm_year_reg,
 				  config->rtc_alarm_on_mask,
-				  config->rtc_alarm_on_mask);
+				  set_bit);
 }
 
 static int da9063_rtc_read_time(struct device *dev, struct rtc_time *tm)
@@ -312,7 +303,7 @@ static int da9063_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 
 	da9063_tm_to_data(&alrm->time, data, rtc);
 
-	ret = da9063_rtc_stop_alarm(dev);
+	ret = da9063_rtc_alarm_irq_enable(dev, 0);
 	if (ret < 0) {
 		dev_err(dev, "Failed to stop alarm: %d\n", ret);
 		return ret;
@@ -330,7 +321,7 @@ static int da9063_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	da9063_data_to_tm(data, &rtc->alarm_time, rtc);
 
 	if (alrm->enabled) {
-		ret = da9063_rtc_start_alarm(dev);
+		ret = da9063_rtc_alarm_irq_enable(dev, 1);
 		if (ret < 0) {
 			dev_err(dev, "Failed to start alarm: %d\n", ret);
 			return ret;
@@ -340,15 +331,6 @@ static int da9063_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	return ret;
 }
 
-static int da9063_rtc_alarm_irq_enable(struct device *dev,
-				       unsigned int enabled)
-{
-	if (enabled)
-		return da9063_rtc_start_alarm(dev);
-	else
-		return da9063_rtc_stop_alarm(dev);
-}
-
 static irqreturn_t da9063_alarm_event(int irq, void *data)
 {
 	struct da9063_compatible_rtc *rtc = data;
@@ -513,4 +495,3 @@ module_platform_driver(da9063_rtc_driver);
 MODULE_AUTHOR("S Twiss <stwiss.opensource@diasemi.com>");
 MODULE_DESCRIPTION("Real time clock device driver for Dialog DA9063");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:" DA9063_DRVNAME_RTC);
diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c
index 44bba356268c..11fce47be780 100644
--- a/drivers/rtc/rtc-jz4740.c
+++ b/drivers/rtc/rtc-jz4740.c
@@ -437,4 +437,3 @@ module_platform_driver(jz4740_rtc_driver);
 MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("RTC driver for the JZ4740 SoC\n");
-MODULE_ALIAS("platform:jz4740-rtc");
diff --git a/drivers/rtc/rtc-loongson.c b/drivers/rtc/rtc-loongson.c
index 97e5625c064c..2ca7ffd5d7a9 100644
--- a/drivers/rtc/rtc-loongson.c
+++ b/drivers/rtc/rtc-loongson.c
@@ -129,6 +129,14 @@ static u32 loongson_rtc_handler(void *id)
 {
 	struct loongson_rtc_priv *priv = (struct loongson_rtc_priv *)id;
 
+	rtc_update_irq(priv->rtcdev, 1, RTC_AF | RTC_IRQF);
+
+	/*
+	 * The TOY_MATCH0_REG should be cleared 0 here,
+	 * otherwise the interrupt cannot be cleared.
+	 */
+	regmap_write(priv->regmap, TOY_MATCH0_REG, 0);
+
 	spin_lock(&priv->lock);
 	/* Disable RTC alarm wakeup and interrupt */
 	writel(readl(priv->pm_base + PM1_EN_REG) & ~RTC_EN,
diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c
index 1f58ae8b151e..c568639d2151 100644
--- a/drivers/rtc/rtc-m41t80.c
+++ b/drivers/rtc/rtc-m41t80.c
@@ -22,6 +22,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/string.h>
+#include <linux/delay.h>
 #ifdef CONFIG_RTC_DRV_M41T80_WDT
 #include <linux/fs.h>
 #include <linux/ioctl.h>
@@ -204,14 +205,14 @@ static int m41t80_rtc_read_time(struct device *dev, struct rtc_time *tm)
 		return flags;
 
 	if (flags & M41T80_FLAGS_OF) {
-		dev_err(&client->dev, "Oscillator failure, data is invalid.\n");
+		dev_err(&client->dev, "Oscillator failure, time may not be accurate, write time to RTC to fix it.\n");
 		return -EINVAL;
 	}
 
 	err = i2c_smbus_read_i2c_block_data(client, M41T80_REG_SSEC,
 					    sizeof(buf), buf);
 	if (err < 0) {
-		dev_err(&client->dev, "Unable to read date\n");
+		dev_dbg(&client->dev, "Unable to read date\n");
 		return err;
 	}
 
@@ -227,21 +228,31 @@ static int m41t80_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	return 0;
 }
 
-static int m41t80_rtc_set_time(struct device *dev, struct rtc_time *tm)
+static int m41t80_rtc_set_time(struct device *dev, struct rtc_time *in_tm)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct m41t80_data *clientdata = i2c_get_clientdata(client);
+	struct rtc_time tm = *in_tm;
 	unsigned char buf[8];
 	int err, flags;
+	time64_t time = 0;
 
+	flags = i2c_smbus_read_byte_data(client, M41T80_REG_FLAGS);
+	if (flags < 0)
+		return flags;
+	if (flags & M41T80_FLAGS_OF) {
+		/* add 4sec of oscillator stablize time otherwise we are behind 4sec */
+		time = rtc_tm_to_time64(&tm);
+		rtc_time64_to_tm(time + 4, &tm);
+	}
 	buf[M41T80_REG_SSEC] = 0;
-	buf[M41T80_REG_SEC] = bin2bcd(tm->tm_sec);
-	buf[M41T80_REG_MIN] = bin2bcd(tm->tm_min);
-	buf[M41T80_REG_HOUR] = bin2bcd(tm->tm_hour);
-	buf[M41T80_REG_DAY] = bin2bcd(tm->tm_mday);
-	buf[M41T80_REG_MON] = bin2bcd(tm->tm_mon + 1);
-	buf[M41T80_REG_YEAR] = bin2bcd(tm->tm_year - 100);
-	buf[M41T80_REG_WDAY] = tm->tm_wday;
+	buf[M41T80_REG_SEC] = bin2bcd(tm.tm_sec);
+	buf[M41T80_REG_MIN] = bin2bcd(tm.tm_min);
+	buf[M41T80_REG_HOUR] = bin2bcd(tm.tm_hour);
+	buf[M41T80_REG_DAY] = bin2bcd(tm.tm_mday);
+	buf[M41T80_REG_MON] = bin2bcd(tm.tm_mon + 1);
+	buf[M41T80_REG_YEAR] = bin2bcd(tm.tm_year - 100);
+	buf[M41T80_REG_WDAY] = tm.tm_wday;
 
 	/* If the square wave output is controlled in the weekday register */
 	if (clientdata->features & M41T80_FEATURE_SQ_ALT) {
@@ -257,20 +268,37 @@ static int m41t80_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	err = i2c_smbus_write_i2c_block_data(client, M41T80_REG_SSEC,
 					     sizeof(buf), buf);
 	if (err < 0) {
-		dev_err(&client->dev, "Unable to write to date registers\n");
+		dev_dbg(&client->dev, "Unable to write to date registers\n");
 		return err;
 	}
-
-	/* Clear the OF bit of Flags Register */
-	flags = i2c_smbus_read_byte_data(client, M41T80_REG_FLAGS);
-	if (flags < 0)
-		return flags;
-
-	err = i2c_smbus_write_byte_data(client, M41T80_REG_FLAGS,
-					flags & ~M41T80_FLAGS_OF);
-	if (err < 0) {
-		dev_err(&client->dev, "Unable to write flags register\n");
-		return err;
+	if (flags & M41T80_FLAGS_OF) {
+		/* OF cannot be immediately reset: oscillator has to be restarted. */
+		dev_warn(&client->dev, "OF bit is still set, kickstarting clock.\n");
+		err = i2c_smbus_write_byte_data(client, M41T80_REG_SEC, M41T80_SEC_ST);
+		if (err < 0) {
+			dev_dbg(&client->dev, "Can't set ST bit\n");
+			return err;
+		}
+		err = i2c_smbus_write_byte_data(client, M41T80_REG_SEC, flags & ~M41T80_SEC_ST);
+		if (err < 0) {
+			dev_dbg(&client->dev, "Can't clear ST bit\n");
+			return err;
+		}
+		/* oscillator must run for 4sec before we attempt to reset OF bit */
+		msleep(4000);
+		/* Clear the OF bit of Flags Register */
+		err = i2c_smbus_write_byte_data(client, M41T80_REG_FLAGS, flags & ~M41T80_FLAGS_OF);
+		if (err < 0) {
+			dev_dbg(&client->dev, "Unable to write flags register\n");
+			return err;
+		}
+		flags = i2c_smbus_read_byte_data(client, M41T80_REG_FLAGS);
+		if (flags < 0) {
+			return flags;
+		} else if (flags & M41T80_FLAGS_OF) {
+			dev_dbg(&client->dev, "Can't clear the OF bit check battery\n");
+			return err;
+		}
 	}
 
 	return err;
@@ -308,7 +336,7 @@ static int m41t80_alarm_irq_enable(struct device *dev, unsigned int enabled)
 
 	retval = i2c_smbus_write_byte_data(client, M41T80_REG_ALARM_MON, flags);
 	if (retval < 0) {
-		dev_err(dev, "Unable to enable alarm IRQ %d\n", retval);
+		dev_dbg(dev, "Unable to enable alarm IRQ %d\n", retval);
 		return retval;
 	}
 	return 0;
@@ -333,7 +361,7 @@ static int m41t80_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	err = i2c_smbus_write_byte_data(client, M41T80_REG_ALARM_MON,
 					ret & ~(M41T80_ALMON_AFE));
 	if (err < 0) {
-		dev_err(dev, "Unable to clear AFE bit\n");
+		dev_dbg(dev, "Unable to clear AFE bit\n");
 		return err;
 	}
 
@@ -347,7 +375,7 @@ static int m41t80_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	err = i2c_smbus_write_byte_data(client, M41T80_REG_FLAGS,
 					ret & ~(M41T80_FLAGS_AF));
 	if (err < 0) {
-		dev_err(dev, "Unable to clear AF bit\n");
+		dev_dbg(dev, "Unable to clear AF bit\n");
 		return err;
 	}
 
diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index 6979d225a78e..692c00ff544b 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -332,6 +332,7 @@ static const struct mtk_rtc_data mt6397_rtc_data = {
 
 static const struct of_device_id mt6397_rtc_of_match[] = {
 	{ .compatible = "mediatek,mt6323-rtc", .data = &mt6397_rtc_data },
+	{ .compatible = "mediatek,mt6357-rtc", .data = &mt6358_rtc_data },
 	{ .compatible = "mediatek,mt6358-rtc", .data = &mt6358_rtc_data },
 	{ .compatible = "mediatek,mt6397-rtc", .data = &mt6397_rtc_data },
 	{ }
diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c
index 5a084d426e58..b2611697fa5e 100644
--- a/drivers/rtc/rtc-pcf8563.c
+++ b/drivers/rtc/rtc-pcf8563.c
@@ -285,7 +285,7 @@ static int pcf8563_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *tm)
 	buf[2] = bin2bcd(tm->time.tm_mday);
 	buf[3] = tm->time.tm_wday & 0x07;
 
-	err = regmap_bulk_write(pcf8563->regmap, PCF8563_REG_SC, buf,
+	err = regmap_bulk_write(pcf8563->regmap, PCF8563_REG_AMN, buf,
 				sizeof(buf));
 	if (err)
 		return err;
diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c
index 3c1dddcc81df..e624f848c22b 100644
--- a/drivers/rtc/rtc-pm8xxx.c
+++ b/drivers/rtc/rtc-pm8xxx.c
@@ -576,13 +576,20 @@ static int pm8xxx_rtc_probe_offset(struct pm8xxx_rtc *rtc_dd)
 	}
 
 	/* Use UEFI storage as fallback if available */
-	if (efivar_is_available()) {
-		rc = pm8xxx_rtc_read_uefi_offset(rtc_dd);
-		if (rc == 0)
-			rtc_dd->use_uefi = true;
+	rtc_dd->use_uefi = of_property_read_bool(rtc_dd->dev->of_node,
+						 "qcom,uefi-rtc-info");
+	if (!rtc_dd->use_uefi)
+		return 0;
+
+	if (!efivar_is_available()) {
+		if (IS_ENABLED(CONFIG_EFI))
+			return -EPROBE_DEFER;
+
+		dev_warn(rtc_dd->dev, "efivars not available\n");
+		rtc_dd->use_uefi = false;
 	}
 
-	return 0;
+	return pm8xxx_rtc_read_uefi_offset(rtc_dd);
 }
 
 static int pm8xxx_rtc_probe(struct platform_device *pdev)
@@ -676,7 +683,6 @@ static struct platform_driver pm8xxx_rtc_driver = {
 
 module_platform_driver(pm8xxx_rtc_driver);
 
-MODULE_ALIAS("platform:rtc-pm8xxx");
 MODULE_DESCRIPTION("PMIC8xxx RTC driver");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Anirudh Ghayal <aghayal@codeaurora.org>");
diff --git a/drivers/rtc/rtc-rzn1.c b/drivers/rtc/rtc-rzn1.c
index eeb9612a666f..c4ed43735457 100644
--- a/drivers/rtc/rtc-rzn1.c
+++ b/drivers/rtc/rtc-rzn1.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/bcd.h>
+#include <linux/clk.h>
 #include <linux/init.h>
 #include <linux/iopoll.h>
 #include <linux/module.h>
@@ -22,9 +23,9 @@
 #include <linux/spinlock.h>
 
 #define RZN1_RTC_CTL0 0x00
-#define   RZN1_RTC_CTL0_SLSB_SUBU 0
 #define   RZN1_RTC_CTL0_SLSB_SCMP BIT(4)
 #define   RZN1_RTC_CTL0_AMPM BIT(5)
+#define   RZN1_RTC_CTL0_CEST BIT(6)
 #define   RZN1_RTC_CTL0_CE BIT(7)
 
 #define RZN1_RTC_CTL1 0x04
@@ -49,6 +50,8 @@
 #define   RZN1_RTC_SUBU_DEV BIT(7)
 #define   RZN1_RTC_SUBU_DECR BIT(6)
 
+#define RZN1_RTC_SCMP 0x3c
+
 #define RZN1_RTC_ALM 0x40
 #define RZN1_RTC_ALH 0x44
 #define RZN1_RTC_ALW 0x48
@@ -356,7 +359,7 @@ static int rzn1_rtc_set_offset(struct device *dev, long offset)
 	return 0;
 }
 
-static const struct rtc_class_ops rzn1_rtc_ops = {
+static const struct rtc_class_ops rzn1_rtc_ops_subu = {
 	.read_time = rzn1_rtc_read_time,
 	.set_time = rzn1_rtc_set_time,
 	.read_alarm = rzn1_rtc_read_alarm,
@@ -366,11 +369,21 @@ static const struct rtc_class_ops rzn1_rtc_ops = {
 	.set_offset = rzn1_rtc_set_offset,
 };
 
+static const struct rtc_class_ops rzn1_rtc_ops_scmp = {
+	.read_time = rzn1_rtc_read_time,
+	.set_time = rzn1_rtc_set_time,
+	.read_alarm = rzn1_rtc_read_alarm,
+	.set_alarm = rzn1_rtc_set_alarm,
+	.alarm_irq_enable = rzn1_rtc_alarm_irq_enable,
+};
+
 static int rzn1_rtc_probe(struct platform_device *pdev)
 {
 	struct rzn1_rtc *rtc;
-	int irq;
-	int ret;
+	u32 val, scmp_val = 0;
+	struct clk *xtal;
+	unsigned long rate;
+	int irq, ret;
 
 	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
 	if (!rtc)
@@ -393,7 +406,6 @@ static int rzn1_rtc_probe(struct platform_device *pdev)
 	rtc->rtcdev->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rtc->rtcdev->range_max = RTC_TIMESTAMP_END_2099;
 	rtc->rtcdev->alarm_offset_max = 7 * 86400;
-	rtc->rtcdev->ops = &rzn1_rtc_ops;
 
 	ret = devm_pm_runtime_enable(&pdev->dev);
 	if (ret < 0)
@@ -402,12 +414,44 @@ static int rzn1_rtc_probe(struct platform_device *pdev)
 	if (ret < 0)
 		return ret;
 
-	/*
-	 * Ensure the clock counter is enabled.
-	 * Set 24-hour mode and possible oscillator offset compensation in SUBU mode.
-	 */
-	writel(RZN1_RTC_CTL0_CE | RZN1_RTC_CTL0_AMPM | RZN1_RTC_CTL0_SLSB_SUBU,
-	       rtc->base + RZN1_RTC_CTL0);
+	/* Only switch to scmp if we have an xtal clock with a valid rate and != 32768 */
+	xtal = devm_clk_get_optional(&pdev->dev, "xtal");
+	if (IS_ERR(xtal)) {
+		ret = PTR_ERR(xtal);
+		goto dis_runtime_pm;
+	} else if (xtal) {
+		rate = clk_get_rate(xtal);
+
+		if (rate < 32000 || rate > BIT(22)) {
+			ret = -EOPNOTSUPP;
+			goto dis_runtime_pm;
+		}
+
+		if (rate != 32768)
+			scmp_val = RZN1_RTC_CTL0_SLSB_SCMP;
+	}
+
+	/* Disable controller during SUBU/SCMP setup */
+	val = readl(rtc->base + RZN1_RTC_CTL0) & ~RZN1_RTC_CTL0_CE;
+	writel(val, rtc->base + RZN1_RTC_CTL0);
+	/* Wait 2-4 32k clock cycles for the disabled controller */
+	ret = readl_poll_timeout(rtc->base + RZN1_RTC_CTL0, val,
+				 !(val & RZN1_RTC_CTL0_CEST), 62, 123);
+	if (ret)
+		goto dis_runtime_pm;
+
+	/* Set desired modes leaving the controller disabled */
+	writel(RZN1_RTC_CTL0_AMPM | scmp_val, rtc->base + RZN1_RTC_CTL0);
+
+	if (scmp_val) {
+		writel(rate - 1, rtc->base + RZN1_RTC_SCMP);
+		rtc->rtcdev->ops = &rzn1_rtc_ops_scmp;
+	} else {
+		rtc->rtcdev->ops = &rzn1_rtc_ops_subu;
+	}
+
+	/* Enable controller finally */
+	writel(RZN1_RTC_CTL0_CE | RZN1_RTC_CTL0_AMPM | scmp_val, rtc->base + RZN1_RTC_CTL0);
 
 	/* Disable all interrupts */
 	writel(0, rtc->base + RZN1_RTC_CTL1);
@@ -444,6 +488,11 @@ dis_runtime_pm:
 
 static void rzn1_rtc_remove(struct platform_device *pdev)
 {
+	struct rzn1_rtc *rtc = platform_get_drvdata(pdev);
+
+	/* Disable all interrupts */
+	writel(0, rtc->base + RZN1_RTC_CTL1);
+
 	pm_runtime_put(&pdev->dev);
 }
 
diff --git a/drivers/rtc/rtc-s32g.c b/drivers/rtc/rtc-s32g.c
new file mode 100644
index 000000000000..3a0818e972eb
--- /dev/null
+++ b/drivers/rtc/rtc-s32g.c
@@ -0,0 +1,385 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2025 NXP
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/iopoll.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+
+#define RTCC_OFFSET	0x4ul
+#define RTCS_OFFSET	0x8ul
+#define APIVAL_OFFSET	0x10ul
+
+/* RTCC fields */
+#define RTCC_CNTEN				BIT(31)
+#define RTCC_APIEN				BIT(15)
+#define RTCC_APIIE				BIT(14)
+#define RTCC_CLKSEL_MASK		GENMASK(13, 12)
+#define RTCC_DIV512EN			BIT(11)
+#define RTCC_DIV32EN			BIT(10)
+
+/* RTCS fields */
+#define RTCS_INV_API	BIT(17)
+#define RTCS_APIF		BIT(13)
+
+#define APIVAL_MAX_VAL		GENMASK(31, 0)
+#define RTC_SYNCH_TIMEOUT	(100 * USEC_PER_MSEC)
+
+/*
+ * S32G2 and S32G3 SoCs have RTC clock source1 reserved and
+ * should not be used.
+ */
+#define RTC_CLK_SRC1_RESERVED		BIT(1)
+
+/*
+ * S32G RTC module has a 512 value and a 32 value hardware frequency
+ * divisors (DIV512 and DIV32) which could be used to achieve higher
+ * counter ranges by lowering the RTC frequency.
+ */
+enum {
+	DIV1 = 1,
+	DIV32 = 32,
+	DIV512 = 512,
+	DIV512_32 = 16384
+};
+
+static const char *const rtc_clk_src[] = {
+	"source0",
+	"source1",
+	"source2",
+	"source3"
+};
+
+struct rtc_priv {
+	struct rtc_device *rdev;
+	void __iomem *rtc_base;
+	struct clk *ipg;
+	struct clk *clk_src;
+	const struct rtc_soc_data *rtc_data;
+	u64 rtc_hz;
+	time64_t sleep_sec;
+	int irq;
+	u32 clk_src_idx;
+};
+
+struct rtc_soc_data {
+	u32 clk_div;
+	u32 reserved_clk_mask;
+};
+
+static const struct rtc_soc_data rtc_s32g2_data = {
+	.clk_div = DIV512_32,
+	.reserved_clk_mask = RTC_CLK_SRC1_RESERVED,
+};
+
+static irqreturn_t s32g_rtc_handler(int irq, void *dev)
+{
+	struct rtc_priv *priv = platform_get_drvdata(dev);
+	u32 status;
+
+	status = readl(priv->rtc_base + RTCS_OFFSET);
+
+	if (status & RTCS_APIF) {
+		writel(0x0, priv->rtc_base + APIVAL_OFFSET);
+		writel(status | RTCS_APIF, priv->rtc_base + RTCS_OFFSET);
+	}
+
+	rtc_update_irq(priv->rdev, 1, RTC_IRQF | RTC_AF);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * The function is not really getting time from the RTC since the S32G RTC
+ * has several limitations. Thus, to setup alarm use system time.
+ */
+static int s32g_rtc_read_time(struct device *dev,
+			      struct rtc_time *tm)
+{
+	struct rtc_priv *priv = dev_get_drvdata(dev);
+	time64_t sec;
+
+	if (check_add_overflow(ktime_get_real_seconds(),
+			       priv->sleep_sec, &sec))
+		return -ERANGE;
+
+	rtc_time64_to_tm(sec, tm);
+
+	return 0;
+}
+
+static int s32g_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct rtc_priv *priv = dev_get_drvdata(dev);
+	u32 rtcc, rtcs;
+
+	rtcc = readl(priv->rtc_base + RTCC_OFFSET);
+	rtcs = readl(priv->rtc_base + RTCS_OFFSET);
+
+	alrm->enabled = rtcc & RTCC_APIIE;
+	if (alrm->enabled)
+		alrm->pending = !(rtcs & RTCS_APIF);
+
+	return 0;
+}
+
+static int s32g_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+	struct rtc_priv *priv = dev_get_drvdata(dev);
+	u32 rtcc;
+
+	/* RTC API functionality is used both for triggering interrupts
+	 * and as a wakeup event. Hence it should always be enabled.
+	 */
+	rtcc = readl(priv->rtc_base + RTCC_OFFSET);
+	rtcc |= RTCC_APIEN | RTCC_APIIE;
+	writel(rtcc, priv->rtc_base + RTCC_OFFSET);
+
+	return 0;
+}
+
+static int s32g_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct rtc_priv *priv = dev_get_drvdata(dev);
+	unsigned long long cycles;
+	long long t_offset;
+	time64_t alrm_time;
+	u32 rtcs;
+	int ret;
+
+	alrm_time = rtc_tm_to_time64(&alrm->time);
+	t_offset = alrm_time - ktime_get_real_seconds() - priv->sleep_sec;
+	if (t_offset < 0)
+		return -ERANGE;
+
+	cycles = t_offset * priv->rtc_hz;
+	if (cycles > APIVAL_MAX_VAL)
+		return -ERANGE;
+
+	/* APIVAL could have been reset from the IRQ handler.
+	 * Hence, we wait in case there is a synchronization process.
+	 */
+	ret = read_poll_timeout(readl, rtcs, !(rtcs & RTCS_INV_API),
+				0, RTC_SYNCH_TIMEOUT, false, priv->rtc_base + RTCS_OFFSET);
+	if (ret)
+		return ret;
+
+	writel(cycles, priv->rtc_base + APIVAL_OFFSET);
+
+	return read_poll_timeout(readl, rtcs, !(rtcs & RTCS_INV_API),
+				0, RTC_SYNCH_TIMEOUT, false, priv->rtc_base + RTCS_OFFSET);
+}
+
+/*
+ * Disable the 32-bit free running counter.
+ * This allows Clock Source and Divisors selection
+ * to be performed without causing synchronization issues.
+ */
+static void s32g_rtc_disable(struct rtc_priv *priv)
+{
+	u32 rtcc = readl(priv->rtc_base + RTCC_OFFSET);
+
+	rtcc &= ~RTCC_CNTEN;
+	writel(rtcc, priv->rtc_base + RTCC_OFFSET);
+}
+
+static void s32g_rtc_enable(struct rtc_priv *priv)
+{
+	u32 rtcc = readl(priv->rtc_base + RTCC_OFFSET);
+
+	rtcc |= RTCC_CNTEN;
+	writel(rtcc, priv->rtc_base + RTCC_OFFSET);
+}
+
+static int rtc_clk_src_setup(struct rtc_priv *priv)
+{
+	u32 rtcc;
+
+	rtcc = FIELD_PREP(RTCC_CLKSEL_MASK, priv->clk_src_idx);
+
+	switch (priv->rtc_data->clk_div) {
+	case DIV512_32:
+		rtcc |= RTCC_DIV512EN;
+		rtcc |= RTCC_DIV32EN;
+		break;
+	case DIV512:
+		rtcc |= RTCC_DIV512EN;
+		break;
+	case DIV32:
+		rtcc |= RTCC_DIV32EN;
+		break;
+	case DIV1:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	rtcc |= RTCC_APIEN | RTCC_APIIE;
+	/*
+	 * Make sure the CNTEN is 0 before we configure
+	 * the clock source and dividers.
+	 */
+	s32g_rtc_disable(priv);
+	writel(rtcc, priv->rtc_base + RTCC_OFFSET);
+	s32g_rtc_enable(priv);
+
+	return 0;
+}
+
+static const struct rtc_class_ops rtc_ops = {
+	.read_time = s32g_rtc_read_time,
+	.read_alarm = s32g_rtc_read_alarm,
+	.set_alarm = s32g_rtc_set_alarm,
+	.alarm_irq_enable = s32g_rtc_alarm_irq_enable,
+};
+
+static int rtc_clk_dts_setup(struct rtc_priv *priv,
+			     struct device *dev)
+{
+	u32 i;
+
+	priv->ipg = devm_clk_get_enabled(dev, "ipg");
+	if (IS_ERR(priv->ipg))
+		return dev_err_probe(dev, PTR_ERR(priv->ipg),
+				"Failed to get 'ipg' clock\n");
+
+	for (i = 0; i < ARRAY_SIZE(rtc_clk_src); i++) {
+		if (priv->rtc_data->reserved_clk_mask & BIT(i))
+			return -EOPNOTSUPP;
+
+		priv->clk_src = devm_clk_get_enabled(dev, rtc_clk_src[i]);
+		if (!IS_ERR(priv->clk_src)) {
+			priv->clk_src_idx = i;
+			break;
+		}
+	}
+
+	if (IS_ERR(priv->clk_src))
+		return dev_err_probe(dev, PTR_ERR(priv->clk_src),
+				"Failed to get rtc module clock source\n");
+
+	return 0;
+}
+
+static int s32g_rtc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rtc_priv *priv;
+	unsigned long rtc_hz;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->rtc_data = of_device_get_match_data(dev);
+	if (!priv->rtc_data)
+		return -ENODEV;
+
+	priv->rtc_base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(priv->rtc_base))
+		return PTR_ERR(priv->rtc_base);
+
+	device_init_wakeup(dev, true);
+
+	ret = rtc_clk_dts_setup(priv, dev);
+	if (ret)
+		return ret;
+
+	priv->rdev = devm_rtc_allocate_device(dev);
+	if (IS_ERR(priv->rdev))
+		return PTR_ERR(priv->rdev);
+
+	ret = rtc_clk_src_setup(priv);
+	if (ret)
+		return ret;
+
+	priv->irq = platform_get_irq(pdev, 0);
+	if (priv->irq < 0) {
+		ret = priv->irq;
+		goto disable_rtc;
+	}
+
+	rtc_hz = clk_get_rate(priv->clk_src);
+	if (!rtc_hz) {
+		dev_err(dev, "Failed to get RTC frequency\n");
+		ret = -EINVAL;
+		goto disable_rtc;
+	}
+
+	priv->rtc_hz = DIV_ROUND_UP(rtc_hz, priv->rtc_data->clk_div);
+
+	platform_set_drvdata(pdev, priv);
+	priv->rdev->ops = &rtc_ops;
+
+	ret = devm_request_irq(dev, priv->irq,
+			       s32g_rtc_handler, 0, dev_name(dev), pdev);
+	if (ret) {
+		dev_err(dev, "Request interrupt %d failed, error: %d\n",
+			priv->irq, ret);
+		goto disable_rtc;
+	}
+
+	ret = devm_rtc_register_device(priv->rdev);
+	if (ret)
+		goto disable_rtc;
+
+	return 0;
+
+disable_rtc:
+	s32g_rtc_disable(priv);
+	return ret;
+}
+
+static int s32g_rtc_suspend(struct device *dev)
+{
+	struct rtc_priv *priv = dev_get_drvdata(dev);
+	u32 apival = readl(priv->rtc_base + APIVAL_OFFSET);
+
+	if (check_add_overflow(priv->sleep_sec, div64_u64(apival, priv->rtc_hz),
+			       &priv->sleep_sec)) {
+		dev_warn(dev, "Overflow on sleep cycles occurred. Resetting to 0.\n");
+		priv->sleep_sec = 0;
+	}
+
+	return 0;
+}
+
+static int s32g_rtc_resume(struct device *dev)
+{
+	struct rtc_priv *priv = dev_get_drvdata(dev);
+
+	/* The transition from resume to run is a reset event.
+	 * This leads to the RTC registers being reset after resume from
+	 * suspend. It is uncommon, but this behaviour has been observed
+	 * on S32G RTC after issuing a Suspend to RAM operation.
+	 * Thus, reconfigure RTC registers on the resume path.
+	 */
+	return rtc_clk_src_setup(priv);
+}
+
+static const struct of_device_id rtc_dt_ids[] = {
+	{ .compatible = "nxp,s32g2-rtc", .data = &rtc_s32g2_data },
+	{ /* sentinel */ },
+};
+
+static DEFINE_SIMPLE_DEV_PM_OPS(s32g_rtc_pm_ops,
+			 s32g_rtc_suspend, s32g_rtc_resume);
+
+static struct platform_driver s32g_rtc_driver = {
+	.driver = {
+		.name = "s32g-rtc",
+		.pm = pm_sleep_ptr(&s32g_rtc_pm_ops),
+		.of_match_table = rtc_dt_ids,
+	},
+	.probe = s32g_rtc_probe,
+};
+module_platform_driver(s32g_rtc_driver);
+
+MODULE_AUTHOR("NXP");
+MODULE_DESCRIPTION("NXP RTC driver for S32G2/S32G3");
+MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index 58c957eb753d..5dd575865adf 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -609,4 +609,3 @@ module_platform_driver(s3c_rtc_driver);
 MODULE_DESCRIPTION("Samsung S3C RTC Driver");
 MODULE_AUTHOR("Ben Dooks <ben@simtec.co.uk>");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:s3c2410-rtc");
diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c
index 9ea40f40188f..f15ef3aa82a0 100644
--- a/drivers/rtc/rtc-sh.c
+++ b/drivers/rtc/rtc-sh.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2006 - 2009  Paul Mundt
  * Copyright (C) 2006  Jamie Lenehan
  * Copyright (C) 2008  Angelo Castello
+ * Copyright (C) 2025  Wolfram Sang, Renesas Electronics Corporation
  *
  * Based on the old arch/sh/kernel/cpu/rtc.c by:
  *
@@ -31,7 +32,7 @@
 /* Default values for RZ/A RTC */
 #define rtc_reg_size		sizeof(u16)
 #define RTC_BIT_INVERTED        0	/* no chip bugs */
-#define RTC_CAP_4_DIGIT_YEAR    (1 << 0)
+#define RTC_CAP_4_DIGIT_YEAR    BIT(0)
 #define RTC_DEF_CAPABILITIES    RTC_CAP_4_DIGIT_YEAR
 #endif
 
@@ -70,62 +71,35 @@
  */
 
 /* ALARM Bits - or with BCD encoded value */
-#define AR_ENB		0x80	/* Enable for alarm cmp   */
-
-/* Period Bits */
-#define PF_HP		0x100	/* Enable Half Period to support 8,32,128Hz */
-#define PF_COUNT	0x200	/* Half periodic counter */
-#define PF_OXS		0x400	/* Periodic One x Second */
-#define PF_KOU		0x800	/* Kernel or User periodic request 1=kernel */
-#define PF_MASK		0xf00
+#define AR_ENB		BIT(7)	/* Enable for alarm cmp   */
 
 /* RCR1 Bits */
-#define RCR1_CF		0x80	/* Carry Flag             */
-#define RCR1_CIE	0x10	/* Carry Interrupt Enable */
-#define RCR1_AIE	0x08	/* Alarm Interrupt Enable */
-#define RCR1_AF		0x01	/* Alarm Flag             */
+#define RCR1_CF		BIT(7)	/* Carry Flag             */
+#define RCR1_CIE	BIT(4)	/* Carry Interrupt Enable */
+#define RCR1_AIE	BIT(3)	/* Alarm Interrupt Enable */
+#define RCR1_AF		BIT(0)	/* Alarm Flag             */
 
 /* RCR2 Bits */
-#define RCR2_PEF	0x80	/* PEriodic interrupt Flag */
-#define RCR2_PESMASK	0x70	/* Periodic interrupt Set  */
-#define RCR2_RTCEN	0x08	/* ENable RTC              */
-#define RCR2_ADJ	0x04	/* ADJustment (30-second)  */
-#define RCR2_RESET	0x02	/* Reset bit               */
-#define RCR2_START	0x01	/* Start bit               */
+#define RCR2_RTCEN	BIT(3)	/* ENable RTC              */
+#define RCR2_ADJ	BIT(2)	/* ADJustment (30-second)  */
+#define RCR2_RESET	BIT(1)	/* Reset bit               */
+#define RCR2_START	BIT(0)	/* Start bit               */
 
 struct sh_rtc {
 	void __iomem		*regbase;
-	unsigned long		regsize;
-	struct resource		*res;
 	int			alarm_irq;
-	int			periodic_irq;
-	int			carry_irq;
 	struct clk		*clk;
 	struct rtc_device	*rtc_dev;
-	spinlock_t		lock;
+	spinlock_t		lock;		/* protecting register access */
 	unsigned long		capabilities;	/* See asm/rtc.h for cap bits */
-	unsigned short		periodic_freq;
 };
 
-static int __sh_rtc_interrupt(struct sh_rtc *rtc)
+static irqreturn_t sh_rtc_alarm(int irq, void *dev_id)
 {
+	struct sh_rtc *rtc = dev_id;
 	unsigned int tmp, pending;
 
-	tmp = readb(rtc->regbase + RCR1);
-	pending = tmp & RCR1_CF;
-	tmp &= ~RCR1_CF;
-	writeb(tmp, rtc->regbase + RCR1);
-
-	/* Users have requested One x Second IRQ */
-	if (pending && rtc->periodic_freq & PF_OXS)
-		rtc_update_irq(rtc->rtc_dev, 1, RTC_UF | RTC_IRQF);
-
-	return pending;
-}
-
-static int __sh_rtc_alarm(struct sh_rtc *rtc)
-{
-	unsigned int tmp, pending;
+	spin_lock(&rtc->lock);
 
 	tmp = readb(rtc->regbase + RCR1);
 	pending = tmp & RCR1_AF;
@@ -135,84 +109,12 @@ static int __sh_rtc_alarm(struct sh_rtc *rtc)
 	if (pending)
 		rtc_update_irq(rtc->rtc_dev, 1, RTC_AF | RTC_IRQF);
 
-	return pending;
-}
-
-static int __sh_rtc_periodic(struct sh_rtc *rtc)
-{
-	unsigned int tmp, pending;
-
-	tmp = readb(rtc->regbase + RCR2);
-	pending = tmp & RCR2_PEF;
-	tmp &= ~RCR2_PEF;
-	writeb(tmp, rtc->regbase + RCR2);
-
-	if (!pending)
-		return 0;
-
-	/* Half period enabled than one skipped and the next notified */
-	if ((rtc->periodic_freq & PF_HP) && (rtc->periodic_freq & PF_COUNT))
-		rtc->periodic_freq &= ~PF_COUNT;
-	else {
-		if (rtc->periodic_freq & PF_HP)
-			rtc->periodic_freq |= PF_COUNT;
-		rtc_update_irq(rtc->rtc_dev, 1, RTC_PF | RTC_IRQF);
-	}
-
-	return pending;
-}
-
-static irqreturn_t sh_rtc_interrupt(int irq, void *dev_id)
-{
-	struct sh_rtc *rtc = dev_id;
-	int ret;
-
-	spin_lock(&rtc->lock);
-	ret = __sh_rtc_interrupt(rtc);
-	spin_unlock(&rtc->lock);
-
-	return IRQ_RETVAL(ret);
-}
-
-static irqreturn_t sh_rtc_alarm(int irq, void *dev_id)
-{
-	struct sh_rtc *rtc = dev_id;
-	int ret;
-
-	spin_lock(&rtc->lock);
-	ret = __sh_rtc_alarm(rtc);
-	spin_unlock(&rtc->lock);
-
-	return IRQ_RETVAL(ret);
-}
-
-static irqreturn_t sh_rtc_periodic(int irq, void *dev_id)
-{
-	struct sh_rtc *rtc = dev_id;
-	int ret;
-
-	spin_lock(&rtc->lock);
-	ret = __sh_rtc_periodic(rtc);
-	spin_unlock(&rtc->lock);
-
-	return IRQ_RETVAL(ret);
-}
-
-static irqreturn_t sh_rtc_shared(int irq, void *dev_id)
-{
-	struct sh_rtc *rtc = dev_id;
-	int ret;
-
-	spin_lock(&rtc->lock);
-	ret = __sh_rtc_interrupt(rtc);
-	ret |= __sh_rtc_alarm(rtc);
-	ret |= __sh_rtc_periodic(rtc);
 	spin_unlock(&rtc->lock);
 
-	return IRQ_RETVAL(ret);
+	return IRQ_RETVAL(pending);
 }
 
-static inline void sh_rtc_setaie(struct device *dev, unsigned int enable)
+static int sh_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
 {
 	struct sh_rtc *rtc = dev_get_drvdata(dev);
 	unsigned int tmp;
@@ -229,45 +131,7 @@ static inline void sh_rtc_setaie(struct device *dev, unsigned int enable)
 	writeb(tmp, rtc->regbase + RCR1);
 
 	spin_unlock_irq(&rtc->lock);
-}
-
-static int sh_rtc_proc(struct device *dev, struct seq_file *seq)
-{
-	struct sh_rtc *rtc = dev_get_drvdata(dev);
-	unsigned int tmp;
-
-	tmp = readb(rtc->regbase + RCR1);
-	seq_printf(seq, "carry_IRQ\t: %s\n", (tmp & RCR1_CIE) ? "yes" : "no");
-
-	tmp = readb(rtc->regbase + RCR2);
-	seq_printf(seq, "periodic_IRQ\t: %s\n",
-		   (tmp & RCR2_PESMASK) ? "yes" : "no");
-
-	return 0;
-}
-
-static inline void sh_rtc_setcie(struct device *dev, unsigned int enable)
-{
-	struct sh_rtc *rtc = dev_get_drvdata(dev);
-	unsigned int tmp;
-
-	spin_lock_irq(&rtc->lock);
-
-	tmp = readb(rtc->regbase + RCR1);
-
-	if (!enable)
-		tmp &= ~RCR1_CIE;
-	else
-		tmp |= RCR1_CIE;
-
-	writeb(tmp, rtc->regbase + RCR1);
-
-	spin_unlock_irq(&rtc->lock);
-}
 
-static int sh_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
-{
-	sh_rtc_setaie(dev, enabled);
 	return 0;
 }
 
@@ -320,14 +184,8 @@ static int sh_rtc_read_time(struct device *dev, struct rtc_time *tm)
 		tm->tm_sec--;
 #endif
 
-	/* only keep the carry interrupt enabled if UIE is on */
-	if (!(rtc->periodic_freq & PF_OXS))
-		sh_rtc_setcie(dev, 0);
-
-	dev_dbg(dev, "%s: tm is secs=%d, mins=%d, hours=%d, "
-		"mday=%d, mon=%d, year=%d, wday=%d\n",
-		__func__,
-		tm->tm_sec, tm->tm_min, tm->tm_hour,
+	dev_dbg(dev, "%s: tm is secs=%d, mins=%d, hours=%d, mday=%d, mon=%d, year=%d, wday=%d\n",
+		__func__, tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon + 1, tm->tm_year, tm->tm_wday);
 
 	return 0;
@@ -461,16 +319,17 @@ static const struct rtc_class_ops sh_rtc_ops = {
 	.set_time	= sh_rtc_set_time,
 	.read_alarm	= sh_rtc_read_alarm,
 	.set_alarm	= sh_rtc_set_alarm,
-	.proc		= sh_rtc_proc,
 	.alarm_irq_enable = sh_rtc_alarm_irq_enable,
 };
 
 static int __init sh_rtc_probe(struct platform_device *pdev)
 {
 	struct sh_rtc *rtc;
-	struct resource *res;
+	struct resource *res, *req_res;
 	char clk_name[14];
 	int clk_id, ret;
+	unsigned int tmp;
+	resource_size_t regsize;
 
 	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
 	if (unlikely(!rtc))
@@ -478,34 +337,32 @@ static int __init sh_rtc_probe(struct platform_device *pdev)
 
 	spin_lock_init(&rtc->lock);
 
-	/* get periodic/carry/alarm irqs */
 	ret = platform_get_irq(pdev, 0);
 	if (unlikely(ret <= 0)) {
 		dev_err(&pdev->dev, "No IRQ resource\n");
 		return -ENOENT;
 	}
 
-	rtc->periodic_irq = ret;
-	rtc->carry_irq = platform_get_irq(pdev, 1);
-	rtc->alarm_irq = platform_get_irq(pdev, 2);
+	if (!pdev->dev.of_node)
+		rtc->alarm_irq = platform_get_irq(pdev, 2);
+	else
+		rtc->alarm_irq = ret;
 
 	res = platform_get_resource(pdev, IORESOURCE_IO, 0);
 	if (!res)
 		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (unlikely(res == NULL)) {
+	if (!res) {
 		dev_err(&pdev->dev, "No IO resource\n");
 		return -ENOENT;
 	}
 
-	rtc->regsize = resource_size(res);
-
-	rtc->res = devm_request_mem_region(&pdev->dev, res->start,
-					rtc->regsize, pdev->name);
-	if (unlikely(!rtc->res))
+	regsize = resource_size(res);
+	req_res = devm_request_mem_region(&pdev->dev, res->start, regsize, pdev->name);
+	if (!req_res)
 		return -EBUSY;
 
-	rtc->regbase = devm_ioremap(&pdev->dev, rtc->res->start, rtc->regsize);
-	if (unlikely(!rtc->regbase))
+	rtc->regbase = devm_ioremap(&pdev->dev, req_res->start, regsize);
+	if (!rtc->regbase)
 		return -EINVAL;
 
 	if (!pdev->dev.of_node) {
@@ -515,8 +372,9 @@ static int __init sh_rtc_probe(struct platform_device *pdev)
 			clk_id = 0;
 
 		snprintf(clk_name, sizeof(clk_name), "rtc%d", clk_id);
-	} else
+	} else {
 		snprintf(clk_name, sizeof(clk_name), "fck");
+	}
 
 	rtc->clk = devm_clk_get(&pdev->dev, clk_name);
 	if (IS_ERR(rtc->clk)) {
@@ -550,51 +408,19 @@ static int __init sh_rtc_probe(struct platform_device *pdev)
 	}
 #endif
 
-	if (rtc->carry_irq <= 0) {
-		/* register shared periodic/carry/alarm irq */
-		ret = devm_request_irq(&pdev->dev, rtc->periodic_irq,
-				sh_rtc_shared, 0, "sh-rtc", rtc);
-		if (unlikely(ret)) {
-			dev_err(&pdev->dev,
-				"request IRQ failed with %d, IRQ %d\n", ret,
-				rtc->periodic_irq);
-			goto err_unmap;
-		}
-	} else {
-		/* register periodic/carry/alarm irqs */
-		ret = devm_request_irq(&pdev->dev, rtc->periodic_irq,
-				sh_rtc_periodic, 0, "sh-rtc period", rtc);
-		if (unlikely(ret)) {
-			dev_err(&pdev->dev,
-				"request period IRQ failed with %d, IRQ %d\n",
-				ret, rtc->periodic_irq);
-			goto err_unmap;
-		}
-
-		ret = devm_request_irq(&pdev->dev, rtc->carry_irq,
-				sh_rtc_interrupt, 0, "sh-rtc carry", rtc);
-		if (unlikely(ret)) {
-			dev_err(&pdev->dev,
-				"request carry IRQ failed with %d, IRQ %d\n",
-				ret, rtc->carry_irq);
-			goto err_unmap;
-		}
-
-		ret = devm_request_irq(&pdev->dev, rtc->alarm_irq,
-				sh_rtc_alarm, 0, "sh-rtc alarm", rtc);
-		if (unlikely(ret)) {
-			dev_err(&pdev->dev,
-				"request alarm IRQ failed with %d, IRQ %d\n",
-				ret, rtc->alarm_irq);
-			goto err_unmap;
-		}
+	ret = devm_request_irq(&pdev->dev, rtc->alarm_irq, sh_rtc_alarm, 0, "sh-rtc", rtc);
+	if (ret) {
+		dev_err(&pdev->dev, "request alarm IRQ failed with %d, IRQ %d\n",
+			ret, rtc->alarm_irq);
+		goto err_unmap;
 	}
 
 	platform_set_drvdata(pdev, rtc);
 
 	/* everything disabled by default */
-	sh_rtc_setaie(&pdev->dev, 0);
-	sh_rtc_setcie(&pdev->dev, 0);
+	tmp = readb(rtc->regbase + RCR1);
+	tmp &= ~(RCR1_CIE | RCR1_AIE);
+	writeb(tmp, rtc->regbase + RCR1);
 
 	rtc->rtc_dev->ops = &sh_rtc_ops;
 	rtc->rtc_dev->max_user_freq = 256;
@@ -624,36 +450,27 @@ static void __exit sh_rtc_remove(struct platform_device *pdev)
 {
 	struct sh_rtc *rtc = platform_get_drvdata(pdev);
 
-	sh_rtc_setaie(&pdev->dev, 0);
-	sh_rtc_setcie(&pdev->dev, 0);
+	sh_rtc_alarm_irq_enable(&pdev->dev, 0);
 
 	clk_disable(rtc->clk);
 }
 
-static void sh_rtc_set_irq_wake(struct device *dev, int enabled)
+static int __maybe_unused sh_rtc_suspend(struct device *dev)
 {
 	struct sh_rtc *rtc = dev_get_drvdata(dev);
 
-	irq_set_irq_wake(rtc->periodic_irq, enabled);
-
-	if (rtc->carry_irq > 0) {
-		irq_set_irq_wake(rtc->carry_irq, enabled);
-		irq_set_irq_wake(rtc->alarm_irq, enabled);
-	}
-}
-
-static int __maybe_unused sh_rtc_suspend(struct device *dev)
-{
 	if (device_may_wakeup(dev))
-		sh_rtc_set_irq_wake(dev, 1);
+		irq_set_irq_wake(rtc->alarm_irq, 1);
 
 	return 0;
 }
 
 static int __maybe_unused sh_rtc_resume(struct device *dev)
 {
+	struct sh_rtc *rtc = dev_get_drvdata(dev);
+
 	if (device_may_wakeup(dev))
-		sh_rtc_set_irq_wake(dev, 0);
+		irq_set_irq_wake(rtc->alarm_irq, 0);
 
 	return 0;
 }
@@ -684,8 +501,8 @@ static struct platform_driver sh_rtc_platform_driver __refdata = {
 module_platform_driver_probe(sh_rtc_platform_driver, sh_rtc_probe);
 
 MODULE_DESCRIPTION("SuperH on-chip RTC driver");
-MODULE_AUTHOR("Paul Mundt <lethal@linux-sh.org>, "
-	      "Jamie Lenehan <lenehan@twibble.org>, "
-	      "Angelo Castello <angelo.castello@st.com>");
+MODULE_AUTHOR("Paul Mundt <lethal@linux-sh.org>");
+MODULE_AUTHOR("Jamie Lenehan <lenehan@twibble.org>");
+MODULE_AUTHOR("Angelo Castello <angelo.castello@st.com>");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index 1b715db47160..ef8fb88aab48 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -1283,7 +1283,6 @@ static struct platform_driver stm32_rtc_driver = {
 
 module_platform_driver(stm32_rtc_driver);
 
-MODULE_ALIAS("platform:" DRIVER_NAME);
 MODULE_AUTHOR("Amelie Delaunay <amelie.delaunay@st.com>");
 MODULE_DESCRIPTION("STMicroelectronics STM32 Real Time Clock driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/scsi/bnx2fc/Kconfig b/drivers/scsi/bnx2fc/Kconfig
index ecdc0f0f4f4e..3cf7e08df809 100644
--- a/drivers/scsi/bnx2fc/Kconfig
+++ b/drivers/scsi/bnx2fc/Kconfig
@@ -5,7 +5,6 @@ config SCSI_BNX2X_FCOE
 	depends on (IPV6 || IPV6=n)
 	depends on LIBFC
 	depends on LIBFCOE
-	depends on MMU
 	select NETDEVICES
 	select ETHERNET
 	select NET_VENDOR_BROADCOM
diff --git a/drivers/scsi/bnx2i/Kconfig b/drivers/scsi/bnx2i/Kconfig
index 0cc06c2ce0b8..75ace2302fed 100644
--- a/drivers/scsi/bnx2i/Kconfig
+++ b/drivers/scsi/bnx2i/Kconfig
@@ -4,7 +4,6 @@ config SCSI_BNX2_ISCSI
 	depends on NET
 	depends on PCI
 	depends on (IPV6 || IPV6=n)
-	depends on MMU
 	select SCSI_ISCSI_ATTRS
 	select NETDEVICES
 	select ETHERNET
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 39aecd34c641..68db4b67a86f 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -56,6 +56,8 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
 		return ret;
 	}
 
+	ida_init(&bus->slave_ida);
+
 	ret = sdw_master_device_add(bus, parent, fwnode);
 	if (ret < 0) {
 		dev_err(parent, "Failed to add master device at link %d\n",
@@ -751,41 +753,36 @@ err:
 static int sdw_assign_device_num(struct sdw_slave *slave)
 {
 	struct sdw_bus *bus = slave->bus;
-	int ret, dev_num;
-	bool new_device = false;
+	struct device *dev = bus->dev;
+	int ret;
 
 	/* check first if device number is assigned, if so reuse that */
 	if (!slave->dev_num) {
 		if (!slave->dev_num_sticky) {
+			int dev_num;
+
 			mutex_lock(&slave->bus->bus_lock);
 			dev_num = sdw_get_device_num(slave);
 			mutex_unlock(&slave->bus->bus_lock);
 			if (dev_num < 0) {
-				dev_err(bus->dev, "Get dev_num failed: %d\n",
-					dev_num);
+				dev_err(dev, "Get dev_num failed: %d\n", dev_num);
 				return dev_num;
 			}
-			slave->dev_num = dev_num;
+
 			slave->dev_num_sticky = dev_num;
-			new_device = true;
 		} else {
-			slave->dev_num = slave->dev_num_sticky;
+			dev_dbg(dev, "Slave already registered, reusing dev_num: %d\n",
+				slave->dev_num_sticky);
 		}
 	}
 
-	if (!new_device)
-		dev_dbg(bus->dev,
-			"Slave already registered, reusing dev_num:%d\n",
-			slave->dev_num);
-
 	/* Clear the slave->dev_num to transfer message on device 0 */
-	dev_num = slave->dev_num;
 	slave->dev_num = 0;
 
-	ret = sdw_write_no_pm(slave, SDW_SCP_DEVNUMBER, dev_num);
+	ret = sdw_write_no_pm(slave, SDW_SCP_DEVNUMBER, slave->dev_num_sticky);
 	if (ret < 0) {
-		dev_err(bus->dev, "Program device_num %d failed: %d\n",
-			dev_num, ret);
+		dev_err(dev, "Program device_num %d failed: %d\n",
+			slave->dev_num_sticky, ret);
 		return ret;
 	}
 
@@ -793,7 +790,7 @@ static int sdw_assign_device_num(struct sdw_slave *slave)
 	slave->dev_num = slave->dev_num_sticky;
 
 	if (bus->ops && bus->ops->new_peripheral_assigned)
-		bus->ops->new_peripheral_assigned(bus, slave, dev_num);
+		bus->ops->new_peripheral_assigned(bus, slave, slave->dev_num);
 
 	return 0;
 }
diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c
index e98d5db81b1c..75d6f16efced 100644
--- a/drivers/soundwire/bus_type.c
+++ b/drivers/soundwire/bus_type.c
@@ -105,9 +105,17 @@ static int sdw_drv_probe(struct device *dev)
 	if (ret)
 		return ret;
 
+	ret = ida_alloc_max(&slave->bus->slave_ida, SDW_FW_MAX_DEVICES, GFP_KERNEL);
+	if (ret < 0) {
+		dev_err(dev, "Failed to allocated ID: %d\n", ret);
+		return ret;
+	}
+	slave->index = ret;
+
 	ret = drv->probe(slave, id);
 	if (ret) {
 		dev_pm_domain_detach(dev, false);
+		ida_free(&slave->bus->slave_ida, slave->index);
 		return ret;
 	}
 
@@ -174,6 +182,8 @@ static int sdw_drv_remove(struct device *dev)
 
 	dev_pm_domain_detach(dev, false);
 
+	ida_free(&slave->bus->slave_ida, slave->index);
+
 	return ret;
 }
 
diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c
index 1cfaccf43eac..c18f0c16f929 100644
--- a/drivers/soundwire/generic_bandwidth_allocation.c
+++ b/drivers/soundwire/generic_bandwidth_allocation.c
@@ -204,6 +204,13 @@ static void _sdw_compute_port_params(struct sdw_bus *bus,
 			port_bo = 1;
 
 			list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
+				/*
+				 * Only runtimes with CONFIGURED, PREPARED, ENABLED, and DISABLED
+				 * states should be included in the bandwidth calculation.
+				 */
+				if (m_rt->stream->state > SDW_STREAM_DISABLED ||
+				    m_rt->stream->state < SDW_STREAM_CONFIGURED)
+					continue;
 				sdw_compute_master_ports(m_rt, &params[i], &port_bo, hstop);
 			}
 
diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h
index d44e70d3c4e3..86abc465260f 100644
--- a/drivers/soundwire/intel.h
+++ b/drivers/soundwire/intel.h
@@ -22,6 +22,7 @@ struct hdac_bus;
  * @shim_lock: mutex to handle access to shared SHIM registers
  * @shim_mask: global pointer to check SHIM register initialization
  * @clock_stop_quirks: mask defining requested behavior on pm_suspend
+ * @mic_privacy: ACE version supports microphone privacy
  * @link_mask: global mask needed for power-up/down sequences
  * @cdns: Cadence master descriptor
  * @list: used to walk-through all masters exposed by the same controller
@@ -42,6 +43,7 @@ struct sdw_intel_link_res {
 	struct mutex *shim_lock; /* protect shared registers */
 	u32 *shim_mask;
 	u32 clock_stop_quirks;
+	bool mic_privacy;
 	u32 link_mask;
 	struct sdw_cdns *cdns;
 	struct list_head list;
diff --git a/drivers/soundwire/intel_ace2x_debugfs.c b/drivers/soundwire/intel_ace2x_debugfs.c
index 206a8d511ebd..fda8f0daaa96 100644
--- a/drivers/soundwire/intel_ace2x_debugfs.c
+++ b/drivers/soundwire/intel_ace2x_debugfs.c
@@ -76,6 +76,12 @@ static int intel_reg_show(struct seq_file *s_file, void *data)
 	ret += intel_sprintf(vs_s, false, buf, ret, SDW_SHIM2_INTEL_VS_IOCTL);
 	ret += intel_sprintf(vs_s, false, buf, ret, SDW_SHIM2_INTEL_VS_ACTMCTL);
 
+	if (sdw->link_res->mic_privacy) {
+		ret += scnprintf(buf + ret, RD_BUF - ret, "\nVS PVCCS\n");
+		ret += intel_sprintf(vs_s, false, buf, ret,
+				     SDW_SHIM2_INTEL_VS_PVCCS);
+	}
+
 	seq_printf(s_file, "%s", buf);
 	kfree(buf);
 
diff --git a/drivers/soundwire/intel_init.c b/drivers/soundwire/intel_init.c
index 5f53666514a4..4ffdabaf9693 100644
--- a/drivers/soundwire/intel_init.c
+++ b/drivers/soundwire/intel_init.c
@@ -77,6 +77,7 @@ static struct sdw_intel_link_dev *intel_link_dev_register(struct sdw_intel_res *
 		link->shim = res->mmio_base +  SDW_SHIM2_GENERIC_BASE(link_id);
 		link->shim_vs = res->mmio_base + SDW_SHIM2_VS_BASE(link_id);
 		link->shim_lock = res->eml_lock;
+		link->mic_privacy = res->mic_privacy;
 	}
 
 	link->ops = res->ops;
diff --git a/drivers/soundwire/irq.c b/drivers/soundwire/irq.c
index c237e6d0766b..f18be37efef8 100644
--- a/drivers/soundwire/irq.c
+++ b/drivers/soundwire/irq.c
@@ -31,7 +31,7 @@ int sdw_irq_create(struct sdw_bus *bus,
 {
 	bus->irq_chip.name = dev_name(bus->dev);
 
-	bus->domain = irq_domain_create_linear(fwnode, SDW_MAX_DEVICES,
+	bus->domain = irq_domain_create_linear(fwnode, SDW_FW_MAX_DEVICES,
 					       &sdw_domain_ops, bus);
 	if (!bus->domain) {
 		dev_err(bus->dev, "Failed to add IRQ domain\n");
@@ -50,12 +50,12 @@ static void sdw_irq_dispose_mapping(void *data)
 {
 	struct sdw_slave *slave = data;
 
-	irq_dispose_mapping(irq_find_mapping(slave->bus->domain, slave->dev_num));
+	irq_dispose_mapping(slave->irq);
 }
 
 void sdw_irq_create_mapping(struct sdw_slave *slave)
 {
-	slave->irq = irq_create_mapping(slave->bus->domain, slave->dev_num);
+	slave->irq = irq_create_mapping(slave->bus->domain, slave->index);
 	if (!slave->irq)
 		dev_warn(&slave->dev, "Failed to map IRQ\n");
 
diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
index 69c1df0f4ca5..aac67a4413ce 100644
--- a/drivers/uio/uio_hv_generic.c
+++ b/drivers/uio/uio_hv_generic.c
@@ -243,6 +243,9 @@ hv_uio_probe(struct hv_device *dev,
 	if (!ring_size)
 		ring_size = SZ_2M;
 
+	/* Adjust ring size if necessary to have it page aligned */
+	ring_size = VMBUS_RING_SIZE(ring_size);
+
 	pdata = devm_kzalloc(&dev->device, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return -ENOMEM;
@@ -274,13 +277,13 @@ hv_uio_probe(struct hv_device *dev,
 	pdata->info.mem[INT_PAGE_MAP].name = "int_page";
 	pdata->info.mem[INT_PAGE_MAP].addr
 		= (uintptr_t)vmbus_connection.int_page;
-	pdata->info.mem[INT_PAGE_MAP].size = PAGE_SIZE;
+	pdata->info.mem[INT_PAGE_MAP].size = HV_HYP_PAGE_SIZE;
 	pdata->info.mem[INT_PAGE_MAP].memtype = UIO_MEM_LOGICAL;
 
 	pdata->info.mem[MON_PAGE_MAP].name = "monitor_page";
 	pdata->info.mem[MON_PAGE_MAP].addr
 		= (uintptr_t)vmbus_connection.monitor_pages[1];
-	pdata->info.mem[MON_PAGE_MAP].size = PAGE_SIZE;
+	pdata->info.mem[MON_PAGE_MAP].size = HV_HYP_PAGE_SIZE;
 	pdata->info.mem[MON_PAGE_MAP].memtype = UIO_MEM_LOGICAL;
 
 	if (channel->device_id == HV_NIC) {
diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index 740311c4fa24..c7a05f842745 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -144,8 +144,8 @@ static struct hid_descriptor hidg_desc = {
 	.bcdHID				= cpu_to_le16(0x0101),
 	.bCountryCode			= 0x00,
 	.bNumDescriptors		= 0x1,
-	/*.desc[0].bDescriptorType	= DYNAMIC */
-	/*.desc[0].wDescriptorLenght	= DYNAMIC */
+	/*.rpt_desc.bDescriptorType	= DYNAMIC */
+	/*.rpt_desc.wDescriptorLength	= DYNAMIC */
 };
 
 /* Super-Speed Support */
@@ -939,8 +939,8 @@ static int hidg_setup(struct usb_function *f,
 			struct hid_descriptor hidg_desc_copy = hidg_desc;
 
 			VDBG(cdev, "USB_REQ_GET_DESCRIPTOR: HID\n");
-			hidg_desc_copy.desc[0].bDescriptorType = HID_DT_REPORT;
-			hidg_desc_copy.desc[0].wDescriptorLength =
+			hidg_desc_copy.rpt_desc.bDescriptorType = HID_DT_REPORT;
+			hidg_desc_copy.rpt_desc.wDescriptorLength =
 				cpu_to_le16(hidg->report_desc_length);
 
 			length = min_t(unsigned short, length,
@@ -1210,8 +1210,8 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f)
 	 * We can use hidg_desc struct here but we should not relay
 	 * that its content won't change after returning from this function.
 	 */
-	hidg_desc.desc[0].bDescriptorType = HID_DT_REPORT;
-	hidg_desc.desc[0].wDescriptorLength =
+	hidg_desc.rpt_desc.bDescriptorType = HID_DT_REPORT;
+	hidg_desc.rpt_desc.wDescriptorLength =
 		cpu_to_le16(hidg->report_desc_length);
 
 	hidg_hs_in_ep_desc.bEndpointAddress =
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 8adf6f954633..5ea884ef36af 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -7166,7 +7166,7 @@ static void tcpm_fw_get_timings(struct tcpm_port *port, struct fwnode_handle *fw
 
 static int tcpm_fw_get_caps(struct tcpm_port *port, struct fwnode_handle *fwnode)
 {
-	struct fwnode_handle *capabilities, *child, *caps = NULL;
+	struct fwnode_handle *capabilities, *caps = NULL;
 	unsigned int nr_src_pdo, nr_snk_pdo;
 	const char *opmode_str;
 	u32 *src_pdo, *snk_pdo;
@@ -7232,9 +7232,7 @@ static int tcpm_fw_get_caps(struct tcpm_port *port, struct fwnode_handle *fwnode
 	if (!capabilities) {
 		port->pd_count = 1;
 	} else {
-		fwnode_for_each_child_node(capabilities, child)
-			port->pd_count++;
-
+		port->pd_count = fwnode_get_child_node_count(capabilities);
 		if (!port->pd_count) {
 			ret = -ENODATA;
 			goto put_capabilities;
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index c3bcb6911c53..2b0172f54665 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 menu "VFIO support for PCI devices"
-	depends on PCI && MMU
+	depends on PCI
 
 config VFIO_PCI_CORE
 	tristate
diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c
index f699e5827ccb..9dc93c5e480b 100644
--- a/drivers/video/backlight/backlight.c
+++ b/drivers/video/backlight/backlight.c
@@ -15,7 +15,6 @@
 #include <linux/notifier.h>
 #include <linux/ctype.h>
 #include <linux/err.h>
-#include <linux/fb.h>
 #include <linux/slab.h>
 
 #ifdef CONFIG_PMAC_BACKLIGHT
@@ -57,10 +56,10 @@
  * a hot-key to adjust backlight, the driver must notify the backlight
  * core that brightness has changed using backlight_force_update().
  *
- * The backlight driver core receives notifications from fbdev and
- * if the event is FB_EVENT_BLANK and if the value of blank, from the
- * FBIOBLANK ioctrl, results in a change in the backlight state the
- * update_status() operation is called.
+ * Display drives can control the backlight device's status using
+ * backlight_notify_blank() and backlight_notify_blank_all(). If this
+ * results in a change in the backlight state the functions call the
+ * update_status() operation.
  */
 
 static struct list_head backlight_dev_list;
@@ -78,85 +77,40 @@ static const char *const backlight_scale_types[] = {
 	[BACKLIGHT_SCALE_NON_LINEAR]	= "non-linear",
 };
 
-#if defined(CONFIG_FB_CORE) || (defined(CONFIG_FB_CORE_MODULE) && \
-				defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE))
-/*
- * fb_notifier_callback
- *
- * This callback gets called when something important happens inside a
- * framebuffer driver. The backlight core only cares about FB_BLANK_UNBLANK
- * which is reported to the driver using backlight_update_status()
- * as a state change.
- *
- * There may be several fbdev's connected to the backlight device,
- * in which case they are kept track of. A state change is only reported
- * if there is a change in backlight for the specified fbdev.
- */
-static int fb_notifier_callback(struct notifier_block *self,
-				unsigned long event, void *data)
+void backlight_notify_blank(struct backlight_device *bd, struct device *display_dev,
+			    bool fb_on, bool prev_fb_on)
 {
-	struct backlight_device *bd;
-	struct fb_event *evdata = data;
-	struct fb_info *info = evdata->info;
-	struct backlight_device *fb_bd = fb_bl_device(info);
-	int node = info->node;
-	int fb_blank = 0;
-
-	/* If we aren't interested in this event, skip it immediately ... */
-	if (event != FB_EVENT_BLANK)
-		return 0;
-
-	bd = container_of(self, struct backlight_device, fb_notif);
-	mutex_lock(&bd->ops_lock);
+	guard(mutex)(&bd->ops_lock);
 
 	if (!bd->ops)
-		goto out;
-	if (bd->ops->controls_device && !bd->ops->controls_device(bd, info->device))
-		goto out;
-	if (fb_bd && fb_bd != bd)
-		goto out;
-
-	fb_blank = *(int *)evdata->data;
-	if (fb_blank == FB_BLANK_UNBLANK && !bd->fb_bl_on[node]) {
-		bd->fb_bl_on[node] = true;
+		return;
+	if (bd->ops->controls_device && !bd->ops->controls_device(bd, display_dev))
+		return;
+
+	if (fb_on && (!prev_fb_on || !bd->use_count)) {
 		if (!bd->use_count++) {
 			bd->props.state &= ~BL_CORE_FBBLANK;
 			backlight_update_status(bd);
 		}
-	} else if (fb_blank != FB_BLANK_UNBLANK && bd->fb_bl_on[node]) {
-		bd->fb_bl_on[node] = false;
+	} else if (!fb_on && prev_fb_on && bd->use_count) {
 		if (!(--bd->use_count)) {
 			bd->props.state |= BL_CORE_FBBLANK;
 			backlight_update_status(bd);
 		}
 	}
-out:
-	mutex_unlock(&bd->ops_lock);
-	return 0;
 }
+EXPORT_SYMBOL(backlight_notify_blank);
 
-static int backlight_register_fb(struct backlight_device *bd)
+void backlight_notify_blank_all(struct device *display_dev, bool fb_on, bool prev_fb_on)
 {
-	memset(&bd->fb_notif, 0, sizeof(bd->fb_notif));
-	bd->fb_notif.notifier_call = fb_notifier_callback;
+	struct backlight_device *bd;
 
-	return fb_register_client(&bd->fb_notif);
-}
+	guard(mutex)(&backlight_dev_list_mutex);
 
-static void backlight_unregister_fb(struct backlight_device *bd)
-{
-	fb_unregister_client(&bd->fb_notif);
-}
-#else
-static inline int backlight_register_fb(struct backlight_device *bd)
-{
-	return 0;
+	list_for_each_entry(bd, &backlight_dev_list, entry)
+		backlight_notify_blank(bd, display_dev, fb_on, prev_fb_on);
 }
-
-static inline void backlight_unregister_fb(struct backlight_device *bd)
-{
-}
-#endif /* CONFIG_FB_CORE */
+EXPORT_SYMBOL(backlight_notify_blank_all);
 
 static void backlight_generate_event(struct backlight_device *bd,
 				     enum backlight_update_reason reason)
@@ -447,12 +401,6 @@ struct backlight_device *backlight_device_register(const char *name,
 		return ERR_PTR(rc);
 	}
 
-	rc = backlight_register_fb(new_bd);
-	if (rc) {
-		device_unregister(&new_bd->dev);
-		return ERR_PTR(rc);
-	}
-
 	new_bd->ops = ops;
 
 #ifdef CONFIG_PMAC_BACKLIGHT
@@ -539,7 +487,6 @@ void backlight_device_unregister(struct backlight_device *bd)
 	bd->ops = NULL;
 	mutex_unlock(&bd->ops_lock);
 
-	backlight_unregister_fb(bd);
 	device_unregister(&bd->dev);
 }
 EXPORT_SYMBOL(backlight_device_unregister);
diff --git a/drivers/video/backlight/lcd.c b/drivers/video/backlight/lcd.c
index 3267acf8dc5b..affe5c52471a 100644
--- a/drivers/video/backlight/lcd.c
+++ b/drivers/video/backlight/lcd.c
@@ -15,86 +15,59 @@
 #include <linux/notifier.h>
 #include <linux/ctype.h>
 #include <linux/err.h>
-#include <linux/fb.h>
 #include <linux/slab.h>
 
-#if defined(CONFIG_FB) || (defined(CONFIG_FB_MODULE) && \
-			   defined(CONFIG_LCD_CLASS_DEVICE_MODULE))
-static int to_lcd_power(int fb_blank)
-{
-	switch (fb_blank) {
-	case FB_BLANK_UNBLANK:
-		return LCD_POWER_ON;
-	/* deprecated; TODO: should become 'off' */
-	case FB_BLANK_NORMAL:
-		return LCD_POWER_REDUCED;
-	case FB_BLANK_VSYNC_SUSPEND:
-		return LCD_POWER_REDUCED_VSYNC_SUSPEND;
-	/* 'off' */
-	case FB_BLANK_HSYNC_SUSPEND:
-	case FB_BLANK_POWERDOWN:
-	default:
-		return LCD_POWER_OFF;
-	}
-}
+static DEFINE_MUTEX(lcd_dev_list_mutex);
+static LIST_HEAD(lcd_dev_list);
 
-/* This callback gets called when something important happens inside a
- * framebuffer driver. We're looking if that important event is blanking,
- * and if it is, we're switching lcd power as well ...
- */
-static int fb_notifier_callback(struct notifier_block *self,
-				 unsigned long event, void *data)
+static void lcd_notify_blank(struct lcd_device *ld, struct device *display_dev,
+			     int power)
 {
-	struct lcd_device *ld = container_of(self, struct lcd_device, fb_notif);
-	struct fb_event *evdata = data;
-	struct fb_info *info = evdata->info;
-	struct lcd_device *fb_lcd = fb_lcd_device(info);
-
 	guard(mutex)(&ld->ops_lock);
 
-	if (!ld->ops)
-		return 0;
-	if (ld->ops->controls_device && !ld->ops->controls_device(ld, info->device))
-		return 0;
-	if (fb_lcd && fb_lcd != ld)
-		return 0;
+	if (!ld->ops || !ld->ops->set_power)
+		return;
+	if (ld->ops->controls_device && !ld->ops->controls_device(ld, display_dev))
+		return;
 
-	if (event == FB_EVENT_BLANK) {
-		int power = to_lcd_power(*(int *)evdata->data);
+	ld->ops->set_power(ld, power);
+}
 
-		if (ld->ops->set_power)
-			ld->ops->set_power(ld, power);
-	} else {
-		const struct fb_videomode *videomode = evdata->data;
+void lcd_notify_blank_all(struct device *display_dev, int power)
+{
+	struct lcd_device *ld;
 
-		if (ld->ops->set_mode)
-			ld->ops->set_mode(ld, videomode->xres, videomode->yres);
-	}
+	guard(mutex)(&lcd_dev_list_mutex);
 
-	return 0;
+	list_for_each_entry(ld, &lcd_dev_list, entry)
+		lcd_notify_blank(ld, display_dev, power);
 }
+EXPORT_SYMBOL(lcd_notify_blank_all);
 
-static int lcd_register_fb(struct lcd_device *ld)
+static void lcd_notify_mode_change(struct lcd_device *ld, struct device *display_dev,
+				   unsigned int width, unsigned int height)
 {
-	memset(&ld->fb_notif, 0, sizeof(ld->fb_notif));
-	ld->fb_notif.notifier_call = fb_notifier_callback;
-	return fb_register_client(&ld->fb_notif);
-}
+	guard(mutex)(&ld->ops_lock);
 
-static void lcd_unregister_fb(struct lcd_device *ld)
-{
-	fb_unregister_client(&ld->fb_notif);
-}
-#else
-static int lcd_register_fb(struct lcd_device *ld)
-{
-	return 0;
+	if (!ld->ops || !ld->ops->set_mode)
+		return;
+	if (ld->ops->controls_device && !ld->ops->controls_device(ld, display_dev))
+		return;
+
+	ld->ops->set_mode(ld, width, height);
 }
 
-static inline void lcd_unregister_fb(struct lcd_device *ld)
+void lcd_notify_mode_change_all(struct device *display_dev,
+				unsigned int width, unsigned int height)
 {
+	struct lcd_device *ld;
+
+	guard(mutex)(&lcd_dev_list_mutex);
+
+	list_for_each_entry(ld, &lcd_dev_list, entry)
+		lcd_notify_mode_change(ld, display_dev, width, height);
 }
-#endif /* CONFIG_FB */
+EXPORT_SYMBOL(lcd_notify_mode_change_all);
 
 static ssize_t lcd_power_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
@@ -245,11 +218,8 @@ struct lcd_device *lcd_device_register(const char *name, struct device *parent,
 		return ERR_PTR(rc);
 	}
 
-	rc = lcd_register_fb(new_ld);
-	if (rc) {
-		device_unregister(&new_ld->dev);
-		return ERR_PTR(rc);
-	}
+	guard(mutex)(&lcd_dev_list_mutex);
+	list_add(&new_ld->entry, &lcd_dev_list);
 
 	return new_ld;
 }
@@ -266,10 +236,12 @@ void lcd_device_unregister(struct lcd_device *ld)
 	if (!ld)
 		return;
 
+	guard(mutex)(&lcd_dev_list_mutex);
+	list_del(&ld->entry);
+
 	mutex_lock(&ld->ops_lock);
 	ld->ops = NULL;
 	mutex_unlock(&ld->ops_lock);
-	lcd_unregister_fb(ld);
 
 	device_unregister(&ld->dev);
 }
diff --git a/drivers/video/backlight/qcom-wled.c b/drivers/video/backlight/qcom-wled.c
index 9afe701b2a1b..a63bb42c8f8b 100644
--- a/drivers/video/backlight/qcom-wled.c
+++ b/drivers/video/backlight/qcom-wled.c
@@ -1406,9 +1406,11 @@ static int wled_configure(struct wled *wled)
 	wled->ctrl_addr = be32_to_cpu(*prop_addr);
 
 	rc = of_property_read_string(dev->of_node, "label", &wled->name);
-	if (rc)
+	if (rc) {
 		wled->name = devm_kasprintf(dev, GFP_KERNEL, "%pOFn", dev->of_node);
-
+		if (!wled->name)
+			return -ENOMEM;
+	}
 	switch (wled->version) {
 	case 3:
 		u32_opts = wled3_opts;
diff --git a/drivers/video/fbdev/core/fb_backlight.c b/drivers/video/fbdev/core/fb_backlight.c
index 6fdaa9f81be9..dbed9696f4c5 100644
--- a/drivers/video/fbdev/core/fb_backlight.c
+++ b/drivers/video/fbdev/core/fb_backlight.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <linux/backlight.h>
 #include <linux/export.h>
 #include <linux/fb.h>
 #include <linux/mutex.h>
@@ -36,4 +37,15 @@ struct backlight_device *fb_bl_device(struct fb_info *info)
 	return info->bl_dev;
 }
 EXPORT_SYMBOL(fb_bl_device);
+
+void fb_bl_notify_blank(struct fb_info *info, int old_blank)
+{
+	bool on = info->blank == FB_BLANK_UNBLANK;
+	bool prev_on = old_blank == FB_BLANK_UNBLANK;
+
+	if (info->bl_dev)
+		backlight_notify_blank(info->bl_dev, info->device, on, prev_on);
+	else
+		backlight_notify_blank_all(info->device, on, prev_on);
+}
 #endif
diff --git a/drivers/video/fbdev/core/fb_info.c b/drivers/video/fbdev/core/fb_info.c
index 4847ebe50d7d..52f9bd2c5417 100644
--- a/drivers/video/fbdev/core/fb_info.c
+++ b/drivers/video/fbdev/core/fb_info.c
@@ -42,6 +42,7 @@ struct fb_info *framebuffer_alloc(size_t size, struct device *dev)
 
 	info->device = dev;
 	info->fbcon_rotate_hint = -1;
+	info->blank = FB_BLANK_UNBLANK;
 
 #if IS_ENABLED(CONFIG_FB_BACKLIGHT)
 	mutex_init(&info->bl_curve_mutex);
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index eca2498f2436..dfcf5e4d1d4c 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -15,6 +15,8 @@
 #include <linux/export.h>
 #include <linux/fb.h>
 #include <linux/fbcon.h>
+#include <linux/lcd.h>
+#include <linux/leds.h>
 
 #include <video/nomodeset.h>
 
@@ -220,6 +222,12 @@ static int fb_check_caps(struct fb_info *info, struct fb_var_screeninfo *var,
 	return err;
 }
 
+static void fb_lcd_notify_mode_change(struct fb_info *info,
+				      struct fb_videomode *mode)
+{
+	lcd_notify_mode_change_all(info->device, mode->xres, mode->yres);
+}
+
 int
 fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var)
 {
@@ -227,7 +235,6 @@ fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var)
 	u32 activate;
 	struct fb_var_screeninfo old_var;
 	struct fb_videomode mode;
-	struct fb_event event;
 	u32 unused;
 
 	if (var->activate & FB_ACTIVATE_INV_MODE) {
@@ -333,32 +340,71 @@ fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var)
 		return ret;
 	}
 
-	event.info = info;
-	event.data = &mode;
-	fb_notifier_call_chain(FB_EVENT_MODE_CHANGE, &event);
+	fb_lcd_notify_mode_change(info, &mode);
 
 	return 0;
 }
 EXPORT_SYMBOL(fb_set_var);
 
-int
-fb_blank(struct fb_info *info, int blank)
+static void fb_lcd_notify_blank(struct fb_info *info)
 {
-	struct fb_event event;
-	int ret = -EINVAL;
+	int power;
+
+	switch (info->blank) {
+	case FB_BLANK_UNBLANK:
+		power = LCD_POWER_ON;
+		break;
+	/* deprecated; TODO: should become 'off' */
+	case FB_BLANK_NORMAL:
+		power = LCD_POWER_REDUCED;
+		break;
+	case FB_BLANK_VSYNC_SUSPEND:
+		power = LCD_POWER_REDUCED_VSYNC_SUSPEND;
+		break;
+	/* 'off' */
+	case FB_BLANK_HSYNC_SUSPEND:
+	case FB_BLANK_POWERDOWN:
+	default:
+		power = LCD_POWER_OFF;
+		break;
+	}
+
+	lcd_notify_blank_all(info->device, power);
+}
+
+static void fb_ledtrig_backlight_notify_blank(struct fb_info *info)
+{
+	if (info->blank == FB_BLANK_UNBLANK)
+		ledtrig_backlight_blank(false);
+	else
+		ledtrig_backlight_blank(true);
+}
+
+int fb_blank(struct fb_info *info, int blank)
+{
+	int old_blank = info->blank;
+	int ret;
+
+	if (!info->fbops->fb_blank)
+		return -EINVAL;
 
 	if (blank > FB_BLANK_POWERDOWN)
 		blank = FB_BLANK_POWERDOWN;
 
-	event.info = info;
-	event.data = &blank;
+	info->blank = blank;
 
-	if (info->fbops->fb_blank)
-		ret = info->fbops->fb_blank(blank, info);
+	ret = info->fbops->fb_blank(blank, info);
+	if (ret)
+		goto err;
+
+	fb_bl_notify_blank(info, old_blank);
+	fb_lcd_notify_blank(info);
+	fb_ledtrig_backlight_notify_blank(info);
 
-	if (!ret)
-		fb_notifier_call_chain(FB_EVENT_BLANK, &event);
+	return 0;
 
+err:
+	info->blank = old_blank;
 	return ret;
 }
 EXPORT_SYMBOL(fb_blank);
@@ -416,6 +462,14 @@ static int do_register_framebuffer(struct fb_info *fb_info)
 	mutex_init(&fb_info->lock);
 	mutex_init(&fb_info->mm_lock);
 
+	/*
+	 * With an fb_blank callback present, we assume that the
+	 * display is blank, so that fb_blank() enables it on the
+	 * first modeset.
+	 */
+	if (fb_info->fbops->fb_blank)
+		fb_info->blank = FB_BLANK_POWERDOWN;
+
 	fb_device_create(fb_info);
 
 	if (fb_info->pixmap.addr == NULL) {
diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c
index 06d75c767579..b8344c40073b 100644
--- a/drivers/video/fbdev/core/fbsysfs.c
+++ b/drivers/video/fbdev/core/fbsysfs.c
@@ -242,11 +242,11 @@ static ssize_t store_blank(struct device *device,
 	return count;
 }
 
-static ssize_t show_blank(struct device *device,
-			  struct device_attribute *attr, char *buf)
+static ssize_t show_blank(struct device *device, struct device_attribute *attr, char *buf)
 {
-//	struct fb_info *fb_info = dev_get_drvdata(device);
-	return 0;
+	struct fb_info *fb_info = dev_get_drvdata(device);
+
+	return sysfs_emit(buf, "%d\n", fb_info->blank);
 }
 
 static ssize_t store_console(struct device *device,
diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index 173e81c2bbcb..b228a5a64479 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -21,7 +21,6 @@
 #include "error.h"
 #include "lru.h"
 #include "recovery.h"
-#include "trace.h"
 #include "varint.h"
 
 #include <linux/kthread.h>
@@ -337,11 +336,10 @@ void bch2_alloc_v4_swab(struct bkey_s k)
 	a->stripe_sectors	= swab32(a->stripe_sectors);
 }
 
-void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k)
+static inline void __bch2_alloc_v4_to_text(struct printbuf *out, struct bch_fs *c,
+					   unsigned dev, const struct bch_alloc_v4 *a)
 {
-	struct bch_alloc_v4 _a;
-	const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &_a);
-	struct bch_dev *ca = c ? bch2_dev_bucket_tryget_noerror(c, k.k->p) : NULL;
+	struct bch_dev *ca = c ? bch2_dev_tryget_noerror(c, dev) : NULL;
 
 	prt_newline(out);
 	printbuf_indent_add(out, 2);
@@ -369,6 +367,19 @@ void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c
 	bch2_dev_put(ca);
 }
 
+void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k)
+{
+	struct bch_alloc_v4 _a;
+	const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &_a);
+
+	__bch2_alloc_v4_to_text(out, c, k.k->p.inode, a);
+}
+
+void bch2_alloc_v4_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k)
+{
+	__bch2_alloc_v4_to_text(out, c, k.k->p.inode, bkey_s_c_to_alloc_v4(k).v);
+}
+
 void __bch2_alloc_to_v4(struct bkey_s_c k, struct bch_alloc_v4 *out)
 {
 	if (k.k->type == KEY_TYPE_alloc_v4) {
@@ -697,8 +708,8 @@ static int __need_discard_or_freespace_err(struct btree_trans *trans,
 				  set ? "" : "un",
 				  bch2_btree_id_str(btree),
 				  buf.buf);
-	if (ret == -BCH_ERR_fsck_ignore ||
-	    ret == -BCH_ERR_fsck_errors_not_fixed)
+	if (bch2_err_matches(ret, BCH_ERR_fsck_ignore) ||
+	    bch2_err_matches(ret, BCH_ERR_fsck_errors_not_fixed))
 		ret = 0;
 
 	printbuf_exit(&buf);
@@ -854,7 +865,7 @@ int bch2_trigger_alloc(struct btree_trans *trans,
 
 	struct bch_dev *ca = bch2_dev_bucket_tryget(c, new.k->p);
 	if (!ca)
-		return -BCH_ERR_trigger_alloc;
+		return bch_err_throw(c, trigger_alloc);
 
 	struct bch_alloc_v4 old_a_convert;
 	const struct bch_alloc_v4 *old_a = bch2_alloc_to_v4(old, &old_a_convert);
@@ -988,14 +999,11 @@ int bch2_trigger_alloc(struct btree_trans *trans,
 		}
 
 		if (new_a->gen != old_a->gen) {
-			rcu_read_lock();
+			guard(rcu)();
 			u8 *gen = bucket_gen(ca, new.k->p.offset);
-			if (unlikely(!gen)) {
-				rcu_read_unlock();
+			if (unlikely(!gen))
 				goto invalid_bucket;
-			}
 			*gen = new_a->gen;
-			rcu_read_unlock();
 		}
 
 #define eval_state(_a, expr)		({ const struct bch_alloc_v4 *a = _a; expr; })
@@ -1021,15 +1029,12 @@ int bch2_trigger_alloc(struct btree_trans *trans,
 	}
 
 	if ((flags & BTREE_TRIGGER_gc) && (flags & BTREE_TRIGGER_insert)) {
-		rcu_read_lock();
+		guard(rcu)();
 		struct bucket *g = gc_bucket(ca, new.k->p.offset);
-		if (unlikely(!g)) {
-			rcu_read_unlock();
+		if (unlikely(!g))
 			goto invalid_bucket;
-		}
 		g->gen_valid	= 1;
 		g->gen		= new_a->gen;
-		rcu_read_unlock();
 	}
 err:
 fsck_err:
@@ -1039,7 +1044,7 @@ fsck_err:
 invalid_bucket:
 	bch2_fs_inconsistent(c, "reference to invalid bucket\n%s",
 			     (bch2_bkey_val_to_text(&buf, c, new.s_c), buf.buf));
-	ret = -BCH_ERR_trigger_alloc;
+	ret = bch_err_throw(c, trigger_alloc);
 	goto err;
 }
 
@@ -1105,13 +1110,12 @@ static bool next_bucket(struct bch_fs *c, struct bch_dev **ca, struct bpos *buck
 		bucket->offset = 0;
 	}
 
-	rcu_read_lock();
+	guard(rcu)();
 	*ca = __bch2_next_dev_idx(c, bucket->inode, NULL);
 	if (*ca) {
 		*bucket = POS((*ca)->dev_idx, (*ca)->mi.first_bucket);
 		bch2_dev_get(*ca);
 	}
-	rcu_read_unlock();
 
 	return *ca != NULL;
 }
@@ -1454,7 +1458,7 @@ delete:
 		ret =   bch2_btree_bit_mod_iter(trans, iter, false) ?:
 			bch2_trans_commit(trans, NULL, NULL,
 				BCH_TRANS_COMMIT_no_enospc) ?:
-			-BCH_ERR_transaction_restart_commit;
+			bch_err_throw(c, transaction_restart_commit);
 		goto out;
 	} else {
 		/*
@@ -1777,14 +1781,16 @@ int bch2_check_alloc_to_lru_refs(struct bch_fs *c)
 
 static int discard_in_flight_add(struct bch_dev *ca, u64 bucket, bool in_progress)
 {
+	struct bch_fs *c = ca->fs;
 	int ret;
 
 	mutex_lock(&ca->discard_buckets_in_flight_lock);
-	darray_for_each(ca->discard_buckets_in_flight, i)
-		if (i->bucket == bucket) {
-			ret = -BCH_ERR_EEXIST_discard_in_flight_add;
-			goto out;
-		}
+	struct discard_in_flight *i =
+		darray_find_p(ca->discard_buckets_in_flight, i, i->bucket == bucket);
+	if (i) {
+		ret = bch_err_throw(c, EEXIST_discard_in_flight_add);
+		goto out;
+	}
 
 	ret = darray_push(&ca->discard_buckets_in_flight, ((struct discard_in_flight) {
 			   .in_progress = in_progress,
@@ -1798,14 +1804,11 @@ out:
 static void discard_in_flight_remove(struct bch_dev *ca, u64 bucket)
 {
 	mutex_lock(&ca->discard_buckets_in_flight_lock);
-	darray_for_each(ca->discard_buckets_in_flight, i)
-		if (i->bucket == bucket) {
-			BUG_ON(!i->in_progress);
-			darray_remove_item(&ca->discard_buckets_in_flight, i);
-			goto found;
-		}
-	BUG();
-found:
+	struct discard_in_flight *i =
+		darray_find_p(ca->discard_buckets_in_flight, i, i->bucket == bucket);
+	BUG_ON(!i || !i->in_progress);
+
+	darray_remove_item(&ca->discard_buckets_in_flight, i);
 	mutex_unlock(&ca->discard_buckets_in_flight_lock);
 }
 
@@ -2504,7 +2507,7 @@ void bch2_recalc_capacity(struct bch_fs *c)
 
 	lockdep_assert_held(&c->state_lock);
 
-	rcu_read_lock();
+	guard(rcu)();
 	for_each_member_device_rcu(c, ca, NULL) {
 		struct block_device *bdev = READ_ONCE(ca->disk_sb.bdev);
 		if (bdev)
@@ -2549,7 +2552,6 @@ void bch2_recalc_capacity(struct bch_fs *c)
 		bucket_size_max = max_t(unsigned, bucket_size_max,
 					ca->mi.bucket_size);
 	}
-	rcu_read_unlock();
 
 	bch2_set_ra_pages(c, ra_pages);
 
@@ -2574,10 +2576,9 @@ u64 bch2_min_rw_member_capacity(struct bch_fs *c)
 {
 	u64 ret = U64_MAX;
 
-	rcu_read_lock();
+	guard(rcu)();
 	for_each_rw_member_rcu(c, ca)
 		ret = min(ret, ca->mi.nbuckets * ca->mi.bucket_size);
-	rcu_read_unlock();
 	return ret;
 }
 
diff --git a/fs/bcachefs/alloc_background.h b/fs/bcachefs/alloc_background.h
index 4f94c6a661bf..0cc5adc55b6f 100644
--- a/fs/bcachefs/alloc_background.h
+++ b/fs/bcachefs/alloc_background.h
@@ -13,11 +13,9 @@
 
 static inline bool bch2_dev_bucket_exists(struct bch_fs *c, struct bpos pos)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	struct bch_dev *ca = bch2_dev_rcu_noerror(c, pos.inode);
-	bool ret = ca && bucket_valid(ca, pos.offset);
-	rcu_read_unlock();
-	return ret;
+	return ca && bucket_valid(ca, pos.offset);
 }
 
 static inline u64 bucket_to_u64(struct bpos bucket)
@@ -253,6 +251,7 @@ int bch2_alloc_v4_validate(struct bch_fs *, struct bkey_s_c,
 			   struct bkey_validate_context);
 void bch2_alloc_v4_swab(struct bkey_s);
 void bch2_alloc_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
+void bch2_alloc_v4_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
 
 #define bch2_bkey_ops_alloc ((struct bkey_ops) {	\
 	.key_validate	= bch2_alloc_v1_validate,	\
@@ -277,7 +276,7 @@ void bch2_alloc_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
 
 #define bch2_bkey_ops_alloc_v4 ((struct bkey_ops) {	\
 	.key_validate	= bch2_alloc_v4_validate,	\
-	.val_to_text	= bch2_alloc_to_text,		\
+	.val_to_text	= bch2_alloc_v4_to_text,	\
 	.swab		= bch2_alloc_v4_swab,		\
 	.trigger	= bch2_trigger_alloc,		\
 	.min_val_size	= 48,				\
diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index 1a52c12c51ae..b375ad610acd 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -69,10 +69,9 @@ const char * const bch2_watermarks[] = {
 
 void bch2_reset_alloc_cursors(struct bch_fs *c)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	for_each_member_device_rcu(c, ca, NULL)
 		memset(ca->alloc_cursor, 0, sizeof(ca->alloc_cursor));
-	rcu_read_unlock();
 }
 
 static void bch2_open_bucket_hash_add(struct bch_fs *c, struct open_bucket *ob)
@@ -166,9 +165,8 @@ static void open_bucket_free_unused(struct bch_fs *c, struct open_bucket *ob)
 	       ARRAY_SIZE(c->open_buckets_partial));
 
 	spin_lock(&c->freelist_lock);
-	rcu_read_lock();
-	bch2_dev_rcu(c, ob->dev)->nr_partial_buckets++;
-	rcu_read_unlock();
+	scoped_guard(rcu)
+		bch2_dev_rcu(c, ob->dev)->nr_partial_buckets++;
 
 	ob->on_partial_list = true;
 	c->open_buckets_partial[c->open_buckets_partial_nr++] =
@@ -229,7 +227,7 @@ static struct open_bucket *__try_alloc_bucket(struct bch_fs *c,
 
 		track_event_change(&c->times[BCH_TIME_blocked_allocate_open_bucket], true);
 		spin_unlock(&c->freelist_lock);
-		return ERR_PTR(-BCH_ERR_open_buckets_empty);
+		return ERR_PTR(bch_err_throw(c, open_buckets_empty));
 	}
 
 	/* Recheck under lock: */
@@ -535,7 +533,7 @@ again:
 
 		track_event_change(&c->times[BCH_TIME_blocked_allocate], true);
 
-		ob = ERR_PTR(-BCH_ERR_freelist_empty);
+		ob = ERR_PTR(bch_err_throw(c, freelist_empty));
 		goto err;
 	}
 
@@ -560,7 +558,7 @@ alloc:
 	}
 err:
 	if (!ob)
-		ob = ERR_PTR(-BCH_ERR_no_buckets_found);
+		ob = ERR_PTR(bch_err_throw(c, no_buckets_found));
 
 	if (!IS_ERR(ob))
 		ob->data_type = req->data_type;
@@ -603,18 +601,18 @@ static int __dev_stripe_cmp(struct dev_stripe_state *stripe,
 
 #define dev_stripe_cmp(l, r) __dev_stripe_cmp(stripe, l, r)
 
-struct dev_alloc_list bch2_dev_alloc_list(struct bch_fs *c,
-					  struct dev_stripe_state *stripe,
-					  struct bch_devs_mask *devs)
+void bch2_dev_alloc_list(struct bch_fs *c,
+			 struct dev_stripe_state *stripe,
+			 struct bch_devs_mask *devs,
+			 struct dev_alloc_list *ret)
 {
-	struct dev_alloc_list ret = { .nr = 0 };
-	unsigned i;
+	ret->nr = 0;
 
+	unsigned i;
 	for_each_set_bit(i, devs->d, BCH_SB_MEMBERS_MAX)
-		ret.data[ret.nr++] = i;
+		ret->data[ret->nr++] = i;
 
-	bubble_sort(ret.data, ret.nr, dev_stripe_cmp);
-	return ret;
+	bubble_sort(ret->data, ret->nr, dev_stripe_cmp);
 }
 
 static const u64 stripe_clock_hand_rescale	= 1ULL << 62; /* trigger rescale at */
@@ -705,18 +703,19 @@ static int add_new_bucket(struct bch_fs *c,
 	return 0;
 }
 
-int bch2_bucket_alloc_set_trans(struct btree_trans *trans,
-				struct alloc_request *req,
-				struct dev_stripe_state *stripe,
-				struct closure *cl)
+inline int bch2_bucket_alloc_set_trans(struct btree_trans *trans,
+				       struct alloc_request *req,
+				       struct dev_stripe_state *stripe,
+				       struct closure *cl)
 {
 	struct bch_fs *c = trans->c;
-	int ret = -BCH_ERR_insufficient_devices;
+	int ret = 0;
 
 	BUG_ON(req->nr_effective >= req->nr_replicas);
 
-	struct dev_alloc_list devs_sorted = bch2_dev_alloc_list(c, stripe, &req->devs_may_alloc);
-	darray_for_each(devs_sorted, i) {
+	bch2_dev_alloc_list(c, stripe, &req->devs_may_alloc, &req->devs_sorted);
+
+	darray_for_each(req->devs_sorted, i) {
 		req->ca = bch2_dev_tryget_noerror(c, *i);
 		if (!req->ca)
 			continue;
@@ -739,13 +738,16 @@ int bch2_bucket_alloc_set_trans(struct btree_trans *trans,
 			continue;
 		}
 
-		if (add_new_bucket(c, req, ob)) {
-			ret = 0;
+		ret = add_new_bucket(c, req, ob);
+		if (ret)
 			break;
-		}
 	}
 
-	return ret;
+	if (ret == 1)
+		return 0;
+	if (ret)
+		return ret;
+	return bch_err_throw(c, insufficient_devices);
 }
 
 /* Allocate from stripes: */
@@ -776,9 +778,9 @@ static int bucket_alloc_from_stripe(struct btree_trans *trans,
 	if (!h)
 		return 0;
 
-	struct dev_alloc_list devs_sorted =
-		bch2_dev_alloc_list(c, &req->wp->stripe, &req->devs_may_alloc);
-	darray_for_each(devs_sorted, i)
+	bch2_dev_alloc_list(c, &req->wp->stripe, &req->devs_may_alloc, &req->devs_sorted);
+
+	darray_for_each(req->devs_sorted, i)
 		for (unsigned ec_idx = 0; ec_idx < h->s->nr_data; ec_idx++) {
 			if (!h->s->blocks[ec_idx])
 				continue;
@@ -872,9 +874,8 @@ static int bucket_alloc_set_partial(struct bch_fs *c,
 					  i);
 			ob->on_partial_list = false;
 
-			rcu_read_lock();
-			bch2_dev_rcu(c, ob->dev)->nr_partial_buckets--;
-			rcu_read_unlock();
+			scoped_guard(rcu)
+				bch2_dev_rcu(c, ob->dev)->nr_partial_buckets--;
 
 			ret = add_new_bucket(c, req, ob);
 			if (ret)
@@ -1056,9 +1057,8 @@ void bch2_open_buckets_stop(struct bch_fs *c, struct bch_dev *ca,
 
 			ob->on_partial_list = false;
 
-			rcu_read_lock();
-			bch2_dev_rcu(c, ob->dev)->nr_partial_buckets--;
-			rcu_read_unlock();
+			scoped_guard(rcu)
+				bch2_dev_rcu(c, ob->dev)->nr_partial_buckets--;
 
 			spin_unlock(&c->freelist_lock);
 			bch2_open_bucket_put(c, ob);
@@ -1086,14 +1086,11 @@ static struct write_point *__writepoint_find(struct hlist_head *head,
 {
 	struct write_point *wp;
 
-	rcu_read_lock();
+	guard(rcu)();
 	hlist_for_each_entry_rcu(wp, head, node)
 		if (wp->write_point == write_point)
-			goto out;
-	wp = NULL;
-out:
-	rcu_read_unlock();
-	return wp;
+			return wp;
+	return NULL;
 }
 
 static inline bool too_many_writepoints(struct bch_fs *c, unsigned factor)
@@ -1104,7 +1101,7 @@ static inline bool too_many_writepoints(struct bch_fs *c, unsigned factor)
 	return stranded * factor > free;
 }
 
-static bool try_increase_writepoints(struct bch_fs *c)
+static noinline bool try_increase_writepoints(struct bch_fs *c)
 {
 	struct write_point *wp;
 
@@ -1117,7 +1114,7 @@ static bool try_increase_writepoints(struct bch_fs *c)
 	return true;
 }
 
-static bool try_decrease_writepoints(struct btree_trans *trans, unsigned old_nr)
+static noinline bool try_decrease_writepoints(struct btree_trans *trans, unsigned old_nr)
 {
 	struct bch_fs *c = trans->c;
 	struct write_point *wp;
@@ -1379,11 +1376,11 @@ err:
 		goto retry;
 
 	if (cl && bch2_err_matches(ret, BCH_ERR_open_buckets_empty))
-		ret = -BCH_ERR_bucket_alloc_blocked;
+		ret = bch_err_throw(c, bucket_alloc_blocked);
 
 	if (cl && !(flags & BCH_WRITE_alloc_nowait) &&
 	    bch2_err_matches(ret, BCH_ERR_freelist_empty))
-		ret = -BCH_ERR_bucket_alloc_blocked;
+		ret = bch_err_throw(c, bucket_alloc_blocked);
 
 	return ret;
 }
@@ -1637,19 +1634,16 @@ static noinline void bch2_print_allocator_stuck(struct bch_fs *c)
 
 	bch2_printbuf_make_room(&buf, 4096);
 
-	rcu_read_lock();
 	buf.atomic++;
-
-	for_each_online_member_rcu(c, ca) {
-		prt_printf(&buf, "Dev %u:\n", ca->dev_idx);
-		printbuf_indent_add(&buf, 2);
-		bch2_dev_alloc_debug_to_text(&buf, ca);
-		printbuf_indent_sub(&buf, 2);
-		prt_newline(&buf);
-	}
-
+	scoped_guard(rcu)
+		for_each_online_member_rcu(c, ca) {
+			prt_printf(&buf, "Dev %u:\n", ca->dev_idx);
+			printbuf_indent_add(&buf, 2);
+			bch2_dev_alloc_debug_to_text(&buf, ca);
+			printbuf_indent_sub(&buf, 2);
+			prt_newline(&buf);
+		}
 	--buf.atomic;
-	rcu_read_unlock();
 
 	prt_printf(&buf, "Copygc debug:\n");
 	printbuf_indent_add(&buf, 2);
diff --git a/fs/bcachefs/alloc_foreground.h b/fs/bcachefs/alloc_foreground.h
index 2e01c7b61ed1..1b3fc8460096 100644
--- a/fs/bcachefs/alloc_foreground.h
+++ b/fs/bcachefs/alloc_foreground.h
@@ -42,6 +42,7 @@ struct alloc_request {
 	struct bch_devs_mask	devs_may_alloc;
 
 	/* bch2_bucket_alloc_set_trans(): */
+	struct dev_alloc_list	devs_sorted;
 	struct bch_dev_usage	usage;
 
 	/* bch2_bucket_alloc_trans(): */
@@ -71,9 +72,10 @@ struct alloc_request {
 	struct bch_devs_mask	scratch_devs_may_alloc;
 };
 
-struct dev_alloc_list bch2_dev_alloc_list(struct bch_fs *,
-					  struct dev_stripe_state *,
-					  struct bch_devs_mask *);
+void bch2_dev_alloc_list(struct bch_fs *,
+			 struct dev_stripe_state *,
+			 struct bch_devs_mask *,
+			 struct dev_alloc_list *);
 void bch2_dev_stripe_increment(struct bch_dev *, struct dev_stripe_state *);
 
 static inline struct bch_dev *ob_dev(struct bch_fs *c, struct open_bucket *ob)
diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index cde7dd115267..e76809e71858 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -48,17 +48,19 @@ void bch2_backpointer_to_text(struct printbuf *out, struct bch_fs *c, struct bke
 {
 	struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k);
 
-	rcu_read_lock();
-	struct bch_dev *ca = bch2_dev_rcu_noerror(c, bp.k->p.inode);
-	if (ca) {
-		u32 bucket_offset;
-		struct bpos bucket = bp_pos_to_bucket_and_offset(ca, bp.k->p, &bucket_offset);
-		rcu_read_unlock();
+	struct bch_dev *ca;
+	u32 bucket_offset;
+	struct bpos bucket;
+	scoped_guard(rcu) {
+		ca = bch2_dev_rcu_noerror(c, bp.k->p.inode);
+		if (ca)
+			bucket = bp_pos_to_bucket_and_offset(ca, bp.k->p, &bucket_offset);
+	}
+
+	if (ca)
 		prt_printf(out, "bucket=%llu:%llu:%u ", bucket.inode, bucket.offset, bucket_offset);
-	} else {
-		rcu_read_unlock();
+	else
 		prt_printf(out, "sector=%llu:%llu ", bp.k->p.inode, bp.k->p.offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT);
-	}
 
 	bch2_btree_id_level_to_text(out, bp.v->btree_id, bp.v->level);
 	prt_str(out, " data_type=");
@@ -140,7 +142,7 @@ static noinline int backpointer_mod_err(struct btree_trans *trans,
 	}
 
 	if (!will_check && __bch2_inconsistent_error(c, &buf))
-		ret = -BCH_ERR_erofs_unfixed_errors;
+		ret = bch_err_throw(c, erofs_unfixed_errors);
 
 	bch_err(c, "%s", buf.buf);
 	printbuf_exit(&buf);
@@ -293,7 +295,7 @@ static struct btree *__bch2_backpointer_get_node(struct btree_trans *trans,
 		return b;
 
 	if (btree_node_will_make_reachable(b)) {
-		b = ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node);
+		b = ERR_PTR(bch_err_throw(c, backpointer_to_overwritten_btree_node));
 	} else {
 		int ret = backpointer_target_not_found(trans, bp, bkey_i_to_s_c(&b->key),
 						       last_flushed, commit);
@@ -351,7 +353,7 @@ static struct bkey_s_c __bch2_backpointer_get_key(struct btree_trans *trans,
 		return ret ? bkey_s_c_err(ret) : bkey_s_c_null;
 	} else {
 		struct btree *b = __bch2_backpointer_get_node(trans, bp, iter, last_flushed, commit);
-		if (b == ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node))
+		if (b == ERR_PTR(bch_err_throw(c, backpointer_to_overwritten_btree_node)))
 			return bkey_s_c_null;
 		if (IS_ERR_OR_NULL(b))
 			return ((struct bkey_s_c) { .k = ERR_CAST(b) });
@@ -591,6 +593,7 @@ check_existing_bp:
 		bkey_for_each_ptr(other_extent_ptrs, ptr)
 			if (ptr->dev == bp->k.p.inode &&
 			    dev_ptr_stale_rcu(ca, ptr)) {
+				rcu_read_unlock();
 				ret = drop_dev_and_update(trans, other_bp.v->btree_id,
 							  other_extent, bp->k.p.inode);
 				if (ret)
@@ -648,7 +651,7 @@ check_existing_bp:
 	prt_newline(&buf);
 	bch2_bkey_val_to_text(&buf, c, other_extent);
 	bch_err(c, "%s", buf.buf);
-	ret = -BCH_ERR_fsck_repair_unimplemented;
+	ret = bch_err_throw(c, fsck_repair_unimplemented);
 	goto err;
 missing:
 	printbuf_reset(&buf);
@@ -679,26 +682,23 @@ static int check_extent_to_backpointers(struct btree_trans *trans,
 		if (p.ptr.dev == BCH_SB_MEMBER_INVALID)
 			continue;
 
-		rcu_read_lock();
-		struct bch_dev *ca = bch2_dev_rcu_noerror(c, p.ptr.dev);
-		if (!ca) {
-			rcu_read_unlock();
-			continue;
-		}
+		bool empty;
+		{
+			/* scoped_guard() is a loop, so it breaks continue */
+			guard(rcu)();
+			struct bch_dev *ca = bch2_dev_rcu_noerror(c, p.ptr.dev);
+			if (!ca)
+				continue;
 
-		if (p.ptr.cached && dev_ptr_stale_rcu(ca, &p.ptr)) {
-			rcu_read_unlock();
-			continue;
-		}
+			if (p.ptr.cached && dev_ptr_stale_rcu(ca, &p.ptr))
+				continue;
 
-		u64 b = PTR_BUCKET_NR(ca, &p.ptr);
-		if (!bch2_bucket_bitmap_test(&ca->bucket_backpointer_mismatch, b)) {
-			rcu_read_unlock();
-			continue;
-		}
+			u64 b = PTR_BUCKET_NR(ca, &p.ptr);
+			if (!bch2_bucket_bitmap_test(&ca->bucket_backpointer_mismatch, b))
+				continue;
 
-		bool empty = bch2_bucket_bitmap_test(&ca->bucket_backpointer_empty, b);
-		rcu_read_unlock();
+			empty = bch2_bucket_bitmap_test(&ca->bucket_backpointer_empty, b);
+		}
 
 		struct bkey_i_backpointer bp;
 		bch2_extent_ptr_to_bp(c, btree, level, k, p, entry, &bp);
@@ -953,7 +953,7 @@ static int check_bucket_backpointer_mismatch(struct btree_trans *trans, struct b
 		    sectors[ALLOC_cached] > a->cached_sectors ||
 		    sectors[ALLOC_stripe] > a->stripe_sectors) {
 			ret = check_bucket_backpointers_to_extents(trans, ca, alloc_k.k->p) ?:
-				-BCH_ERR_transaction_restart_nested;
+				bch_err_throw(c, transaction_restart_nested);
 			goto err;
 		}
 
@@ -981,7 +981,7 @@ static bool backpointer_node_has_missing(struct bch_fs *c, struct bkey_s_c k)
 	case KEY_TYPE_btree_ptr_v2: {
 		bool ret = false;
 
-		rcu_read_lock();
+		guard(rcu)();
 		struct bpos pos = bkey_s_c_to_btree_ptr_v2(k).v->min_key;
 		while (pos.inode <= k.k->p.inode) {
 			if (pos.inode >= c->sb.nr_devices)
@@ -1009,7 +1009,6 @@ static bool backpointer_node_has_missing(struct bch_fs *c, struct bkey_s_c k)
 next:
 			pos = SPOS(pos.inode + 1, 0, 0);
 		}
-		rcu_read_unlock();
 
 		return ret;
 	}
@@ -1352,7 +1351,7 @@ static int bch2_bucket_bitmap_set(struct bch_dev *ca, struct bucket_bitmap *b, u
 			b->buckets = kvcalloc(BITS_TO_LONGS(ca->mi.nbuckets),
 					      sizeof(unsigned long), GFP_KERNEL);
 			if (!b->buckets)
-				return -BCH_ERR_ENOMEM_backpointer_mismatches_bitmap;
+				return bch_err_throw(ca->fs, ENOMEM_backpointer_mismatches_bitmap);
 		}
 
 		b->nr += !__test_and_set_bit(bit, b->buckets);
@@ -1361,7 +1360,8 @@ static int bch2_bucket_bitmap_set(struct bch_dev *ca, struct bucket_bitmap *b, u
 	return 0;
 }
 
-int bch2_bucket_bitmap_resize(struct bucket_bitmap *b, u64 old_size, u64 new_size)
+int bch2_bucket_bitmap_resize(struct bch_dev *ca, struct bucket_bitmap *b,
+			      u64 old_size, u64 new_size)
 {
 	scoped_guard(mutex, &b->lock) {
 		if (!b->buckets)
@@ -1370,7 +1370,7 @@ int bch2_bucket_bitmap_resize(struct bucket_bitmap *b, u64 old_size, u64 new_siz
 		unsigned long *n = kvcalloc(BITS_TO_LONGS(new_size),
 					    sizeof(unsigned long), GFP_KERNEL);
 		if (!n)
-			return -BCH_ERR_ENOMEM_backpointer_mismatches_bitmap;
+			return bch_err_throw(ca->fs, ENOMEM_backpointer_mismatches_bitmap);
 
 		memcpy(n, b->buckets,
 		       BITS_TO_LONGS(min(old_size, new_size)) * sizeof(unsigned long));
diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h
index 6840561084ce..7e71afee1ac0 100644
--- a/fs/bcachefs/backpointers.h
+++ b/fs/bcachefs/backpointers.h
@@ -53,11 +53,10 @@ static inline struct bpos bp_pos_to_bucket_and_offset(const struct bch_dev *ca,
 
 static inline bool bp_pos_to_bucket_nodev_noerror(struct bch_fs *c, struct bpos bp_pos, struct bpos *bucket)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	struct bch_dev *ca = bch2_dev_rcu_noerror(c, bp_pos.inode);
 	if (ca)
 		*bucket = bp_pos_to_bucket(ca, bp_pos);
-	rcu_read_unlock();
 	return ca != NULL;
 }
 
@@ -195,7 +194,7 @@ static inline bool bch2_bucket_bitmap_test(struct bucket_bitmap *b, u64 i)
 	return bitmap && test_bit(i, bitmap);
 }
 
-int bch2_bucket_bitmap_resize(struct bucket_bitmap *, u64, u64);
+int bch2_bucket_bitmap_resize(struct bch_dev *, struct bucket_bitmap *, u64, u64);
 void bch2_bucket_bitmap_free(struct bucket_bitmap *);
 
 #endif /* _BCACHEFS_BACKPOINTERS_BACKGROUND_H */
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 7824da2af9d0..3651a296d506 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -183,6 +183,16 @@
 #define pr_fmt(fmt) "%s() " fmt "\n", __func__
 #endif
 
+#ifdef CONFIG_BCACHEFS_DEBUG
+#define ENUMERATED_REF_DEBUG
+#endif
+
+#ifndef dynamic_fault
+#define dynamic_fault(...)		0
+#endif
+
+#define race_fault(...)			dynamic_fault("bcachefs:race")
+
 #include <linux/backing-dev-defs.h>
 #include <linux/bug.h>
 #include <linux/bio.h>
@@ -219,15 +229,30 @@
 #include "time_stats.h"
 #include "util.h"
 
-#ifdef CONFIG_BCACHEFS_DEBUG
-#define ENUMERATED_REF_DEBUG
-#endif
-
-#ifndef dynamic_fault
-#define dynamic_fault(...)		0
-#endif
+#include "alloc_types.h"
+#include "async_objs_types.h"
+#include "btree_gc_types.h"
+#include "btree_types.h"
+#include "btree_node_scan_types.h"
+#include "btree_write_buffer_types.h"
+#include "buckets_types.h"
+#include "buckets_waiting_for_journal_types.h"
+#include "clock_types.h"
+#include "disk_groups_types.h"
+#include "ec_types.h"
+#include "enumerated_ref_types.h"
+#include "journal_types.h"
+#include "keylist_types.h"
+#include "quota_types.h"
+#include "rebalance_types.h"
+#include "recovery_passes_types.h"
+#include "replicas_types.h"
+#include "sb-members_types.h"
+#include "subvolume_types.h"
+#include "super_types.h"
+#include "thread_with_file_types.h"
 
-#define race_fault(...)			dynamic_fault("bcachefs:race")
+#include "trace.h"
 
 #define count_event(_c, _name)	this_cpu_inc((_c)->counters[BCH_COUNTER_##_name])
 
@@ -380,6 +405,14 @@ do {									\
 		pr_info(fmt, ##__VA_ARGS__);				\
 } while (0)
 
+static inline int __bch2_err_trace(struct bch_fs *c, int err)
+{
+	trace_error_throw(c, err, _THIS_IP_);
+	return err;
+}
+
+#define bch_err_throw(_c, _err) __bch2_err_trace(_c, -BCH_ERR_##_err)
+
 /* Parameters that are useful for debugging, but should always be compiled in: */
 #define BCH_DEBUG_PARAMS_ALWAYS()					\
 	BCH_DEBUG_PARAM(key_merging_disabled,				\
@@ -486,29 +519,6 @@ enum bch_time_stats {
 	BCH_TIME_STAT_NR
 };
 
-#include "alloc_types.h"
-#include "async_objs_types.h"
-#include "btree_gc_types.h"
-#include "btree_types.h"
-#include "btree_node_scan_types.h"
-#include "btree_write_buffer_types.h"
-#include "buckets_types.h"
-#include "buckets_waiting_for_journal_types.h"
-#include "clock_types.h"
-#include "disk_groups_types.h"
-#include "ec_types.h"
-#include "enumerated_ref_types.h"
-#include "journal_types.h"
-#include "keylist_types.h"
-#include "quota_types.h"
-#include "rebalance_types.h"
-#include "recovery_passes_types.h"
-#include "replicas_types.h"
-#include "sb-members_types.h"
-#include "subvolume_types.h"
-#include "super_types.h"
-#include "thread_with_file_types.h"
-
 /* Number of nodes btree coalesce will try to coalesce at once */
 #define GC_MERGE_NODES		4U
 
diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index 8557cbd3d818..91e0aa796e6b 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -149,7 +149,7 @@ static int btree_node_data_alloc(struct bch_fs *c, struct btree *b, gfp_t gfp)
 
 	b->data = kvmalloc(btree_buf_bytes(b), gfp);
 	if (!b->data)
-		return -BCH_ERR_ENOMEM_btree_node_mem_alloc;
+		return bch_err_throw(c, ENOMEM_btree_node_mem_alloc);
 #ifdef __KERNEL__
 	b->aux_data = kvmalloc(btree_aux_data_bytes(b), gfp);
 #else
@@ -162,7 +162,7 @@ static int btree_node_data_alloc(struct bch_fs *c, struct btree *b, gfp_t gfp)
 	if (!b->aux_data) {
 		kvfree(b->data);
 		b->data = NULL;
-		return -BCH_ERR_ENOMEM_btree_node_mem_alloc;
+		return bch_err_throw(c, ENOMEM_btree_node_mem_alloc);
 	}
 
 	return 0;
@@ -353,21 +353,21 @@ static int __btree_node_reclaim_checks(struct bch_fs *c, struct btree *b,
 
 	if (btree_node_noevict(b)) {
 		bc->not_freed[BCH_BTREE_CACHE_NOT_FREED_noevict]++;
-		return -BCH_ERR_ENOMEM_btree_node_reclaim;
+		return bch_err_throw(c, ENOMEM_btree_node_reclaim);
 	}
 	if (btree_node_write_blocked(b)) {
 		bc->not_freed[BCH_BTREE_CACHE_NOT_FREED_write_blocked]++;
-		return -BCH_ERR_ENOMEM_btree_node_reclaim;
+		return bch_err_throw(c, ENOMEM_btree_node_reclaim);
 	}
 	if (btree_node_will_make_reachable(b)) {
 		bc->not_freed[BCH_BTREE_CACHE_NOT_FREED_will_make_reachable]++;
-		return -BCH_ERR_ENOMEM_btree_node_reclaim;
+		return bch_err_throw(c, ENOMEM_btree_node_reclaim);
 	}
 
 	if (btree_node_dirty(b)) {
 		if (!flush) {
 			bc->not_freed[BCH_BTREE_CACHE_NOT_FREED_dirty]++;
-			return -BCH_ERR_ENOMEM_btree_node_reclaim;
+			return bch_err_throw(c, ENOMEM_btree_node_reclaim);
 		}
 
 		if (locked) {
@@ -393,7 +393,7 @@ static int __btree_node_reclaim_checks(struct bch_fs *c, struct btree *b,
 				bc->not_freed[BCH_BTREE_CACHE_NOT_FREED_read_in_flight]++;
 			else if (btree_node_write_in_flight(b))
 				bc->not_freed[BCH_BTREE_CACHE_NOT_FREED_write_in_flight]++;
-			return -BCH_ERR_ENOMEM_btree_node_reclaim;
+			return bch_err_throw(c, ENOMEM_btree_node_reclaim);
 		}
 
 		if (locked)
@@ -424,13 +424,13 @@ retry_unlocked:
 
 	if (!six_trylock_intent(&b->c.lock)) {
 		bc->not_freed[BCH_BTREE_CACHE_NOT_FREED_lock_intent]++;
-		return -BCH_ERR_ENOMEM_btree_node_reclaim;
+		return bch_err_throw(c, ENOMEM_btree_node_reclaim);
 	}
 
 	if (!six_trylock_write(&b->c.lock)) {
 		bc->not_freed[BCH_BTREE_CACHE_NOT_FREED_lock_write]++;
 		six_unlock_intent(&b->c.lock);
-		return -BCH_ERR_ENOMEM_btree_node_reclaim;
+		return bch_err_throw(c, ENOMEM_btree_node_reclaim);
 	}
 
 	/* recheck under lock */
@@ -682,7 +682,7 @@ int bch2_fs_btree_cache_init(struct bch_fs *c)
 
 	return 0;
 err:
-	return -BCH_ERR_ENOMEM_fs_btree_cache_init;
+	return bch_err_throw(c, ENOMEM_fs_btree_cache_init);
 }
 
 void bch2_fs_btree_cache_init_early(struct btree_cache *bc)
@@ -727,7 +727,7 @@ int bch2_btree_cache_cannibalize_lock(struct btree_trans *trans, struct closure
 
 	if (!cl) {
 		trace_and_count(c, btree_cache_cannibalize_lock_fail, trans);
-		return -BCH_ERR_ENOMEM_btree_cache_cannibalize_lock;
+		return bch_err_throw(c, ENOMEM_btree_cache_cannibalize_lock);
 	}
 
 	closure_wait(&bc->alloc_wait, cl);
@@ -741,7 +741,7 @@ int bch2_btree_cache_cannibalize_lock(struct btree_trans *trans, struct closure
 	}
 
 	trace_and_count(c, btree_cache_cannibalize_lock_fail, trans);
-	return -BCH_ERR_btree_cache_cannibalize_lock_blocked;
+	return bch_err_throw(c, btree_cache_cannibalize_lock_blocked);
 
 success:
 	trace_and_count(c, btree_cache_cannibalize_lock, trans);
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 91b6395421df..9ddcbe1bda78 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -150,7 +150,7 @@ static int set_node_min(struct bch_fs *c, struct btree *b, struct bpos new_min)
 
 	new = kmalloc_array(BKEY_BTREE_PTR_U64s_MAX, sizeof(u64), GFP_KERNEL);
 	if (!new)
-		return -BCH_ERR_ENOMEM_gc_repair_key;
+		return bch_err_throw(c, ENOMEM_gc_repair_key);
 
 	btree_ptr_to_v2(b, new);
 	b->data->min_key	= new_min;
@@ -190,7 +190,7 @@ static int set_node_max(struct bch_fs *c, struct btree *b, struct bpos new_max)
 
 	new = kmalloc_array(BKEY_BTREE_PTR_U64s_MAX, sizeof(u64), GFP_KERNEL);
 	if (!new)
-		return -BCH_ERR_ENOMEM_gc_repair_key;
+		return bch_err_throw(c, ENOMEM_gc_repair_key);
 
 	btree_ptr_to_v2(b, new);
 	b->data->max_key	= new_max;
@@ -935,7 +935,7 @@ static int bch2_gc_alloc_start(struct bch_fs *c)
 		ret = genradix_prealloc(&ca->buckets_gc, ca->mi.nbuckets, GFP_KERNEL);
 		if (ret) {
 			bch2_dev_put(ca);
-			ret = -BCH_ERR_ENOMEM_gc_alloc_start;
+			ret = bch_err_throw(c, ENOMEM_gc_alloc_start);
 			break;
 		}
 	}
@@ -1093,42 +1093,41 @@ static int gc_btree_gens_key(struct btree_trans *trans,
 {
 	struct bch_fs *c = trans->c;
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
-	struct bkey_i *u;
-	int ret;
 
 	if (unlikely(test_bit(BCH_FS_going_ro, &c->flags)))
 		return -EROFS;
 
-	rcu_read_lock();
-	bkey_for_each_ptr(ptrs, ptr) {
-		struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev);
-		if (!ca)
-			continue;
+	bool too_stale = false;
+	scoped_guard(rcu) {
+		bkey_for_each_ptr(ptrs, ptr) {
+			struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev);
+			if (!ca)
+				continue;
 
-		if (dev_ptr_stale(ca, ptr) > 16) {
-			rcu_read_unlock();
-			goto update;
+			too_stale |= dev_ptr_stale(ca, ptr) > 16;
 		}
+
+		if (!too_stale)
+			bkey_for_each_ptr(ptrs, ptr) {
+				struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev);
+				if (!ca)
+					continue;
+
+				u8 *gen = &ca->oldest_gen[PTR_BUCKET_NR(ca, ptr)];
+				if (gen_after(*gen, ptr->gen))
+					*gen = ptr->gen;
+			}
 	}
 
-	bkey_for_each_ptr(ptrs, ptr) {
-		struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev);
-		if (!ca)
-			continue;
+	if (too_stale) {
+		struct bkey_i *u = bch2_bkey_make_mut(trans, iter, &k, 0);
+		int ret = PTR_ERR_OR_ZERO(u);
+		if (ret)
+			return ret;
 
-		u8 *gen = &ca->oldest_gen[PTR_BUCKET_NR(ca, ptr)];
-		if (gen_after(*gen, ptr->gen))
-			*gen = ptr->gen;
+		bch2_extent_normalize(c, bkey_i_to_s(u));
 	}
-	rcu_read_unlock();
-	return 0;
-update:
-	u = bch2_bkey_make_mut(trans, iter, &k, 0);
-	ret = PTR_ERR_OR_ZERO(u);
-	if (ret)
-		return ret;
 
-	bch2_extent_normalize(c, bkey_i_to_s(u));
 	return 0;
 }
 
@@ -1181,7 +1180,7 @@ int bch2_gc_gens(struct bch_fs *c)
 		ca->oldest_gen = kvmalloc(gens->nbuckets, GFP_KERNEL);
 		if (!ca->oldest_gen) {
 			bch2_dev_put(ca);
-			ret = -BCH_ERR_ENOMEM_gc_gens;
+			ret = bch_err_throw(c, ENOMEM_gc_gens);
 			goto err;
 		}
 
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 34018296053a..57eff3012a7b 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -557,7 +557,7 @@ static int __btree_err(int ret,
 		       const char *fmt, ...)
 {
 	if (c->recovery.curr_pass == BCH_RECOVERY_PASS_scan_for_btree_nodes)
-		return -BCH_ERR_fsck_fix;
+		return bch_err_throw(c, fsck_fix);
 
 	bool have_retry = false;
 	int ret2;
@@ -572,9 +572,9 @@ static int __btree_err(int ret,
 	}
 
 	if (!have_retry && ret == -BCH_ERR_btree_node_read_err_want_retry)
-		ret = -BCH_ERR_btree_node_read_err_fixable;
+		ret = bch_err_throw(c, btree_node_read_err_fixable);
 	if (!have_retry && ret == -BCH_ERR_btree_node_read_err_must_retry)
-		ret = -BCH_ERR_btree_node_read_err_bad_node;
+		ret = bch_err_throw(c, btree_node_read_err_bad_node);
 
 	bch2_sb_error_count(c, err_type);
 
@@ -602,14 +602,14 @@ static int __btree_err(int ret,
 		switch (ret) {
 		case -BCH_ERR_btree_node_read_err_fixable:
 			ret2 = bch2_fsck_err_opt(c, FSCK_CAN_FIX, err_type);
-			if (ret2 != -BCH_ERR_fsck_fix &&
-			    ret2 != -BCH_ERR_fsck_ignore) {
+			if (!bch2_err_matches(ret2, BCH_ERR_fsck_fix) &&
+			    !bch2_err_matches(ret2, BCH_ERR_fsck_ignore)) {
 				ret = ret2;
 				goto fsck_err;
 			}
 
 			if (!have_retry)
-				ret = -BCH_ERR_fsck_fix;
+				ret = bch_err_throw(c, fsck_fix);
 			goto out;
 		case -BCH_ERR_btree_node_read_err_bad_node:
 			prt_str(&out, ", ");
@@ -631,14 +631,14 @@ static int __btree_err(int ret,
 	switch (ret) {
 	case -BCH_ERR_btree_node_read_err_fixable:
 		ret2 = __bch2_fsck_err(c, NULL, FSCK_CAN_FIX, err_type, "%s", out.buf);
-		if (ret2 != -BCH_ERR_fsck_fix &&
-		    ret2 != -BCH_ERR_fsck_ignore) {
+		if (!bch2_err_matches(ret2, BCH_ERR_fsck_fix) &&
+		    !bch2_err_matches(ret2, BCH_ERR_fsck_ignore)) {
 			ret = ret2;
 			goto fsck_err;
 		}
 
 		if (!have_retry)
-			ret = -BCH_ERR_fsck_fix;
+			ret = bch_err_throw(c, fsck_fix);
 		goto out;
 	case -BCH_ERR_btree_node_read_err_bad_node:
 		prt_str(&out, ", ");
@@ -660,7 +660,7 @@ fsck_err:
 			       failed, err_msg,				\
 			       msg, ##__VA_ARGS__);			\
 									\
-	if (_ret != -BCH_ERR_fsck_fix) {				\
+	if (!bch2_err_matches(_ret, BCH_ERR_fsck_fix)) {		\
 		ret = _ret;						\
 		goto fsck_err;						\
 	}								\
@@ -1325,14 +1325,13 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 
 	btree_node_reset_sib_u64s(b);
 
-	rcu_read_lock();
-	bkey_for_each_ptr(bch2_bkey_ptrs(bkey_i_to_s(&b->key)), ptr) {
-		struct bch_dev *ca2 = bch2_dev_rcu(c, ptr->dev);
+	scoped_guard(rcu)
+		bkey_for_each_ptr(bch2_bkey_ptrs(bkey_i_to_s(&b->key)), ptr) {
+			struct bch_dev *ca2 = bch2_dev_rcu(c, ptr->dev);
 
-		if (!ca2 || ca2->mi.state != BCH_MEMBER_STATE_rw)
-			set_btree_node_need_rewrite(b);
-	}
-	rcu_read_unlock();
+			if (!ca2 || ca2->mi.state != BCH_MEMBER_STATE_rw)
+				set_btree_node_need_rewrite(b);
+		}
 
 	if (!ptr_written)
 		set_btree_node_need_rewrite(b);
@@ -1688,7 +1687,7 @@ static int btree_node_read_all_replicas(struct bch_fs *c, struct btree *b, bool
 
 	ra = kzalloc(sizeof(*ra), GFP_NOFS);
 	if (!ra)
-		return -BCH_ERR_ENOMEM_btree_node_read_all_replicas;
+		return bch_err_throw(c, ENOMEM_btree_node_read_all_replicas);
 
 	closure_init(&ra->cl, NULL);
 	ra->c	= c;
@@ -1870,7 +1869,7 @@ static int __bch2_btree_root_read(struct btree_trans *trans, enum btree_id id,
 		bch2_btree_node_hash_remove(&c->btree_cache, b);
 		mutex_unlock(&c->btree_cache.lock);
 
-		ret = -BCH_ERR_btree_node_read_error;
+		ret = bch_err_throw(c, btree_node_read_error);
 		goto err;
 	}
 
@@ -2020,7 +2019,7 @@ int bch2_btree_node_scrub(struct btree_trans *trans,
 	struct bch_fs *c = trans->c;
 
 	if (!enumerated_ref_tryget(&c->writes, BCH_WRITE_REF_btree_node_scrub))
-		return -BCH_ERR_erofs_no_writes;
+		return bch_err_throw(c, erofs_no_writes);
 
 	struct extent_ptr_decoded pick;
 	int ret = bch2_bkey_pick_read_device(c, k, NULL, &pick, dev);
@@ -2030,7 +2029,7 @@ int bch2_btree_node_scrub(struct btree_trans *trans,
 	struct bch_dev *ca = bch2_dev_get_ioref(c, pick.ptr.dev, READ,
 						BCH_DEV_READ_REF_btree_node_scrub);
 	if (!ca) {
-		ret = -BCH_ERR_device_offline;
+		ret = bch_err_throw(c, device_offline);
 		goto err;
 	}
 
@@ -2167,7 +2166,7 @@ static void btree_node_write_work(struct work_struct *work)
 		bch2_dev_list_has_dev(wbio->wbio.failed, ptr->dev));
 
 	if (!bch2_bkey_nr_ptrs(bkey_i_to_s_c(&wbio->key))) {
-		ret = -BCH_ERR_btree_node_write_all_failed;
+		ret = bch_err_throw(c, btree_node_write_all_failed);
 		goto err;
 	}
 
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index b4bf4217a3fa..b78403376c07 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -890,8 +890,7 @@ static noinline void btree_node_mem_ptr_set(struct btree_trans *trans,
 
 static noinline int btree_node_iter_and_journal_peek(struct btree_trans *trans,
 						     struct btree_path *path,
-						     unsigned flags,
-						     struct bkey_buf *out)
+						     unsigned flags)
 {
 	struct bch_fs *c = trans->c;
 	struct btree_path_level *l = path_l(path);
@@ -915,7 +914,7 @@ static noinline int btree_node_iter_and_journal_peek(struct btree_trans *trans,
 		goto err;
 	}
 
-	bch2_bkey_buf_reassemble(out, c, k);
+	bkey_reassemble(&trans->btree_path_down, k);
 
 	if ((flags & BTREE_ITER_prefetch) &&
 	    c->opts.btree_node_prefetch)
@@ -926,6 +925,22 @@ err:
 	return ret;
 }
 
+static noinline_for_stack int btree_node_missing_err(struct btree_trans *trans,
+						     struct btree_path *path)
+{
+	struct bch_fs *c = trans->c;
+	struct printbuf buf = PRINTBUF;
+
+	prt_str(&buf, "node not found at pos ");
+	bch2_bpos_to_text(&buf, path->pos);
+	prt_str(&buf, " within parent node ");
+	bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&path_l(path)->b->key));
+
+	bch2_fs_fatal_error(c, "%s", buf.buf);
+	printbuf_exit(&buf);
+	return bch_err_throw(c, btree_need_topology_repair);
+}
+
 static __always_inline int btree_path_down(struct btree_trans *trans,
 					   struct btree_path *path,
 					   unsigned flags,
@@ -936,51 +951,38 @@ static __always_inline int btree_path_down(struct btree_trans *trans,
 	struct btree *b;
 	unsigned level = path->level - 1;
 	enum six_lock_type lock_type = __btree_lock_want(path, level);
-	struct bkey_buf tmp;
 	int ret;
 
 	EBUG_ON(!btree_node_locked(path, path->level));
 
-	bch2_bkey_buf_init(&tmp);
-
 	if (unlikely(trans->journal_replay_not_finished)) {
-		ret = btree_node_iter_and_journal_peek(trans, path, flags, &tmp);
+		ret = btree_node_iter_and_journal_peek(trans, path, flags);
 		if (ret)
-			goto err;
+			return ret;
 	} else {
 		struct bkey_packed *k = bch2_btree_node_iter_peek(&l->iter, l->b);
-		if (!k) {
-			struct printbuf buf = PRINTBUF;
-
-			prt_str(&buf, "node not found at pos ");
-			bch2_bpos_to_text(&buf, path->pos);
-			prt_str(&buf, " within parent node ");
-			bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&l->b->key));
+		if (unlikely(!k))
+			return btree_node_missing_err(trans, path);
 
-			bch2_fs_fatal_error(c, "%s", buf.buf);
-			printbuf_exit(&buf);
-			ret = -BCH_ERR_btree_need_topology_repair;
-			goto err;
-		}
-
-		bch2_bkey_buf_unpack(&tmp, c, l->b, k);
+		bch2_bkey_unpack(l->b, &trans->btree_path_down, k);
 
-		if ((flags & BTREE_ITER_prefetch) &&
+		if (unlikely((flags & BTREE_ITER_prefetch)) &&
 		    c->opts.btree_node_prefetch) {
 			ret = btree_path_prefetch(trans, path);
 			if (ret)
-				goto err;
+				return ret;
 		}
 	}
 
-	b = bch2_btree_node_get(trans, path, tmp.k, level, lock_type, trace_ip);
+	b = bch2_btree_node_get(trans, path, &trans->btree_path_down,
+				level, lock_type, trace_ip);
 	ret = PTR_ERR_OR_ZERO(b);
 	if (unlikely(ret))
-		goto err;
+		return ret;
 
-	if (likely(!trans->journal_replay_not_finished &&
-		   tmp.k->k.type == KEY_TYPE_btree_ptr_v2) &&
-	    unlikely(b != btree_node_mem_ptr(tmp.k)))
+	if (unlikely(b != btree_node_mem_ptr(&trans->btree_path_down)) &&
+	    likely(!trans->journal_replay_not_finished &&
+		   trans->btree_path_down.k.type == KEY_TYPE_btree_ptr_v2))
 		btree_node_mem_ptr_set(trans, path, level + 1, b);
 
 	if (btree_node_read_locked(path, level + 1))
@@ -992,9 +994,7 @@ static __always_inline int btree_path_down(struct btree_trans *trans,
 	bch2_btree_path_level_init(trans, path, b);
 
 	bch2_btree_path_verify_locks(trans, path);
-err:
-	bch2_bkey_buf_exit(&tmp, c);
-	return ret;
+	return 0;
 }
 
 static int bch2_btree_path_traverse_all(struct btree_trans *trans)
@@ -1006,7 +1006,7 @@ static int bch2_btree_path_traverse_all(struct btree_trans *trans)
 	int ret = 0;
 
 	if (trans->in_traverse_all)
-		return -BCH_ERR_transaction_restart_in_traverse_all;
+		return bch_err_throw(c, transaction_restart_in_traverse_all);
 
 	trans->in_traverse_all = true;
 retry_all:
@@ -3568,13 +3568,12 @@ bch2_btree_bkey_cached_common_to_text(struct printbuf *out,
 				      struct btree_bkey_cached_common *b)
 {
 	struct six_lock_count c = six_lock_counts(&b->lock);
-	struct task_struct *owner;
 	pid_t pid;
 
-	rcu_read_lock();
-	owner = READ_ONCE(b->lock.owner);
-	pid = owner ? owner->pid : 0;
-	rcu_read_unlock();
+	scoped_guard(rcu) {
+		struct task_struct *owner = READ_ONCE(b->lock.owner);
+		pid = owner ? owner->pid : 0;
+	}
 
 	prt_printf(out, "\t%px %c ", b, b->cached ? 'c' : 'b');
 	bch2_btree_id_to_text(out, b->btree_id);
@@ -3603,7 +3602,7 @@ void bch2_btree_trans_to_text(struct printbuf *out, struct btree_trans *trans)
 	prt_printf(out, "%i %s\n", task ? task->pid : 0, trans->fn);
 
 	/* trans->paths is rcu protected vs. freeing */
-	rcu_read_lock();
+	guard(rcu)();
 	out->atomic++;
 
 	struct btree_path *paths = rcu_dereference(trans->paths);
@@ -3646,7 +3645,6 @@ void bch2_btree_trans_to_text(struct printbuf *out, struct btree_trans *trans)
 	}
 out:
 	--out->atomic;
-	rcu_read_unlock();
 }
 
 void bch2_fs_btree_iter_exit(struct bch_fs *c)
diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h
index 2cabb5f0f484..09dd3e52622e 100644
--- a/fs/bcachefs/btree_iter.h
+++ b/fs/bcachefs/btree_iter.h
@@ -963,16 +963,6 @@ struct bkey_s_c bch2_btree_iter_peek_and_restart_outlined(struct btree_trans *,
 	_p;								\
 })
 
-#define bch2_trans_run(_c, _do)						\
-({									\
-	struct btree_trans *trans = bch2_trans_get(_c);			\
-	int _ret = (_do);						\
-	bch2_trans_put(trans);						\
-	_ret;								\
-})
-
-#define bch2_trans_do(_c, _do)	bch2_trans_run(_c, lockrestart_do(trans, _do))
-
 struct btree_trans *__bch2_trans_get(struct bch_fs *, unsigned);
 void bch2_trans_put(struct btree_trans *);
 
@@ -990,6 +980,27 @@ unsigned bch2_trans_get_fn_idx(const char *);
 	__bch2_trans_get(_c, trans_fn_idx);				\
 })
 
+/*
+ * We don't use DEFINE_CLASS() because using a function for the constructor
+ * breaks bch2_trans_get()'s use of __func__
+ */
+typedef struct btree_trans * class_btree_trans_t;
+static inline void class_btree_trans_destructor(struct btree_trans **p)
+{
+	struct btree_trans *trans = *p;
+	bch2_trans_put(trans);
+}
+
+#define class_btree_trans_constructor(_c)	bch2_trans_get(_c)
+
+#define bch2_trans_run(_c, _do)						\
+({									\
+	CLASS(btree_trans, trans)(_c);					\
+	(_do);								\
+})
+
+#define bch2_trans_do(_c, _do)	bch2_trans_run(_c, lockrestart_do(trans, _do))
+
 void bch2_btree_trans_to_text(struct printbuf *, struct btree_trans *);
 
 void bch2_fs_btree_iter_exit(struct bch_fs *);
diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c
index ade3b5addd75..cf7398751644 100644
--- a/fs/bcachefs/btree_journal_iter.c
+++ b/fs/bcachefs/btree_journal_iter.c
@@ -292,7 +292,7 @@ int bch2_journal_key_insert_take(struct bch_fs *c, enum btree_id id,
 		if (!new_keys.data) {
 			bch_err(c, "%s: error allocating new key array (size %zu)",
 				__func__, new_keys.size);
-			return -BCH_ERR_ENOMEM_journal_key_insert;
+			return bch_err_throw(c, ENOMEM_journal_key_insert);
 		}
 
 		/* Since @keys was full, there was no gap: */
@@ -331,7 +331,7 @@ int bch2_journal_key_insert(struct bch_fs *c, enum btree_id id,
 
 	n = kmalloc(bkey_bytes(&k->k), GFP_KERNEL);
 	if (!n)
-		return -BCH_ERR_ENOMEM_journal_key_insert;
+		return bch_err_throw(c, ENOMEM_journal_key_insert);
 
 	bkey_copy(n, k);
 	ret = bch2_journal_key_insert_take(c, id, level, n);
@@ -457,11 +457,9 @@ static void bch2_journal_iter_advance(struct journal_iter *iter)
 
 static struct bkey_s_c bch2_journal_iter_peek(struct journal_iter *iter)
 {
-	struct bkey_s_c ret = bkey_s_c_null;
-
 	journal_iter_verify(iter);
 
-	rcu_read_lock();
+	guard(rcu)();
 	while (iter->idx < iter->keys->size) {
 		struct journal_key *k = iter->keys->data + iter->idx;
 
@@ -470,19 +468,16 @@ static struct bkey_s_c bch2_journal_iter_peek(struct journal_iter *iter)
 			break;
 		BUG_ON(cmp);
 
-		if (!k->overwritten) {
-			ret = bkey_i_to_s_c(k->k);
-			break;
-		}
+		if (!k->overwritten)
+			return bkey_i_to_s_c(k->k);
 
 		if (k->overwritten_range)
 			iter->idx = idx_to_pos(iter->keys, rcu_dereference(k->overwritten_range)->end);
 		else
 			bch2_journal_iter_advance(iter);
 	}
-	rcu_read_unlock();
 
-	return ret;
+	return bkey_s_c_null;
 }
 
 static void bch2_journal_iter_exit(struct journal_iter *iter)
@@ -741,7 +736,7 @@ int bch2_journal_keys_sort(struct bch_fs *c)
 				if (keys->nr * 8 > keys->size * 7) {
 					bch_err(c, "Too many journal keys for slowpath; have %zu compacted, buf size %zu, processed %zu keys at seq %llu",
 						keys->nr, keys->size, nr_read, le64_to_cpu(i->j.seq));
-					return -BCH_ERR_ENOMEM_journal_keys_sort;
+					return bch_err_throw(c, ENOMEM_journal_keys_sort);
 				}
 
 				BUG_ON(darray_push(keys, n));
diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c
index 9da950e7eb7d..d96188b92db2 100644
--- a/fs/bcachefs/btree_key_cache.c
+++ b/fs/bcachefs/btree_key_cache.c
@@ -187,27 +187,23 @@ lock:
 static struct bkey_cached *
 bkey_cached_reuse(struct btree_key_cache *c)
 {
-	struct bucket_table *tbl;
+
+	guard(rcu)();
+	struct bucket_table *tbl = rht_dereference_rcu(c->table.tbl, &c->table);
 	struct rhash_head *pos;
 	struct bkey_cached *ck;
-	unsigned i;
 
-	rcu_read_lock();
-	tbl = rht_dereference_rcu(c->table.tbl, &c->table);
-	for (i = 0; i < tbl->size; i++)
+	for (unsigned i = 0; i < tbl->size; i++)
 		rht_for_each_entry_rcu(ck, pos, tbl, i, hash) {
 			if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags) &&
 			    bkey_cached_lock_for_evict(ck)) {
 				if (bkey_cached_evict(c, ck))
-					goto out;
+					return ck;
 				six_unlock_write(&ck->c.lock);
 				six_unlock_intent(&ck->c.lock);
 			}
 		}
-	ck = NULL;
-out:
-	rcu_read_unlock();
-	return ck;
+	return NULL;
 }
 
 static int btree_key_cache_create(struct btree_trans *trans,
@@ -242,7 +238,7 @@ static int btree_key_cache_create(struct btree_trans *trans,
 		if (unlikely(!ck)) {
 			bch_err(c, "error allocating memory for key cache item, btree %s",
 				bch2_btree_id_str(ck_path->btree_id));
-			return -BCH_ERR_ENOMEM_btree_key_cache_create;
+			return bch_err_throw(c, ENOMEM_btree_key_cache_create);
 		}
 	}
 
@@ -260,7 +256,7 @@ static int btree_key_cache_create(struct btree_trans *trans,
 		if (unlikely(!new_k)) {
 			bch_err(trans->c, "error allocating memory for key cache key, btree %s u64s %u",
 				bch2_btree_id_str(ck->key.btree_id), key_u64s);
-			ret = -BCH_ERR_ENOMEM_btree_key_cache_fill;
+			ret = bch_err_throw(c, ENOMEM_btree_key_cache_fill);
 		} else if (ret) {
 			kfree(new_k);
 			goto err;
@@ -826,20 +822,20 @@ int bch2_fs_btree_key_cache_init(struct btree_key_cache *bc)
 
 	bc->nr_pending = alloc_percpu(size_t);
 	if (!bc->nr_pending)
-		return -BCH_ERR_ENOMEM_fs_btree_cache_init;
+		return bch_err_throw(c, ENOMEM_fs_btree_cache_init);
 
 	if (rcu_pending_init(&bc->pending[0], &c->btree_trans_barrier, __bkey_cached_free) ||
 	    rcu_pending_init(&bc->pending[1], &c->btree_trans_barrier, __bkey_cached_free))
-		return -BCH_ERR_ENOMEM_fs_btree_cache_init;
+		return bch_err_throw(c, ENOMEM_fs_btree_cache_init);
 
 	if (rhashtable_init(&bc->table, &bch2_btree_key_cache_params))
-		return -BCH_ERR_ENOMEM_fs_btree_cache_init;
+		return bch_err_throw(c, ENOMEM_fs_btree_cache_init);
 
 	bc->table_init_done = true;
 
 	shrink = shrinker_alloc(0, "%s-btree_key_cache", c->name);
 	if (!shrink)
-		return -BCH_ERR_ENOMEM_fs_btree_cache_init;
+		return bch_err_throw(c, ENOMEM_fs_btree_cache_init);
 	bc->shrink = shrink;
 	shrink->count_objects	= bch2_btree_key_cache_count;
 	shrink->scan_objects	= bch2_btree_key_cache_scan;
diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index 2f2aed0c9916..47035aae232e 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -194,6 +194,30 @@ static int btree_trans_abort_preference(struct btree_trans *trans)
 	return 3;
 }
 
+static noinline __noreturn void break_cycle_fail(struct lock_graph *g)
+{
+	struct printbuf buf = PRINTBUF;
+	buf.atomic++;
+
+	prt_printf(&buf, bch2_fmt(g->g->trans->c, "cycle of nofail locks"));
+
+	for (struct trans_waiting_for_lock *i = g->g; i < g->g + g->nr; i++) {
+		struct btree_trans *trans = i->trans;
+
+		bch2_btree_trans_to_text(&buf, trans);
+
+		prt_printf(&buf, "backtrace:\n");
+		printbuf_indent_add(&buf, 2);
+		bch2_prt_task_backtrace(&buf, trans->locking_wait.task, 2, GFP_NOWAIT);
+		printbuf_indent_sub(&buf, 2);
+		prt_newline(&buf);
+	}
+
+	bch2_print_str_nonblocking(g->g->trans->c, KERN_ERR, buf.buf);
+	printbuf_exit(&buf);
+	BUG();
+}
+
 static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle,
 				struct trans_waiting_for_lock *from)
 {
@@ -219,28 +243,8 @@ static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle,
 		}
 	}
 
-	if (unlikely(!best)) {
-		struct printbuf buf = PRINTBUF;
-		buf.atomic++;
-
-		prt_printf(&buf, bch2_fmt(g->g->trans->c, "cycle of nofail locks"));
-
-		for (i = g->g; i < g->g + g->nr; i++) {
-			struct btree_trans *trans = i->trans;
-
-			bch2_btree_trans_to_text(&buf, trans);
-
-			prt_printf(&buf, "backtrace:\n");
-			printbuf_indent_add(&buf, 2);
-			bch2_prt_task_backtrace(&buf, trans->locking_wait.task, 2, GFP_NOWAIT);
-			printbuf_indent_sub(&buf, 2);
-			prt_newline(&buf);
-		}
-
-		bch2_print_str_nonblocking(g->g->trans->c, KERN_ERR, buf.buf);
-		printbuf_exit(&buf);
-		BUG();
-	}
+	if (unlikely(!best))
+		break_cycle_fail(g);
 
 	ret = abort_lock(g, abort);
 out:
@@ -255,15 +259,14 @@ static int lock_graph_descend(struct lock_graph *g, struct btree_trans *trans,
 			      struct printbuf *cycle)
 {
 	struct btree_trans *orig_trans = g->g->trans;
-	struct trans_waiting_for_lock *i;
 
-	for (i = g->g; i < g->g + g->nr; i++)
+	for (struct trans_waiting_for_lock *i = g->g; i < g->g + g->nr; i++)
 		if (i->trans == trans) {
 			closure_put(&trans->ref);
 			return break_cycle(g, cycle, i);
 		}
 
-	if (g->nr == ARRAY_SIZE(g->g)) {
+	if (unlikely(g->nr == ARRAY_SIZE(g->g))) {
 		closure_put(&trans->ref);
 
 		if (orig_trans->lock_may_not_fail)
@@ -308,7 +311,7 @@ int bch2_check_for_deadlock(struct btree_trans *trans, struct printbuf *cycle)
 	lock_graph_down(&g, trans);
 
 	/* trans->paths is rcu protected vs. freeing */
-	rcu_read_lock();
+	guard(rcu)();
 	if (cycle)
 		cycle->atomic++;
 next:
@@ -406,7 +409,6 @@ up:
 out:
 	if (cycle)
 		--cycle->atomic;
-	rcu_read_unlock();
 	return ret;
 }
 
diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c
index 5a97a6b8a757..a35847734a60 100644
--- a/fs/bcachefs/btree_node_scan.c
+++ b/fs/bcachefs/btree_node_scan.c
@@ -363,6 +363,8 @@ static int handle_overwrites(struct bch_fs *c,
 				min_heap_sift_down(nodes_heap, 0, &found_btree_node_heap_cbs, NULL);
 			}
 		}
+
+		cond_resched();
 	}
 
 	return 0;
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index 1c03c965d836..d9710801e3ee 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -376,7 +376,7 @@ static inline int btree_key_can_insert(struct btree_trans *trans,
 				       struct btree *b, unsigned u64s)
 {
 	if (!bch2_btree_node_insert_fits(b, u64s))
-		return -BCH_ERR_btree_insert_btree_node_full;
+		return bch_err_throw(trans->c, btree_insert_btree_node_full);
 
 	return 0;
 }
@@ -394,9 +394,10 @@ btree_key_can_insert_cached_slowpath(struct btree_trans *trans, unsigned flags,
 
 	new_k = kmalloc(new_u64s * sizeof(u64), GFP_KERNEL);
 	if (!new_k) {
-		bch_err(trans->c, "error allocating memory for key cache key, btree %s u64s %u",
+		struct bch_fs *c = trans->c;
+		bch_err(c, "error allocating memory for key cache key, btree %s u64s %u",
 			bch2_btree_id_str(path->btree_id), new_u64s);
-		return -BCH_ERR_ENOMEM_btree_key_cache_insert;
+		return bch_err_throw(c, ENOMEM_btree_key_cache_insert);
 	}
 
 	ret =   bch2_trans_relock(trans) ?:
@@ -432,7 +433,7 @@ static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags
 	if (watermark < BCH_WATERMARK_reclaim &&
 	    !test_bit(BKEY_CACHED_DIRTY, &ck->flags) &&
 	    bch2_btree_key_cache_must_wait(c))
-		return -BCH_ERR_btree_insert_need_journal_reclaim;
+		return bch_err_throw(c, btree_insert_need_journal_reclaim);
 
 	/*
 	 * bch2_varint_decode can read past the end of the buffer by at most 7
@@ -894,7 +895,7 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags,
 		 */
 		if ((flags & BCH_TRANS_COMMIT_journal_reclaim) &&
 		    watermark < BCH_WATERMARK_reclaim) {
-			ret = -BCH_ERR_journal_reclaim_would_deadlock;
+			ret = bch_err_throw(c, journal_reclaim_would_deadlock);
 			goto out;
 		}
 
@@ -966,14 +967,27 @@ do_bch2_trans_commit_to_journal_replay(struct btree_trans *trans)
 
 	for (struct jset_entry *i = btree_trans_journal_entries_start(trans);
 	     i != btree_trans_journal_entries_top(trans);
-	     i = vstruct_next(i))
+	     i = vstruct_next(i)) {
 		if (i->type == BCH_JSET_ENTRY_btree_keys ||
 		    i->type == BCH_JSET_ENTRY_write_buffer_keys) {
-			int ret = bch2_journal_key_insert(c, i->btree_id, i->level, i->start);
-			if (ret)
-				return ret;
+			jset_entry_for_each_key(i, k) {
+				int ret = bch2_journal_key_insert(c, i->btree_id, i->level, k);
+				if (ret)
+					return ret;
+			}
 		}
 
+		if (i->type == BCH_JSET_ENTRY_btree_root) {
+			guard(mutex)(&c->btree_root_lock);
+
+			struct btree_root *r = bch2_btree_id_root(c, i->btree_id);
+
+			bkey_copy(&r->key, i->start);
+			r->level = i->level;
+			r->alive = true;
+		}
+	}
+
 	for (struct bkey_i *i = btree_trans_subbuf_base(trans, &trans->accounting);
 	     i != btree_trans_subbuf_top(trans, &trans->accounting);
 	     i = bkey_next(i)) {
@@ -1011,7 +1025,7 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 		if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags)))
 			ret = do_bch2_trans_commit_to_journal_replay(trans);
 		else
-			ret = -BCH_ERR_erofs_trans_commit;
+			ret = bch_err_throw(c, erofs_trans_commit);
 		goto out_reset;
 	}
 
@@ -1093,7 +1107,7 @@ err:
 	 * restart:
 	 */
 	if (flags & BCH_TRANS_COMMIT_no_journal_res) {
-		ret = -BCH_ERR_transaction_restart_nested;
+		ret = bch_err_throw(c, transaction_restart_nested);
 		goto out;
 	}
 
diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h
index 9d641bf9d2a2..c61c4171ae50 100644
--- a/fs/bcachefs/btree_types.h
+++ b/fs/bcachefs/btree_types.h
@@ -555,6 +555,8 @@ struct btree_trans {
 	unsigned		journal_u64s;
 	unsigned		extra_disk_res; /* XXX kill */
 
+	__BKEY_PADDED(btree_path_down, BKEY_BTREE_PTR_VAL_U64s_MAX);
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif
diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c
index 5dac09c98026..e97e78c10f49 100644
--- a/fs/bcachefs/btree_update.c
+++ b/fs/bcachefs/btree_update.c
@@ -123,65 +123,44 @@ static int need_whiteout_for_snapshot(struct btree_trans *trans,
 }
 
 int __bch2_insert_snapshot_whiteouts(struct btree_trans *trans,
-				   enum btree_id id,
-				   struct bpos old_pos,
-				   struct bpos new_pos)
+				     enum btree_id btree, struct bpos pos,
+				     snapshot_id_list *s)
 {
-	struct bch_fs *c = trans->c;
-	struct btree_iter old_iter, new_iter = {};
-	struct bkey_s_c old_k, new_k;
-	snapshot_id_list s;
-	struct bkey_i *update;
 	int ret = 0;
 
-	if (!bch2_snapshot_has_children(c, old_pos.snapshot))
-		return 0;
-
-	darray_init(&s);
+	darray_for_each(*s, id) {
+		pos.snapshot = *id;
 
-	bch2_trans_iter_init(trans, &old_iter, id, old_pos,
-			     BTREE_ITER_not_extents|
-			     BTREE_ITER_all_snapshots);
-	while ((old_k = bch2_btree_iter_prev(trans, &old_iter)).k &&
-	       !(ret = bkey_err(old_k)) &&
-	       bkey_eq(old_pos, old_k.k->p)) {
-		struct bpos whiteout_pos =
-			SPOS(new_pos.inode, new_pos.offset, old_k.k->p.snapshot);
-
-		if (!bch2_snapshot_is_ancestor(c, old_k.k->p.snapshot, old_pos.snapshot) ||
-		    snapshot_list_has_ancestor(c, &s, old_k.k->p.snapshot))
-			continue;
-
-		new_k = bch2_bkey_get_iter(trans, &new_iter, id, whiteout_pos,
-					   BTREE_ITER_not_extents|
-					   BTREE_ITER_intent);
-		ret = bkey_err(new_k);
+		struct btree_iter iter;
+		struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, btree, pos,
+						       BTREE_ITER_not_extents|
+						       BTREE_ITER_intent);
+		ret = bkey_err(k);
 		if (ret)
 			break;
 
-		if (new_k.k->type == KEY_TYPE_deleted) {
-			update = bch2_trans_kmalloc(trans, sizeof(struct bkey_i));
+		if (k.k->type == KEY_TYPE_deleted) {
+			struct bkey_i *update = bch2_trans_kmalloc(trans, sizeof(struct bkey_i));
 			ret = PTR_ERR_OR_ZERO(update);
-			if (ret)
+			if (ret) {
+				bch2_trans_iter_exit(trans, &iter);
 				break;
+			}
 
 			bkey_init(&update->k);
-			update->k.p		= whiteout_pos;
+			update->k.p		= pos;
 			update->k.type		= KEY_TYPE_whiteout;
 
-			ret = bch2_trans_update(trans, &new_iter, update,
+			ret = bch2_trans_update(trans, &iter, update,
 						BTREE_UPDATE_internal_snapshot_node);
 		}
-		bch2_trans_iter_exit(trans, &new_iter);
+		bch2_trans_iter_exit(trans, &iter);
 
-		ret = snapshot_list_add(c, &s, old_k.k->p.snapshot);
 		if (ret)
 			break;
 	}
-	bch2_trans_iter_exit(trans, &new_iter);
-	bch2_trans_iter_exit(trans, &old_iter);
-	darray_exit(&s);
 
+	darray_exit(s);
 	return ret;
 }
 
@@ -608,7 +587,7 @@ int bch2_bkey_get_empty_slot(struct btree_trans *trans, struct btree_iter *iter,
 	BUG_ON(k.k->type != KEY_TYPE_deleted);
 
 	if (bkey_gt(k.k->p, end)) {
-		ret = -BCH_ERR_ENOSPC_btree_slot;
+		ret = bch_err_throw(trans->c, ENOSPC_btree_slot);
 		goto err;
 	}
 
diff --git a/fs/bcachefs/btree_update.h b/fs/bcachefs/btree_update.h
index f907eaa8b185..9feef1dc4de5 100644
--- a/fs/bcachefs/btree_update.h
+++ b/fs/bcachefs/btree_update.h
@@ -4,6 +4,7 @@
 
 #include "btree_iter.h"
 #include "journal.h"
+#include "snapshot.h"
 
 struct bch_fs;
 struct btree;
@@ -74,7 +75,7 @@ static inline int bch2_btree_delete_at_buffered(struct btree_trans *trans,
 }
 
 int __bch2_insert_snapshot_whiteouts(struct btree_trans *, enum btree_id,
-				     struct bpos, struct bpos);
+				     struct bpos, snapshot_id_list *);
 
 /*
  * For use when splitting extents in existing snapshots:
@@ -88,11 +89,20 @@ static inline int bch2_insert_snapshot_whiteouts(struct btree_trans *trans,
 						 struct bpos old_pos,
 						 struct bpos new_pos)
 {
+	BUG_ON(old_pos.snapshot != new_pos.snapshot);
+
 	if (!btree_type_has_snapshots(btree) ||
 	    bkey_eq(old_pos, new_pos))
 		return 0;
 
-	return __bch2_insert_snapshot_whiteouts(trans, btree, old_pos, new_pos);
+	snapshot_id_list s;
+	int ret = bch2_get_snapshot_overwrites(trans, btree, old_pos, &s);
+	if (ret)
+		return ret;
+
+	return s.nr
+		? __bch2_insert_snapshot_whiteouts(trans, btree, new_pos, &s)
+		: 0;
 }
 
 int bch2_trans_update_extent_overwrite(struct btree_trans *, struct btree_iter *,
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 74e65714fecd..d2ecb782919b 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -57,8 +57,6 @@ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b)
 	struct bkey_buf prev;
 	int ret = 0;
 
-	printbuf_indent_add_nextline(&buf, 2);
-
 	BUG_ON(b->key.k.type == KEY_TYPE_btree_ptr_v2 &&
 	       !bpos_eq(bkey_i_to_btree_ptr_v2(&b->key)->v.min_key,
 			b->data->min_key));
@@ -69,20 +67,23 @@ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b)
 
 	if (b == btree_node_root(c, b)) {
 		if (!bpos_eq(b->data->min_key, POS_MIN)) {
-			ret = __bch2_topology_error(c, &buf);
-
+			bch2_log_msg_start(c, &buf);
+			prt_printf(&buf, "btree root with incorrect min_key: ");
 			bch2_bpos_to_text(&buf, b->data->min_key);
-			log_fsck_err(trans, btree_root_bad_min_key,
-				      "btree root with incorrect min_key: %s", buf.buf);
-			goto out;
+			prt_newline(&buf);
+
+			bch2_count_fsck_err(c, btree_root_bad_min_key, &buf);
+			goto err;
 		}
 
 		if (!bpos_eq(b->data->max_key, SPOS_MAX)) {
-			ret = __bch2_topology_error(c, &buf);
+			bch2_log_msg_start(c, &buf);
+			prt_printf(&buf, "btree root with incorrect max_key: ");
 			bch2_bpos_to_text(&buf, b->data->max_key);
-			log_fsck_err(trans, btree_root_bad_max_key,
-				      "btree root with incorrect max_key: %s", buf.buf);
-			goto out;
+			prt_newline(&buf);
+
+			bch2_count_fsck_err(c, btree_root_bad_max_key, &buf);
+			goto err;
 		}
 	}
 
@@ -100,19 +101,15 @@ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b)
 			: bpos_successor(prev.k->k.p);
 
 		if (!bpos_eq(expected_min, bp.v->min_key)) {
-			ret = __bch2_topology_error(c, &buf);
-
-			prt_str(&buf, "end of prev node doesn't match start of next node\nin ");
-			bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level);
-			prt_str(&buf, " node ");
-			bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
+			prt_str(&buf, "end of prev node doesn't match start of next node");
 			prt_str(&buf, "\nprev ");
 			bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k));
 			prt_str(&buf, "\nnext ");
 			bch2_bkey_val_to_text(&buf, c, k);
+			prt_newline(&buf);
 
-			log_fsck_err(trans, btree_node_topology_bad_min_key, "%s", buf.buf);
-			goto out;
+			bch2_count_fsck_err(c, btree_node_topology_bad_min_key, &buf);
+			goto err;
 		}
 
 		bch2_bkey_buf_reassemble(&prev, c, k);
@@ -120,32 +117,34 @@ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b)
 	}
 
 	if (bkey_deleted(&prev.k->k)) {
-		ret = __bch2_topology_error(c, &buf);
-
-		prt_str(&buf, "empty interior node\nin ");
-		bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level);
-		prt_str(&buf, " node ");
-		bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
-
-		log_fsck_err(trans, btree_node_topology_empty_interior_node, "%s", buf.buf);
-	} else if (!bpos_eq(prev.k->k.p, b->key.k.p)) {
-		ret = __bch2_topology_error(c, &buf);
+		prt_printf(&buf, "empty interior node\n");
+		bch2_count_fsck_err(c, btree_node_topology_empty_interior_node, &buf);
+		goto err;
+	}
 
-		prt_str(&buf, "last child node doesn't end at end of parent node\nin ");
-		bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level);
-		prt_str(&buf, " node ");
-		bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
-		prt_str(&buf, "\nlast key ");
+	if (!bpos_eq(prev.k->k.p, b->key.k.p)) {
+		prt_str(&buf, "last child node doesn't end at end of parent node\nchild: ");
 		bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k));
+		prt_newline(&buf);
 
-		log_fsck_err(trans, btree_node_topology_bad_max_key, "%s", buf.buf);
+		bch2_count_fsck_err(c, btree_node_topology_bad_max_key, &buf);
+		goto err;
 	}
 out:
-fsck_err:
 	bch2_btree_and_journal_iter_exit(&iter);
 	bch2_bkey_buf_exit(&prev, c);
 	printbuf_exit(&buf);
 	return ret;
+err:
+	bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level);
+	prt_char(&buf, ' ');
+	bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
+	prt_newline(&buf);
+
+	ret = __bch2_topology_error(c, &buf);
+	bch2_print_str(c, KERN_ERR, buf.buf);
+	BUG_ON(!ret);
+	goto out;
 }
 
 /* Calculate ideal packed bkey format for new btree nodes: */
@@ -685,12 +684,31 @@ static void btree_update_nodes_written(struct btree_update *as)
 
 	/*
 	 * Wait for any in flight writes to finish before we free the old nodes
-	 * on disk:
+	 * on disk. But we haven't pinned those old nodes in the btree cache,
+	 * they might have already been evicted.
+	 *
+	 * The update we're completing deleted references to those nodes from the
+	 * btree, so we know if they've been evicted they can't be pulled back in.
+	 * We just have to check if the nodes we have pointers to are still those
+	 * old nodes, and haven't been reused.
+	 *
+	 * This can't be done locklessly because the data buffer might have been
+	 * vmalloc allocated, and they're not RCU freed. We also need the
+	 * __no_kmsan_checks annotation because even with the btree node read
+	 * lock, nothing tells us that the data buffer has been initialized (if
+	 * the btree node has been reused for a different node, and the data
+	 * buffer swapped for a new data buffer).
 	 */
 	for (i = 0; i < as->nr_old_nodes; i++) {
 		b = as->old_nodes[i];
 
-		if (btree_node_seq_matches(b, as->old_nodes_seq[i]))
+		bch2_trans_begin(trans);
+		btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read);
+		bool seq_matches = btree_node_seq_matches(b, as->old_nodes_seq[i]);
+		six_unlock_read(&b->c.lock);
+		bch2_trans_unlock_long(trans);
+
+		if (seq_matches)
 			wait_on_bit_io(&b->flags, BTREE_NODE_write_in_flight_inner,
 				       TASK_UNINTERRUPTIBLE);
 	}
@@ -1245,7 +1263,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 		if (bch2_err_matches(ret, ENOSPC) &&
 		    (flags & BCH_TRANS_COMMIT_journal_reclaim) &&
 		    watermark < BCH_WATERMARK_reclaim) {
-			ret = -BCH_ERR_journal_reclaim_would_deadlock;
+			ret = bch_err_throw(c, journal_reclaim_would_deadlock);
 			goto err;
 		}
 
@@ -2178,7 +2196,7 @@ static int get_iter_to_node(struct btree_trans *trans, struct btree_iter *iter,
 	if (btree_iter_path(trans, iter)->l[b->c.level].b != b) {
 		/* node has been freed: */
 		BUG_ON(!btree_node_dying(b));
-		ret = -BCH_ERR_btree_node_dying;
+		ret = bch_err_throw(trans->c, btree_node_dying);
 		goto err;
 	}
 
@@ -2792,16 +2810,16 @@ int bch2_fs_btree_interior_update_init(struct bch_fs *c)
 	c->btree_interior_update_worker =
 		alloc_workqueue("btree_update", WQ_UNBOUND|WQ_MEM_RECLAIM, 8);
 	if (!c->btree_interior_update_worker)
-		return -BCH_ERR_ENOMEM_btree_interior_update_worker_init;
+		return bch_err_throw(c, ENOMEM_btree_interior_update_worker_init);
 
 	c->btree_node_rewrite_worker =
 		alloc_ordered_workqueue("btree_node_rewrite", WQ_UNBOUND);
 	if (!c->btree_node_rewrite_worker)
-		return -BCH_ERR_ENOMEM_btree_interior_update_worker_init;
+		return bch_err_throw(c, ENOMEM_btree_interior_update_worker_init);
 
 	if (mempool_init_kmalloc_pool(&c->btree_interior_update_pool, 1,
 				      sizeof(struct btree_update)))
-		return -BCH_ERR_ENOMEM_btree_interior_update_pool_init;
+		return bch_err_throw(c, ENOMEM_btree_interior_update_pool_init);
 
 	return 0;
 }
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index efb0c64d0aac..90b21e61d2b6 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -394,7 +394,7 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans)
 		bool accounting_accumulated = false;
 		do {
 			if (race_fault()) {
-				ret = -BCH_ERR_journal_reclaim_would_deadlock;
+				ret = bch_err_throw(c, journal_reclaim_would_deadlock);
 				break;
 			}
 
@@ -633,7 +633,7 @@ int bch2_btree_write_buffer_tryflush(struct btree_trans *trans)
 	struct bch_fs *c = trans->c;
 
 	if (!enumerated_ref_tryget(&c->writes, BCH_WRITE_REF_btree_write_buffer))
-		return -BCH_ERR_erofs_no_writes;
+		return bch_err_throw(c, erofs_no_writes);
 
 	int ret = bch2_btree_write_buffer_flush_nocheck_rw(trans);
 	enumerated_ref_put(&c->writes, BCH_WRITE_REF_btree_write_buffer);
@@ -676,7 +676,7 @@ int bch2_btree_write_buffer_maybe_flush(struct btree_trans *trans,
 			goto err;
 
 		bch2_bkey_buf_copy(last_flushed, c, tmp.k);
-		ret = -BCH_ERR_transaction_restart_write_buffer_flush;
+		ret = bch_err_throw(c, transaction_restart_write_buffer_flush);
 	}
 err:
 	bch2_bkey_buf_exit(&tmp, c);
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index 09eb5a543ae4..f25903c10e8a 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -221,6 +221,20 @@ static int bch2_check_fix_ptr(struct btree_trans *trans,
 			 bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
 		if (!p.ptr.cached &&
 		    data_type == BCH_DATA_btree) {
+			switch (g->data_type) {
+			case BCH_DATA_sb:
+				bch_err(c, "btree and superblock in the same bucket - cannot repair");
+				ret = bch_err_throw(c, fsck_repair_unimplemented);
+				goto out;
+			case BCH_DATA_journal:
+				ret = bch2_dev_journal_bucket_delete(ca, PTR_BUCKET_NR(ca, &p.ptr));
+				bch_err_msg(c, ret, "error deleting journal bucket %zu",
+					    PTR_BUCKET_NR(ca, &p.ptr));
+				if (ret)
+					goto out;
+				break;
+			}
+
 			g->data_type		= data_type;
 			g->stripe_sectors	= 0;
 			g->dirty_sectors	= 0;
@@ -270,6 +284,9 @@ int bch2_check_fix_ptrs(struct btree_trans *trans,
 	struct printbuf buf = PRINTBUF;
 	int ret = 0;
 
+	/* We don't yet do btree key updates correctly for when we're RW */
+	BUG_ON(test_bit(BCH_FS_rw, &c->flags));
+
 	bkey_for_each_ptr_decode(k.k, ptrs_c, p, entry_c) {
 		ret = bch2_check_fix_ptr(trans, k, p, entry_c, &do_update);
 		if (ret)
@@ -277,20 +294,13 @@ int bch2_check_fix_ptrs(struct btree_trans *trans,
 	}
 
 	if (do_update) {
-		if (flags & BTREE_TRIGGER_is_root) {
-			bch_err(c, "cannot update btree roots yet");
-			ret = -EINVAL;
-			goto err;
-		}
-
 		struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k);
 		ret = PTR_ERR_OR_ZERO(new);
 		if (ret)
 			goto err;
 
-		rcu_read_lock();
-		bch2_bkey_drop_ptrs(bkey_i_to_s(new), ptr, !bch2_dev_exists(c, ptr->dev));
-		rcu_read_unlock();
+		scoped_guard(rcu)
+			bch2_bkey_drop_ptrs(bkey_i_to_s(new), ptr, !bch2_dev_exists(c, ptr->dev));
 
 		if (level) {
 			/*
@@ -299,14 +309,11 @@ int bch2_check_fix_ptrs(struct btree_trans *trans,
 			 * sort it out:
 			 */
 			struct bkey_ptrs ptrs = bch2_bkey_ptrs(bkey_i_to_s(new));
-			rcu_read_lock();
-			bkey_for_each_ptr(ptrs, ptr) {
-				struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev);
-				struct bucket *g = PTR_GC_BUCKET(ca, ptr);
-
-				ptr->gen = g->gen;
-			}
-			rcu_read_unlock();
+			scoped_guard(rcu)
+				bkey_for_each_ptr(ptrs, ptr) {
+					struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev);
+					ptr->gen = PTR_GC_BUCKET(ca, ptr)->gen;
+				}
 		} else {
 			struct bkey_ptrs ptrs;
 			union bch_extent_entry *entry;
@@ -370,19 +377,41 @@ found:
 			bch_info(c, "new key %s", buf.buf);
 		}
 
-		struct btree_iter iter;
-		bch2_trans_node_iter_init(trans, &iter, btree, new->k.p, 0, level,
-					  BTREE_ITER_intent|BTREE_ITER_all_snapshots);
-		ret =   bch2_btree_iter_traverse(trans, &iter) ?:
-			bch2_trans_update(trans, &iter, new,
-					  BTREE_UPDATE_internal_snapshot_node|
-					  BTREE_TRIGGER_norun);
-		bch2_trans_iter_exit(trans, &iter);
-		if (ret)
-			goto err;
+		if (!(flags & BTREE_TRIGGER_is_root)) {
+			struct btree_iter iter;
+			bch2_trans_node_iter_init(trans, &iter, btree, new->k.p, 0, level,
+						  BTREE_ITER_intent|BTREE_ITER_all_snapshots);
+			ret =   bch2_btree_iter_traverse(trans, &iter) ?:
+				bch2_trans_update(trans, &iter, new,
+						  BTREE_UPDATE_internal_snapshot_node|
+						  BTREE_TRIGGER_norun);
+			bch2_trans_iter_exit(trans, &iter);
+			if (ret)
+				goto err;
+
+			if (level)
+				bch2_btree_node_update_key_early(trans, btree, level - 1, k, new);
+		} else {
+			struct jset_entry *e = bch2_trans_jset_entry_alloc(trans,
+					       jset_u64s(new->k.u64s));
+			ret = PTR_ERR_OR_ZERO(e);
+			if (ret)
+				goto err;
+
+			journal_entry_set(e,
+					  BCH_JSET_ENTRY_btree_root,
+					  btree, level - 1,
+					  new, new->k.u64s);
 
-		if (level)
-			bch2_btree_node_update_key_early(trans, btree, level - 1, k, new);
+			/*
+			 * no locking, we're single threaded and not rw yet, see
+			 * the big assertino above that we repeat here:
+			 */
+			BUG_ON(test_bit(BCH_FS_rw, &c->flags));
+
+			struct btree *b = bch2_btree_id_root(c, btree)->b;
+			bkey_copy(&b->key, new);
+		}
 	}
 err:
 	printbuf_exit(&buf);
@@ -406,7 +435,15 @@ static int bucket_ref_update_err(struct btree_trans *trans, struct printbuf *buf
 	if (insert) {
 		bch2_trans_updates_to_text(buf, trans);
 		__bch2_inconsistent_error(c, buf);
-		ret = -BCH_ERR_bucket_ref_update;
+		/*
+		 * If we're in recovery, run_explicit_recovery_pass might give
+		 * us an error code for rewinding recovery
+		 */
+		if (!ret)
+			ret = bch_err_throw(c, bucket_ref_update);
+	} else {
+		/* Always ignore overwrite errors, so that deletion works */
+		ret = 0;
 	}
 
 	if (print || insert)
@@ -595,7 +632,7 @@ static int bch2_trigger_pointer(struct btree_trans *trans,
 	struct bch_dev *ca = bch2_dev_tryget(c, p.ptr.dev);
 	if (unlikely(!ca)) {
 		if (insert && p.ptr.dev != BCH_SB_MEMBER_INVALID)
-			ret = -BCH_ERR_trigger_pointer;
+			ret = bch_err_throw(c, trigger_pointer);
 		goto err;
 	}
 
@@ -603,7 +640,7 @@ static int bch2_trigger_pointer(struct btree_trans *trans,
 	if (!bucket_valid(ca, bucket.offset)) {
 		if (insert) {
 			bch2_dev_bucket_missing(ca, bucket.offset);
-			ret = -BCH_ERR_trigger_pointer;
+			ret = bch_err_throw(c, trigger_pointer);
 		}
 		goto err;
 	}
@@ -625,7 +662,7 @@ static int bch2_trigger_pointer(struct btree_trans *trans,
 		if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u\n  %s",
 					    p.ptr.dev,
 					    (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
-			ret = -BCH_ERR_trigger_pointer;
+			ret = bch_err_throw(c, trigger_pointer);
 			goto err;
 		}
 
@@ -651,6 +688,8 @@ static int bch2_trigger_stripe_ptr(struct btree_trans *trans,
 				s64 sectors,
 				enum btree_iter_update_trigger_flags flags)
 {
+	struct bch_fs *c = trans->c;
+
 	if (flags & BTREE_TRIGGER_transactional) {
 		struct btree_iter iter;
 		struct bkey_i_stripe *s = bch2_bkey_get_mut_typed(trans, &iter,
@@ -668,7 +707,7 @@ static int bch2_trigger_stripe_ptr(struct btree_trans *trans,
 			bch2_trans_inconsistent(trans,
 				"stripe pointer doesn't match stripe %llu",
 				(u64) p.ec.idx);
-			ret = -BCH_ERR_trigger_stripe_pointer;
+			ret = bch_err_throw(c, trigger_stripe_pointer);
 			goto err;
 		}
 
@@ -688,13 +727,11 @@ err:
 	}
 
 	if (flags & BTREE_TRIGGER_gc) {
-		struct bch_fs *c = trans->c;
-
 		struct gc_stripe *m = genradix_ptr_alloc(&c->gc_stripes, p.ec.idx, GFP_KERNEL);
 		if (!m) {
 			bch_err(c, "error allocating memory for gc_stripes, idx %llu",
 				(u64) p.ec.idx);
-			return -BCH_ERR_ENOMEM_mark_stripe_ptr;
+			return bch_err_throw(c, ENOMEM_mark_stripe_ptr);
 		}
 
 		gc_stripe_lock(m);
@@ -709,7 +746,7 @@ err:
 			__bch2_inconsistent_error(c, &buf);
 			bch2_print_str(c, KERN_ERR, buf.buf);
 			printbuf_exit(&buf);
-			return -BCH_ERR_trigger_stripe_pointer;
+			return bch_err_throw(c, trigger_stripe_pointer);
 		}
 
 		m->block_sectors[p.ec.block] += sectors;
@@ -732,8 +769,7 @@ err:
 static int __trigger_extent(struct btree_trans *trans,
 			    enum btree_id btree_id, unsigned level,
 			    struct bkey_s_c k,
-			    enum btree_iter_update_trigger_flags flags,
-			    s64 *replicas_sectors)
+			    enum btree_iter_update_trigger_flags flags)
 {
 	bool gc = flags & BTREE_TRIGGER_gc;
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
@@ -744,6 +780,8 @@ static int __trigger_extent(struct btree_trans *trans,
 		: BCH_DATA_user;
 	int ret = 0;
 
+	s64 replicas_sectors = 0;
+
 	struct disk_accounting_pos acc_replicas_key;
 	memset(&acc_replicas_key, 0, sizeof(acc_replicas_key));
 	acc_replicas_key.type = BCH_DISK_ACCOUNTING_replicas;
@@ -770,7 +808,7 @@ static int __trigger_extent(struct btree_trans *trans,
 			if (ret)
 				return ret;
 		} else if (!p.has_ec) {
-			*replicas_sectors       += disk_sectors;
+			replicas_sectors       += disk_sectors;
 			replicas_entry_add_dev(&acc_replicas_key.replicas, p.ptr.dev);
 		} else {
 			ret = bch2_trigger_stripe_ptr(trans, k, p, data_type, disk_sectors, flags);
@@ -808,13 +846,13 @@ static int __trigger_extent(struct btree_trans *trans,
 	}
 
 	if (acc_replicas_key.replicas.nr_devs) {
-		ret = bch2_disk_accounting_mod(trans, &acc_replicas_key, replicas_sectors, 1, gc);
+		ret = bch2_disk_accounting_mod(trans, &acc_replicas_key, &replicas_sectors, 1, gc);
 		if (ret)
 			return ret;
 	}
 
 	if (acc_replicas_key.replicas.nr_devs && !level && k.k->p.snapshot) {
-		ret = bch2_disk_accounting_mod2_nr(trans, gc, replicas_sectors, 1, snapshot, k.k->p.snapshot);
+		ret = bch2_disk_accounting_mod2_nr(trans, gc, &replicas_sectors, 1, snapshot, k.k->p.snapshot);
 		if (ret)
 			return ret;
 	}
@@ -830,7 +868,7 @@ static int __trigger_extent(struct btree_trans *trans,
 	}
 
 	if (level) {
-		ret = bch2_disk_accounting_mod2_nr(trans, gc, replicas_sectors, 1, btree, btree_id);
+		ret = bch2_disk_accounting_mod2_nr(trans, gc, &replicas_sectors, 1, btree, btree_id);
 		if (ret)
 			return ret;
 	} else {
@@ -839,7 +877,7 @@ static int __trigger_extent(struct btree_trans *trans,
 		s64 v[3] = {
 			insert ? 1 : -1,
 			insert ? k.k->size : -((s64) k.k->size),
-			*replicas_sectors,
+			replicas_sectors,
 		};
 		ret = bch2_disk_accounting_mod2(trans, gc, v, inum, k.k->p.inode);
 		if (ret)
@@ -871,20 +909,16 @@ int bch2_trigger_extent(struct btree_trans *trans,
 		return 0;
 
 	if (flags & (BTREE_TRIGGER_transactional|BTREE_TRIGGER_gc)) {
-		s64 old_replicas_sectors = 0, new_replicas_sectors = 0;
-
 		if (old.k->type) {
 			int ret = __trigger_extent(trans, btree, level, old,
-						   flags & ~BTREE_TRIGGER_insert,
-						   &old_replicas_sectors);
+						   flags & ~BTREE_TRIGGER_insert);
 			if (ret)
 				return ret;
 		}
 
 		if (new.k->type) {
 			int ret = __trigger_extent(trans, btree, level, new.s_c,
-						   flags & ~BTREE_TRIGGER_overwrite,
-						   &new_replicas_sectors);
+						   flags & ~BTREE_TRIGGER_overwrite);
 			if (ret)
 				return ret;
 		}
@@ -971,15 +1005,16 @@ static int __bch2_trans_mark_metadata_bucket(struct btree_trans *trans,
 			   bch2_data_type_str(type),
 			   bch2_data_type_str(type));
 
-		bool print = bch2_count_fsck_err(c, bucket_metadata_type_mismatch, &buf);
+		bch2_count_fsck_err(c, bucket_metadata_type_mismatch, &buf);
 
-		bch2_run_explicit_recovery_pass(c, &buf,
+		ret = bch2_run_explicit_recovery_pass(c, &buf,
 					BCH_RECOVERY_PASS_check_allocations, 0);
 
-		if (print)
-			bch2_print_str(c, KERN_ERR, buf.buf);
+		/* Always print, this is always fatal */
+		bch2_print_str(c, KERN_ERR, buf.buf);
 		printbuf_exit(&buf);
-		ret = -BCH_ERR_metadata_bucket_inconsistency;
+		if (!ret)
+			ret = bch_err_throw(c, metadata_bucket_inconsistency);
 		goto err;
 	}
 
@@ -1032,7 +1067,7 @@ static int bch2_mark_metadata_bucket(struct btree_trans *trans, struct bch_dev *
 err_unlock:
 	bucket_unlock(g);
 err:
-	return -BCH_ERR_metadata_bucket_inconsistency;
+	return bch_err_throw(c, metadata_bucket_inconsistency);
 }
 
 int bch2_trans_mark_metadata_bucket(struct btree_trans *trans,
@@ -1247,7 +1282,7 @@ recalculate:
 		ret = 0;
 	} else {
 		atomic64_set(&c->sectors_available, sectors_available);
-		ret = -BCH_ERR_ENOSPC_disk_reservation;
+		ret = bch_err_throw(c, ENOSPC_disk_reservation);
 	}
 
 	mutex_unlock(&c->sectors_available_lock);
@@ -1276,7 +1311,7 @@ int bch2_buckets_nouse_alloc(struct bch_fs *c)
 					    GFP_KERNEL|__GFP_ZERO);
 		if (!ca->buckets_nouse) {
 			bch2_dev_put(ca);
-			return -BCH_ERR_ENOMEM_buckets_nouse;
+			return bch_err_throw(c, ENOMEM_buckets_nouse);
 		}
 	}
 
@@ -1301,12 +1336,12 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets)
 		lockdep_assert_held(&c->state_lock);
 
 	if (resize && ca->buckets_nouse)
-		return -BCH_ERR_no_resize_with_buckets_nouse;
+		return bch_err_throw(c, no_resize_with_buckets_nouse);
 
 	bucket_gens = bch2_kvmalloc(struct_size(bucket_gens, b, nbuckets),
 				    GFP_KERNEL|__GFP_ZERO);
 	if (!bucket_gens) {
-		ret = -BCH_ERR_ENOMEM_bucket_gens;
+		ret = bch_err_throw(c, ENOMEM_bucket_gens);
 		goto err;
 	}
 
@@ -1325,9 +1360,9 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets)
 		       sizeof(bucket_gens->b[0]) * copy);
 	}
 
-	ret =   bch2_bucket_bitmap_resize(&ca->bucket_backpointer_mismatch,
+	ret =   bch2_bucket_bitmap_resize(ca, &ca->bucket_backpointer_mismatch,
 					  ca->mi.nbuckets, nbuckets) ?:
-		bch2_bucket_bitmap_resize(&ca->bucket_backpointer_empty,
+		bch2_bucket_bitmap_resize(ca, &ca->bucket_backpointer_empty,
 					  ca->mi.nbuckets, nbuckets);
 
 	rcu_assign_pointer(ca->bucket_gens, bucket_gens);
@@ -1354,7 +1389,7 @@ int bch2_dev_buckets_alloc(struct bch_fs *c, struct bch_dev *ca)
 {
 	ca->usage = alloc_percpu(struct bch_dev_usage_full);
 	if (!ca->usage)
-		return -BCH_ERR_ENOMEM_usage_init;
+		return bch_err_throw(c, ENOMEM_usage_init);
 
 	return bch2_dev_buckets_resize(c, ca, ca->mi.nbuckets);
 }
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index af1532de4a37..49a3807a5eab 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -84,10 +84,8 @@ static inline int bucket_gen_get_rcu(struct bch_dev *ca, size_t b)
 
 static inline int bucket_gen_get(struct bch_dev *ca, size_t b)
 {
-	rcu_read_lock();
-	int ret = bucket_gen_get_rcu(ca, b);
-	rcu_read_unlock();
-	return ret;
+	guard(rcu)();
+	return bucket_gen_get_rcu(ca, b);
 }
 
 static inline size_t PTR_BUCKET_NR(const struct bch_dev *ca,
@@ -156,10 +154,8 @@ static inline int dev_ptr_stale_rcu(struct bch_dev *ca, const struct bch_extent_
  */
 static inline int dev_ptr_stale(struct bch_dev *ca, const struct bch_extent_ptr *ptr)
 {
-	rcu_read_lock();
-	int ret = dev_ptr_stale_rcu(ca, ptr);
-	rcu_read_unlock();
-	return ret;
+	guard(rcu)();
+	return dev_ptr_stale_rcu(ca, ptr);
 }
 
 /* Device usage: */
diff --git a/fs/bcachefs/buckets_waiting_for_journal.c b/fs/bcachefs/buckets_waiting_for_journal.c
index c8a488e6b7b8..832eff93acb6 100644
--- a/fs/bcachefs/buckets_waiting_for_journal.c
+++ b/fs/bcachefs/buckets_waiting_for_journal.c
@@ -108,7 +108,8 @@ int bch2_set_bucket_needs_journal_commit(struct buckets_waiting_for_journal *b,
 realloc:
 	n = kvmalloc(sizeof(*n) + (sizeof(n->d[0]) << new_bits), GFP_KERNEL);
 	if (!n) {
-		ret = -BCH_ERR_ENOMEM_buckets_waiting_for_journal_set;
+		struct bch_fs *c = container_of(b, struct bch_fs, buckets_waiting_for_journal);
+		ret = bch_err_throw(c, ENOMEM_buckets_waiting_for_journal_set);
 		goto out;
 	}
 
diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c
index 4066946b26bc..2d38466eddfd 100644
--- a/fs/bcachefs/chardev.c
+++ b/fs/bcachefs/chardev.c
@@ -613,15 +613,12 @@ static long bch2_ioctl_disk_get_idx(struct bch_fs *c,
 	if (!dev)
 		return -EINVAL;
 
-	rcu_read_lock();
+	guard(rcu)();
 	for_each_online_member_rcu(c, ca)
-		if (ca->dev == dev) {
-			rcu_read_unlock();
+		if (ca->dev == dev)
 			return ca->dev_idx;
-		}
-	rcu_read_unlock();
 
-	return -BCH_ERR_ENOENT_dev_idx_not_found;
+	return bch_err_throw(c, ENOENT_dev_idx_not_found);
 }
 
 static long bch2_ioctl_disk_resize(struct bch_fs *c,
diff --git a/fs/bcachefs/checksum.c b/fs/bcachefs/checksum.c
index d3e2e4f776c6..a6795e73f0b9 100644
--- a/fs/bcachefs/checksum.c
+++ b/fs/bcachefs/checksum.c
@@ -173,7 +173,7 @@ int bch2_encrypt(struct bch_fs *c, unsigned type,
 
 	if (bch2_fs_inconsistent_on(!c->chacha20_key_set,
 				    c, "attempting to encrypt without encryption key"))
-		return -BCH_ERR_no_encryption_key;
+		return bch_err_throw(c, no_encryption_key);
 
 	bch2_chacha20(&c->chacha20_key, nonce, data, len);
 	return 0;
@@ -262,7 +262,7 @@ int __bch2_encrypt_bio(struct bch_fs *c, unsigned type,
 
 	if (bch2_fs_inconsistent_on(!c->chacha20_key_set,
 				    c, "attempting to encrypt without encryption key"))
-		return -BCH_ERR_no_encryption_key;
+		return bch_err_throw(c, no_encryption_key);
 
 	bch2_chacha20_init(&chacha_state, &c->chacha20_key, nonce);
 
@@ -375,7 +375,7 @@ int bch2_rechecksum_bio(struct bch_fs *c, struct bio *bio,
 		prt_str(&buf, ")");
 		WARN_RATELIMIT(1, "%s", buf.buf);
 		printbuf_exit(&buf);
-		return -BCH_ERR_recompute_checksum;
+		return bch_err_throw(c, recompute_checksum);
 	}
 
 	for (i = splits; i < splits + ARRAY_SIZE(splits); i++) {
@@ -659,7 +659,7 @@ int bch2_enable_encryption(struct bch_fs *c, bool keyed)
 	crypt = bch2_sb_field_resize(&c->disk_sb, crypt,
 				     sizeof(*crypt) / sizeof(u64));
 	if (!crypt) {
-		ret = -BCH_ERR_ENOSPC_sb_crypt;
+		ret = bch_err_throw(c, ENOSPC_sb_crypt);
 		goto err;
 	}
 
diff --git a/fs/bcachefs/clock.c b/fs/bcachefs/clock.c
index f57f9f4774e6..8e9264b5a84e 100644
--- a/fs/bcachefs/clock.c
+++ b/fs/bcachefs/clock.c
@@ -53,7 +53,6 @@ void bch2_io_timer_del(struct io_clock *clock, struct io_timer *timer)
 
 struct io_clock_wait {
 	struct io_timer		io_timer;
-	struct timer_list	cpu_timer;
 	struct task_struct	*task;
 	int			expired;
 };
@@ -67,15 +66,6 @@ static void io_clock_wait_fn(struct io_timer *timer)
 	wake_up_process(wait->task);
 }
 
-static void io_clock_cpu_timeout(struct timer_list *timer)
-{
-	struct io_clock_wait *wait = container_of(timer,
-				struct io_clock_wait, cpu_timer);
-
-	wait->expired = 1;
-	wake_up_process(wait->task);
-}
-
 void bch2_io_clock_schedule_timeout(struct io_clock *clock, u64 until)
 {
 	struct io_clock_wait wait = {
@@ -90,8 +80,8 @@ void bch2_io_clock_schedule_timeout(struct io_clock *clock, u64 until)
 	bch2_io_timer_del(clock, &wait.io_timer);
 }
 
-void bch2_kthread_io_clock_wait(struct io_clock *clock,
-				u64 io_until, unsigned long cpu_timeout)
+unsigned long bch2_kthread_io_clock_wait_once(struct io_clock *clock,
+				     u64 io_until, unsigned long cpu_timeout)
 {
 	bool kthread = (current->flags & PF_KTHREAD) != 0;
 	struct io_clock_wait wait = {
@@ -103,27 +93,26 @@ void bch2_kthread_io_clock_wait(struct io_clock *clock,
 
 	bch2_io_timer_add(clock, &wait.io_timer);
 
-	timer_setup_on_stack(&wait.cpu_timer, io_clock_cpu_timeout, 0);
-
-	if (cpu_timeout != MAX_SCHEDULE_TIMEOUT)
-		mod_timer(&wait.cpu_timer, cpu_timeout + jiffies);
-
-	do {
-		set_current_state(TASK_INTERRUPTIBLE);
-		if (kthread && kthread_should_stop())
-			break;
-
-		if (wait.expired)
-			break;
-
-		schedule();
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (!(kthread && kthread_should_stop())) {
+		cpu_timeout = schedule_timeout(cpu_timeout);
 		try_to_freeze();
-	} while (0);
+	}
 
 	__set_current_state(TASK_RUNNING);
-	timer_delete_sync(&wait.cpu_timer);
-	timer_destroy_on_stack(&wait.cpu_timer);
 	bch2_io_timer_del(clock, &wait.io_timer);
+	return cpu_timeout;
+}
+
+void bch2_kthread_io_clock_wait(struct io_clock *clock,
+				u64 io_until, unsigned long cpu_timeout)
+{
+	bool kthread = (current->flags & PF_KTHREAD) != 0;
+
+	while (!(kthread && kthread_should_stop()) &&
+	       cpu_timeout &&
+	       atomic64_read(&clock->now) < io_until)
+		cpu_timeout = bch2_kthread_io_clock_wait_once(clock, io_until, cpu_timeout);
 }
 
 static struct io_timer *get_expired_timer(struct io_clock *clock, u64 now)
diff --git a/fs/bcachefs/clock.h b/fs/bcachefs/clock.h
index 82c79c8baf92..8769be2aa21e 100644
--- a/fs/bcachefs/clock.h
+++ b/fs/bcachefs/clock.h
@@ -4,6 +4,7 @@
 
 void bch2_io_timer_add(struct io_clock *, struct io_timer *);
 void bch2_io_timer_del(struct io_clock *, struct io_timer *);
+unsigned long bch2_kthread_io_clock_wait_once(struct io_clock *, u64, unsigned long);
 void bch2_kthread_io_clock_wait(struct io_clock *, u64, unsigned long);
 
 void __bch2_increment_clock(struct io_clock *, u64);
diff --git a/fs/bcachefs/compress.c b/fs/bcachefs/compress.c
index 1bca61d17092..b37b1f325f0a 100644
--- a/fs/bcachefs/compress.c
+++ b/fs/bcachefs/compress.c
@@ -187,7 +187,7 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src,
 			     __bch2_compression_types[crc.compression_type]))
 			ret = bch2_check_set_has_compressed_data(c, opt);
 		else
-			ret = -BCH_ERR_compression_workspace_not_initialized;
+			ret = bch_err_throw(c, compression_workspace_not_initialized);
 		if (ret)
 			goto err;
 	}
@@ -200,7 +200,7 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src,
 		ret2 = LZ4_decompress_safe_partial(src_data.b, dst_data,
 						   src_len, dst_len, dst_len);
 		if (ret2 != dst_len)
-			ret = -BCH_ERR_decompress_lz4;
+			ret = bch_err_throw(c, decompress_lz4);
 		break;
 	case BCH_COMPRESSION_TYPE_gzip: {
 		z_stream strm = {
@@ -219,7 +219,7 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src,
 		mempool_free(workspace, workspace_pool);
 
 		if (ret2 != Z_STREAM_END)
-			ret = -BCH_ERR_decompress_gzip;
+			ret = bch_err_throw(c, decompress_gzip);
 		break;
 	}
 	case BCH_COMPRESSION_TYPE_zstd: {
@@ -227,7 +227,7 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src,
 		size_t real_src_len = le32_to_cpup(src_data.b);
 
 		if (real_src_len > src_len - 4) {
-			ret = -BCH_ERR_decompress_zstd_src_len_bad;
+			ret = bch_err_throw(c, decompress_zstd_src_len_bad);
 			goto err;
 		}
 
@@ -241,7 +241,7 @@ static int __bio_uncompress(struct bch_fs *c, struct bio *src,
 		mempool_free(workspace, workspace_pool);
 
 		if (ret2 != dst_len)
-			ret = -BCH_ERR_decompress_zstd;
+			ret = bch_err_throw(c, decompress_zstd);
 		break;
 	}
 	default:
@@ -270,7 +270,7 @@ int bch2_bio_uncompress_inplace(struct bch_write_op *op,
 		bch2_write_op_error(op, op->pos.offset,
 				    "extent too big to decompress (%u > %u)",
 				    crc->uncompressed_size << 9, c->opts.encoded_extent_max);
-		return -BCH_ERR_decompress_exceeded_max_encoded_extent;
+		return bch_err_throw(c, decompress_exceeded_max_encoded_extent);
 	}
 
 	data = __bounce_alloc(c, dst_len, WRITE);
@@ -314,7 +314,7 @@ int bch2_bio_uncompress(struct bch_fs *c, struct bio *src,
 
 	if (crc.uncompressed_size << 9	> c->opts.encoded_extent_max ||
 	    crc.compressed_size << 9	> c->opts.encoded_extent_max)
-		return -BCH_ERR_decompress_exceeded_max_encoded_extent;
+		return bch_err_throw(c, decompress_exceeded_max_encoded_extent);
 
 	dst_data = dst_len == dst_iter.bi_size
 		? __bio_map_or_bounce(c, dst, dst_iter, WRITE)
@@ -656,12 +656,12 @@ static int __bch2_fs_compress_init(struct bch_fs *c, u64 features)
 	if (!mempool_initialized(&c->compression_bounce[READ]) &&
 	    mempool_init_kvmalloc_pool(&c->compression_bounce[READ],
 				       1, c->opts.encoded_extent_max))
-		return -BCH_ERR_ENOMEM_compression_bounce_read_init;
+		return bch_err_throw(c, ENOMEM_compression_bounce_read_init);
 
 	if (!mempool_initialized(&c->compression_bounce[WRITE]) &&
 	    mempool_init_kvmalloc_pool(&c->compression_bounce[WRITE],
 				       1, c->opts.encoded_extent_max))
-		return -BCH_ERR_ENOMEM_compression_bounce_write_init;
+		return bch_err_throw(c, ENOMEM_compression_bounce_write_init);
 
 	for (i = compression_types;
 	     i < compression_types + ARRAY_SIZE(compression_types);
@@ -675,7 +675,7 @@ static int __bch2_fs_compress_init(struct bch_fs *c, u64 features)
 		if (mempool_init_kvmalloc_pool(
 				&c->compress_workspace[i->type],
 				1, i->compress_workspace))
-			return -BCH_ERR_ENOMEM_compression_workspace_init;
+			return bch_err_throw(c, ENOMEM_compression_workspace_init);
 	}
 
 	return 0;
diff --git a/fs/bcachefs/darray.h b/fs/bcachefs/darray.h
index 50ec3decfe8c..4080ee99aadd 100644
--- a/fs/bcachefs/darray.h
+++ b/fs/bcachefs/darray.h
@@ -8,6 +8,7 @@
  * Inspired by CCAN's darray
  */
 
+#include <linux/cleanup.h>
 #include <linux/slab.h>
 
 #define DARRAY_PREALLOCATED(_type, _nr)					\
@@ -87,7 +88,23 @@ int __bch2_darray_resize_noprof(darray_char *, size_t, size_t, gfp_t);
 #define darray_remove_item(_d, _pos)					\
 	array_remove_item((_d)->data, (_d)->nr, (_pos) - (_d)->data)
 
-#define __darray_for_each(_d, _i)						\
+#define darray_find_p(_d, _i, cond)					\
+({									\
+	typeof((_d).data) _ret = NULL;					\
+									\
+	darray_for_each(_d, _i)						\
+		if (cond) {						\
+			_ret = _i;					\
+			break;						\
+		}							\
+	_ret;								\
+})
+
+#define darray_find(_d, _item)	darray_find_p(_d, _i, *_i == _item)
+
+/* Iteration: */
+
+#define __darray_for_each(_d, _i)					\
 	for ((_i) = (_d).data; _i < (_d).data + (_d).nr; _i++)
 
 #define darray_for_each(_d, _i)						\
@@ -96,6 +113,8 @@ int __bch2_darray_resize_noprof(darray_char *, size_t, size_t, gfp_t);
 #define darray_for_each_reverse(_d, _i)					\
 	for (typeof(&(_d).data[0]) _i = (_d).data + (_d).nr - 1; _i >= (_d).data && (_d).nr; --_i)
 
+/* Init/exit */
+
 #define darray_init(_d)							\
 do {									\
 	(_d)->nr = 0;							\
@@ -111,4 +130,29 @@ do {									\
 	darray_init(_d);						\
 } while (0)
 
+#define DEFINE_DARRAY_CLASS(_type)					\
+DEFINE_CLASS(_type, _type, darray_exit(&(_T)), (_type) {}, void)
+
+#define DEFINE_DARRAY(_type)						\
+typedef DARRAY(_type)	darray_##_type;					\
+DEFINE_DARRAY_CLASS(darray_##_type)
+
+#define DEFINE_DARRAY_NAMED(_name, _type)				\
+typedef DARRAY(_type)	_name;						\
+DEFINE_DARRAY_CLASS(_name)
+
+DEFINE_DARRAY_CLASS(darray_char);
+DEFINE_DARRAY_CLASS(darray_str)
+DEFINE_DARRAY_CLASS(darray_const_str)
+
+DEFINE_DARRAY_CLASS(darray_u8)
+DEFINE_DARRAY_CLASS(darray_u16)
+DEFINE_DARRAY_CLASS(darray_u32)
+DEFINE_DARRAY_CLASS(darray_u64)
+
+DEFINE_DARRAY_CLASS(darray_s8)
+DEFINE_DARRAY_CLASS(darray_s16)
+DEFINE_DARRAY_CLASS(darray_s32)
+DEFINE_DARRAY_CLASS(darray_s64)
+
 #endif /* _BCACHEFS_DARRAY_H */
diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index c34e5b88ba9d..5f1174348974 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -66,37 +66,46 @@ static void bkey_nocow_unlock(struct bch_fs *c, struct bkey_s_c k)
 	}
 }
 
-static bool bkey_nocow_lock(struct bch_fs *c, struct moving_context *ctxt, struct bkey_s_c k)
+static noinline_for_stack
+bool __bkey_nocow_lock(struct bch_fs *c, struct moving_context *ctxt, struct bkey_ptrs_c ptrs,
+		       const struct bch_extent_ptr *start)
 {
-	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
+	if (!ctxt) {
+		bkey_for_each_ptr(ptrs, ptr) {
+			if (ptr == start)
+				break;
+
+			struct bch_dev *ca = bch2_dev_have_ref(c, ptr->dev);
+			struct bpos bucket = PTR_BUCKET_POS(ca, ptr);
+			bch2_bucket_nocow_unlock(&c->nocow_locks, bucket, 0);
+		}
+		return false;
+	}
 
-	bkey_for_each_ptr(ptrs, ptr) {
+	__bkey_for_each_ptr(start, ptrs.end, ptr) {
 		struct bch_dev *ca = bch2_dev_have_ref(c, ptr->dev);
 		struct bpos bucket = PTR_BUCKET_POS(ca, ptr);
 
-		if (ctxt) {
-			bool locked;
-
-			move_ctxt_wait_event(ctxt,
-				(locked = bch2_bucket_nocow_trylock(&c->nocow_locks, bucket, 0)) ||
-				list_empty(&ctxt->ios));
+		bool locked;
+		move_ctxt_wait_event(ctxt,
+				     (locked = bch2_bucket_nocow_trylock(&c->nocow_locks, bucket, 0)) ||
+				     list_empty(&ctxt->ios));
+		if (!locked)
+			bch2_bucket_nocow_lock(&c->nocow_locks, bucket, 0);
+	}
+	return true;
+}
 
-			if (!locked)
-				bch2_bucket_nocow_lock(&c->nocow_locks, bucket, 0);
-		} else {
-			if (!bch2_bucket_nocow_trylock(&c->nocow_locks, bucket, 0)) {
-				bkey_for_each_ptr(ptrs, ptr2) {
-					if (ptr2 == ptr)
-						break;
+static bool bkey_nocow_lock(struct bch_fs *c, struct moving_context *ctxt, struct bkey_ptrs_c ptrs)
+{
+	bkey_for_each_ptr(ptrs, ptr) {
+		struct bch_dev *ca = bch2_dev_have_ref(c, ptr->dev);
+		struct bpos bucket = PTR_BUCKET_POS(ca, ptr);
 
-					ca = bch2_dev_have_ref(c, ptr2->dev);
-					bucket = PTR_BUCKET_POS(ca, ptr2);
-					bch2_bucket_nocow_unlock(&c->nocow_locks, bucket, 0);
-				}
-				return false;
-			}
-		}
+		if (!bch2_bucket_nocow_trylock(&c->nocow_locks, bucket, 0))
+			return __bkey_nocow_lock(c, ctxt, ptrs, ptr);
 	}
+
 	return true;
 }
 
@@ -246,7 +255,7 @@ static int data_update_invalid_bkey(struct data_update *m,
 	bch2_print_str(c, KERN_ERR, buf.buf);
 	printbuf_exit(&buf);
 
-	return -BCH_ERR_invalid_bkey;
+	return bch_err_throw(c, invalid_bkey);
 }
 
 static int __bch2_data_update_index_update(struct btree_trans *trans,
@@ -367,21 +376,21 @@ restart_drop_conflicting_replicas:
 			bch2_bkey_durability(c, bkey_i_to_s_c(&new->k_i));
 
 		/* Now, drop excess replicas: */
-		rcu_read_lock();
+		scoped_guard(rcu) {
 restart_drop_extra_replicas:
-		bkey_for_each_ptr_decode(old.k, bch2_bkey_ptrs(bkey_i_to_s(insert)), p, entry) {
-			unsigned ptr_durability = bch2_extent_ptr_durability(c, &p);
+			bkey_for_each_ptr_decode(old.k, bch2_bkey_ptrs(bkey_i_to_s(insert)), p, entry) {
+				unsigned ptr_durability = bch2_extent_ptr_durability(c, &p);
 
-			if (!p.ptr.cached &&
-			    durability - ptr_durability >= m->op.opts.data_replicas) {
-				durability -= ptr_durability;
+				if (!p.ptr.cached &&
+				    durability - ptr_durability >= m->op.opts.data_replicas) {
+					durability -= ptr_durability;
 
-				bch2_extent_ptr_set_cached(c, &m->op.opts,
-							   bkey_i_to_s(insert), &entry->ptr);
-				goto restart_drop_extra_replicas;
+					bch2_extent_ptr_set_cached(c, &m->op.opts,
+								   bkey_i_to_s(insert), &entry->ptr);
+					goto restart_drop_extra_replicas;
+				}
 			}
 		}
-		rcu_read_unlock();
 
 		/* Finally, add the pointers we just wrote: */
 		extent_for_each_ptr_decode(extent_i_to_s(new), p, entry)
@@ -523,8 +532,9 @@ void bch2_data_update_exit(struct data_update *update)
 	bch2_bkey_buf_exit(&update->k, c);
 }
 
-static int bch2_update_unwritten_extent(struct btree_trans *trans,
-					struct data_update *update)
+static noinline_for_stack
+int bch2_update_unwritten_extent(struct btree_trans *trans,
+				 struct data_update *update)
 {
 	struct bch_fs *c = update->op.c;
 	struct bkey_i_extent *e;
@@ -716,18 +726,10 @@ int bch2_extent_drop_ptrs(struct btree_trans *trans,
 		bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
 }
 
-int bch2_data_update_bios_init(struct data_update *m, struct bch_fs *c,
-			       struct bch_io_opts *io_opts)
+static int __bch2_data_update_bios_init(struct data_update *m, struct bch_fs *c,
+					struct bch_io_opts *io_opts,
+					unsigned buf_bytes)
 {
-	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(bkey_i_to_s_c(m->k.k));
-	const union bch_extent_entry *entry;
-	struct extent_ptr_decoded p;
-
-	/* write path might have to decompress data: */
-	unsigned buf_bytes = 0;
-	bkey_for_each_ptr_decode(&m->k.k->k, ptrs, p, entry)
-		buf_bytes = max_t(unsigned, buf_bytes, p.crc.uncompressed_size << 9);
-
 	unsigned nr_vecs = DIV_ROUND_UP(buf_bytes, PAGE_SIZE);
 
 	m->bvecs = kmalloc_array(nr_vecs, sizeof*(m->bvecs), GFP_KERNEL);
@@ -751,11 +753,26 @@ int bch2_data_update_bios_init(struct data_update *m, struct bch_fs *c,
 	return 0;
 }
 
+int bch2_data_update_bios_init(struct data_update *m, struct bch_fs *c,
+			       struct bch_io_opts *io_opts)
+{
+	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(bkey_i_to_s_c(m->k.k));
+	const union bch_extent_entry *entry;
+	struct extent_ptr_decoded p;
+
+	/* write path might have to decompress data: */
+	unsigned buf_bytes = 0;
+	bkey_for_each_ptr_decode(&m->k.k->k, ptrs, p, entry)
+		buf_bytes = max_t(unsigned, buf_bytes, p.crc.uncompressed_size << 9);
+
+	return __bch2_data_update_bios_init(m, c, io_opts, buf_bytes);
+}
+
 static int can_write_extent(struct bch_fs *c, struct data_update *m)
 {
 	if ((m->op.flags & BCH_WRITE_alloc_nowait) &&
 	    unlikely(c->open_buckets_nr_free <= bch2_open_buckets_reserved(m->op.watermark)))
-		return -BCH_ERR_data_update_done_would_block;
+		return bch_err_throw(c, data_update_done_would_block);
 
 	unsigned target = m->op.flags & BCH_WRITE_only_specified_devs
 		? m->op.target
@@ -765,7 +782,8 @@ static int can_write_extent(struct bch_fs *c, struct data_update *m)
 	darray_for_each(m->op.devs_have, i)
 		__clear_bit(*i, devs.d);
 
-	rcu_read_lock();
+	guard(rcu)();
+
 	unsigned nr_replicas = 0, i;
 	for_each_set_bit(i, devs.d, BCH_SB_MEMBERS_MAX) {
 		struct bch_dev *ca = bch2_dev_rcu_noerror(c, i);
@@ -782,12 +800,11 @@ static int can_write_extent(struct bch_fs *c, struct data_update *m)
 		if (nr_replicas >= m->op.nr_replicas)
 			break;
 	}
-	rcu_read_unlock();
 
 	if (!nr_replicas)
-		return -BCH_ERR_data_update_done_no_rw_devs;
+		return bch_err_throw(c, data_update_done_no_rw_devs);
 	if (nr_replicas < m->op.nr_replicas)
-		return -BCH_ERR_insufficient_devices;
+		return bch_err_throw(c, insufficient_devices);
 	return 0;
 }
 
@@ -802,19 +819,21 @@ int bch2_data_update_init(struct btree_trans *trans,
 			  struct bkey_s_c k)
 {
 	struct bch_fs *c = trans->c;
-	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
-	const union bch_extent_entry *entry;
-	struct extent_ptr_decoded p;
-	unsigned reserve_sectors = k.k->size * data_opts.extra_replicas;
 	int ret = 0;
 
-	/*
-	 * fs is corrupt  we have a key for a snapshot node that doesn't exist,
-	 * and we have to check for this because we go rw before repairing the
-	 * snapshots table - just skip it, we can move it later.
-	 */
-	if (unlikely(k.k->p.snapshot && !bch2_snapshot_exists(c, k.k->p.snapshot)))
-		return -BCH_ERR_data_update_done_no_snapshot;
+	if (k.k->p.snapshot) {
+		ret = bch2_check_key_has_snapshot(trans, iter, k);
+		if (bch2_err_matches(ret, BCH_ERR_recovery_will_run)) {
+			/* Can't repair yet, waiting on other recovery passes */
+			return bch_err_throw(c, data_update_done_no_snapshot);
+		}
+		if (ret < 0)
+			return ret;
+		if (ret) /* key was deleted */
+			return bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?:
+				bch_err_throw(c, data_update_done_no_snapshot);
+		ret = 0;
+	}
 
 	bch2_bkey_buf_init(&m->k);
 	bch2_bkey_buf_reassemble(&m->k, c, k);
@@ -842,10 +861,17 @@ int bch2_data_update_init(struct btree_trans *trans,
 
 	unsigned durability_have = 0, durability_removing = 0;
 
+	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(bkey_i_to_s_c(m->k.k));
+	const union bch_extent_entry *entry;
+	struct extent_ptr_decoded p;
+	unsigned reserve_sectors = k.k->size * data_opts.extra_replicas;
+	unsigned buf_bytes = 0;
+	bool unwritten = false;
+
 	unsigned ptr_bit = 1;
 	bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
 		if (!p.ptr.cached) {
-			rcu_read_lock();
+			guard(rcu)();
 			if (ptr_bit & m->data_opts.rewrite_ptrs) {
 				if (crc_is_compressed(p.crc))
 					reserve_sectors += k.k->size;
@@ -856,7 +882,6 @@ int bch2_data_update_init(struct btree_trans *trans,
 				bch2_dev_list_add_dev(&m->op.devs_have, p.ptr.dev);
 				durability_have += bch2_extent_ptr_durability(c, &p);
 			}
-			rcu_read_unlock();
 		}
 
 		/*
@@ -872,6 +897,9 @@ int bch2_data_update_init(struct btree_trans *trans,
 		if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible)
 			m->op.incompressible = true;
 
+		buf_bytes = max_t(unsigned, buf_bytes, p.crc.uncompressed_size << 9);
+		unwritten |= p.ptr.unwritten;
+
 		ptr_bit <<= 1;
 	}
 
@@ -910,7 +938,7 @@ int bch2_data_update_init(struct btree_trans *trans,
 		if (iter)
 			ret = bch2_extent_drop_ptrs(trans, iter, k, io_opts, &m->data_opts);
 		if (!ret)
-			ret = -BCH_ERR_data_update_done_no_writes_needed;
+			ret = bch_err_throw(c, data_update_done_no_writes_needed);
 		goto out_bkey_buf_exit;
 	}
 
@@ -941,23 +969,25 @@ int bch2_data_update_init(struct btree_trans *trans,
 	}
 
 	if (!bkey_get_dev_refs(c, k)) {
-		ret = -BCH_ERR_data_update_done_no_dev_refs;
+		ret = bch_err_throw(c, data_update_done_no_dev_refs);
 		goto out_put_disk_res;
 	}
 
 	if (c->opts.nocow_enabled &&
-	    !bkey_nocow_lock(c, ctxt, k)) {
-		ret = -BCH_ERR_nocow_lock_blocked;
+	    !bkey_nocow_lock(c, ctxt, ptrs)) {
+		ret = bch_err_throw(c, nocow_lock_blocked);
 		goto out_put_dev_refs;
 	}
 
-	if (bkey_extent_is_unwritten(k)) {
+	if (unwritten) {
 		ret = bch2_update_unwritten_extent(trans, m) ?:
-			-BCH_ERR_data_update_done_unwritten;
+			bch_err_throw(c, data_update_done_unwritten);
 		goto out_nocow_unlock;
 	}
 
-	ret = bch2_data_update_bios_init(m, c, io_opts);
+	bch2_trans_unlock(trans);
+
+	ret = __bch2_data_update_bios_init(m, c, io_opts, buf_bytes);
 	if (ret)
 		goto out_nocow_unlock;
 
diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c
index 4fa70634c90e..901f643ead83 100644
--- a/fs/bcachefs/debug.c
+++ b/fs/bcachefs/debug.c
@@ -492,6 +492,8 @@ static void bch2_cached_btree_node_to_text(struct printbuf *out, struct bch_fs *
 	prt_printf(out, "journal pin %px:\t%llu\n",
 		   &b->writes[1].journal, b->writes[1].journal.seq);
 
+	prt_printf(out, "ob:\t%u\n", b->ob.nr);
+
 	printbuf_indent_sub(out, 2);
 }
 
@@ -508,27 +510,27 @@ static ssize_t bch2_cached_btree_nodes_read(struct file *file, char __user *buf,
 	i->ret	= 0;
 
 	do {
-		struct bucket_table *tbl;
-		struct rhash_head *pos;
-		struct btree *b;
-
 		ret = bch2_debugfs_flush_buf(i);
 		if (ret)
 			return ret;
 
-		rcu_read_lock();
 		i->buf.atomic++;
-		tbl = rht_dereference_rcu(c->btree_cache.table.tbl,
-					  &c->btree_cache.table);
-		if (i->iter < tbl->size) {
-			rht_for_each_entry_rcu(b, pos, tbl, i->iter, hash)
-				bch2_cached_btree_node_to_text(&i->buf, c, b);
-			i->iter++;
-		} else {
-			done = true;
+		scoped_guard(rcu) {
+			struct bucket_table *tbl =
+				rht_dereference_rcu(c->btree_cache.table.tbl,
+						    &c->btree_cache.table);
+			if (i->iter < tbl->size) {
+				struct rhash_head *pos;
+				struct btree *b;
+
+				rht_for_each_entry_rcu(b, pos, tbl, i->iter, hash)
+					bch2_cached_btree_node_to_text(&i->buf, c, b);
+				i->iter++;
+			} else {
+				done = true;
+			}
 		}
 		--i->buf.atomic;
-		rcu_read_unlock();
 	} while (!done);
 
 	if (i->buf.allocation_failure)
diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c
index d198001838f3..300f7cc8abdf 100644
--- a/fs/bcachefs/dirent.c
+++ b/fs/bcachefs/dirent.c
@@ -231,70 +231,64 @@ void bch2_dirent_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c
 	prt_printf(out, " type %s", bch2_d_type_str(d.v->d_type));
 }
 
-static struct bkey_i_dirent *dirent_alloc_key(struct btree_trans *trans,
-				subvol_inum dir,
-				u8 type,
-				int name_len, int cf_name_len,
-				u64 dst)
+int bch2_dirent_init_name(struct bkey_i_dirent *dirent,
+			  const struct bch_hash_info *hash_info,
+			  const struct qstr *name,
+			  const struct qstr *cf_name)
 {
-	struct bkey_i_dirent *dirent;
-	unsigned u64s = BKEY_U64s + dirent_val_u64s(name_len, cf_name_len);
+	EBUG_ON(hash_info->cf_encoding == NULL && cf_name);
+	int cf_len = 0;
 
-	BUG_ON(u64s > U8_MAX);
-
-	dirent = bch2_trans_kmalloc(trans, u64s * sizeof(u64));
-	if (IS_ERR(dirent))
-		return dirent;
+	if (name->len > BCH_NAME_MAX)
+		return -ENAMETOOLONG;
 
-	bkey_dirent_init(&dirent->k_i);
-	dirent->k.u64s = u64s;
+	dirent->v.d_casefold = hash_info->cf_encoding != NULL;
 
-	if (type != DT_SUBVOL) {
-		dirent->v.d_inum = cpu_to_le64(dst);
+	if (!dirent->v.d_casefold) {
+		memcpy(&dirent->v.d_name[0], name->name, name->len);
+		memset(&dirent->v.d_name[name->len], 0,
+		       bkey_val_bytes(&dirent->k) -
+		       offsetof(struct bch_dirent, d_name) -
+		       name->len);
 	} else {
-		dirent->v.d_parent_subvol = cpu_to_le32(dir.subvol);
-		dirent->v.d_child_subvol = cpu_to_le32(dst);
-	}
+#ifdef CONFIG_UNICODE
+		memcpy(&dirent->v.d_cf_name_block.d_names[0], name->name, name->len);
 
-	dirent->v.d_type = type;
-	dirent->v.d_unused = 0;
-	dirent->v.d_casefold = cf_name_len ? 1 : 0;
+		char *cf_out = &dirent->v.d_cf_name_block.d_names[name->len];
 
-	return dirent;
-}
+		if (cf_name) {
+			cf_len = cf_name->len;
 
-static void dirent_init_regular_name(struct bkey_i_dirent *dirent,
-				     const struct qstr *name)
-{
-	EBUG_ON(dirent->v.d_casefold);
+			memcpy(cf_out, cf_name->name, cf_name->len);
+		} else {
+			cf_len = utf8_casefold(hash_info->cf_encoding, name,
+					       cf_out,
+					       bkey_val_end(bkey_i_to_s(&dirent->k_i)) - (void *) cf_out);
+			if (cf_len <= 0)
+				return cf_len;
+		}
 
-	memcpy(&dirent->v.d_name[0], name->name, name->len);
-	memset(&dirent->v.d_name[name->len], 0,
-		bkey_val_bytes(&dirent->k) -
-		offsetof(struct bch_dirent, d_name) -
-		name->len);
-}
+		memset(&dirent->v.d_cf_name_block.d_names[name->len + cf_len], 0,
+		       bkey_val_bytes(&dirent->k) -
+		       offsetof(struct bch_dirent, d_cf_name_block.d_names) -
+		       name->len + cf_len);
 
-static void dirent_init_casefolded_name(struct bkey_i_dirent *dirent,
-					const struct qstr *name,
-					const struct qstr *cf_name)
-{
-	EBUG_ON(!dirent->v.d_casefold);
-	EBUG_ON(!cf_name->len);
-
-	dirent->v.d_cf_name_block.d_name_len = cpu_to_le16(name->len);
-	dirent->v.d_cf_name_block.d_cf_name_len = cpu_to_le16(cf_name->len);
-	memcpy(&dirent->v.d_cf_name_block.d_names[0], name->name, name->len);
-	memcpy(&dirent->v.d_cf_name_block.d_names[name->len], cf_name->name, cf_name->len);
-	memset(&dirent->v.d_cf_name_block.d_names[name->len + cf_name->len], 0,
-		bkey_val_bytes(&dirent->k) -
-		offsetof(struct bch_dirent, d_cf_name_block.d_names) -
-		name->len + cf_name->len);
-
-	EBUG_ON(bch2_dirent_get_casefold_name(dirent_i_to_s_c(dirent)).len != cf_name->len);
+		dirent->v.d_cf_name_block.d_name_len = cpu_to_le16(name->len);
+		dirent->v.d_cf_name_block.d_cf_name_len = cpu_to_le16(cf_len);
+
+		EBUG_ON(bch2_dirent_get_casefold_name(dirent_i_to_s_c(dirent)).len != cf_len);
+#else
+	return -EOPNOTSUPP;
+#endif
+	}
+
+	unsigned u64s = dirent_val_u64s(name->len, cf_len);
+	BUG_ON(u64s > bkey_val_u64s(&dirent->k));
+	set_bkey_val_u64s(&dirent->k, u64s);
+	return 0;
 }
 
-static struct bkey_i_dirent *dirent_create_key(struct btree_trans *trans,
+struct bkey_i_dirent *bch2_dirent_create_key(struct btree_trans *trans,
 				const struct bch_hash_info *hash_info,
 				subvol_inum dir,
 				u8 type,
@@ -302,31 +296,28 @@ static struct bkey_i_dirent *dirent_create_key(struct btree_trans *trans,
 				const struct qstr *cf_name,
 				u64 dst)
 {
-	struct bkey_i_dirent *dirent;
-	struct qstr _cf_name;
-
-	if (name->len > BCH_NAME_MAX)
-		return ERR_PTR(-ENAMETOOLONG);
+	struct bkey_i_dirent *dirent = bch2_trans_kmalloc(trans, BKEY_U64s_MAX * sizeof(u64));
+	if (IS_ERR(dirent))
+		return dirent;
 
-	if (hash_info->cf_encoding && !cf_name) {
-		int ret = bch2_casefold(trans, hash_info, name, &_cf_name);
-		if (ret)
-			return ERR_PTR(ret);
+	bkey_dirent_init(&dirent->k_i);
+	dirent->k.u64s = BKEY_U64s_MAX;
 
-		cf_name = &_cf_name;
+	if (type != DT_SUBVOL) {
+		dirent->v.d_inum = cpu_to_le64(dst);
+	} else {
+		dirent->v.d_parent_subvol = cpu_to_le32(dir.subvol);
+		dirent->v.d_child_subvol = cpu_to_le32(dst);
 	}
 
-	dirent = dirent_alloc_key(trans, dir, type, name->len, cf_name ? cf_name->len : 0, dst);
-	if (IS_ERR(dirent))
-		return dirent;
+	dirent->v.d_type = type;
+	dirent->v.d_unused = 0;
 
-	if (cf_name)
-		dirent_init_casefolded_name(dirent, name, cf_name);
-	else
-		dirent_init_regular_name(dirent, name);
+	int ret = bch2_dirent_init_name(dirent, hash_info, name, cf_name);
+	if (ret)
+		return ERR_PTR(ret);
 
 	EBUG_ON(bch2_dirent_get_name(dirent_i_to_s_c(dirent)).len != name->len);
-
 	return dirent;
 }
 
@@ -341,7 +332,7 @@ int bch2_dirent_create_snapshot(struct btree_trans *trans,
 	struct bkey_i_dirent *dirent;
 	int ret;
 
-	dirent = dirent_create_key(trans, hash_info, dir_inum, type, name, NULL, dst_inum);
+	dirent = bch2_dirent_create_key(trans, hash_info, dir_inum, type, name, NULL, dst_inum);
 	ret = PTR_ERR_OR_ZERO(dirent);
 	if (ret)
 		return ret;
@@ -365,7 +356,7 @@ int bch2_dirent_create(struct btree_trans *trans, subvol_inum dir,
 	struct bkey_i_dirent *dirent;
 	int ret;
 
-	dirent = dirent_create_key(trans, hash_info, dir, type, name, NULL, dst_inum);
+	dirent = bch2_dirent_create_key(trans, hash_info, dir, type, name, NULL, dst_inum);
 	ret = PTR_ERR_OR_ZERO(dirent);
 	if (ret)
 		return ret;
@@ -402,8 +393,8 @@ int bch2_dirent_read_target(struct btree_trans *trans, subvol_inum dir,
 }
 
 int bch2_dirent_rename(struct btree_trans *trans,
-		subvol_inum src_dir, struct bch_hash_info *src_hash, u64 *src_dir_i_size,
-		subvol_inum dst_dir, struct bch_hash_info *dst_hash, u64 *dst_dir_i_size,
+		subvol_inum src_dir, struct bch_hash_info *src_hash,
+		subvol_inum dst_dir, struct bch_hash_info *dst_hash,
 		const struct qstr *src_name, subvol_inum *src_inum, u64 *src_offset,
 		const struct qstr *dst_name, subvol_inum *dst_inum, u64 *dst_offset,
 		enum bch_rename_mode mode)
@@ -470,8 +461,8 @@ int bch2_dirent_rename(struct btree_trans *trans,
 		*src_offset = dst_iter.pos.offset;
 
 	/* Create new dst key: */
-	new_dst = dirent_create_key(trans, dst_hash, dst_dir, 0, dst_name,
-				    dst_hash->cf_encoding ? &dst_name_lookup : NULL, 0);
+	new_dst = bch2_dirent_create_key(trans, dst_hash, dst_dir, 0, dst_name,
+					 dst_hash->cf_encoding ? &dst_name_lookup : NULL, 0);
 	ret = PTR_ERR_OR_ZERO(new_dst);
 	if (ret)
 		goto out;
@@ -481,8 +472,8 @@ int bch2_dirent_rename(struct btree_trans *trans,
 
 	/* Create new src key: */
 	if (mode == BCH_RENAME_EXCHANGE) {
-		new_src = dirent_create_key(trans, src_hash, src_dir, 0, src_name,
-					    src_hash->cf_encoding ? &src_name_lookup : NULL, 0);
+		new_src = bch2_dirent_create_key(trans, src_hash, src_dir, 0, src_name,
+						 src_hash->cf_encoding ? &src_name_lookup : NULL, 0);
 		ret = PTR_ERR_OR_ZERO(new_src);
 		if (ret)
 			goto out;
@@ -542,14 +533,6 @@ int bch2_dirent_rename(struct btree_trans *trans,
 	    new_src->v.d_type == DT_SUBVOL)
 		new_src->v.d_parent_subvol = cpu_to_le32(src_dir.subvol);
 
-	if (old_dst.k)
-		*dst_dir_i_size -= bkey_bytes(old_dst.k);
-	*src_dir_i_size -= bkey_bytes(old_src.k);
-
-	if (mode == BCH_RENAME_EXCHANGE)
-		*src_dir_i_size += bkey_bytes(&new_src->k);
-	*dst_dir_i_size += bkey_bytes(&new_dst->k);
-
 	ret = bch2_trans_update(trans, &dst_iter, &new_dst->k_i, 0);
 	if (ret)
 		goto out;
@@ -656,7 +639,7 @@ int bch2_empty_dir_snapshot(struct btree_trans *trans, u64 dir, u32 subvol, u32
 			struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k);
 			if (d.v->d_type == DT_SUBVOL && le32_to_cpu(d.v->d_parent_subvol) != subvol)
 				continue;
-			ret = -BCH_ERR_ENOTEMPTY_dir_not_empty;
+			ret = bch_err_throw(trans->c, ENOTEMPTY_dir_not_empty);
 			break;
 		}
 	bch2_trans_iter_exit(trans, &iter);
@@ -692,7 +675,9 @@ static int bch2_dir_emit(struct dir_context *ctx, struct bkey_s_c_dirent d, subv
 	return !ret;
 }
 
-int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx)
+int bch2_readdir(struct bch_fs *c, subvol_inum inum,
+		 struct bch_hash_info *hash_info,
+		 struct dir_context *ctx)
 {
 	struct bkey_buf sk;
 	bch2_bkey_buf_init(&sk);
@@ -710,7 +695,11 @@ int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx)
 			struct bkey_s_c_dirent dirent = bkey_i_to_s_c_dirent(sk.k);
 
 			subvol_inum target;
-			int ret2 = bch2_dirent_read_target(trans, inum, dirent, &target);
+
+			bool need_second_pass = false;
+			int ret2 = bch2_str_hash_check_key(trans, NULL, &bch2_dirent_hash_desc,
+							   hash_info, &iter, k, &need_second_pass) ?:
+				bch2_dirent_read_target(trans, inum, dirent, &target);
 			if (ret2 > 0)
 				continue;
 
@@ -740,7 +729,7 @@ static int lookup_first_inode(struct btree_trans *trans, u64 inode_nr,
 		ret = bch2_inode_unpack(k, inode);
 		goto found;
 	}
-	ret = -BCH_ERR_ENOENT_inode;
+	ret = bch_err_throw(trans->c, ENOENT_inode);
 found:
 	bch_err_msg(trans->c, ret, "fetching inode %llu", inode_nr);
 	bch2_trans_iter_exit(trans, &iter);
diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h
index d3e7ae669575..70fb0b581221 100644
--- a/fs/bcachefs/dirent.h
+++ b/fs/bcachefs/dirent.h
@@ -38,7 +38,7 @@ static inline int bch2_maybe_casefold(struct btree_trans *trans,
 	}
 }
 
-struct qstr bch2_dirent_get_name(struct bkey_s_c_dirent d);
+struct qstr bch2_dirent_get_name(struct bkey_s_c_dirent);
 
 static inline unsigned dirent_val_u64s(unsigned len, unsigned cf_len)
 {
@@ -59,6 +59,14 @@ static inline void dirent_copy_target(struct bkey_i_dirent *dst,
 	dst->v.d_type = src.v->d_type;
 }
 
+int bch2_dirent_init_name(struct bkey_i_dirent *,
+			  const struct bch_hash_info *,
+			  const struct qstr *,
+			  const struct qstr *);
+struct bkey_i_dirent *bch2_dirent_create_key(struct btree_trans *,
+				const struct bch_hash_info *, subvol_inum, u8,
+				const struct qstr *, const struct qstr *, u64);
+
 int bch2_dirent_create_snapshot(struct btree_trans *, u32, u64, u32,
 			const struct bch_hash_info *, u8,
 			const struct qstr *, u64, u64 *,
@@ -80,8 +88,8 @@ enum bch_rename_mode {
 };
 
 int bch2_dirent_rename(struct btree_trans *,
-		       subvol_inum, struct bch_hash_info *, u64 *,
-		       subvol_inum, struct bch_hash_info *, u64 *,
+		       subvol_inum, struct bch_hash_info *,
+		       subvol_inum, struct bch_hash_info *,
 		       const struct qstr *, subvol_inum *, u64 *,
 		       const struct qstr *, subvol_inum *, u64 *,
 		       enum bch_rename_mode);
@@ -95,7 +103,7 @@ u64 bch2_dirent_lookup(struct bch_fs *, subvol_inum,
 
 int bch2_empty_dir_snapshot(struct btree_trans *, u64, u32, u32);
 int bch2_empty_dir_trans(struct btree_trans *, subvol_inum);
-int bch2_readdir(struct bch_fs *, subvol_inum, struct dir_context *);
+int bch2_readdir(struct bch_fs *, subvol_inum, struct bch_hash_info *, struct dir_context *);
 
 int bch2_fsck_remove_dirent(struct btree_trans *, struct bpos);
 
diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c
index b3840ff7c407..3d59a57a5256 100644
--- a/fs/bcachefs/disk_accounting.c
+++ b/fs/bcachefs/disk_accounting.c
@@ -390,7 +390,7 @@ static int __bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accoun
 err:
 	free_percpu(n.v[1]);
 	free_percpu(n.v[0]);
-	return -BCH_ERR_ENOMEM_disk_accounting;
+	return bch_err_throw(c, ENOMEM_disk_accounting);
 }
 
 int bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accounting a,
@@ -401,7 +401,7 @@ int bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accounting a,
 	if (mode != BCH_ACCOUNTING_read &&
 	    accounting_to_replicas(&r.e, a.k->p) &&
 	    !bch2_replicas_marked_locked(c, &r.e))
-		return -BCH_ERR_btree_insert_need_mark_replicas;
+		return bch_err_throw(c, btree_insert_need_mark_replicas);
 
 	percpu_up_read(&c->mark_lock);
 	percpu_down_write(&c->mark_lock);
@@ -419,7 +419,7 @@ int bch2_accounting_mem_insert_locked(struct bch_fs *c, struct bkey_s_c_accounti
 	if (mode != BCH_ACCOUNTING_read &&
 	    accounting_to_replicas(&r.e, a.k->p) &&
 	    !bch2_replicas_marked_locked(c, &r.e))
-		return -BCH_ERR_btree_insert_need_mark_replicas;
+		return bch_err_throw(c, btree_insert_need_mark_replicas);
 
 	return __bch2_accounting_mem_insert(c, a);
 }
@@ -559,7 +559,7 @@ int bch2_gc_accounting_start(struct bch_fs *c)
 					     sizeof(u64), GFP_KERNEL);
 		if (!e->v[1]) {
 			bch2_accounting_free_counters(acc, true);
-			ret = -BCH_ERR_ENOMEM_disk_accounting;
+			ret = bch_err_throw(c, ENOMEM_disk_accounting);
 			break;
 		}
 	}
@@ -737,7 +737,7 @@ invalid_device:
 				bch2_disk_accounting_mod(trans, acc, v, nr, false)) ?:
 			-BCH_ERR_remove_disk_accounting_entry;
 	} else {
-		ret = -BCH_ERR_remove_disk_accounting_entry;
+		ret = bch_err_throw(c, remove_disk_accounting_entry);
 	}
 	goto fsck_err;
 }
@@ -897,8 +897,8 @@ int bch2_accounting_read(struct bch_fs *c)
 		case BCH_DISK_ACCOUNTING_replicas:
 			fs_usage_data_type_to_base(usage, k.replicas.data_type, v[0]);
 			break;
-		case BCH_DISK_ACCOUNTING_dev_data_type:
-			rcu_read_lock();
+		case BCH_DISK_ACCOUNTING_dev_data_type: {
+			guard(rcu)();
 			struct bch_dev *ca = bch2_dev_rcu_noerror(c, k.dev_data_type.dev);
 			if (ca) {
 				struct bch_dev_usage_type __percpu *d = &ca->usage->d[k.dev_data_type.data_type];
@@ -910,9 +910,9 @@ int bch2_accounting_read(struct bch_fs *c)
 				    k.dev_data_type.data_type == BCH_DATA_journal)
 					usage->hidden += v[0] * ca->mi.bucket_size;
 			}
-			rcu_read_unlock();
 			break;
 		}
+		}
 	}
 	preempt_enable();
 fsck_err:
@@ -1006,19 +1006,18 @@ void bch2_verify_accounting_clean(struct bch_fs *c)
 			case BCH_DISK_ACCOUNTING_replicas:
 				fs_usage_data_type_to_base(&base, acc_k.replicas.data_type, a.v->d[0]);
 				break;
-			case BCH_DISK_ACCOUNTING_dev_data_type: {
-				rcu_read_lock();
-				struct bch_dev *ca = bch2_dev_rcu_noerror(c, acc_k.dev_data_type.dev);
-				if (!ca) {
-					rcu_read_unlock();
-					continue;
+			case BCH_DISK_ACCOUNTING_dev_data_type:
+				{
+					guard(rcu)(); /* scoped guard is a loop, and doesn't play nicely with continue */
+					struct bch_dev *ca = bch2_dev_rcu_noerror(c, acc_k.dev_data_type.dev);
+					if (!ca)
+						continue;
+
+					v[0] = percpu_u64_get(&ca->usage->d[acc_k.dev_data_type.data_type].buckets);
+					v[1] = percpu_u64_get(&ca->usage->d[acc_k.dev_data_type.data_type].sectors);
+					v[2] = percpu_u64_get(&ca->usage->d[acc_k.dev_data_type.data_type].fragmented);
 				}
 
-				v[0] = percpu_u64_get(&ca->usage->d[acc_k.dev_data_type.data_type].buckets);
-				v[1] = percpu_u64_get(&ca->usage->d[acc_k.dev_data_type.data_type].sectors);
-				v[2] = percpu_u64_get(&ca->usage->d[acc_k.dev_data_type.data_type].fragmented);
-				rcu_read_unlock();
-
 				if (memcmp(a.v->d, v, 3 * sizeof(u64))) {
 					struct printbuf buf = PRINTBUF;
 
@@ -1032,7 +1031,6 @@ void bch2_verify_accounting_clean(struct bch_fs *c)
 					mismatch = true;
 				}
 			}
-			}
 
 			0;
 		})));
diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h
index f6098e33ab30..d61abebf3e0b 100644
--- a/fs/bcachefs/disk_accounting.h
+++ b/fs/bcachefs/disk_accounting.h
@@ -174,17 +174,17 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans,
 		case BCH_DISK_ACCOUNTING_replicas:
 			fs_usage_data_type_to_base(&trans->fs_usage_delta, acc_k.replicas.data_type, a.v->d[0]);
 			break;
-		case BCH_DISK_ACCOUNTING_dev_data_type:
-			rcu_read_lock();
+		case BCH_DISK_ACCOUNTING_dev_data_type: {
+			guard(rcu)();
 			struct bch_dev *ca = bch2_dev_rcu_noerror(c, acc_k.dev_data_type.dev);
 			if (ca) {
 				this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].buckets, a.v->d[0]);
 				this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].sectors, a.v->d[1]);
 				this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].fragmented, a.v->d[2]);
 			}
-			rcu_read_unlock();
 			break;
 		}
+		}
 	}
 
 	unsigned idx;
diff --git a/fs/bcachefs/disk_groups.c b/fs/bcachefs/disk_groups.c
index c20ecf5e5381..cde842ac1886 100644
--- a/fs/bcachefs/disk_groups.c
+++ b/fs/bcachefs/disk_groups.c
@@ -130,7 +130,7 @@ int bch2_sb_disk_groups_to_cpu(struct bch_fs *c)
 
 	cpu_g = kzalloc(struct_size(cpu_g, entries, nr_groups), GFP_KERNEL);
 	if (!cpu_g)
-		return -BCH_ERR_ENOMEM_disk_groups_to_cpu;
+		return bch_err_throw(c, ENOMEM_disk_groups_to_cpu);
 
 	cpu_g->nr = nr_groups;
 
@@ -170,36 +170,28 @@ int bch2_sb_disk_groups_to_cpu(struct bch_fs *c)
 const struct bch_devs_mask *bch2_target_to_mask(struct bch_fs *c, unsigned target)
 {
 	struct target t = target_decode(target);
-	struct bch_devs_mask *devs;
 
-	rcu_read_lock();
+	guard(rcu)();
 
 	switch (t.type) {
 	case TARGET_NULL:
-		devs = NULL;
-		break;
+		return NULL;
 	case TARGET_DEV: {
 		struct bch_dev *ca = t.dev < c->sb.nr_devices
 			? rcu_dereference(c->devs[t.dev])
 			: NULL;
-		devs = ca ? &ca->self : NULL;
-		break;
+		return ca ? &ca->self : NULL;
 	}
 	case TARGET_GROUP: {
 		struct bch_disk_groups_cpu *g = rcu_dereference(c->disk_groups);
 
-		devs = g && t.group < g->nr && !g->entries[t.group].deleted
+		return g && t.group < g->nr && !g->entries[t.group].deleted
 			? &g->entries[t.group].devs
 			: NULL;
-		break;
 	}
 	default:
 		BUG();
 	}
-
-	rcu_read_unlock();
-
-	return devs;
 }
 
 bool bch2_dev_in_target(struct bch_fs *c, unsigned dev, unsigned target)
@@ -384,7 +376,7 @@ void bch2_disk_groups_to_text(struct printbuf *out, struct bch_fs *c)
 	bch2_printbuf_make_room(out, 4096);
 
 	out->atomic++;
-	rcu_read_lock();
+	guard(rcu)();
 	struct bch_disk_groups_cpu *g = rcu_dereference(c->disk_groups);
 
 	for (unsigned i = 0; i < (g ? g->nr : 0); i++) {
@@ -405,16 +397,14 @@ next:
 		prt_newline(out);
 	}
 
-	rcu_read_unlock();
 	out->atomic--;
 }
 
 void bch2_disk_path_to_text(struct printbuf *out, struct bch_fs *c, unsigned v)
 {
 	out->atomic++;
-	rcu_read_lock();
+	guard(rcu)();
 	__bch2_disk_path_to_text(out, rcu_dereference(c->disk_groups), v),
-	rcu_read_unlock();
 	--out->atomic;
 }
 
@@ -535,13 +525,11 @@ void bch2_target_to_text(struct printbuf *out, struct bch_fs *c, unsigned v)
 	switch (t.type) {
 	case TARGET_NULL:
 		prt_printf(out, "none");
-		break;
+		return;
 	case TARGET_DEV: {
-		struct bch_dev *ca;
-
 		out->atomic++;
-		rcu_read_lock();
-		ca = t.dev < c->sb.nr_devices
+		guard(rcu)();
+		struct bch_dev *ca = t.dev < c->sb.nr_devices
 			? rcu_dereference(c->devs[t.dev])
 			: NULL;
 
@@ -552,13 +540,12 @@ void bch2_target_to_text(struct printbuf *out, struct bch_fs *c, unsigned v)
 		else
 			prt_printf(out, "invalid device %u", t.dev);
 
-		rcu_read_unlock();
 		out->atomic--;
-		break;
+		return;
 	}
 	case TARGET_GROUP:
 		bch2_disk_path_to_text(out, c, t.group);
-		break;
+		return;
 	default:
 		BUG();
 	}
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index c581426e3894..543dbba9b14f 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -213,7 +213,7 @@ static int __mark_stripe_bucket(struct btree_trans *trans,
 				a->dirty_sectors,
 				a->stripe, s.k->p.offset,
 				(bch2_bkey_val_to_text(&buf, c, s.s_c), buf.buf))) {
-			ret = -BCH_ERR_mark_stripe;
+			ret = bch_err_throw(c, mark_stripe);
 			goto err;
 		}
 
@@ -224,7 +224,7 @@ static int __mark_stripe_bucket(struct btree_trans *trans,
 				a->dirty_sectors,
 				a->cached_sectors,
 				(bch2_bkey_val_to_text(&buf, c, s.s_c), buf.buf))) {
-			ret = -BCH_ERR_mark_stripe;
+			ret = bch_err_throw(c, mark_stripe);
 			goto err;
 		}
 	} else {
@@ -234,7 +234,7 @@ static int __mark_stripe_bucket(struct btree_trans *trans,
 				bucket.inode, bucket.offset, a->gen,
 				a->stripe,
 				(bch2_bkey_val_to_text(&buf, c, s.s_c), buf.buf))) {
-			ret = -BCH_ERR_mark_stripe;
+			ret = bch_err_throw(c, mark_stripe);
 			goto err;
 		}
 
@@ -244,7 +244,7 @@ static int __mark_stripe_bucket(struct btree_trans *trans,
 				bch2_data_type_str(a->data_type),
 				bch2_data_type_str(data_type),
 				(bch2_bkey_val_to_text(&buf, c, s.s_c), buf.buf))) {
-			ret = -BCH_ERR_mark_stripe;
+			ret = bch_err_throw(c, mark_stripe);
 			goto err;
 		}
 
@@ -256,7 +256,7 @@ static int __mark_stripe_bucket(struct btree_trans *trans,
 				a->dirty_sectors,
 				a->cached_sectors,
 				(bch2_bkey_val_to_text(&buf, c, s.s_c), buf.buf))) {
-			ret = -BCH_ERR_mark_stripe;
+			ret = bch_err_throw(c, mark_stripe);
 			goto err;
 		}
 	}
@@ -295,7 +295,7 @@ static int mark_stripe_bucket(struct btree_trans *trans,
 	struct bch_dev *ca = bch2_dev_tryget(c, ptr->dev);
 	if (unlikely(!ca)) {
 		if (ptr->dev != BCH_SB_MEMBER_INVALID && !(flags & BTREE_TRIGGER_overwrite))
-			ret = -BCH_ERR_mark_stripe;
+			ret = bch_err_throw(c, mark_stripe);
 		goto err;
 	}
 
@@ -325,7 +325,7 @@ static int mark_stripe_bucket(struct btree_trans *trans,
 		if (bch2_fs_inconsistent_on(!g, c, "reference to invalid bucket on device %u\n%s",
 					    ptr->dev,
 					    (bch2_bkey_val_to_text(&buf, c, s.s_c), buf.buf))) {
-			ret = -BCH_ERR_mark_stripe;
+			ret = bch_err_throw(c, mark_stripe);
 			goto err;
 		}
 
@@ -428,7 +428,7 @@ int bch2_trigger_stripe(struct btree_trans *trans,
 			gc = genradix_ptr_alloc(&c->gc_stripes, idx, GFP_KERNEL);
 			if (!gc) {
 				bch_err(c, "error allocating memory for gc_stripes, idx %llu", idx);
-				return -BCH_ERR_ENOMEM_mark_stripe;
+				return bch_err_throw(c, ENOMEM_mark_stripe);
 			}
 
 			/*
@@ -536,7 +536,8 @@ static void ec_stripe_buf_exit(struct ec_stripe_buf *buf)
 }
 
 /* XXX: this is a non-mempoolified memory allocation: */
-static int ec_stripe_buf_init(struct ec_stripe_buf *buf,
+static int ec_stripe_buf_init(struct bch_fs *c,
+			      struct ec_stripe_buf *buf,
 			      unsigned offset, unsigned size)
 {
 	struct bch_stripe *v = &bkey_i_to_stripe(&buf->key)->v;
@@ -564,7 +565,7 @@ static int ec_stripe_buf_init(struct ec_stripe_buf *buf,
 	return 0;
 err:
 	ec_stripe_buf_exit(buf);
-	return -BCH_ERR_ENOMEM_stripe_buf;
+	return bch_err_throw(c, ENOMEM_stripe_buf);
 }
 
 /* Checksumming: */
@@ -840,7 +841,7 @@ int bch2_ec_read_extent(struct btree_trans *trans, struct bch_read_bio *rbio,
 
 	buf = kzalloc(sizeof(*buf), GFP_NOFS);
 	if (!buf)
-		return -BCH_ERR_ENOMEM_ec_read_extent;
+		return bch_err_throw(c, ENOMEM_ec_read_extent);
 
 	ret = lockrestart_do(trans, get_stripe_key_trans(trans, rbio->pick.ec.idx, buf));
 	if (ret) {
@@ -861,7 +862,7 @@ int bch2_ec_read_extent(struct btree_trans *trans, struct bch_read_bio *rbio,
 		goto err;
 	}
 
-	ret = ec_stripe_buf_init(buf, offset, bio_sectors(&rbio->bio));
+	ret = ec_stripe_buf_init(c, buf, offset, bio_sectors(&rbio->bio));
 	if (ret) {
 		msg = "-ENOMEM";
 		goto err;
@@ -894,7 +895,7 @@ err:
 	bch_err_ratelimited(c,
 			    "error doing reconstruct read: %s\n  %s", msg, msgbuf.buf);
 	printbuf_exit(&msgbuf);
-	ret = -BCH_ERR_stripe_reconstruct;
+	ret = bch_err_throw(c, stripe_reconstruct);
 	goto out;
 }
 
@@ -904,7 +905,7 @@ static int __ec_stripe_mem_alloc(struct bch_fs *c, size_t idx, gfp_t gfp)
 {
 	if (c->gc_pos.phase != GC_PHASE_not_running &&
 	    !genradix_ptr_alloc(&c->gc_stripes, idx, gfp))
-		return -BCH_ERR_ENOMEM_ec_stripe_mem_alloc;
+		return bch_err_throw(c, ENOMEM_ec_stripe_mem_alloc);
 
 	return 0;
 }
@@ -1129,7 +1130,7 @@ static int ec_stripe_update_extent(struct btree_trans *trans,
 
 		bch2_fs_inconsistent(c, "%s", buf.buf);
 		printbuf_exit(&buf);
-		return -BCH_ERR_erasure_coding_found_btree_node;
+		return bch_err_throw(c, erasure_coding_found_btree_node);
 	}
 
 	k = bch2_backpointer_get_key(trans, bp, &iter, BTREE_ITER_intent, last_flushed);
@@ -1195,7 +1196,7 @@ static int ec_stripe_update_bucket(struct btree_trans *trans, struct ec_stripe_b
 
 	struct bch_dev *ca = bch2_dev_tryget(c, ptr.dev);
 	if (!ca)
-		return -BCH_ERR_ENOENT_dev_not_found;
+		return bch_err_throw(c, ENOENT_dev_not_found);
 
 	struct bpos bucket_pos = PTR_BUCKET_POS(ca, &ptr);
 
@@ -1256,7 +1257,7 @@ static void zero_out_rest_of_ec_bucket(struct bch_fs *c,
 	struct bch_dev *ca = bch2_dev_get_ioref(c, ob->dev, WRITE,
 				BCH_DEV_WRITE_REF_ec_bucket_zero);
 	if (!ca) {
-		s->err = -BCH_ERR_erofs_no_writes;
+		s->err = bch_err_throw(c, erofs_no_writes);
 		return;
 	}
 
@@ -1320,7 +1321,7 @@ static void ec_stripe_create(struct ec_stripe_new *s)
 
 		if (ec_do_recov(c, &s->existing_stripe)) {
 			bch_err(c, "error creating stripe: error reading existing stripe");
-			ret = -BCH_ERR_ec_block_read;
+			ret = bch_err_throw(c, ec_block_read);
 			goto err;
 		}
 
@@ -1346,7 +1347,7 @@ static void ec_stripe_create(struct ec_stripe_new *s)
 
 	if (ec_nr_failed(&s->new_stripe)) {
 		bch_err(c, "error creating stripe: error writing redundancy buckets");
-		ret = -BCH_ERR_ec_block_write;
+		ret = bch_err_throw(c, ec_block_write);
 		goto err;
 	}
 
@@ -1578,26 +1579,26 @@ static struct ec_stripe_new *ec_new_stripe_alloc(struct bch_fs *c, struct ec_str
 static void ec_stripe_head_devs_update(struct bch_fs *c, struct ec_stripe_head *h)
 {
 	struct bch_devs_mask devs = h->devs;
+	unsigned nr_devs, nr_devs_with_durability;
 
-	rcu_read_lock();
-	h->devs = target_rw_devs(c, BCH_DATA_user, h->disk_label
-				 ? group_to_target(h->disk_label - 1)
-				 : 0);
-	unsigned nr_devs = dev_mask_nr(&h->devs);
+	scoped_guard(rcu) {
+		h->devs = target_rw_devs(c, BCH_DATA_user, h->disk_label
+					 ? group_to_target(h->disk_label - 1)
+					 : 0);
+		nr_devs = dev_mask_nr(&h->devs);
 
-	for_each_member_device_rcu(c, ca, &h->devs)
-		if (!ca->mi.durability)
-			__clear_bit(ca->dev_idx, h->devs.d);
-	unsigned nr_devs_with_durability = dev_mask_nr(&h->devs);
+		for_each_member_device_rcu(c, ca, &h->devs)
+			if (!ca->mi.durability)
+				__clear_bit(ca->dev_idx, h->devs.d);
+		nr_devs_with_durability = dev_mask_nr(&h->devs);
 
-	h->blocksize = pick_blocksize(c, &h->devs);
+		h->blocksize = pick_blocksize(c, &h->devs);
 
-	h->nr_active_devs = 0;
-	for_each_member_device_rcu(c, ca, &h->devs)
-		if (ca->mi.bucket_size == h->blocksize)
-			h->nr_active_devs++;
-
-	rcu_read_unlock();
+		h->nr_active_devs = 0;
+		for_each_member_device_rcu(c, ca, &h->devs)
+			if (ca->mi.bucket_size == h->blocksize)
+				h->nr_active_devs++;
+	}
 
 	/*
 	 * If we only have redundancy + 1 devices, we're better off with just
@@ -1865,7 +1866,7 @@ static int init_new_stripe_from_existing(struct bch_fs *c, struct ec_stripe_new
 	s->nr_data = existing_v->nr_blocks -
 		existing_v->nr_redundant;
 
-	int ret = ec_stripe_buf_init(&s->existing_stripe, 0, le16_to_cpu(existing_v->sectors));
+	int ret = ec_stripe_buf_init(c, &s->existing_stripe, 0, le16_to_cpu(existing_v->sectors));
 	if (ret) {
 		bch2_stripe_close(c, s);
 		return ret;
@@ -1925,7 +1926,7 @@ static int __bch2_ec_stripe_head_reuse(struct btree_trans *trans, struct ec_stri
 	}
 	bch2_trans_iter_exit(trans, &lru_iter);
 	if (!ret)
-		ret = -BCH_ERR_stripe_alloc_blocked;
+		ret = bch_err_throw(c, stripe_alloc_blocked);
 	if (ret == 1)
 		ret = 0;
 	if (ret)
@@ -1966,7 +1967,7 @@ static int __bch2_ec_stripe_head_reserve(struct btree_trans *trans, struct ec_st
 				continue;
 			}
 
-			ret = -BCH_ERR_ENOSPC_stripe_create;
+			ret = bch_err_throw(c, ENOSPC_stripe_create);
 			break;
 		}
 
@@ -2024,7 +2025,7 @@ struct ec_stripe_head *bch2_ec_stripe_head_get(struct btree_trans *trans,
 	if (!h->s) {
 		h->s = ec_new_stripe_alloc(c, h);
 		if (!h->s) {
-			ret = -BCH_ERR_ENOMEM_ec_new_stripe_alloc;
+			ret = bch_err_throw(c, ENOMEM_ec_new_stripe_alloc);
 			bch_err(c, "failed to allocate new stripe");
 			goto err;
 		}
@@ -2089,7 +2090,7 @@ alloc_existing:
 		goto err;
 
 allocate_buf:
-	ret = ec_stripe_buf_init(&s->new_stripe, 0, h->blocksize);
+	ret = ec_stripe_buf_init(c, &s->new_stripe, 0, h->blocksize);
 	if (ret)
 		goto err;
 
@@ -2115,6 +2116,7 @@ int bch2_invalidate_stripe_to_dev(struct btree_trans *trans,
 	if (k.k->type != KEY_TYPE_stripe)
 		return 0;
 
+	struct bch_fs *c = trans->c;
 	struct bkey_i_stripe *s =
 		bch2_bkey_make_mut_typed(trans, iter, &k, 0, stripe);
 	int ret = PTR_ERR_OR_ZERO(s);
@@ -2141,23 +2143,22 @@ int bch2_invalidate_stripe_to_dev(struct btree_trans *trans,
 
 	unsigned nr_good = 0;
 
-	rcu_read_lock();
-	bkey_for_each_ptr(ptrs, ptr) {
-		if (ptr->dev == dev_idx)
-			ptr->dev = BCH_SB_MEMBER_INVALID;
+	scoped_guard(rcu)
+		bkey_for_each_ptr(ptrs, ptr) {
+			if (ptr->dev == dev_idx)
+				ptr->dev = BCH_SB_MEMBER_INVALID;
 
-		struct bch_dev *ca = bch2_dev_rcu(trans->c, ptr->dev);
-		nr_good += ca && ca->mi.state != BCH_MEMBER_STATE_failed;
-	}
-	rcu_read_unlock();
+			struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev);
+			nr_good += ca && ca->mi.state != BCH_MEMBER_STATE_failed;
+		}
 
 	if (nr_good < s->v.nr_blocks && !(flags & BCH_FORCE_IF_DATA_DEGRADED))
-		return -BCH_ERR_remove_would_lose_data;
+		return bch_err_throw(c, remove_would_lose_data);
 
 	unsigned nr_data = s->v.nr_blocks - s->v.nr_redundant;
 
 	if (nr_good < nr_data && !(flags & BCH_FORCE_IF_DATA_LOST))
-		return -BCH_ERR_remove_would_lose_data;
+		return bch_err_throw(c, remove_would_lose_data);
 
 	sectors = -sectors;
 
@@ -2178,14 +2179,15 @@ static int bch2_invalidate_stripe_to_dev_from_alloc(struct btree_trans *trans, s
 		return 0;
 
 	if (a->stripe_sectors) {
-		bch_err(trans->c, "trying to invalidate device in stripe when bucket has stripe data");
-		return -BCH_ERR_invalidate_stripe_to_dev;
+		struct bch_fs *c = trans->c;
+		bch_err(c, "trying to invalidate device in stripe when bucket has stripe data");
+		return bch_err_throw(c, invalidate_stripe_to_dev);
 	}
 
 	struct btree_iter iter;
 	struct bkey_s_c_stripe s =
 		bch2_bkey_get_iter_typed(trans, &iter, BTREE_ID_stripes, POS(0, a->stripe),
-					BTREE_ITER_slots, stripe);
+					 BTREE_ITER_slots, stripe);
 	int ret = bkey_err(s);
 	if (ret)
 		return ret;
diff --git a/fs/bcachefs/errcode.c b/fs/bcachefs/errcode.c
index 43557bebd0f8..c39cf304c681 100644
--- a/fs/bcachefs/errcode.c
+++ b/fs/bcachefs/errcode.c
@@ -13,12 +13,13 @@ static const char * const bch2_errcode_strs[] = {
 	NULL
 };
 
-static unsigned bch2_errcode_parents[] = {
+static const unsigned bch2_errcode_parents[] = {
 #define x(class, err) [BCH_ERR_##err - BCH_ERR_START] = class,
 	BCH_ERRCODES()
 #undef x
 };
 
+__attribute__((const))
 const char *bch2_err_str(int err)
 {
 	const char *errstr;
@@ -36,6 +37,7 @@ const char *bch2_err_str(int err)
 	return errstr ?: "(Invalid error)";
 }
 
+__attribute__((const))
 bool __bch2_err_matches(int err, int class)
 {
 	err	= abs(err);
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index 62843e772b2c..ac3264134a15 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -182,9 +182,12 @@
 	x(BCH_ERR_fsck,			fsck_errors_not_fixed)			\
 	x(BCH_ERR_fsck,			fsck_repair_unimplemented)		\
 	x(BCH_ERR_fsck,			fsck_repair_impossible)			\
-	x(EINVAL,			restart_recovery)			\
-	x(EINVAL,			cannot_rewind_recovery)			\
+	x(EINVAL,			recovery_will_run)			\
+	x(BCH_ERR_recovery_will_run,	restart_recovery)			\
+	x(BCH_ERR_recovery_will_run,	cannot_rewind_recovery)			\
+	x(BCH_ERR_recovery_will_run,	recovery_pass_will_run)			\
 	x(0,				data_update_done)			\
+	x(0,				bkey_was_deleted)			\
 	x(BCH_ERR_data_update_done,	data_update_done_would_block)		\
 	x(BCH_ERR_data_update_done,	data_update_done_unwritten)		\
 	x(BCH_ERR_data_update_done,	data_update_done_no_writes_needed)	\
@@ -211,6 +214,8 @@
 	x(EINVAL,			remove_would_lose_data)			\
 	x(EINVAL,			no_resize_with_buckets_nouse)		\
 	x(EINVAL,			inode_unpack_error)			\
+	x(EINVAL,			inode_not_unlinked)			\
+	x(EINVAL,			inode_has_child_snapshot)		\
 	x(EINVAL,			varint_decode_error)			\
 	x(EINVAL,			erasure_coding_found_btree_node)	\
 	x(EINVAL,			option_negative)			\
@@ -357,9 +362,11 @@ enum bch_errcode {
 	BCH_ERR_MAX
 };
 
-const char *bch2_err_str(int);
-bool __bch2_err_matches(int, int);
+__attribute__((const)) const char *bch2_err_str(int);
 
+__attribute__((const)) bool __bch2_err_matches(int, int);
+
+__attribute__((const))
 static inline bool _bch2_err_matches(int err, int class)
 {
 	return err < 0 && __bch2_err_matches(err, class);
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index c2cad28635bf..63951e293c47 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -100,10 +100,10 @@ int __bch2_topology_error(struct bch_fs *c, struct printbuf *out)
 	set_bit(BCH_FS_topology_error, &c->flags);
 	if (!test_bit(BCH_FS_in_recovery, &c->flags)) {
 		__bch2_inconsistent_error(c, out);
-		return -BCH_ERR_btree_need_topology_repair;
+		return bch_err_throw(c, btree_need_topology_repair);
 	} else {
 		return bch2_run_explicit_recovery_pass(c, out, BCH_RECOVERY_PASS_check_topology, 0) ?:
-			-BCH_ERR_btree_node_read_validate_error;
+			bch_err_throw(c, btree_node_read_validate_error);
 	}
 }
 
@@ -403,23 +403,23 @@ int bch2_fsck_err_opt(struct bch_fs *c,
 
 	if (test_bit(BCH_FS_in_fsck, &c->flags)) {
 		if (!(flags & (FSCK_CAN_FIX|FSCK_CAN_IGNORE)))
-			return -BCH_ERR_fsck_repair_unimplemented;
+			return bch_err_throw(c, fsck_repair_unimplemented);
 
 		switch (c->opts.fix_errors) {
 		case FSCK_FIX_exit:
-			return -BCH_ERR_fsck_errors_not_fixed;
+			return bch_err_throw(c, fsck_errors_not_fixed);
 		case FSCK_FIX_yes:
 			if (flags & FSCK_CAN_FIX)
-				return -BCH_ERR_fsck_fix;
+				return bch_err_throw(c, fsck_fix);
 			fallthrough;
 		case FSCK_FIX_no:
 			if (flags & FSCK_CAN_IGNORE)
-				return -BCH_ERR_fsck_ignore;
-			return -BCH_ERR_fsck_errors_not_fixed;
+				return bch_err_throw(c, fsck_ignore);
+			return bch_err_throw(c, fsck_errors_not_fixed);
 		case FSCK_FIX_ask:
 			if (flags & FSCK_AUTOFIX)
-				return -BCH_ERR_fsck_fix;
-			return -BCH_ERR_fsck_ask;
+				return bch_err_throw(c, fsck_fix);
+			return bch_err_throw(c, fsck_ask);
 		default:
 			BUG();
 		}
@@ -427,12 +427,12 @@ int bch2_fsck_err_opt(struct bch_fs *c,
 		if ((flags & FSCK_AUTOFIX) &&
 		    (c->opts.errors == BCH_ON_ERROR_continue ||
 		     c->opts.errors == BCH_ON_ERROR_fix_safe))
-			return -BCH_ERR_fsck_fix;
+			return bch_err_throw(c, fsck_fix);
 
 		if (c->opts.errors == BCH_ON_ERROR_continue &&
 		    (flags & FSCK_CAN_IGNORE))
-			return -BCH_ERR_fsck_ignore;
-		return -BCH_ERR_fsck_errors_not_fixed;
+			return bch_err_throw(c, fsck_ignore);
+		return bch_err_throw(c, fsck_errors_not_fixed);
 	}
 }
 
@@ -444,7 +444,7 @@ int __bch2_fsck_err(struct bch_fs *c,
 {
 	va_list args;
 	struct printbuf buf = PRINTBUF, *out = &buf;
-	int ret = -BCH_ERR_fsck_ignore;
+	int ret = 0;
 	const char *action_orig = "fix?", *action = action_orig;
 
 	might_sleep();
@@ -474,8 +474,8 @@ int __bch2_fsck_err(struct bch_fs *c,
 
 	if (test_bit(err, c->sb.errors_silent))
 		return flags & FSCK_CAN_FIX
-			? -BCH_ERR_fsck_fix
-			: -BCH_ERR_fsck_ignore;
+			? bch_err_throw(c, fsck_fix)
+			: bch_err_throw(c, fsck_ignore);
 
 	printbuf_indent_add_nextline(out, 2);
 
@@ -517,10 +517,10 @@ int __bch2_fsck_err(struct bch_fs *c,
 		prt_str(out, ", ");
 		if (flags & FSCK_CAN_FIX) {
 			prt_actioning(out, action);
-			ret = -BCH_ERR_fsck_fix;
+			ret = bch_err_throw(c, fsck_fix);
 		} else {
 			prt_str(out, ", continuing");
-			ret = -BCH_ERR_fsck_ignore;
+			ret = bch_err_throw(c, fsck_ignore);
 		}
 
 		goto print;
@@ -532,18 +532,18 @@ int __bch2_fsck_err(struct bch_fs *c,
 					 "run fsck, and forward to devs so error can be marked for self-healing");
 			inconsistent = true;
 			print = true;
-			ret = -BCH_ERR_fsck_errors_not_fixed;
+			ret = bch_err_throw(c, fsck_errors_not_fixed);
 		} else if (flags & FSCK_CAN_FIX) {
 			prt_str(out, ", ");
 			prt_actioning(out, action);
-			ret = -BCH_ERR_fsck_fix;
+			ret = bch_err_throw(c, fsck_fix);
 		} else {
 			prt_str(out, ", continuing");
-			ret = -BCH_ERR_fsck_ignore;
+			ret = bch_err_throw(c, fsck_ignore);
 		}
 	} else if (c->opts.fix_errors == FSCK_FIX_exit) {
 		prt_str(out, ", exiting");
-		ret = -BCH_ERR_fsck_errors_not_fixed;
+		ret = bch_err_throw(c, fsck_errors_not_fixed);
 	} else if (flags & FSCK_CAN_FIX) {
 		int fix = s && s->fix
 			? s->fix
@@ -562,30 +562,37 @@ int __bch2_fsck_err(struct bch_fs *c,
 					: FSCK_FIX_yes;
 
 			ret = ret & 1
-				? -BCH_ERR_fsck_fix
-				: -BCH_ERR_fsck_ignore;
+				? bch_err_throw(c, fsck_fix)
+				: bch_err_throw(c, fsck_ignore);
 		} else if (fix == FSCK_FIX_yes ||
 			   (c->opts.nochanges &&
 			    !(flags & FSCK_CAN_IGNORE))) {
 			prt_str(out, ", ");
 			prt_actioning(out, action);
-			ret = -BCH_ERR_fsck_fix;
+			ret = bch_err_throw(c, fsck_fix);
 		} else {
 			prt_str(out, ", not ");
 			prt_actioning(out, action);
+			ret = bch_err_throw(c, fsck_ignore);
+		}
+	} else {
+		if (flags & FSCK_CAN_IGNORE) {
+			prt_str(out, ", continuing");
+			ret = bch_err_throw(c, fsck_ignore);
+		} else {
+			prt_str(out, " (repair unimplemented)");
+			ret = bch_err_throw(c, fsck_repair_unimplemented);
 		}
-	} else if (!(flags & FSCK_CAN_IGNORE)) {
-		prt_str(out, " (repair unimplemented)");
 	}
 
-	if (ret == -BCH_ERR_fsck_ignore &&
+	if (bch2_err_matches(ret, BCH_ERR_fsck_ignore) &&
 	    (c->opts.fix_errors == FSCK_FIX_exit ||
 	     !(flags & FSCK_CAN_IGNORE)))
-		ret = -BCH_ERR_fsck_errors_not_fixed;
+		ret = bch_err_throw(c, fsck_errors_not_fixed);
 
 	if (test_bit(BCH_FS_in_fsck, &c->flags) &&
-	    (ret != -BCH_ERR_fsck_fix &&
-	     ret != -BCH_ERR_fsck_ignore)) {
+	    (!bch2_err_matches(ret, BCH_ERR_fsck_fix) &&
+	     !bch2_err_matches(ret, BCH_ERR_fsck_ignore))) {
 		exiting = true;
 		print = true;
 	}
@@ -613,26 +620,26 @@ print:
 
 	if (s)
 		s->ret = ret;
-
+err_unlock:
+	mutex_unlock(&c->fsck_error_msgs_lock);
+err:
 	/*
 	 * We don't yet track whether the filesystem currently has errors, for
 	 * log_fsck_err()s: that would require us to track for every error type
 	 * which recovery pass corrects it, to get the fsck exit status correct:
 	 */
-	if (flags & FSCK_CAN_FIX) {
-		if (ret == -BCH_ERR_fsck_fix) {
-			set_bit(BCH_FS_errors_fixed, &c->flags);
-		} else {
-			set_bit(BCH_FS_errors_not_fixed, &c->flags);
-			set_bit(BCH_FS_error, &c->flags);
-		}
+	if (bch2_err_matches(ret, BCH_ERR_fsck_fix)) {
+		set_bit(BCH_FS_errors_fixed, &c->flags);
+	} else {
+		set_bit(BCH_FS_errors_not_fixed, &c->flags);
+		set_bit(BCH_FS_error, &c->flags);
 	}
-err_unlock:
-	mutex_unlock(&c->fsck_error_msgs_lock);
-err:
+
 	if (action != action_orig)
 		kfree(action);
 	printbuf_exit(&buf);
+
+	BUG_ON(!ret);
 	return ret;
 }
 
@@ -650,12 +657,12 @@ int __bch2_bkey_fsck_err(struct bch_fs *c,
 			 const char *fmt, ...)
 {
 	if (from.flags & BCH_VALIDATE_silent)
-		return -BCH_ERR_fsck_delete_bkey;
+		return bch_err_throw(c, fsck_delete_bkey);
 
 	unsigned fsck_flags = 0;
 	if (!(from.flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit))) {
 		if (test_bit(err, c->sb.errors_silent))
-			return -BCH_ERR_fsck_delete_bkey;
+			return bch_err_throw(c, fsck_delete_bkey);
 
 		fsck_flags |= FSCK_AUTOFIX|FSCK_CAN_FIX;
 	}
diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h
index 5123d4c86770..0c3c3a24fc6f 100644
--- a/fs/bcachefs/error.h
+++ b/fs/bcachefs/error.h
@@ -105,13 +105,13 @@ void bch2_free_fsck_errs(struct bch_fs *);
 #define fsck_err_wrap(_do)						\
 ({									\
 	int _ret = _do;							\
-	if (_ret != -BCH_ERR_fsck_fix &&				\
-	    _ret != -BCH_ERR_fsck_ignore) {				\
+	if (!bch2_err_matches(_ret, BCH_ERR_fsck_fix) &&		\
+	    !bch2_err_matches(_ret, BCH_ERR_fsck_ignore)) {		\
 		ret = _ret;						\
 		goto fsck_err;						\
 	}								\
 									\
-	_ret == -BCH_ERR_fsck_fix;					\
+	bch2_err_matches(_ret, BCH_ERR_fsck_fix);			\
 })
 
 #define __fsck_err(...)		fsck_err_wrap(bch2_fsck_err(__VA_ARGS__))
@@ -170,10 +170,10 @@ do {									\
 	int _ret = __bch2_bkey_fsck_err(c, k, from,			\
 				BCH_FSCK_ERR_##_err_type,		\
 				_err_msg, ##__VA_ARGS__);		\
-	if (_ret != -BCH_ERR_fsck_fix &&				\
-	    _ret != -BCH_ERR_fsck_ignore)				\
+	if (!bch2_err_matches(_ret, BCH_ERR_fsck_fix) &&		\
+	    !bch2_err_matches(_ret, BCH_ERR_fsck_ignore))		\
 		ret = _ret;						\
-	ret = -BCH_ERR_fsck_delete_bkey;				\
+	ret = bch_err_throw(c, fsck_delete_bkey);			\
 	goto fsck_err;							\
 } while (0)
 
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index 1ac9897f189d..036e4ad95987 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -65,15 +65,15 @@ void bch2_io_failures_to_text(struct printbuf *out,
 			continue;
 
 		bch2_printbuf_make_room(out, 1024);
-		rcu_read_lock();
 		out->atomic++;
-		struct bch_dev *ca = bch2_dev_rcu_noerror(c, f->dev);
-		if (ca)
-			prt_str(out, ca->name);
-		else
-			prt_printf(out, "(invalid device %u)", f->dev);
+		scoped_guard(rcu) {
+			struct bch_dev *ca = bch2_dev_rcu_noerror(c, f->dev);
+			if (ca)
+				prt_str(out, ca->name);
+			else
+				prt_printf(out, "(invalid device %u)", f->dev);
+		}
 		--out->atomic;
-		rcu_read_unlock();
 
 		prt_char(out, ' ');
 
@@ -193,7 +193,7 @@ int bch2_bkey_pick_read_device(struct bch_fs *c, struct bkey_s_c k,
 	bool have_dirty_ptrs = false, have_pick = false;
 
 	if (k.k->type == KEY_TYPE_error)
-		return -BCH_ERR_key_type_error;
+		return bch_err_throw(c, key_type_error);
 
 	rcu_read_lock();
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
@@ -286,17 +286,17 @@ int bch2_bkey_pick_read_device(struct bch_fs *c, struct bkey_s_c k,
 	if (!have_dirty_ptrs)
 		return 0;
 	if (have_missing_devs)
-		return -BCH_ERR_no_device_to_read_from;
+		return bch_err_throw(c, no_device_to_read_from);
 	if (have_csum_errors)
-		return -BCH_ERR_data_read_csum_err;
+		return bch_err_throw(c, data_read_csum_err);
 	if (have_io_errors)
-		return -BCH_ERR_data_read_io_err;
+		return bch_err_throw(c, data_read_io_err);
 
 	/*
 	 * If we get here, we have pointers (bkey_ptrs_validate() ensures that),
 	 * but they don't point to valid devices:
 	 */
-	return -BCH_ERR_no_devices_valid;
+	return bch_err_throw(c, no_devices_valid);
 }
 
 /* KEY_TYPE_btree_ptr: */
@@ -407,6 +407,8 @@ bool bch2_extent_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_c r)
 	lp.crc = bch2_extent_crc_unpack(l.k, NULL);
 	rp.crc = bch2_extent_crc_unpack(r.k, NULL);
 
+	guard(rcu)();
+
 	while (__bkey_ptr_next_decode(l.k, l_ptrs.end, lp, en_l) &&
 	       __bkey_ptr_next_decode(r.k, r_ptrs.end, rp, en_r)) {
 		if (lp.ptr.offset + lp.crc.offset + lp.crc.live_size !=
@@ -418,10 +420,8 @@ bool bch2_extent_merge(struct bch_fs *c, struct bkey_s l, struct bkey_s_c r)
 			return false;
 
 		/* Extents may not straddle buckets: */
-		rcu_read_lock();
 		struct bch_dev *ca = bch2_dev_rcu(c, lp.ptr.dev);
 		bool same_bucket = ca && PTR_BUCKET_NR(ca, &lp.ptr) == PTR_BUCKET_NR(ca, &rp.ptr);
-		rcu_read_unlock();
 
 		if (!same_bucket)
 			return false;
@@ -838,11 +838,9 @@ unsigned bch2_bkey_durability(struct bch_fs *c, struct bkey_s_c k)
 	struct extent_ptr_decoded p;
 	unsigned durability = 0;
 
-	rcu_read_lock();
+	guard(rcu)();
 	bkey_for_each_ptr_decode(k.k, ptrs, p, entry)
 		durability += bch2_extent_ptr_durability(c, &p);
-	rcu_read_unlock();
-
 	return durability;
 }
 
@@ -853,12 +851,10 @@ static unsigned bch2_bkey_durability_safe(struct bch_fs *c, struct bkey_s_c k)
 	struct extent_ptr_decoded p;
 	unsigned durability = 0;
 
-	rcu_read_lock();
+	guard(rcu)();
 	bkey_for_each_ptr_decode(k.k, ptrs, p, entry)
 		if (p.ptr.dev < c->sb.nr_devices && c->devs[p.ptr.dev])
 			durability += bch2_extent_ptr_durability(c, &p);
-	rcu_read_unlock();
-
 	return durability;
 }
 
@@ -1015,20 +1011,16 @@ bool bch2_bkey_has_target(struct bch_fs *c, struct bkey_s_c k, unsigned target)
 {
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
 	struct bch_dev *ca;
-	bool ret = false;
 
-	rcu_read_lock();
+	guard(rcu)();
 	bkey_for_each_ptr(ptrs, ptr)
 		if (bch2_dev_in_target(c, ptr->dev, target) &&
 		    (ca = bch2_dev_rcu(c, ptr->dev)) &&
 		    (!ptr->cached ||
-		     !dev_ptr_stale_rcu(ca, ptr))) {
-			ret = true;
-			break;
-		}
-	rcu_read_unlock();
+		     !dev_ptr_stale_rcu(ca, ptr)))
+			return true;
 
-	return ret;
+	return false;
 }
 
 bool bch2_bkey_matches_ptr(struct bch_fs *c, struct bkey_s_c k,
@@ -1142,7 +1134,7 @@ void bch2_extent_ptr_set_cached(struct bch_fs *c,
 	bool have_cached_ptr;
 	unsigned drop_dev = ptr->dev;
 
-	rcu_read_lock();
+	guard(rcu)();
 restart_drop_ptrs:
 	ptrs = bch2_bkey_ptrs(k);
 	have_cached_ptr = false;
@@ -1175,10 +1167,8 @@ restart_drop_ptrs:
 		goto drop;
 
 	ptr->cached = true;
-	rcu_read_unlock();
 	return;
 drop:
-	rcu_read_unlock();
 	bch2_bkey_drop_ptr_noerror(k, ptr);
 }
 
@@ -1194,12 +1184,11 @@ bool bch2_extent_normalize(struct bch_fs *c, struct bkey_s k)
 {
 	struct bch_dev *ca;
 
-	rcu_read_lock();
+	guard(rcu)();
 	bch2_bkey_drop_ptrs(k, ptr,
 		ptr->cached &&
 		(!(ca = bch2_dev_rcu(c, ptr->dev)) ||
 		 dev_ptr_stale_rcu(ca, ptr) > 0));
-	rcu_read_unlock();
 
 	return bkey_deleted(k.k);
 }
@@ -1217,7 +1206,7 @@ bool bch2_extent_normalize_by_opts(struct bch_fs *c,
 	struct bkey_ptrs ptrs;
 	bool have_cached_ptr;
 
-	rcu_read_lock();
+	guard(rcu)();
 restart_drop_ptrs:
 	ptrs = bch2_bkey_ptrs(k);
 	have_cached_ptr = false;
@@ -1230,7 +1219,6 @@ restart_drop_ptrs:
 			}
 			have_cached_ptr = true;
 		}
-	rcu_read_unlock();
 
 	return bkey_deleted(k.k);
 }
@@ -1238,7 +1226,7 @@ restart_drop_ptrs:
 void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *c, const struct bch_extent_ptr *ptr)
 {
 	out->atomic++;
-	rcu_read_lock();
+	guard(rcu)();
 	struct bch_dev *ca = bch2_dev_rcu_noerror(c, ptr->dev);
 	if (!ca) {
 		prt_printf(out, "ptr: %u:%llu gen %u%s", ptr->dev,
@@ -1262,7 +1250,6 @@ void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *c, const struc
 		else if (stale)
 			prt_printf(out, " invalid");
 	}
-	rcu_read_unlock();
 	--out->atomic;
 }
 
@@ -1528,7 +1515,7 @@ int bch2_bkey_ptrs_validate(struct bch_fs *c, struct bkey_s_c k,
 				struct bch_compression_opt opt = __bch2_compression_decode(r->compression);
 				prt_printf(err, "invalid compression opt %u:%u",
 					   opt.type, opt.level);
-				return -BCH_ERR_invalid_bkey;
+				return bch_err_throw(c, invalid_bkey);
 			}
 #endif
 			break;
diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
index e3a75dcca60c..66bacdd49f78 100644
--- a/fs/bcachefs/fs-io-buffered.c
+++ b/fs/bcachefs/fs-io-buffered.c
@@ -394,17 +394,9 @@ struct bch_writepage_state {
 	struct bch_io_opts	opts;
 	struct bch_folio_sector	*tmp;
 	unsigned		tmp_sectors;
+	struct blk_plug		plug;
 };
 
-static inline struct bch_writepage_state bch_writepage_state_init(struct bch_fs *c,
-								  struct bch_inode_info *inode)
-{
-	struct bch_writepage_state ret = { 0 };
-
-	bch2_inode_opts_get(&ret.opts, c, &inode->ei_inode);
-	return ret;
-}
-
 /*
  * Determine when a writepage io is full. We have to limit writepage bios to a
  * single page per bvec (i.e. 1MB with 4k pages) because that is the limit to
@@ -666,17 +658,17 @@ do_io:
 int bch2_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	struct bch_fs *c = mapping->host->i_sb->s_fs_info;
-	struct bch_writepage_state w =
-		bch_writepage_state_init(c, to_bch_ei(mapping->host));
-	struct blk_plug plug;
-	int ret;
+	struct bch_writepage_state *w = kzalloc(sizeof(*w), GFP_NOFS|__GFP_NOFAIL);
 
-	blk_start_plug(&plug);
-	ret = write_cache_pages(mapping, wbc, __bch2_writepage, &w);
-	if (w.io)
-		bch2_writepage_do_io(&w);
-	blk_finish_plug(&plug);
-	kfree(w.tmp);
+	bch2_inode_opts_get(&w->opts, c, &to_bch_ei(mapping->host)->ei_inode);
+
+	blk_start_plug(&w->plug);
+	int ret = write_cache_pages(mapping, wbc, __bch2_writepage, w);
+	if (w->io)
+		bch2_writepage_do_io(w);
+	blk_finish_plug(&w->plug);
+	kfree(w->tmp);
+	kfree(w);
 	return bch2_err_class(ret);
 }
 
diff --git a/fs/bcachefs/fs-io-pagecache.c b/fs/bcachefs/fs-io-pagecache.c
index fbae9c1de746..c2cc405822f2 100644
--- a/fs/bcachefs/fs-io-pagecache.c
+++ b/fs/bcachefs/fs-io-pagecache.c
@@ -447,7 +447,7 @@ static int __bch2_folio_reservation_get(struct bch_fs *c,
 
 					if (!reserved) {
 						bch2_disk_reservation_put(c, &disk_res);
-						return -BCH_ERR_ENOSPC_disk_reservation;
+						return bch_err_throw(c, ENOSPC_disk_reservation);
 					}
 					break;
 				}
diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c
index b1e9ee28fc0f..a233f45875e9 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -71,12 +71,12 @@ void bch2_inode_flush_nocow_writes_async(struct bch_fs *c,
 	memset(&inode->ei_devs_need_flush, 0, sizeof(inode->ei_devs_need_flush));
 
 	for_each_set_bit(dev, devs.d, BCH_SB_MEMBERS_MAX) {
-		rcu_read_lock();
-		ca = rcu_dereference(c->devs[dev]);
-		if (ca && !enumerated_ref_tryget(&ca->io_ref[WRITE],
-					BCH_DEV_WRITE_REF_nocow_flush))
-			ca = NULL;
-		rcu_read_unlock();
+		scoped_guard(rcu) {
+			ca = rcu_dereference(c->devs[dev]);
+			if (ca && !enumerated_ref_tryget(&ca->io_ref[WRITE],
+							 BCH_DEV_WRITE_REF_nocow_flush))
+				ca = NULL;
+		}
 
 		if (!ca)
 			continue;
diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index 05361a793206..4e72e654da96 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -268,13 +268,13 @@ static long bch2_ioctl_subvolume_create(struct bch_fs *c, struct file *filp,
 	}
 
 	if (dst_dentry->d_inode) {
-		error = -BCH_ERR_EEXIST_subvolume_create;
+		error = bch_err_throw(c, EEXIST_subvolume_create);
 		goto err3;
 	}
 
 	dir = dst_path.dentry->d_inode;
 	if (IS_DEADDIR(dir)) {
-		error = -BCH_ERR_ENOENT_directory_dead;
+		error = bch_err_throw(c, ENOENT_directory_dead);
 		goto err3;
 	}
 
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index ddfe89d84966..85d13f800165 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -124,8 +124,9 @@ retry:
 		goto err;
 
 	struct bch_extent_rebalance new_r = bch2_inode_rebalance_opts_get(c, &inode_u);
+	bool rebalance_changed = memcmp(&old_r, &new_r, sizeof(new_r));
 
-	if (memcmp(&old_r, &new_r, sizeof(new_r))) {
+	if (rebalance_changed) {
 		ret = bch2_set_rebalance_needs_scan_trans(trans, inode_u.bi_inum);
 		if (ret)
 			goto err;
@@ -146,6 +147,9 @@ err:
 	if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
 		goto retry;
 
+	if (rebalance_changed)
+		bch2_rebalance_wakeup(c);
+
 	bch2_fs_fatal_err_on(bch2_err_matches(ret, ENOENT), c,
 			     "%s: inode %llu:%llu not found when updating",
 			     bch2_err_str(ret),
@@ -1569,11 +1573,12 @@ static int bch2_vfs_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct bch_inode_info *inode = file_bch_inode(file);
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
+	struct bch_hash_info hash = bch2_hash_info_init(c, &inode->ei_inode);
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
 
-	int ret = bch2_readdir(c, inode_inum(inode), ctx);
+	int ret = bch2_readdir(c, inode_inum(inode), &hash, ctx);
 
 	bch_err_fn(c, ret);
 	return bch2_err_class(ret);
@@ -2002,14 +2007,14 @@ retry:
 			goto err;
 
 		if (k.k->type != KEY_TYPE_dirent) {
-			ret = -BCH_ERR_ENOENT_dirent_doesnt_match_inode;
+			ret = bch_err_throw(c, ENOENT_dirent_doesnt_match_inode);
 			goto err;
 		}
 
 		d = bkey_s_c_to_dirent(k);
 		ret = bch2_dirent_read_target(trans, inode_inum(dir), d, &target);
 		if (ret > 0)
-			ret = -BCH_ERR_ENOENT_dirent_doesnt_match_inode;
+			ret = bch_err_throw(c, ENOENT_dirent_doesnt_match_inode);
 		if (ret)
 			goto err;
 
@@ -2175,7 +2180,13 @@ static void bch2_evict_inode(struct inode *vinode)
 				KEY_TYPE_QUOTA_WARN);
 		bch2_quota_acct(c, inode->ei_qid, Q_INO, -1,
 				KEY_TYPE_QUOTA_WARN);
-		bch2_inode_rm(c, inode_inum(inode));
+		int ret = bch2_inode_rm(c, inode_inum(inode));
+		if (ret && !bch2_err_matches(ret, EROFS)) {
+			bch_err_msg(c, ret, "VFS incorrectly tried to delete inode %llu:%llu",
+				    inode->ei_inum.subvol,
+				    inode->ei_inum.inum);
+			bch2_sb_error_count(c, BCH_FSCK_ERR_vfs_bad_inode_rm);
+		}
 
 		/*
 		 * If we are deleting, we need it present in the vfs hash table
@@ -2322,14 +2333,13 @@ static int bch2_show_devname(struct seq_file *seq, struct dentry *root)
 	struct bch_fs *c = root->d_sb->s_fs_info;
 	bool first = true;
 
-	rcu_read_lock();
+	guard(rcu)();
 	for_each_online_member_rcu(c, ca) {
 		if (!first)
 			seq_putc(seq, ':');
 		first = false;
 		seq_puts(seq, ca->disk_sb.sb_name);
 	}
-	rcu_read_unlock();
 
 	return 0;
 }
@@ -2526,16 +2536,16 @@ got_sb:
 
 	sb->s_bdi->ra_pages		= VM_READAHEAD_PAGES;
 
-	rcu_read_lock();
-	for_each_online_member_rcu(c, ca) {
-		struct block_device *bdev = ca->disk_sb.bdev;
+	scoped_guard(rcu) {
+		for_each_online_member_rcu(c, ca) {
+			struct block_device *bdev = ca->disk_sb.bdev;
 
-		/* XXX: create an anonymous device for multi device filesystems */
-		sb->s_bdev	= bdev;
-		sb->s_dev	= bdev->bd_dev;
-		break;
+			/* XXX: create an anonymous device for multi device filesystems */
+			sb->s_bdev	= bdev;
+			sb->s_dev	= bdev->bd_dev;
+			break;
+		}
 	}
-	rcu_read_unlock();
 
 	c->dev = sb->s_dev;
 
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 49f46df8340e..68ed69a255e1 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -23,14 +23,15 @@
 #include <linux/bsearch.h>
 #include <linux/dcache.h> /* struct qstr */
 
-static int dirent_points_to_inode_nowarn(struct bkey_s_c_dirent d,
+static int dirent_points_to_inode_nowarn(struct bch_fs *c,
+					 struct bkey_s_c_dirent d,
 					 struct bch_inode_unpacked *inode)
 {
 	if (d.v->d_type == DT_SUBVOL
 	    ? le32_to_cpu(d.v->d_child_subvol)	== inode->bi_subvol
 	    : le64_to_cpu(d.v->d_inum)		== inode->bi_inum)
 		return 0;
-	return -BCH_ERR_ENOENT_dirent_doesnt_match_inode;
+	return bch_err_throw(c, ENOENT_dirent_doesnt_match_inode);
 }
 
 static void dirent_inode_mismatch_msg(struct printbuf *out,
@@ -49,7 +50,7 @@ static int dirent_points_to_inode(struct bch_fs *c,
 				  struct bkey_s_c_dirent dirent,
 				  struct bch_inode_unpacked *inode)
 {
-	int ret = dirent_points_to_inode_nowarn(dirent, inode);
+	int ret = dirent_points_to_inode_nowarn(c, dirent, inode);
 	if (ret) {
 		struct printbuf buf = PRINTBUF;
 		dirent_inode_mismatch_msg(&buf, c, dirent, inode);
@@ -152,7 +153,7 @@ static int find_snapshot_tree_subvol(struct btree_trans *trans,
 			goto found;
 		}
 	}
-	ret = -BCH_ERR_ENOENT_no_snapshot_tree_subvol;
+	ret = bch_err_throw(trans->c, ENOENT_no_snapshot_tree_subvol);
 found:
 	bch2_trans_iter_exit(trans, &iter);
 	return ret;
@@ -229,7 +230,7 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot,
 
 	if (d_type != DT_DIR) {
 		bch_err(c, "error looking up lost+found: not a directory");
-		return -BCH_ERR_ENOENT_not_directory;
+		return bch_err_throw(c, ENOENT_not_directory);
 	}
 
 	/*
@@ -531,7 +532,7 @@ static int reconstruct_subvol(struct btree_trans *trans, u32 snapshotid, u32 sub
 
 	if (!bch2_snapshot_is_leaf(c, snapshotid)) {
 		bch_err(c, "need to reconstruct subvol, but have interior node snapshot");
-		return -BCH_ERR_fsck_repair_unimplemented;
+		return bch_err_throw(c, fsck_repair_unimplemented);
 	}
 
 	/*
@@ -643,11 +644,6 @@ static int reconstruct_inode(struct btree_trans *trans, enum btree_id btree, u32
 	return __bch2_fsck_write_inode(trans, &new_inode);
 }
 
-struct snapshots_seen {
-	struct bpos			pos;
-	snapshot_id_list		ids;
-};
-
 static inline void snapshots_seen_exit(struct snapshots_seen *s)
 {
 	darray_exit(&s->ids);
@@ -890,14 +886,11 @@ lookup_inode_for_snapshot(struct btree_trans *trans, struct inode_walker *w, str
 {
 	struct bch_fs *c = trans->c;
 
-	struct inode_walker_entry *i;
-	__darray_for_each(w->inodes, i)
-		if (bch2_snapshot_is_ancestor(c, k.k->p.snapshot, i->inode.bi_snapshot))
-			goto found;
+	struct inode_walker_entry *i = darray_find_p(w->inodes, i,
+		    bch2_snapshot_is_ancestor(c, k.k->p.snapshot, i->inode.bi_snapshot));
 
-	return NULL;
-found:
-	BUG_ON(k.k->p.snapshot > i->inode.bi_snapshot);
+	if (!i)
+		return NULL;
 
 	struct printbuf buf = PRINTBUF;
 	int ret = 0;
@@ -947,7 +940,7 @@ found:
 		if (ret)
 			goto fsck_err;
 
-		ret = -BCH_ERR_transaction_restart_nested;
+		ret = bch_err_throw(c, transaction_restart_nested);
 		goto fsck_err;
 	}
 
@@ -992,7 +985,8 @@ int bch2_fsck_update_backpointers(struct btree_trans *trans,
 	int ret = 0;
 
 	if (d->v.d_type == DT_SUBVOL) {
-		BUG();
+		bch_err(trans->c, "%s does not support DT_SUBVOL", __func__);
+		ret = -BCH_ERR_fsck_repair_unimplemented;
 	} else {
 		ret = get_visible_inodes(trans, &target, s, le64_to_cpu(d->v.d_inum));
 		if (ret)
@@ -1048,7 +1042,7 @@ static int check_inode_dirent_inode(struct btree_trans *trans,
 	if (ret && !bch2_err_matches(ret, ENOENT))
 		return ret;
 
-	if ((ret || dirent_points_to_inode_nowarn(d, inode)) &&
+	if ((ret || dirent_points_to_inode_nowarn(c, d, inode)) &&
 	    inode->bi_subvol &&
 	    (inode->bi_flags & BCH_INODE_has_child_snapshot)) {
 		/* Older version of a renamed subvolume root: we won't have a
@@ -1069,7 +1063,7 @@ static int check_inode_dirent_inode(struct btree_trans *trans,
 			trans, inode_points_to_missing_dirent,
 			"inode points to missing dirent\n%s",
 			(bch2_inode_unpacked_to_text(&buf, inode), buf.buf)) ||
-	    fsck_err_on(!ret && dirent_points_to_inode_nowarn(d, inode),
+	    fsck_err_on(!ret && dirent_points_to_inode_nowarn(c, d, inode),
 			trans, inode_points_to_wrong_dirent,
 			"%s",
 			(printbuf_reset(&buf),
@@ -1174,6 +1168,14 @@ static int check_inode(struct btree_trans *trans,
 		ret = 0;
 	}
 
+	if (fsck_err_on(S_ISDIR(u.bi_mode) && u.bi_size,
+			trans, inode_dir_has_nonzero_i_size,
+			"directory %llu:%u with nonzero i_size %lli",
+			u.bi_inum, u.bi_snapshot, u.bi_size)) {
+		u.bi_size = 0;
+		do_update = true;
+	}
+
 	ret = bch2_inode_has_child_snapshots(trans, k.k->p);
 	if (ret < 0)
 		goto err;
@@ -1452,7 +1454,7 @@ static int check_key_has_inode(struct btree_trans *trans,
 			goto err;
 
 		inode->last_pos.inode--;
-		ret = -BCH_ERR_transaction_restart_nested;
+		ret = bch_err_throw(c, transaction_restart_nested);
 		goto err;
 	}
 
@@ -1569,7 +1571,7 @@ static int extent_ends_at(struct bch_fs *c,
 			      sizeof(seen->ids.data[0]) * seen->ids.size,
 			      GFP_KERNEL);
 	if (!n.seen.ids.data)
-		return -BCH_ERR_ENOMEM_fsck_extent_ends_at;
+		return bch_err_throw(c, ENOMEM_fsck_extent_ends_at);
 
 	__darray_for_each(extent_ends->e, i) {
 		if (i->snapshot == k.k->p.snapshot) {
@@ -1619,7 +1621,7 @@ static int overlapping_extents_found(struct btree_trans *trans,
 
 		bch_err(c, "%s: error finding first overlapping extent when repairing, got%s",
 			__func__, buf.buf);
-		ret = -BCH_ERR_internal_fsck_err;
+		ret = bch_err_throw(c, internal_fsck_err);
 		goto err;
 	}
 
@@ -1644,7 +1646,7 @@ static int overlapping_extents_found(struct btree_trans *trans,
 	    pos2.size != k2.k->size) {
 		bch_err(c, "%s: error finding seconding overlapping extent when repairing%s",
 			__func__, buf.buf);
-		ret = -BCH_ERR_internal_fsck_err;
+		ret = bch_err_throw(c, internal_fsck_err);
 		goto err;
 	}
 
@@ -1692,7 +1694,7 @@ static int overlapping_extents_found(struct btree_trans *trans,
 			 * We overwrote the second extent - restart
 			 * check_extent() from the top:
 			 */
-			ret = -BCH_ERR_transaction_restart_nested;
+			ret = bch_err_throw(c, transaction_restart_nested);
 		}
 	}
 fsck_err:
@@ -2045,7 +2047,7 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter *
 			(bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf))) {
 		if (!new_parent_subvol) {
 			bch_err(c, "could not find a subvol for snapshot %u", d.k->p.snapshot);
-			return -BCH_ERR_fsck_repair_unimplemented;
+			return bch_err_throw(c, fsck_repair_unimplemented);
 		}
 
 		struct bkey_i_dirent *new_dirent = bch2_bkey_make_mut_typed(trans, iter, &d.s_c, 0, dirent);
@@ -2107,7 +2109,7 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter *
 
 	if (ret) {
 		bch_err(c, "subvol %u points to missing inode root %llu", target_subvol, target_inum);
-		ret = -BCH_ERR_fsck_repair_unimplemented;
+		ret = bch_err_throw(c, fsck_repair_unimplemented);
 		goto err;
 	}
 
@@ -2139,7 +2141,8 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
 			struct bch_hash_info *hash_info,
 			struct inode_walker *dir,
 			struct inode_walker *target,
-			struct snapshots_seen *s)
+			struct snapshots_seen *s,
+			bool *need_second_pass)
 {
 	struct bch_fs *c = trans->c;
 	struct inode_walker_entry *i;
@@ -2181,7 +2184,12 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
 		*hash_info = bch2_hash_info_init(c, &i->inode);
 	dir->first_this_inode = false;
 
-	ret = bch2_str_hash_check_key(trans, s, &bch2_dirent_hash_desc, hash_info, iter, k);
+#ifdef CONFIG_UNICODE
+	hash_info->cf_encoding = bch2_inode_casefold(c, &i->inode) ? c->cf_encoding : NULL;
+#endif
+
+	ret = bch2_str_hash_check_key(trans, s, &bch2_dirent_hash_desc, hash_info,
+				      iter, k, need_second_pass);
 	if (ret < 0)
 		goto err;
 	if (ret) {
@@ -2202,31 +2210,34 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
 			(printbuf_reset(&buf),
 			 bch2_bkey_val_to_text(&buf, c, k),
 			 buf.buf))) {
-		struct qstr name = bch2_dirent_get_name(d);
-		u32 subvol = d.v->d_type == DT_SUBVOL
-			? le32_to_cpu(d.v->d_parent_subvol)
-			: 0;
+		subvol_inum dir_inum = { .subvol = d.v->d_type == DT_SUBVOL
+				? le32_to_cpu(d.v->d_parent_subvol)
+				: 0,
+		};
 		u64 target = d.v->d_type == DT_SUBVOL
 			? le32_to_cpu(d.v->d_child_subvol)
 			: le64_to_cpu(d.v->d_inum);
-		u64 dir_offset;
+		struct qstr name = bch2_dirent_get_name(d);
+
+		struct bkey_i_dirent *new_d =
+			bch2_dirent_create_key(trans, hash_info, dir_inum,
+					       d.v->d_type, &name, NULL, target);
+		ret = PTR_ERR_OR_ZERO(new_d);
+		if (ret)
+			goto out;
 
-		ret =   bch2_hash_delete_at(trans,
+		new_d->k.p.inode	= d.k->p.inode;
+		new_d->k.p.snapshot	= d.k->p.snapshot;
+
+		struct btree_iter dup_iter = {};
+		ret =	bch2_hash_delete_at(trans,
 					    bch2_dirent_hash_desc, hash_info, iter,
 					    BTREE_UPDATE_internal_snapshot_node) ?:
-			bch2_dirent_create_snapshot(trans, subvol,
-						    d.k->p.inode, d.k->p.snapshot,
-						    hash_info,
-						    d.v->d_type,
-						    &name,
-						    target,
-						    &dir_offset,
-						    BTREE_ITER_with_updates|
-						    BTREE_UPDATE_internal_snapshot_node|
-						    STR_HASH_must_create) ?:
-			bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
-
-		/* might need another check_dirents pass */
+			bch2_str_hash_repair_key(trans, s,
+						 &bch2_dirent_hash_desc, hash_info,
+						 iter, bkey_i_to_s_c(&new_d->k_i),
+						 &dup_iter, bkey_s_c_null,
+						 need_second_pass);
 		goto out;
 	}
 
@@ -2294,7 +2305,6 @@ out:
 err:
 fsck_err:
 	printbuf_exit(&buf);
-	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -2308,16 +2318,31 @@ int bch2_check_dirents(struct bch_fs *c)
 	struct inode_walker target = inode_walker_init();
 	struct snapshots_seen s;
 	struct bch_hash_info hash_info;
+	bool need_second_pass = false, did_second_pass = false;
+	int ret;
 
 	snapshots_seen_init(&s);
-
-	int ret = bch2_trans_run(c,
-		for_each_btree_key(trans, iter, BTREE_ID_dirents,
+again:
+	ret = bch2_trans_run(c,
+		for_each_btree_key_commit(trans, iter, BTREE_ID_dirents,
 				POS(BCACHEFS_ROOT_INO, 0),
 				BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k,
-			check_dirent(trans, &iter, k, &hash_info, &dir, &target, &s)) ?:
+				NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
+			check_dirent(trans, &iter, k, &hash_info, &dir, &target, &s,
+				     &need_second_pass)) ?:
 		check_subdir_count_notnested(trans, &dir));
 
+	if (!ret && need_second_pass && !did_second_pass) {
+		bch_info(c, "check_dirents requires second pass");
+		swap(did_second_pass, need_second_pass);
+		goto again;
+	}
+
+	if (!ret && need_second_pass) {
+		bch_err(c, "dirents not repairing");
+		ret = -EINVAL;
+	}
+
 	snapshots_seen_exit(&s);
 	inode_walker_exit(&dir);
 	inode_walker_exit(&target);
@@ -2331,16 +2356,14 @@ static int check_xattr(struct btree_trans *trans, struct btree_iter *iter,
 		       struct inode_walker *inode)
 {
 	struct bch_fs *c = trans->c;
-	struct inode_walker_entry *i;
-	int ret;
 
-	ret = bch2_check_key_has_snapshot(trans, iter, k);
+	int ret = bch2_check_key_has_snapshot(trans, iter, k);
 	if (ret < 0)
 		return ret;
 	if (ret)
 		return 0;
 
-	i = walk_inode(trans, inode, k);
+	struct inode_walker_entry *i = walk_inode(trans, inode, k);
 	ret = PTR_ERR_OR_ZERO(i);
 	if (ret)
 		return ret;
@@ -2356,9 +2379,9 @@ static int check_xattr(struct btree_trans *trans, struct btree_iter *iter,
 		*hash_info = bch2_hash_info_init(c, &i->inode);
 	inode->first_this_inode = false;
 
-	ret = bch2_str_hash_check_key(trans, NULL, &bch2_xattr_hash_desc, hash_info, iter, k);
-	bch_err_fn(c, ret);
-	return ret;
+	bool need_second_pass = false;
+	return bch2_str_hash_check_key(trans, NULL, &bch2_xattr_hash_desc, hash_info,
+				      iter, k, &need_second_pass);
 }
 
 /*
@@ -2747,7 +2770,7 @@ static int add_nlink(struct bch_fs *c, struct nlink_table *t,
 		if (!d) {
 			bch_err(c, "fsck: error allocating memory for nlink_table, size %zu",
 				new_size);
-			return -BCH_ERR_ENOMEM_fsck_add_nlink;
+			return bch_err_throw(c, ENOMEM_fsck_add_nlink);
 		}
 
 		if (t->d)
diff --git a/fs/bcachefs/fsck.h b/fs/bcachefs/fsck.h
index 574948278cd4..e5fe7cf7b251 100644
--- a/fs/bcachefs/fsck.h
+++ b/fs/bcachefs/fsck.h
@@ -4,6 +4,12 @@
 
 #include "str_hash.h"
 
+/* recoverds snapshot IDs of overwrites at @pos */
+struct snapshots_seen {
+	struct bpos			pos;
+	snapshot_id_list		ids;
+};
+
 int bch2_fsck_update_backpointers(struct btree_trans *,
 				  struct snapshots_seen *,
 				  const struct bch_hash_desc,
diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index 5cf70108ae2f..53e5dc1f6ac1 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -38,6 +38,7 @@ static const char * const bch2_inode_flag_strs[] = {
 #undef  x
 
 static int delete_ancestor_snapshot_inodes(struct btree_trans *, struct bpos);
+static int may_delete_deleted_inum(struct btree_trans *, subvol_inum);
 
 static const u8 byte_table[8] = { 1, 2, 3, 4, 6, 8, 10, 13 };
 
@@ -1041,7 +1042,7 @@ again:
 		goto found_slot;
 
 	if (!ret && start == min)
-		ret = -BCH_ERR_ENOSPC_inode_create;
+		ret = bch_err_throw(trans->c, ENOSPC_inode_create);
 
 	if (ret) {
 		bch2_trans_iter_exit(trans, iter);
@@ -1130,19 +1131,23 @@ int bch2_inode_rm(struct bch_fs *c, subvol_inum inum)
 	u32 snapshot;
 	int ret;
 
+	ret = lockrestart_do(trans, may_delete_deleted_inum(trans, inum));
+	if (ret)
+		goto err2;
+
 	/*
 	 * If this was a directory, there shouldn't be any real dirents left -
 	 * but there could be whiteouts (from hash collisions) that we should
 	 * delete:
 	 *
-	 * XXX: the dirent could ideally would delete whiteouts when they're no
+	 * XXX: the dirent code ideally would delete whiteouts when they're no
 	 * longer needed
 	 */
 	ret   = bch2_inode_delete_keys(trans, inum, BTREE_ID_extents) ?:
 		bch2_inode_delete_keys(trans, inum, BTREE_ID_xattrs) ?:
 		bch2_inode_delete_keys(trans, inum, BTREE_ID_dirents);
 	if (ret)
-		goto err;
+		goto err2;
 retry:
 	bch2_trans_begin(trans);
 
@@ -1161,7 +1166,7 @@ retry:
 		bch2_fs_inconsistent(c,
 				     "inode %llu:%u not found when deleting",
 				     inum.inum, snapshot);
-		ret = -BCH_ERR_ENOENT_inode;
+		ret = bch_err_throw(c, ENOENT_inode);
 		goto err;
 	}
 
@@ -1328,7 +1333,7 @@ retry:
 		bch2_fs_inconsistent(c,
 				     "inode %llu:%u not found when deleting",
 				     inum, snapshot);
-		ret = -BCH_ERR_ENOENT_inode;
+		ret = bch_err_throw(c, ENOENT_inode);
 		goto err;
 	}
 
@@ -1392,10 +1397,8 @@ int bch2_inode_rm_snapshot(struct btree_trans *trans, u64 inum, u32 snapshot)
 		delete_ancestor_snapshot_inodes(trans, SPOS(0, inum, snapshot));
 }
 
-static int may_delete_deleted_inode(struct btree_trans *trans,
-				    struct btree_iter *iter,
-				    struct bpos pos,
-				    bool *need_another_pass)
+static int may_delete_deleted_inode(struct btree_trans *trans, struct bpos pos,
+				    bool from_deleted_inodes)
 {
 	struct bch_fs *c = trans->c;
 	struct btree_iter inode_iter;
@@ -1409,12 +1412,14 @@ static int may_delete_deleted_inode(struct btree_trans *trans,
 	if (ret)
 		return ret;
 
-	ret = bkey_is_inode(k.k) ? 0 : -BCH_ERR_ENOENT_inode;
-	if (fsck_err_on(!bkey_is_inode(k.k),
+	ret = bkey_is_inode(k.k) ? 0 : bch_err_throw(c, ENOENT_inode);
+	if (fsck_err_on(from_deleted_inodes && ret,
 			trans, deleted_inode_missing,
 			"nonexistent inode %llu:%u in deleted_inodes btree",
 			pos.offset, pos.snapshot))
 		goto delete;
+	if (ret)
+		goto out;
 
 	ret = bch2_inode_unpack(k, &inode);
 	if (ret)
@@ -1422,7 +1427,8 @@ static int may_delete_deleted_inode(struct btree_trans *trans,
 
 	if (S_ISDIR(inode.bi_mode)) {
 		ret = bch2_empty_dir_snapshot(trans, pos.offset, 0, pos.snapshot);
-		if (fsck_err_on(bch2_err_matches(ret, ENOTEMPTY),
+		if (fsck_err_on(from_deleted_inodes &&
+				bch2_err_matches(ret, ENOTEMPTY),
 				trans, deleted_inode_is_dir,
 				"non empty directory %llu:%u in deleted_inodes btree",
 				pos.offset, pos.snapshot))
@@ -1431,17 +1437,25 @@ static int may_delete_deleted_inode(struct btree_trans *trans,
 			goto out;
 	}
 
-	if (fsck_err_on(!(inode.bi_flags & BCH_INODE_unlinked),
+	ret = inode.bi_flags & BCH_INODE_unlinked ? 0 : bch_err_throw(c, inode_not_unlinked);
+	if (fsck_err_on(from_deleted_inodes && ret,
 			trans, deleted_inode_not_unlinked,
 			"non-deleted inode %llu:%u in deleted_inodes btree",
 			pos.offset, pos.snapshot))
 		goto delete;
+	if (ret)
+		goto out;
 
-	if (fsck_err_on(inode.bi_flags & BCH_INODE_has_child_snapshot,
+	ret = !(inode.bi_flags & BCH_INODE_has_child_snapshot)
+		? 0 : bch_err_throw(c, inode_has_child_snapshot);
+
+	if (fsck_err_on(from_deleted_inodes && ret,
 			trans, deleted_inode_has_child_snapshots,
 			"inode with child snapshots %llu:%u in deleted_inodes btree",
 			pos.offset, pos.snapshot))
 		goto delete;
+	if (ret)
+		goto out;
 
 	ret = bch2_inode_has_child_snapshots(trans, k.k->p);
 	if (ret < 0)
@@ -1458,19 +1472,28 @@ static int may_delete_deleted_inode(struct btree_trans *trans,
 			if (ret)
 				goto out;
 		}
+
+		if (!from_deleted_inodes) {
+			ret =   bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?:
+				bch_err_throw(c, inode_has_child_snapshot);
+			goto out;
+		}
+
 		goto delete;
 
 	}
 
-	if (test_bit(BCH_FS_clean_recovery, &c->flags) &&
-	    !fsck_err(trans, deleted_inode_but_clean,
-		      "filesystem marked as clean but have deleted inode %llu:%u",
-		      pos.offset, pos.snapshot)) {
-		ret = 0;
-		goto out;
-	}
+	if (from_deleted_inodes) {
+		if (test_bit(BCH_FS_clean_recovery, &c->flags) &&
+		    !fsck_err(trans, deleted_inode_but_clean,
+			      "filesystem marked as clean but have deleted inode %llu:%u",
+			      pos.offset, pos.snapshot)) {
+			ret = 0;
+			goto out;
+		}
 
-	ret = 1;
+		ret = 1;
+	}
 out:
 fsck_err:
 	bch2_trans_iter_exit(trans, &inode_iter);
@@ -1481,12 +1504,19 @@ delete:
 	goto out;
 }
 
+static int may_delete_deleted_inum(struct btree_trans *trans, subvol_inum inum)
+{
+	u32 snapshot;
+
+	return bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot) ?:
+		may_delete_deleted_inode(trans, SPOS(0, inum.inum, snapshot), false);
+}
+
 int bch2_delete_dead_inodes(struct bch_fs *c)
 {
 	struct btree_trans *trans = bch2_trans_get(c);
-	bool need_another_pass;
 	int ret;
-again:
+
 	/*
 	 * if we ran check_inodes() unlinked inodes will have already been
 	 * cleaned up but the write buffer will be out of sync; therefore we
@@ -1496,8 +1526,6 @@ again:
 	if (ret)
 		goto err;
 
-	need_another_pass = false;
-
 	/*
 	 * Weird transaction restart handling here because on successful delete,
 	 * bch2_inode_rm_snapshot() will return a nested transaction restart,
@@ -1507,7 +1535,7 @@ again:
 	ret = for_each_btree_key_commit(trans, iter, BTREE_ID_deleted_inodes, POS_MIN,
 					BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k,
 					NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({
-		ret = may_delete_deleted_inode(trans, &iter, k.k->p, &need_another_pass);
+		ret = may_delete_deleted_inode(trans, k.k->p, true);
 		if (ret > 0) {
 			bch_verbose_ratelimited(c, "deleting unlinked inode %llu:%u",
 						k.k->p.offset, k.k->p.snapshot);
@@ -1528,10 +1556,8 @@ again:
 
 		ret;
 	}));
-
-	if (!ret && need_another_pass)
-		goto again;
 err:
 	bch2_trans_put(trans);
+	bch_err_fn(c, ret);
 	return ret;
 }
diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h
index 77ad2d549541..82cec2836cbd 100644
--- a/fs/bcachefs/inode.h
+++ b/fs/bcachefs/inode.h
@@ -283,15 +283,6 @@ static inline void bch2_inode_nlink_set(struct bch_inode_unpacked *bi,
 int bch2_inode_nlink_inc(struct bch_inode_unpacked *);
 void bch2_inode_nlink_dec(struct btree_trans *, struct bch_inode_unpacked *);
 
-static inline bool bch2_inode_should_have_single_bp(struct bch_inode_unpacked *inode)
-{
-	bool inode_has_bp = inode->bi_dir || inode->bi_dir_offset;
-
-	return S_ISDIR(inode->bi_mode) ||
-		inode->bi_subvol ||
-		(!inode->bi_nlink && inode_has_bp);
-}
-
 struct bch_opts bch2_inode_opts_to_opts(struct bch_inode_unpacked *);
 void bch2_inode_opts_get(struct bch_io_opts *, struct bch_fs *,
 			 struct bch_inode_unpacked *);
diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c
index cc07729a4b62..bf72b1d2e2cb 100644
--- a/fs/bcachefs/io_misc.c
+++ b/fs/bcachefs/io_misc.c
@@ -91,7 +91,7 @@ int bch2_extent_fallocate(struct btree_trans *trans,
 				opts.data_replicas,
 				BCH_WATERMARK_normal, 0, &cl, &wp);
 		if (bch2_err_matches(ret, BCH_ERR_operation_blocked))
-			ret = -BCH_ERR_transaction_restart_nested;
+			ret = bch_err_throw(c, transaction_restart_nested);
 		if (ret)
 			goto err;
 
diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c
index cc708d46557e..a77779afad01 100644
--- a/fs/bcachefs/io_read.c
+++ b/fs/bcachefs/io_read.c
@@ -56,7 +56,7 @@ static bool bch2_target_congested(struct bch_fs *c, u16 target)
 	if (!target)
 		return false;
 
-	rcu_read_lock();
+	guard(rcu)();
 	devs = bch2_target_to_mask(c, target) ?:
 		&c->rw_devs[BCH_DATA_user];
 
@@ -73,7 +73,6 @@ static bool bch2_target_congested(struct bch_fs *c, u16 target)
 		total += max(congested, 0LL);
 		nr++;
 	}
-	rcu_read_unlock();
 
 	return get_random_u32_below(nr * CONGESTED_MAX) < total;
 }
@@ -138,21 +137,21 @@ static inline int should_promote(struct bch_fs *c, struct bkey_s_c k,
 		BUG_ON(!opts.promote_target);
 
 		if (!(flags & BCH_READ_may_promote))
-			return -BCH_ERR_nopromote_may_not;
+			return bch_err_throw(c, nopromote_may_not);
 
 		if (bch2_bkey_has_target(c, k, opts.promote_target))
-			return -BCH_ERR_nopromote_already_promoted;
+			return bch_err_throw(c, nopromote_already_promoted);
 
 		if (bkey_extent_is_unwritten(k))
-			return -BCH_ERR_nopromote_unwritten;
+			return bch_err_throw(c, nopromote_unwritten);
 
 		if (bch2_target_congested(c, opts.promote_target))
-			return -BCH_ERR_nopromote_congested;
+			return bch_err_throw(c, nopromote_congested);
 	}
 
 	if (rhashtable_lookup_fast(&c->promote_table, &pos,
 				   bch_promote_params))
-		return -BCH_ERR_nopromote_in_flight;
+		return bch_err_throw(c, nopromote_in_flight);
 
 	return 0;
 }
@@ -240,7 +239,7 @@ static struct bch_read_bio *__promote_alloc(struct btree_trans *trans,
 
 	struct promote_op *op = kzalloc(sizeof(*op), GFP_KERNEL);
 	if (!op) {
-		ret = -BCH_ERR_nopromote_enomem;
+		ret = bch_err_throw(c, nopromote_enomem);
 		goto err_put;
 	}
 
@@ -249,7 +248,7 @@ static struct bch_read_bio *__promote_alloc(struct btree_trans *trans,
 
 	if (rhashtable_lookup_insert_fast(&c->promote_table, &op->hash,
 					  bch_promote_params)) {
-		ret = -BCH_ERR_nopromote_in_flight;
+		ret = bch_err_throw(c, nopromote_in_flight);
 		goto err;
 	}
 
@@ -545,7 +544,7 @@ retry:
 
 	if (!bkey_and_val_eq(k, bkey_i_to_s_c(u->k.k))) {
 		/* extent we wanted to read no longer exists: */
-		rbio->ret = -BCH_ERR_data_read_key_overwritten;
+		rbio->ret = bch_err_throw(trans->c, data_read_key_overwritten);
 		goto err;
 	}
 
@@ -1036,7 +1035,7 @@ int __bch2_read_extent(struct btree_trans *trans, struct bch_read_bio *orig,
 
 	if ((bch2_bkey_extent_flags(k) & BIT_ULL(BCH_EXTENT_FLAG_poisoned)) &&
 	    !orig->data_update)
-		return -BCH_ERR_extent_poisoned;
+		return bch_err_throw(c, extent_poisoned);
 retry_pick:
 	ret = bch2_bkey_pick_read_device(c, k, failed, &pick, dev);
 
@@ -1074,7 +1073,7 @@ retry_pick:
 
 		bch_err_ratelimited(c, "%s", buf.buf);
 		printbuf_exit(&buf);
-		ret = -BCH_ERR_data_read_no_encryption_key;
+		ret = bch_err_throw(c, data_read_no_encryption_key);
 		goto err;
 	}
 
@@ -1128,7 +1127,7 @@ retry_pick:
 			if (ca)
 				enumerated_ref_put(&ca->io_ref[READ],
 					BCH_DEV_READ_REF_io_read);
-			rbio->ret = -BCH_ERR_data_read_buffer_too_small;
+			rbio->ret = bch_err_throw(c, data_read_buffer_too_small);
 			goto out_read_done;
 		}
 
@@ -1333,7 +1332,7 @@ hole:
 	 * have to signal that:
 	 */
 	if (u)
-		orig->ret = -BCH_ERR_data_read_key_overwritten;
+		orig->ret = bch_err_throw(c, data_read_key_overwritten);
 
 	zero_fill_bio_iter(&orig->bio, iter);
 out_read_done:
@@ -1510,18 +1509,18 @@ int bch2_fs_io_read_init(struct bch_fs *c)
 					 c->opts.btree_node_size,
 					 c->opts.encoded_extent_max) /
 				   PAGE_SIZE, 0))
-		return -BCH_ERR_ENOMEM_bio_bounce_pages_init;
+		return bch_err_throw(c, ENOMEM_bio_bounce_pages_init);
 
 	if (bioset_init(&c->bio_read, 1, offsetof(struct bch_read_bio, bio),
 			BIOSET_NEED_BVECS))
-		return -BCH_ERR_ENOMEM_bio_read_init;
+		return bch_err_throw(c, ENOMEM_bio_read_init);
 
 	if (bioset_init(&c->bio_read_split, 1, offsetof(struct bch_read_bio, bio),
 			BIOSET_NEED_BVECS))
-		return -BCH_ERR_ENOMEM_bio_read_split_init;
+		return bch_err_throw(c, ENOMEM_bio_read_split_init);
 
 	if (rhashtable_init(&c->promote_table, &bch_promote_params))
-		return -BCH_ERR_ENOMEM_promote_table_init;
+		return bch_err_throw(c, ENOMEM_promote_table_init);
 
 	return 0;
 }
diff --git a/fs/bcachefs/io_read.h b/fs/bcachefs/io_read.h
index c08b9c047b3e..45c959018919 100644
--- a/fs/bcachefs/io_read.h
+++ b/fs/bcachefs/io_read.h
@@ -91,6 +91,8 @@ static inline int bch2_read_indirect_extent(struct btree_trans *trans,
 		return 0;
 
 	*data_btree = BTREE_ID_reflink;
+
+	struct bch_fs *c = trans->c;
 	struct btree_iter iter;
 	struct bkey_s_c k = bch2_lookup_indirect_extent(trans, &iter,
 						offset_into_extent,
@@ -102,10 +104,10 @@ static inline int bch2_read_indirect_extent(struct btree_trans *trans,
 
 	if (bkey_deleted(k.k)) {
 		bch2_trans_iter_exit(trans, &iter);
-		return -BCH_ERR_missing_indirect_extent;
+		return bch_err_throw(c, missing_indirect_extent);
 	}
 
-	bch2_bkey_buf_reassemble(extent, trans->c, k);
+	bch2_bkey_buf_reassemble(extent, c, k);
 	bch2_trans_iter_exit(trans, &iter);
 	return 0;
 }
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index 52a60982a66b..88b1eec8eff3 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -558,6 +558,7 @@ static void bch2_write_done(struct closure *cl)
 
 static noinline int bch2_write_drop_io_error_ptrs(struct bch_write_op *op)
 {
+	struct bch_fs *c = op->c;
 	struct keylist *keys = &op->insert_keys;
 	struct bkey_i *src, *dst = keys->keys, *n;
 
@@ -569,7 +570,7 @@ static noinline int bch2_write_drop_io_error_ptrs(struct bch_write_op *op)
 					    test_bit(ptr->dev, op->failed.d));
 
 			if (!bch2_bkey_nr_ptrs(bkey_i_to_s_c(src)))
-				return -BCH_ERR_data_write_io;
+				return bch_err_throw(c, data_write_io);
 		}
 
 		if (dst != src)
@@ -976,7 +977,7 @@ csum_err:
 		op->crc.csum_type < BCH_CSUM_NR
 		? __bch2_csum_types[op->crc.csum_type]
 		: "(unknown)");
-	return -BCH_ERR_data_write_csum;
+	return bch_err_throw(c, data_write_csum);
 }
 
 static int bch2_write_extent(struct bch_write_op *op, struct write_point *wp,
@@ -1208,16 +1209,13 @@ static bool bch2_extent_is_writeable(struct bch_write_op *op,
 
 	e = bkey_s_c_to_extent(k);
 
-	rcu_read_lock();
+	guard(rcu)();
 	extent_for_each_ptr_decode(e, p, entry) {
-		if (crc_is_encoded(p.crc) || p.has_ec) {
-			rcu_read_unlock();
+		if (crc_is_encoded(p.crc) || p.has_ec)
 			return false;
-		}
 
 		replicas += bch2_extent_ptr_durability(c, &p);
 	}
-	rcu_read_unlock();
 
 	return replicas >= op->opts.data_replicas;
 }
@@ -1290,7 +1288,7 @@ static void bch2_nocow_write_convert_unwritten(struct bch_write_op *op)
 static void __bch2_nocow_write_done(struct bch_write_op *op)
 {
 	if (unlikely(op->flags & BCH_WRITE_io_error)) {
-		op->error = -BCH_ERR_data_write_io;
+		op->error = bch_err_throw(op->c, data_write_io);
 	} else if (unlikely(op->flags & BCH_WRITE_convert_unwritten))
 		bch2_nocow_write_convert_unwritten(op);
 }
@@ -1483,10 +1481,10 @@ err_bucket_stale:
 				    "pointer to invalid bucket in nocow path on device %llu\n  %s",
 				    stale_at->b.inode,
 				    (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
-		ret = -BCH_ERR_data_write_invalid_ptr;
+		ret = bch_err_throw(c, data_write_invalid_ptr);
 	} else {
 		/* We can retry this: */
-		ret = -BCH_ERR_transaction_restart;
+		ret = bch_err_throw(c, transaction_restart);
 	}
 	printbuf_exit(&buf);
 
@@ -1693,18 +1691,18 @@ CLOSURE_CALLBACK(bch2_write)
 
 	if (unlikely(bio->bi_iter.bi_size & (c->opts.block_size - 1))) {
 		bch2_write_op_error(op, op->pos.offset, "misaligned write");
-		op->error = -BCH_ERR_data_write_misaligned;
+		op->error = bch_err_throw(c, data_write_misaligned);
 		goto err;
 	}
 
 	if (c->opts.nochanges) {
-		op->error = -BCH_ERR_erofs_no_writes;
+		op->error = bch_err_throw(c, erofs_no_writes);
 		goto err;
 	}
 
 	if (!(op->flags & BCH_WRITE_move) &&
 	    !enumerated_ref_tryget(&c->writes, BCH_WRITE_REF_write)) {
-		op->error = -BCH_ERR_erofs_no_writes;
+		op->error = bch_err_throw(c, erofs_no_writes);
 		goto err;
 	}
 
@@ -1776,7 +1774,7 @@ int bch2_fs_io_write_init(struct bch_fs *c)
 {
 	if (bioset_init(&c->bio_write,   1, offsetof(struct bch_write_bio, bio), BIOSET_NEED_BVECS) ||
 	    bioset_init(&c->replica_set, 4, offsetof(struct bch_write_bio, bio), 0))
-		return -BCH_ERR_ENOMEM_bio_write_init;
+		return bch_err_throw(c, ENOMEM_bio_write_init);
 
 	return 0;
 }
diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index 09b70fd140a1..dda802a656cf 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -397,7 +397,7 @@ static int journal_entry_open(struct journal *j)
 	BUG_ON(BCH_SB_CLEAN(c->disk_sb.sb));
 
 	if (j->blocked)
-		return -BCH_ERR_journal_blocked;
+		return bch_err_throw(c, journal_blocked);
 
 	if (j->cur_entry_error)
 		return j->cur_entry_error;
@@ -407,23 +407,23 @@ static int journal_entry_open(struct journal *j)
 		return ret;
 
 	if (!fifo_free(&j->pin))
-		return -BCH_ERR_journal_pin_full;
+		return bch_err_throw(c, journal_pin_full);
 
 	if (nr_unwritten_journal_entries(j) == ARRAY_SIZE(j->buf))
-		return -BCH_ERR_journal_max_in_flight;
+		return bch_err_throw(c, journal_max_in_flight);
 
 	if (atomic64_read(&j->seq) - j->seq_write_started == JOURNAL_STATE_BUF_NR)
-		return -BCH_ERR_journal_max_open;
+		return bch_err_throw(c, journal_max_open);
 
 	if (unlikely(journal_cur_seq(j) >= JOURNAL_SEQ_MAX)) {
 		bch_err(c, "cannot start: journal seq overflow");
 		if (bch2_fs_emergency_read_only_locked(c))
 			bch_err(c, "fatal error - emergency read only");
-		return -BCH_ERR_journal_shutdown;
+		return bch_err_throw(c, journal_shutdown);
 	}
 
 	if (!j->free_buf && !buf->data)
-		return -BCH_ERR_journal_buf_enomem; /* will retry after write completion frees up a buf */
+		return bch_err_throw(c, journal_buf_enomem); /* will retry after write completion frees up a buf */
 
 	BUG_ON(!j->cur_entry_sectors);
 
@@ -447,7 +447,7 @@ static int journal_entry_open(struct journal *j)
 	u64s = clamp_t(int, u64s, 0, JOURNAL_ENTRY_CLOSED_VAL - 1);
 
 	if (u64s <= (ssize_t) j->early_journal_entries.nr)
-		return -BCH_ERR_journal_full;
+		return bch_err_throw(c, journal_full);
 
 	if (fifo_empty(&j->pin) && j->reclaim_thread)
 		wake_up_process(j->reclaim_thread);
@@ -464,7 +464,7 @@ static int journal_entry_open(struct journal *j)
 			journal_cur_seq(j));
 		if (bch2_fs_emergency_read_only_locked(c))
 			bch_err(c, "fatal error - emergency read only");
-		return -BCH_ERR_journal_shutdown;
+		return bch_err_throw(c, journal_shutdown);
 	}
 
 	BUG_ON(j->pin.back - 1 != atomic64_read(&j->seq));
@@ -597,16 +597,16 @@ retry:
 		return ret;
 
 	if (j->blocked)
-		return -BCH_ERR_journal_blocked;
+		return bch_err_throw(c, journal_blocked);
 
 	if ((flags & BCH_WATERMARK_MASK) < j->watermark) {
-		ret = -BCH_ERR_journal_full;
+		ret = bch_err_throw(c, journal_full);
 		can_discard = j->can_discard;
 		goto out;
 	}
 
 	if (nr_unwritten_journal_entries(j) == ARRAY_SIZE(j->buf) && !journal_entry_is_open(j)) {
-		ret = -BCH_ERR_journal_max_in_flight;
+		ret = bch_err_throw(c, journal_max_in_flight);
 		goto out;
 	}
 
@@ -647,7 +647,7 @@ out:
 		goto retry;
 
 	if (journal_error_check_stuck(j, ret, flags))
-		ret = -BCH_ERR_journal_stuck;
+		ret = bch_err_throw(c, journal_stuck);
 
 	if (ret == -BCH_ERR_journal_max_in_flight &&
 	    track_event_change(&c->times[BCH_TIME_blocked_journal_max_in_flight], true) &&
@@ -708,10 +708,9 @@ static unsigned max_dev_latency(struct bch_fs *c)
 {
 	u64 nsecs = 0;
 
-	rcu_read_lock();
+	guard(rcu)();
 	for_each_rw_member_rcu(c, ca)
 		nsecs = max(nsecs, ca->io_latency[WRITE].stats.max_duration);
-	rcu_read_unlock();
 
 	return nsecs_to_jiffies(nsecs);
 }
@@ -813,6 +812,7 @@ out:
 int bch2_journal_flush_seq_async(struct journal *j, u64 seq,
 				 struct closure *parent)
 {
+	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct journal_buf *buf;
 	int ret = 0;
 
@@ -828,7 +828,7 @@ int bch2_journal_flush_seq_async(struct journal *j, u64 seq,
 
 	/* Recheck under lock: */
 	if (j->err_seq && seq >= j->err_seq) {
-		ret = -BCH_ERR_journal_flush_err;
+		ret = bch_err_throw(c, journal_flush_err);
 		goto out;
 	}
 
@@ -999,7 +999,7 @@ int bch2_journal_meta(struct journal *j)
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 
 	if (!enumerated_ref_tryget(&c->writes, BCH_WRITE_REF_journal))
-		return -BCH_ERR_erofs_no_writes;
+		return bch_err_throw(c, erofs_no_writes);
 
 	int ret = __bch2_journal_meta(j);
 	enumerated_ref_put(&c->writes, BCH_WRITE_REF_journal);
@@ -1132,7 +1132,7 @@ static int bch2_set_nr_journal_buckets_iter(struct bch_dev *ca, unsigned nr,
 	new_buckets	= kcalloc(nr, sizeof(u64), GFP_KERNEL);
 	new_bucket_seq	= kcalloc(nr, sizeof(u64), GFP_KERNEL);
 	if (!bu || !ob || !new_buckets || !new_bucket_seq) {
-		ret = -BCH_ERR_ENOMEM_set_nr_journal_buckets;
+		ret = bch_err_throw(c, ENOMEM_set_nr_journal_buckets);
 		goto err_free;
 	}
 
@@ -1304,6 +1304,66 @@ int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca,
 	return ret;
 }
 
+int bch2_dev_journal_bucket_delete(struct bch_dev *ca, u64 b)
+{
+	struct bch_fs *c = ca->fs;
+	struct journal *j = &c->journal;
+	struct journal_device *ja = &ca->journal;
+
+	guard(mutex)(&c->sb_lock);
+	unsigned pos;
+	for (pos = 0; pos < ja->nr; pos++)
+		if (ja->buckets[pos] == b)
+			break;
+
+	if (pos == ja->nr) {
+		bch_err(ca, "journal bucket %llu not found when deleting", b);
+		return -EINVAL;
+	}
+
+	u64 *new_buckets = kcalloc(ja->nr, sizeof(u64), GFP_KERNEL);;
+	if (!new_buckets)
+		return bch_err_throw(c, ENOMEM_set_nr_journal_buckets);
+
+	memcpy(new_buckets, ja->buckets, ja->nr * sizeof(u64));
+	memmove(&new_buckets[pos],
+		&new_buckets[pos + 1],
+		(ja->nr - 1 - pos) * sizeof(new_buckets[0]));
+
+	int ret = bch2_journal_buckets_to_sb(c, ca, ja->buckets, ja->nr - 1) ?:
+		bch2_write_super(c);
+	if (ret) {
+		kfree(new_buckets);
+		return ret;
+	}
+
+	scoped_guard(spinlock, &j->lock) {
+		if (pos < ja->discard_idx)
+			--ja->discard_idx;
+		if (pos < ja->dirty_idx_ondisk)
+			--ja->dirty_idx_ondisk;
+		if (pos < ja->dirty_idx)
+			--ja->dirty_idx;
+		if (pos < ja->cur_idx)
+			--ja->cur_idx;
+
+		ja->nr--;
+
+		memmove(&ja->buckets[pos],
+			&ja->buckets[pos + 1],
+			(ja->nr - pos) * sizeof(ja->buckets[0]));
+
+		memmove(&ja->bucket_seq[pos],
+			&ja->bucket_seq[pos + 1],
+			(ja->nr - pos) * sizeof(ja->bucket_seq[0]));
+
+		bch2_journal_space_available(j);
+	}
+
+	kfree(new_buckets);
+	return 0;
+}
+
 int bch2_dev_journal_alloc(struct bch_dev *ca, bool new_fs)
 {
 	struct bch_fs *c = ca->fs;
@@ -1313,14 +1373,14 @@ int bch2_dev_journal_alloc(struct bch_dev *ca, bool new_fs)
 
 	if (c->sb.features & BIT_ULL(BCH_FEATURE_small_image)) {
 		bch_err(c, "cannot allocate journal, filesystem is an unresized image file");
-		return -BCH_ERR_erofs_filesystem_full;
+		return bch_err_throw(c, erofs_filesystem_full);
 	}
 
 	unsigned nr;
 	int ret;
 
 	if (dynamic_fault("bcachefs:add:journal_alloc")) {
-		ret = -BCH_ERR_ENOMEM_set_nr_journal_buckets;
+		ret = bch_err_throw(c, ENOMEM_set_nr_journal_buckets);
 		goto err;
 	}
 
@@ -1459,7 +1519,7 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
 	init_fifo(&j->pin, roundup_pow_of_two(nr), GFP_KERNEL);
 	if (!j->pin.data) {
 		bch_err(c, "error reallocating journal fifo (%llu open entries)", nr);
-		return -BCH_ERR_ENOMEM_journal_pin_fifo;
+		return bch_err_throw(c, ENOMEM_journal_pin_fifo);
 	}
 
 	j->replay_journal_seq	= last_seq;
@@ -1547,6 +1607,7 @@ void bch2_dev_journal_exit(struct bch_dev *ca)
 
 int bch2_dev_journal_init(struct bch_dev *ca, struct bch_sb *sb)
 {
+	struct bch_fs *c = ca->fs;
 	struct journal_device *ja = &ca->journal;
 	struct bch_sb_field_journal *journal_buckets =
 		bch2_sb_field_get(sb, journal);
@@ -1566,7 +1627,7 @@ int bch2_dev_journal_init(struct bch_dev *ca, struct bch_sb *sb)
 
 	ja->bucket_seq = kcalloc(ja->nr, sizeof(u64), GFP_KERNEL);
 	if (!ja->bucket_seq)
-		return -BCH_ERR_ENOMEM_dev_journal_init;
+		return bch_err_throw(c, ENOMEM_dev_journal_init);
 
 	unsigned nr_bvecs = DIV_ROUND_UP(JOURNAL_ENTRY_SIZE_MAX, PAGE_SIZE);
 
@@ -1574,7 +1635,7 @@ int bch2_dev_journal_init(struct bch_dev *ca, struct bch_sb *sb)
 		ja->bio[i] = kzalloc(struct_size(ja->bio[i], bio.bi_inline_vecs,
 				     nr_bvecs), GFP_KERNEL);
 		if (!ja->bio[i])
-			return -BCH_ERR_ENOMEM_dev_journal_init;
+			return bch_err_throw(c, ENOMEM_dev_journal_init);
 
 		ja->bio[i]->ca = ca;
 		ja->bio[i]->buf_idx = i;
@@ -1583,7 +1644,7 @@ int bch2_dev_journal_init(struct bch_dev *ca, struct bch_sb *sb)
 
 	ja->buckets = kcalloc(ja->nr, sizeof(u64), GFP_KERNEL);
 	if (!ja->buckets)
-		return -BCH_ERR_ENOMEM_dev_journal_init;
+		return bch_err_throw(c, ENOMEM_dev_journal_init);
 
 	if (journal_buckets_v2) {
 		unsigned nr = bch2_sb_field_journal_v2_nr_entries(journal_buckets_v2);
@@ -1637,10 +1698,12 @@ void bch2_fs_journal_init_early(struct journal *j)
 
 int bch2_fs_journal_init(struct journal *j)
 {
+	struct bch_fs *c = container_of(j, struct bch_fs, journal);
+
 	j->free_buf_size = j->buf_size_want = JOURNAL_ENTRY_SIZE_MIN;
 	j->free_buf = kvmalloc(j->free_buf_size, GFP_KERNEL);
 	if (!j->free_buf)
-		return -BCH_ERR_ENOMEM_journal_buf;
+		return bch_err_throw(c, ENOMEM_journal_buf);
 
 	for (unsigned i = 0; i < ARRAY_SIZE(j->buf); i++)
 		j->buf[i].idx = i;
@@ -1648,7 +1711,7 @@ int bch2_fs_journal_init(struct journal *j)
 	j->wq = alloc_workqueue("bcachefs_journal",
 				WQ_HIGHPRI|WQ_FREEZABLE|WQ_UNBOUND|WQ_MEM_RECLAIM, 512);
 	if (!j->wq)
-		return -BCH_ERR_ENOMEM_fs_other_alloc;
+		return bch_err_throw(c, ENOMEM_fs_other_alloc);
 	return 0;
 }
 
@@ -1672,7 +1735,7 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j)
 	printbuf_tabstop_push(out, 28);
 	out->atomic++;
 
-	rcu_read_lock();
+	guard(rcu)();
 	s = READ_ONCE(j->reservations);
 
 	prt_printf(out, "flags:\t");
@@ -1763,8 +1826,6 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j)
 
 	prt_printf(out, "replicas want %u need %u\n", c->opts.metadata_replicas, c->opts.metadata_replicas_required);
 
-	rcu_read_unlock();
-
 	--out->atomic;
 }
 
diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h
index 8ff00a0ec778..83734fe4331f 100644
--- a/fs/bcachefs/journal.h
+++ b/fs/bcachefs/journal.h
@@ -444,8 +444,9 @@ struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *, u
 void __bch2_journal_debug_to_text(struct printbuf *, struct journal *);
 void bch2_journal_debug_to_text(struct printbuf *, struct journal *);
 
-int bch2_set_nr_journal_buckets(struct bch_fs *, struct bch_dev *,
-				unsigned nr);
+int bch2_set_nr_journal_buckets(struct bch_fs *, struct bch_dev *, unsigned);
+int bch2_dev_journal_bucket_delete(struct bch_dev *, u64);
+
 int bch2_dev_journal_alloc(struct bch_dev *, bool);
 int bch2_fs_journal_alloc(struct bch_fs *);
 
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 63bb207208b2..0b15d71a8d2d 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -49,25 +49,27 @@ void bch2_journal_pos_from_member_info_resume(struct bch_fs *c)
 	mutex_unlock(&c->sb_lock);
 }
 
-void bch2_journal_ptrs_to_text(struct printbuf *out, struct bch_fs *c,
-			       struct journal_replay *j)
+static void bch2_journal_ptr_to_text(struct printbuf *out, struct bch_fs *c, struct journal_ptr *p)
+{
+	struct bch_dev *ca = bch2_dev_tryget_noerror(c, p->dev);
+	prt_printf(out, "%s %u:%u:%u (sector %llu)",
+		   ca ? ca->name : "(invalid dev)",
+		   p->dev, p->bucket, p->bucket_offset, p->sector);
+	bch2_dev_put(ca);
+}
+
+void bch2_journal_ptrs_to_text(struct printbuf *out, struct bch_fs *c, struct journal_replay *j)
 {
 	darray_for_each(j->ptrs, i) {
 		if (i != j->ptrs.data)
 			prt_printf(out, " ");
-		prt_printf(out, "%u:%u:%u (sector %llu)",
-			   i->dev, i->bucket, i->bucket_offset, i->sector);
+		bch2_journal_ptr_to_text(out, c, i);
 	}
 }
 
-static void bch2_journal_replay_to_text(struct printbuf *out, struct bch_fs *c,
-					struct journal_replay *j)
+static void bch2_journal_datetime_to_text(struct printbuf *out, struct jset *j)
 {
-	prt_printf(out, "seq %llu ", le64_to_cpu(j->j.seq));
-
-	bch2_journal_ptrs_to_text(out, c, j);
-
-	for_each_jset_entry_type(entry, &j->j, BCH_JSET_ENTRY_datetime) {
+	for_each_jset_entry_type(entry, j, BCH_JSET_ENTRY_datetime) {
 		struct jset_entry_datetime *datetime =
 			container_of(entry, struct jset_entry_datetime, entry);
 		bch2_prt_datetime(out, le64_to_cpu(datetime->seconds));
@@ -75,6 +77,15 @@ static void bch2_journal_replay_to_text(struct printbuf *out, struct bch_fs *c,
 	}
 }
 
+static void bch2_journal_replay_to_text(struct printbuf *out, struct bch_fs *c,
+					struct journal_replay *j)
+{
+	prt_printf(out, "seq %llu ", le64_to_cpu(j->j.seq));
+	bch2_journal_datetime_to_text(out, &j->j);
+	prt_char(out, ' ');
+	bch2_journal_ptrs_to_text(out, c, j);
+}
+
 static struct nonce journal_nonce(const struct jset *jset)
 {
 	return (struct nonce) {{
@@ -188,7 +199,7 @@ static int journal_entry_add(struct bch_fs *c, struct bch_dev *ca,
 				journal_entry_radix_idx(c, le64_to_cpu(j->seq)),
 				GFP_KERNEL);
 	if (!_i)
-		return -BCH_ERR_ENOMEM_journal_entry_add;
+		return bch_err_throw(c, ENOMEM_journal_entry_add);
 
 	/*
 	 * Duplicate journal entries? If so we want the one that didn't have a
@@ -231,7 +242,7 @@ static int journal_entry_add(struct bch_fs *c, struct bch_dev *ca,
 replace:
 	i = kvmalloc(offsetof(struct journal_replay, j) + bytes, GFP_KERNEL);
 	if (!i)
-		return -BCH_ERR_ENOMEM_journal_entry_add;
+		return bch_err_throw(c, ENOMEM_journal_entry_add);
 
 	darray_init(&i->ptrs);
 	i->csum_good		= entry_ptr.csum_good;
@@ -311,7 +322,7 @@ static void journal_entry_err_msg(struct printbuf *out,
 		bch2_sb_error_count(c, BCH_FSCK_ERR_##_err);		\
 		if (bch2_fs_inconsistent(c,				\
 				"corrupt metadata before write: %s\n", _buf.buf)) {\
-			ret = -BCH_ERR_fsck_errors_not_fixed;		\
+			ret = bch_err_throw(c, fsck_errors_not_fixed);		\
 			goto fsck_err;					\
 		}							\
 		break;							\
@@ -418,6 +429,10 @@ static void journal_entry_btree_keys_to_text(struct printbuf *out, struct bch_fs
 	bool first = true;
 
 	jset_entry_for_each_key(entry, k) {
+		/* We may be called on entries that haven't been validated: */
+		if (!k->k.u64s)
+			break;
+
 		if (!first) {
 			prt_newline(out);
 			bch2_prt_jset_entry_type(out, entry->type);
@@ -1005,19 +1020,19 @@ struct journal_read_buf {
 	size_t		size;
 };
 
-static int journal_read_buf_realloc(struct journal_read_buf *b,
+static int journal_read_buf_realloc(struct bch_fs *c, struct journal_read_buf *b,
 				    size_t new_size)
 {
 	void *n;
 
 	/* the bios are sized for this many pages, max: */
 	if (new_size > JOURNAL_ENTRY_SIZE_MAX)
-		return -BCH_ERR_ENOMEM_journal_read_buf_realloc;
+		return bch_err_throw(c, ENOMEM_journal_read_buf_realloc);
 
 	new_size = roundup_pow_of_two(new_size);
 	n = kvmalloc(new_size, GFP_KERNEL);
 	if (!n)
-		return -BCH_ERR_ENOMEM_journal_read_buf_realloc;
+		return bch_err_throw(c, ENOMEM_journal_read_buf_realloc);
 
 	kvfree(b->data);
 	b->data = n;
@@ -1037,7 +1052,6 @@ static int journal_read_bucket(struct bch_dev *ca,
 	u64 offset = bucket_to_sector(ca, ja->buckets[bucket]),
 	    end = offset + ca->mi.bucket_size;
 	bool saw_bad = false, csum_good;
-	struct printbuf err = PRINTBUF;
 	int ret = 0;
 
 	pr_debug("reading %u", bucket);
@@ -1053,7 +1067,7 @@ reread:
 
 			bio = bio_kmalloc(nr_bvecs, GFP_KERNEL);
 			if (!bio)
-				return -BCH_ERR_ENOMEM_journal_read_bucket;
+				return bch_err_throw(c, ENOMEM_journal_read_bucket);
 			bio_init(bio, ca->disk_sb.bdev, bio->bi_inline_vecs, nr_bvecs, REQ_OP_READ);
 
 			bio->bi_iter.bi_sector = offset;
@@ -1064,7 +1078,7 @@ reread:
 			kfree(bio);
 
 			if (!ret && bch2_meta_read_fault("journal"))
-				ret = -BCH_ERR_EIO_fault_injected;
+				ret = bch_err_throw(c, EIO_fault_injected);
 
 			bch2_account_io_completion(ca, BCH_MEMBER_ERROR_read,
 						   submit_time, !ret);
@@ -1078,7 +1092,7 @@ reread:
 				 * found on a different device, and missing or
 				 * no journal entries will be handled later
 				 */
-				goto out;
+				return 0;
 			}
 
 			j = buf->data;
@@ -1092,15 +1106,15 @@ reread:
 			break;
 		case JOURNAL_ENTRY_REREAD:
 			if (vstruct_bytes(j) > buf->size) {
-				ret = journal_read_buf_realloc(buf,
+				ret = journal_read_buf_realloc(c, buf,
 							vstruct_bytes(j));
 				if (ret)
-					goto err;
+					return ret;
 			}
 			goto reread;
 		case JOURNAL_ENTRY_NONE:
 			if (!saw_bad)
-				goto out;
+				return 0;
 			/*
 			 * On checksum error we don't really trust the size
 			 * field of the journal entry we read, so try reading
@@ -1109,7 +1123,7 @@ reread:
 			sectors = block_sectors(c);
 			goto next_block;
 		default:
-			goto err;
+			return ret;
 		}
 
 		if (le64_to_cpu(j->seq) > ja->highest_seq_found) {
@@ -1126,22 +1140,20 @@ reread:
 		 * bucket:
 		 */
 		if (le64_to_cpu(j->seq) < ja->bucket_seq[bucket])
-			goto out;
+			return 0;
 
 		ja->bucket_seq[bucket] = le64_to_cpu(j->seq);
 
-		enum bch_csum_type csum_type = JSET_CSUM_TYPE(j);
 		struct bch_csum csum;
 		csum_good = jset_csum_good(c, j, &csum);
 
 		bch2_account_io_completion(ca, BCH_MEMBER_ERROR_checksum, 0, csum_good);
 
 		if (!csum_good) {
-			bch_err_dev_ratelimited(ca, "%s",
-				(printbuf_reset(&err),
-				 prt_str(&err, "journal "),
-				 bch2_csum_err_msg(&err, csum_type, j->csum, csum),
-				 err.buf));
+			/*
+			 * Don't print an error here, we'll print the error
+			 * later if we need this journal entry
+			 */
 			saw_bad = true;
 		}
 
@@ -1153,6 +1165,7 @@ reread:
 		mutex_lock(&jlist->lock);
 		ret = journal_entry_add(c, ca, (struct journal_ptr) {
 					.csum_good	= csum_good,
+					.csum		= csum,
 					.dev		= ca->dev_idx,
 					.bucket		= bucket,
 					.bucket_offset	= offset -
@@ -1167,7 +1180,7 @@ reread:
 		case JOURNAL_ENTRY_ADD_OUT_OF_RANGE:
 			break;
 		default:
-			goto err;
+			return ret;
 		}
 next_block:
 		pr_debug("next");
@@ -1176,11 +1189,7 @@ next_block:
 		j = ((void *) j) + (sectors << 9);
 	}
 
-out:
-	ret = 0;
-err:
-	printbuf_exit(&err);
-	return ret;
+	return 0;
 }
 
 static CLOSURE_CALLBACK(bch2_journal_read_device)
@@ -1197,7 +1206,7 @@ static CLOSURE_CALLBACK(bch2_journal_read_device)
 	if (!ja->nr)
 		goto out;
 
-	ret = journal_read_buf_realloc(&buf, PAGE_SIZE);
+	ret = journal_read_buf_realloc(c, &buf, PAGE_SIZE);
 	if (ret)
 		goto err;
 
@@ -1229,13 +1238,105 @@ err:
 	goto out;
 }
 
+noinline_for_stack
+static void bch2_journal_print_checksum_error(struct bch_fs *c, struct journal_replay *j)
+{
+	struct printbuf buf = PRINTBUF;
+	enum bch_csum_type csum_type = JSET_CSUM_TYPE(&j->j);
+	bool have_good = false;
+
+	prt_printf(&buf, "invalid journal checksum(s) at seq %llu ", le64_to_cpu(j->j.seq));
+	bch2_journal_datetime_to_text(&buf, &j->j);
+	prt_newline(&buf);
+
+	darray_for_each(j->ptrs, ptr)
+		if (!ptr->csum_good) {
+			bch2_journal_ptr_to_text(&buf, c, ptr);
+			prt_char(&buf, ' ');
+			bch2_csum_to_text(&buf, csum_type, ptr->csum);
+			prt_newline(&buf);
+		} else {
+			have_good = true;
+		}
+
+	prt_printf(&buf, "should be ");
+	bch2_csum_to_text(&buf, csum_type, j->j.csum);
+
+	if (have_good)
+		prt_printf(&buf, "\n(had good copy on another device)");
+
+	bch2_print_str(c, KERN_ERR, buf.buf);
+	printbuf_exit(&buf);
+}
+
+noinline_for_stack
+static int bch2_journal_check_for_missing(struct bch_fs *c, u64 start_seq, u64 end_seq)
+{
+	struct printbuf buf = PRINTBUF;
+	int ret = 0;
+
+	struct genradix_iter radix_iter;
+	struct journal_replay *i, **_i, *prev = NULL;
+	u64 seq = start_seq;
+
+	genradix_for_each(&c->journal_entries, radix_iter, _i) {
+		i = *_i;
+
+		if (journal_replay_ignore(i))
+			continue;
+
+		BUG_ON(seq > le64_to_cpu(i->j.seq));
+
+		while (seq < le64_to_cpu(i->j.seq)) {
+			while (seq < le64_to_cpu(i->j.seq) &&
+			       bch2_journal_seq_is_blacklisted(c, seq, false))
+				seq++;
+
+			if (seq == le64_to_cpu(i->j.seq))
+				break;
+
+			u64 missing_start = seq;
+
+			while (seq < le64_to_cpu(i->j.seq) &&
+			       !bch2_journal_seq_is_blacklisted(c, seq, false))
+				seq++;
+
+			u64 missing_end = seq - 1;
+
+			printbuf_reset(&buf);
+			prt_printf(&buf, "journal entries %llu-%llu missing! (replaying %llu-%llu)",
+				   missing_start, missing_end,
+				   start_seq, end_seq);
+
+			prt_printf(&buf, "\nprev at ");
+			if (prev) {
+				bch2_journal_ptrs_to_text(&buf, c, prev);
+				prt_printf(&buf, " size %zu", vstruct_sectors(&prev->j, c->block_bits));
+			} else
+				prt_printf(&buf, "(none)");
+
+			prt_printf(&buf, "\nnext at ");
+			bch2_journal_ptrs_to_text(&buf, c, i);
+			prt_printf(&buf, ", continue?");
+
+			fsck_err(c, journal_entries_missing, "%s", buf.buf);
+		}
+
+		prev = i;
+		seq++;
+	}
+fsck_err:
+	printbuf_exit(&buf);
+	return ret;
+}
+
 int bch2_journal_read(struct bch_fs *c,
 		      u64 *last_seq,
 		      u64 *blacklist_seq,
 		      u64 *start_seq)
 {
 	struct journal_list jlist;
-	struct journal_replay *i, **_i, *prev = NULL;
+	struct journal_replay *i, **_i;
 	struct genradix_iter radix_iter;
 	struct printbuf buf = PRINTBUF;
 	bool degraded = false, last_write_torn = false;
@@ -1326,12 +1427,12 @@ int bch2_journal_read(struct bch_fs *c,
 		return 0;
 	}
 
-	bch_info(c, "journal read done, replaying entries %llu-%llu",
-		 *last_seq, *blacklist_seq - 1);
-
+	printbuf_reset(&buf);
+	prt_printf(&buf, "journal read done, replaying entries %llu-%llu",
+		   *last_seq, *blacklist_seq - 1);
 	if (*start_seq != *blacklist_seq)
-		bch_info(c, "dropped unflushed entries %llu-%llu",
-			 *blacklist_seq, *start_seq - 1);
+		prt_printf(&buf, " (unflushed %llu-%llu)", *blacklist_seq, *start_seq - 1);
+	bch_info(c, "%s", buf.buf);
 
 	/* Drop blacklisted entries and entries older than last_seq: */
 	genradix_for_each(&c->journal_entries, radix_iter, _i) {
@@ -1354,56 +1455,9 @@ int bch2_journal_read(struct bch_fs *c,
 		}
 	}
 
-	/* Check for missing entries: */
-	seq = *last_seq;
-	genradix_for_each(&c->journal_entries, radix_iter, _i) {
-		i = *_i;
-
-		if (journal_replay_ignore(i))
-			continue;
-
-		BUG_ON(seq > le64_to_cpu(i->j.seq));
-
-		while (seq < le64_to_cpu(i->j.seq)) {
-			u64 missing_start, missing_end;
-			struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF;
-
-			while (seq < le64_to_cpu(i->j.seq) &&
-			       bch2_journal_seq_is_blacklisted(c, seq, false))
-				seq++;
-
-			if (seq == le64_to_cpu(i->j.seq))
-				break;
-
-			missing_start = seq;
-
-			while (seq < le64_to_cpu(i->j.seq) &&
-			       !bch2_journal_seq_is_blacklisted(c, seq, false))
-				seq++;
-
-			if (prev) {
-				bch2_journal_ptrs_to_text(&buf1, c, prev);
-				prt_printf(&buf1, " size %zu", vstruct_sectors(&prev->j, c->block_bits));
-			} else
-				prt_printf(&buf1, "(none)");
-			bch2_journal_ptrs_to_text(&buf2, c, i);
-
-			missing_end = seq - 1;
-			fsck_err(c, journal_entries_missing,
-				 "journal entries %llu-%llu missing! (replaying %llu-%llu)\n"
-				 "prev at %s\n"
-				 "next at %s, continue?",
-				 missing_start, missing_end,
-				 *last_seq, *blacklist_seq - 1,
-				 buf1.buf, buf2.buf);
-
-			printbuf_exit(&buf1);
-			printbuf_exit(&buf2);
-		}
-
-		prev = i;
-		seq++;
-	}
+	ret = bch2_journal_check_for_missing(c, *last_seq, *blacklist_seq - 1);
+	if (ret)
+		goto err;
 
 	genradix_for_each(&c->journal_entries, radix_iter, _i) {
 		union bch_replicas_padded replicas = {
@@ -1416,15 +1470,15 @@ int bch2_journal_read(struct bch_fs *c,
 		if (journal_replay_ignore(i))
 			continue;
 
-		darray_for_each(i->ptrs, ptr) {
-			struct bch_dev *ca = bch2_dev_have_ref(c, ptr->dev);
-
-			if (!ptr->csum_good)
-				bch_err_dev_offset(ca, ptr->sector,
-						   "invalid journal checksum, seq %llu%s",
-						   le64_to_cpu(i->j.seq),
-						   i->csum_good ? " (had good copy on another device)" : "");
-		}
+		/*
+		 * Don't print checksum errors until we know we're going to use
+		 * a given journal entry:
+		 */
+		darray_for_each(i->ptrs, ptr)
+			if (!ptr->csum_good) {
+				bch2_journal_print_checksum_error(c, i);
+				break;
+			}
 
 		ret = jset_validate(c,
 				    bch2_dev_have_ref(c, i->ptrs.data[0].dev),
@@ -1467,7 +1521,7 @@ static void journal_advance_devs_to_next_bucket(struct journal *j,
 {
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 
-	rcu_read_lock();
+	guard(rcu)();
 	darray_for_each(*devs, i) {
 		struct bch_dev *ca = rcu_dereference(c->devs[*i]);
 		if (!ca)
@@ -1489,7 +1543,6 @@ static void journal_advance_devs_to_next_bucket(struct journal *j,
 			ja->bucket_seq[ja->cur_idx] = le64_to_cpu(seq);
 		}
 	}
-	rcu_read_unlock();
 }
 
 static void __journal_write_alloc(struct journal *j,
@@ -1559,7 +1612,7 @@ static int journal_write_alloc(struct journal *j, struct journal_buf *w,
 
 retry_target:
 	devs = target_rw_devs(c, BCH_DATA_journal, target);
-	devs_sorted = bch2_dev_alloc_list(c, &j->wp.stripe, &devs);
+	bch2_dev_alloc_list(c, &j->wp.stripe, &devs, &devs_sorted);
 retry_alloc:
 	__journal_write_alloc(j, w, &devs_sorted, sectors, replicas, replicas_want);
 
@@ -1581,6 +1634,16 @@ retry_alloc:
 done:
 	BUG_ON(bkey_val_u64s(&w->key.k) > BCH_REPLICAS_MAX);
 
+#if 0
+	/*
+	 * XXX: we need a way to alert the user when we go degraded for any
+	 * reason
+	 */
+	if (*replicas < min(replicas_want,
+			    dev_mask_nr(&c->rw_devs[BCH_DATA_free]))) {
+	}
+#endif
+
 	return *replicas >= replicas_need ? 0 : -BCH_ERR_insufficient_journal_devices;
 }
 
@@ -1628,7 +1691,7 @@ static CLOSURE_CALLBACK(journal_write_done)
 			       : j->noflush_write_time, j->write_start_time);
 
 	if (!w->devs_written.nr) {
-		err = -BCH_ERR_journal_write_err;
+		err = bch_err_throw(c, journal_write_err);
 	} else {
 		bch2_devlist_to_replicas(&replicas.e, BCH_DATA_journal,
 					 w->devs_written);
@@ -2058,7 +2121,7 @@ CLOSURE_CALLBACK(bch2_journal_write)
 	struct journal *j = container_of(w, struct journal, buf[w->idx]);
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	union bch_replicas_padded replicas;
-	unsigned nr_rw_members = dev_mask_nr(&c->rw_devs[BCH_DATA_journal]);
+	unsigned nr_rw_members = dev_mask_nr(&c->rw_devs[BCH_DATA_free]);
 	int ret;
 
 	BUG_ON(BCH_SB_CLEAN(c->disk_sb.sb));
diff --git a/fs/bcachefs/journal_io.h b/fs/bcachefs/journal_io.h
index 12b39fcb4424..6fa82c4050fe 100644
--- a/fs/bcachefs/journal_io.h
+++ b/fs/bcachefs/journal_io.h
@@ -9,6 +9,7 @@ void bch2_journal_pos_from_member_info_resume(struct bch_fs *);
 
 struct journal_ptr {
 	bool		csum_good;
+	struct bch_csum	csum;
 	u8		dev;
 	u32		bucket;
 	u32		bucket_offset;
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index 70f36f6bc482..cd6201741c59 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -83,18 +83,20 @@ static struct journal_space
 journal_dev_space_available(struct journal *j, struct bch_dev *ca,
 			    enum journal_space_from from)
 {
+	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct journal_device *ja = &ca->journal;
 	unsigned sectors, buckets, unwritten;
+	unsigned bucket_size_aligned = round_down(ca->mi.bucket_size, block_sectors(c));
 	u64 seq;
 
 	if (from == journal_space_total)
 		return (struct journal_space) {
-			.next_entry	= ca->mi.bucket_size,
-			.total		= ca->mi.bucket_size * ja->nr,
+			.next_entry	= bucket_size_aligned,
+			.total		= bucket_size_aligned * ja->nr,
 		};
 
 	buckets = bch2_journal_dev_buckets_available(j, ja, from);
-	sectors = ja->sectors_free;
+	sectors = round_down(ja->sectors_free, block_sectors(c));
 
 	/*
 	 * We that we don't allocate the space for a journal entry
@@ -109,7 +111,7 @@ journal_dev_space_available(struct journal *j, struct bch_dev *ca,
 			continue;
 
 		/* entry won't fit on this device, skip: */
-		if (unwritten > ca->mi.bucket_size)
+		if (unwritten > bucket_size_aligned)
 			continue;
 
 		if (unwritten >= sectors) {
@@ -119,7 +121,7 @@ journal_dev_space_available(struct journal *j, struct bch_dev *ca,
 			}
 
 			buckets--;
-			sectors = ca->mi.bucket_size;
+			sectors = bucket_size_aligned;
 		}
 
 		sectors -= unwritten;
@@ -127,12 +129,12 @@ journal_dev_space_available(struct journal *j, struct bch_dev *ca,
 
 	if (sectors < ca->mi.bucket_size && buckets) {
 		buckets--;
-		sectors = ca->mi.bucket_size;
+		sectors = bucket_size_aligned;
 	}
 
 	return (struct journal_space) {
 		.next_entry	= sectors,
-		.total		= sectors + buckets * ca->mi.bucket_size,
+		.total		= sectors + buckets * bucket_size_aligned,
 	};
 }
 
@@ -146,7 +148,6 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne
 
 	BUG_ON(nr_devs_want > ARRAY_SIZE(dev_space));
 
-	rcu_read_lock();
 	for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal]) {
 		if (!ca->journal.nr ||
 		    !ca->mi.durability)
@@ -164,7 +165,6 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne
 
 		array_insert_item(dev_space, nr_devs, pos, space);
 	}
-	rcu_read_unlock();
 
 	if (nr_devs < nr_devs_want)
 		return (struct journal_space) { 0, 0 };
@@ -189,8 +189,8 @@ void bch2_journal_space_available(struct journal *j)
 	int ret = 0;
 
 	lockdep_assert_held(&j->lock);
+	guard(rcu)();
 
-	rcu_read_lock();
 	for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal]) {
 		struct journal_device *ja = &ca->journal;
 
@@ -210,7 +210,6 @@ void bch2_journal_space_available(struct journal *j)
 		max_entry_size = min_t(unsigned, max_entry_size, ca->mi.bucket_size);
 		nr_online++;
 	}
-	rcu_read_unlock();
 
 	j->can_discard = can_discard;
 
@@ -221,15 +220,13 @@ void bch2_journal_space_available(struct journal *j)
 			prt_printf(&buf, "insufficient writeable journal devices available: have %u, need %u\n"
 				   "rw journal devs:", nr_online, metadata_replicas_required(c));
 
-			rcu_read_lock();
 			for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal])
 				prt_printf(&buf, " %s", ca->name);
-			rcu_read_unlock();
 
 			bch_err(c, "%s", buf.buf);
 			printbuf_exit(&buf);
 		}
-		ret = -BCH_ERR_insufficient_journal_devices;
+		ret = bch_err_throw(c, insufficient_journal_devices);
 		goto out;
 	}
 
@@ -243,7 +240,7 @@ void bch2_journal_space_available(struct journal *j)
 	total		= j->space[journal_space_total].total;
 
 	if (!j->space[journal_space_discarded].next_entry)
-		ret = -BCH_ERR_journal_full;
+		ret = bch_err_throw(c, journal_full);
 
 	if ((j->space[journal_space_clean_ondisk].next_entry <
 	     j->space[journal_space_clean_ondisk].total) &&
@@ -256,8 +253,7 @@ void bch2_journal_space_available(struct journal *j)
 	bch2_journal_set_watermark(j);
 out:
 	j->cur_entry_sectors	= !ret
-		? round_down(j->space[journal_space_discarded].next_entry,
-			     block_sectors(c))
+		? j->space[journal_space_discarded].next_entry
 		: 0;
 	j->cur_entry_error	= ret;
 
@@ -625,9 +621,9 @@ static u64 journal_seq_to_flush(struct journal *j)
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	u64 seq_to_flush = 0;
 
-	spin_lock(&j->lock);
+	guard(spinlock)(&j->lock);
+	guard(rcu)();
 
-	rcu_read_lock();
 	for_each_rw_member_rcu(c, ca) {
 		struct journal_device *ja = &ca->journal;
 		unsigned nr_buckets, bucket_to_flush;
@@ -642,15 +638,11 @@ static u64 journal_seq_to_flush(struct journal *j)
 		seq_to_flush = max(seq_to_flush,
 				   ja->bucket_seq[bucket_to_flush]);
 	}
-	rcu_read_unlock();
 
 	/* Also flush if the pin fifo is more than half full */
-	seq_to_flush = max_t(s64, seq_to_flush,
-			     (s64) journal_cur_seq(j) -
-			     (j->pin.size >> 1));
-	spin_unlock(&j->lock);
-
-	return seq_to_flush;
+	return max_t(s64, seq_to_flush,
+		     (s64) journal_cur_seq(j) -
+		     (j->pin.size >> 1));
 }
 
 /**
diff --git a/fs/bcachefs/journal_sb.c b/fs/bcachefs/journal_sb.c
index 62b910f2fb27..0cb9b93f13e7 100644
--- a/fs/bcachefs/journal_sb.c
+++ b/fs/bcachefs/journal_sb.c
@@ -210,7 +210,7 @@ int bch2_journal_buckets_to_sb(struct bch_fs *c, struct bch_dev *ca,
 	j = bch2_sb_field_resize(&ca->disk_sb, journal_v2,
 			 (sizeof(*j) + sizeof(j->d[0]) * nr_compacted) / sizeof(u64));
 	if (!j)
-		return -BCH_ERR_ENOSPC_sb_journal;
+		return bch_err_throw(c, ENOSPC_sb_journal);
 
 	bch2_sb_field_delete(&ca->disk_sb, BCH_SB_FIELD_journal);
 
diff --git a/fs/bcachefs/journal_seq_blacklist.c b/fs/bcachefs/journal_seq_blacklist.c
index c5a7d800a0f5..af4fe416d9ec 100644
--- a/fs/bcachefs/journal_seq_blacklist.c
+++ b/fs/bcachefs/journal_seq_blacklist.c
@@ -78,7 +78,7 @@ int bch2_journal_seq_blacklist_add(struct bch_fs *c, u64 start, u64 end)
 	bl = bch2_sb_field_resize(&c->disk_sb, journal_seq_blacklist,
 				  sb_blacklist_u64s(nr + 1));
 	if (!bl) {
-		ret = -BCH_ERR_ENOSPC_sb_journal_seq_blacklist;
+		ret = bch_err_throw(c, ENOSPC_sb_journal_seq_blacklist);
 		goto out;
 	}
 
@@ -152,7 +152,7 @@ int bch2_blacklist_table_initialize(struct bch_fs *c)
 
 	t = kzalloc(struct_size(t, entries, nr), GFP_KERNEL);
 	if (!t)
-		return -BCH_ERR_ENOMEM_blacklist_table_init;
+		return bch_err_throw(c, ENOMEM_blacklist_table_init);
 
 	t->nr = nr;
 
diff --git a/fs/bcachefs/lru.c b/fs/bcachefs/lru.c
index 2f63fc6d456f..57b5b3263b08 100644
--- a/fs/bcachefs/lru.c
+++ b/fs/bcachefs/lru.c
@@ -145,13 +145,11 @@ static u64 bkey_lru_type_idx(struct bch_fs *c,
 	case BCH_LRU_fragmentation: {
 		a = bch2_alloc_to_v4(k, &a_convert);
 
-		rcu_read_lock();
+		guard(rcu)();
 		struct bch_dev *ca = bch2_dev_rcu_noerror(c, k.k->p.inode);
-		u64 idx = ca
+		return ca
 			? alloc_lru_idx_fragmentation(*a, ca)
 			: 0;
-		rcu_read_unlock();
-		return idx;
 	}
 	case BCH_LRU_stripes:
 		return k.k->type == KEY_TYPE_stripe
diff --git a/fs/bcachefs/migrate.c b/fs/bcachefs/migrate.c
index bb7a92270c09..f296cce95338 100644
--- a/fs/bcachefs/migrate.c
+++ b/fs/bcachefs/migrate.c
@@ -35,7 +35,7 @@ static int drop_dev_ptrs(struct bch_fs *c, struct bkey_s k,
 	nr_good = bch2_bkey_durability(c, k.s_c);
 	if ((!nr_good && !(flags & lost)) ||
 	    (nr_good < replicas && !(flags & degraded)))
-		return -BCH_ERR_remove_would_lose_data;
+		return bch_err_throw(c, remove_would_lose_data);
 
 	return 0;
 }
@@ -156,7 +156,7 @@ static int bch2_dev_metadata_drop(struct bch_fs *c,
 
 	/* don't handle this yet: */
 	if (flags & BCH_FORCE_IF_METADATA_LOST)
-		return -BCH_ERR_remove_with_metadata_missing_unimplemented;
+		return bch_err_throw(c, remove_with_metadata_missing_unimplemented);
 
 	trans = bch2_trans_get(c);
 	bch2_bkey_buf_init(&k);
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index 79f4722621d5..eec591e947bd 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -38,30 +38,74 @@ const char * const bch2_data_ops_strs[] = {
 	NULL
 };
 
-static void trace_io_move2(struct bch_fs *c, struct bkey_s_c k,
-			       struct bch_io_opts *io_opts,
-			       struct data_update_opts *data_opts)
+struct evacuate_bucket_arg {
+	struct bpos		bucket;
+	int			gen;
+	struct data_update_opts	data_opts;
+};
+
+static bool evacuate_bucket_pred(struct bch_fs *, void *,
+				 enum btree_id, struct bkey_s_c,
+				 struct bch_io_opts *,
+				 struct data_update_opts *);
+
+static noinline void
+trace_io_move2(struct bch_fs *c, struct bkey_s_c k,
+	       struct bch_io_opts *io_opts,
+	       struct data_update_opts *data_opts)
 {
-	if (trace_io_move_enabled()) {
-		struct printbuf buf = PRINTBUF;
+	struct printbuf buf = PRINTBUF;
 
-		bch2_bkey_val_to_text(&buf, c, k);
-		prt_newline(&buf);
-		bch2_data_update_opts_to_text(&buf, c, io_opts, data_opts);
-		trace_io_move(c, buf.buf);
-		printbuf_exit(&buf);
-	}
+	bch2_bkey_val_to_text(&buf, c, k);
+	prt_newline(&buf);
+	bch2_data_update_opts_to_text(&buf, c, io_opts, data_opts);
+	trace_io_move(c, buf.buf);
+	printbuf_exit(&buf);
 }
 
-static void trace_io_move_read2(struct bch_fs *c, struct bkey_s_c k)
+static noinline void trace_io_move_read2(struct bch_fs *c, struct bkey_s_c k)
 {
-	if (trace_io_move_read_enabled()) {
-		struct printbuf buf = PRINTBUF;
+	struct printbuf buf = PRINTBUF;
 
-		bch2_bkey_val_to_text(&buf, c, k);
-		trace_io_move_read(c, buf.buf);
-		printbuf_exit(&buf);
+	bch2_bkey_val_to_text(&buf, c, k);
+	trace_io_move_read(c, buf.buf);
+	printbuf_exit(&buf);
+}
+
+static noinline void
+trace_io_move_pred2(struct bch_fs *c, struct bkey_s_c k,
+		    struct bch_io_opts *io_opts,
+		    struct data_update_opts *data_opts,
+		    move_pred_fn pred, void *_arg, bool p)
+{
+	struct printbuf buf = PRINTBUF;
+
+	prt_printf(&buf, "%ps: %u", pred, p);
+
+	if (pred == evacuate_bucket_pred) {
+		struct evacuate_bucket_arg *arg = _arg;
+		prt_printf(&buf, " gen=%u", arg->gen);
 	}
+
+	prt_newline(&buf);
+	bch2_bkey_val_to_text(&buf, c, k);
+	prt_newline(&buf);
+	bch2_data_update_opts_to_text(&buf, c, io_opts, data_opts);
+	trace_io_move_pred(c, buf.buf);
+	printbuf_exit(&buf);
+}
+
+static noinline void
+trace_io_move_evacuate_bucket2(struct bch_fs *c, struct bpos bucket, int gen)
+{
+	struct printbuf buf = PRINTBUF;
+
+	prt_printf(&buf, "bucket: ");
+	bch2_bpos_to_text(&buf, bucket);
+	prt_printf(&buf, " gen: %i\n", gen);
+
+	trace_io_move_evacuate_bucket(c, buf.buf);
+	printbuf_exit(&buf);
 }
 
 struct moving_io {
@@ -298,7 +342,8 @@ int bch2_move_extent(struct moving_context *ctxt,
 	struct bch_fs *c = trans->c;
 	int ret = -ENOMEM;
 
-	trace_io_move2(c, k, &io_opts, &data_opts);
+	if (trace_io_move_enabled())
+		trace_io_move2(c, k, &io_opts, &data_opts);
 	this_cpu_add(c->counters[BCH_COUNTER_io_move], k.k->size);
 
 	if (ctxt->stats)
@@ -314,16 +359,14 @@ int bch2_move_extent(struct moving_context *ctxt,
 		return 0;
 	}
 
-	/*
-	 * Before memory allocations & taking nocow locks in
-	 * bch2_data_update_init():
-	 */
-	bch2_trans_unlock(trans);
-
-	struct moving_io *io = kzalloc(sizeof(struct moving_io), GFP_KERNEL);
+	struct moving_io *io = allocate_dropping_locks(trans, ret,
+				kzalloc(sizeof(struct moving_io), _gfp));
 	if (!io)
 		goto err;
 
+	if (ret)
+		goto err_free;
+
 	INIT_LIST_HEAD(&io->io_list);
 	io->write.ctxt		= ctxt;
 	io->read_sectors	= k.k->size;
@@ -343,6 +386,8 @@ int bch2_move_extent(struct moving_context *ctxt,
 		io->write.op.c		= c;
 		io->write.data_opts	= data_opts;
 
+		bch2_trans_unlock(trans);
+
 		ret = bch2_data_update_bios_init(&io->write, c, &io_opts);
 		if (ret)
 			goto err_free;
@@ -364,7 +409,8 @@ int bch2_move_extent(struct moving_context *ctxt,
 		atomic_inc(&io->b->count);
 	}
 
-	trace_io_move_read2(c, k);
+	if (trace_io_move_read_enabled())
+		trace_io_move_read2(c, k);
 
 	mutex_lock(&ctxt->lock);
 	atomic_add(io->read_sectors, &ctxt->read_sectors);
@@ -390,9 +436,6 @@ int bch2_move_extent(struct moving_context *ctxt,
 err_free:
 	kfree(io);
 err:
-	if (bch2_err_matches(ret, BCH_ERR_data_update_done))
-		return 0;
-
 	if (bch2_err_matches(ret, EROFS) ||
 	    bch2_err_matches(ret, BCH_ERR_transaction_restart))
 		return ret;
@@ -408,6 +451,9 @@ err:
 		trace_io_move_start_fail(c, buf.buf);
 		printbuf_exit(&buf);
 	}
+
+	if (bch2_err_matches(ret, BCH_ERR_data_update_done))
+		return 0;
 	return ret;
 }
 
@@ -496,6 +542,7 @@ int bch2_move_get_io_opts_one(struct btree_trans *trans,
 		bch2_inode_opts_get(io_opts, c, &inode);
 	}
 	bch2_trans_iter_exit(trans, &inode_iter);
+	/* seem to be spinning here? */
 out:
 	return bch2_get_update_rebalance_opts(trans, io_opts, extent_iter, extent_k);
 }
@@ -910,7 +957,13 @@ static int __bch2_move_data_phys(struct moving_context *ctxt,
 		}
 
 		struct data_update_opts data_opts = {};
-		if (!pred(c, arg, bp.v->btree_id, k, &io_opts, &data_opts)) {
+		bool p = pred(c, arg, bp.v->btree_id, k, &io_opts, &data_opts);
+
+		if (trace_io_move_pred_enabled())
+			trace_io_move_pred2(c, k, &io_opts, &data_opts,
+					    pred, arg, p);
+
+		if (!p) {
 			bch2_trans_iter_exit(trans, &iter);
 			goto next;
 		}
@@ -918,7 +971,7 @@ static int __bch2_move_data_phys(struct moving_context *ctxt,
 		if (data_opts.scrub &&
 		    !bch2_dev_idx_is_online(c, data_opts.read_dev)) {
 			bch2_trans_iter_exit(trans, &iter);
-			ret = -BCH_ERR_device_offline;
+			ret = bch_err_throw(c, device_offline);
 			break;
 		}
 
@@ -993,12 +1046,6 @@ int bch2_move_data_phys(struct bch_fs *c,
 	return ret;
 }
 
-struct evacuate_bucket_arg {
-	struct bpos		bucket;
-	int			gen;
-	struct data_update_opts	data_opts;
-};
-
 static bool evacuate_bucket_pred(struct bch_fs *c, void *_arg,
 				 enum btree_id btree, struct bkey_s_c k,
 				 struct bch_io_opts *io_opts,
@@ -1025,8 +1072,13 @@ int bch2_evacuate_bucket(struct moving_context *ctxt,
 			 struct bpos bucket, int gen,
 			 struct data_update_opts data_opts)
 {
+	struct bch_fs *c = ctxt->trans->c;
 	struct evacuate_bucket_arg arg = { bucket, gen, data_opts, };
 
+	count_event(c, io_move_evacuate_bucket);
+	if (trace_io_move_evacuate_bucket_enabled())
+		trace_io_move_evacuate_bucket2(c, bucket, gen);
+
 	return __bch2_move_data_phys(ctxt, bucket_in_flight,
 				   bucket.inode,
 				   bucket.offset,
@@ -1124,7 +1176,7 @@ static bool rereplicate_pred(struct bch_fs *c, void *arg,
 		? c->opts.metadata_replicas
 		: io_opts->data_replicas;
 
-	rcu_read_lock();
+	guard(rcu)();
 	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
 	unsigned i = 0;
 	bkey_for_each_ptr(ptrs, ptr) {
@@ -1134,7 +1186,6 @@ static bool rereplicate_pred(struct bch_fs *c, void *arg,
 			data_opts->kill_ptrs |= BIT(i);
 		i++;
 	}
-	rcu_read_unlock();
 
 	if (!data_opts->kill_ptrs &&
 	    (!nr_good || nr_good >= replicas))
@@ -1242,7 +1293,7 @@ static bool drop_extra_replicas_pred(struct bch_fs *c, void *arg,
 	struct extent_ptr_decoded p;
 	unsigned i = 0;
 
-	rcu_read_lock();
+	guard(rcu)();
 	bkey_for_each_ptr_decode(k.k, bch2_bkey_ptrs_c(k), p, entry) {
 		unsigned d = bch2_extent_ptr_durability(c, &p);
 
@@ -1253,7 +1304,6 @@ static bool drop_extra_replicas_pred(struct bch_fs *c, void *arg,
 
 		i++;
 	}
-	rcu_read_unlock();
 
 	return data_opts->kill_ptrs != 0;
 }
diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index e7a2a13554d7..6d7b1d5f7697 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -293,11 +293,9 @@ u64 bch2_copygc_wait_amount(struct bch_fs *c)
 {
 	u64 wait = U64_MAX;
 
-	rcu_read_lock();
+	guard(rcu)();
 	for_each_rw_member_rcu(c, ca)
 		wait = min(wait, bch2_copygc_dev_wait_amount(ca));
-	rcu_read_unlock();
-
 	return wait;
 }
 
@@ -321,21 +319,21 @@ void bch2_copygc_wait_to_text(struct printbuf *out, struct bch_fs *c)
 
 	bch2_printbuf_make_room(out, 4096);
 
-	rcu_read_lock();
+	struct task_struct *t;
 	out->atomic++;
+	scoped_guard(rcu) {
+		prt_printf(out, "Currently calculated wait:\n");
+		for_each_rw_member_rcu(c, ca) {
+			prt_printf(out, "  %s:\t", ca->name);
+			prt_human_readable_u64(out, bch2_copygc_dev_wait_amount(ca));
+			prt_newline(out);
+		}
 
-	prt_printf(out, "Currently calculated wait:\n");
-	for_each_rw_member_rcu(c, ca) {
-		prt_printf(out, "  %s:\t", ca->name);
-		prt_human_readable_u64(out, bch2_copygc_dev_wait_amount(ca));
-		prt_newline(out);
+		t = rcu_dereference(c->copygc_thread);
+		if (t)
+			get_task_struct(t);
 	}
-
-	struct task_struct *t = rcu_dereference(c->copygc_thread);
-	if (t)
-		get_task_struct(t);
 	--out->atomic;
-	rcu_read_unlock();
 
 	if (t) {
 		bch2_prt_task_backtrace(out, t, 0, GFP_KERNEL);
diff --git a/fs/bcachefs/movinggc.h b/fs/bcachefs/movinggc.h
index b9683d22bab0..f615910d6f98 100644
--- a/fs/bcachefs/movinggc.h
+++ b/fs/bcachefs/movinggc.h
@@ -7,11 +7,10 @@ void bch2_copygc_wait_to_text(struct printbuf *, struct bch_fs *);
 
 static inline void bch2_copygc_wakeup(struct bch_fs *c)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	struct task_struct *p = rcu_dereference(c->copygc_thread);
 	if (p)
 		wake_up_process(p);
-	rcu_read_unlock();
 }
 
 void bch2_copygc_stop(struct bch_fs *);
diff --git a/fs/bcachefs/namei.c b/fs/bcachefs/namei.c
index a84b69d6caef..24120037c031 100644
--- a/fs/bcachefs/namei.c
+++ b/fs/bcachefs/namei.c
@@ -287,7 +287,7 @@ int bch2_unlink_trans(struct btree_trans *trans,
 	}
 
 	if (deleting_subvol && !inode_u->bi_subvol) {
-		ret = -BCH_ERR_ENOENT_not_subvol;
+		ret = bch_err_throw(c, ENOENT_not_subvol);
 		goto err;
 	}
 
@@ -425,8 +425,8 @@ int bch2_rename_trans(struct btree_trans *trans,
 	}
 
 	ret = bch2_dirent_rename(trans,
-				 src_dir, &src_hash, &src_dir_u->bi_size,
-				 dst_dir, &dst_hash, &dst_dir_u->bi_size,
+				 src_dir, &src_hash,
+				 dst_dir, &dst_hash,
 				 src_name, &src_inum, &src_offset,
 				 dst_name, &dst_inum, &dst_offset,
 				 mode);
@@ -633,7 +633,7 @@ static int __bch2_inum_to_path(struct btree_trans *trans,
 			break;
 
 		if (!inode.bi_dir && !inode.bi_dir_offset) {
-			ret = -BCH_ERR_ENOENT_inode_no_backpointer;
+			ret = bch_err_throw(trans->c, ENOENT_inode_no_backpointer);
 			goto disconnected;
 		}
 
@@ -733,15 +733,6 @@ static int bch2_check_dirent_inode_dirent(struct btree_trans *trans,
 		return __bch2_fsck_write_inode(trans, target);
 	}
 
-	if (bch2_inode_should_have_single_bp(target) &&
-	    !fsck_err(trans, inode_wrong_backpointer,
-		      "dirent points to inode that does not point back:\n%s",
-		      (bch2_bkey_val_to_text(&buf, c, d.s_c),
-		       prt_newline(&buf),
-		       bch2_inode_unpacked_to_text(&buf, target),
-		       buf.buf)))
-		goto err;
-
 	struct bkey_s_c_dirent bp_dirent =
 		bch2_bkey_get_iter_typed(trans, &bp_iter, BTREE_ID_dirents,
 			      SPOS(target->bi_dir, target->bi_dir_offset, target->bi_snapshot),
@@ -768,6 +759,7 @@ static int bch2_check_dirent_inode_dirent(struct btree_trans *trans,
 			ret = __bch2_fsck_write_inode(trans, target);
 		}
 	} else {
+		printbuf_reset(&buf);
 		bch2_bkey_val_to_text(&buf, c, d.s_c);
 		prt_newline(&buf);
 		bch2_bkey_val_to_text(&buf, c, bp_dirent.s_c);
@@ -857,7 +849,8 @@ int __bch2_check_dirent_target(struct btree_trans *trans,
 			n->v.d_inum = cpu_to_le64(target->bi_inum);
 		}
 
-		ret = bch2_trans_update(trans, dirent_iter, &n->k_i, 0);
+		ret = bch2_trans_update(trans, dirent_iter, &n->k_i,
+					BTREE_UPDATE_internal_snapshot_node);
 		if (ret)
 			goto err;
 	}
diff --git a/fs/bcachefs/printbuf.h b/fs/bcachefs/printbuf.h
index 1ca476adbf6f..8f4e28d440ac 100644
--- a/fs/bcachefs/printbuf.h
+++ b/fs/bcachefs/printbuf.h
@@ -140,6 +140,14 @@ void bch2_prt_bitflags_vector(struct printbuf *, const char * const[],
 	.size	= _size,				\
 })
 
+static inline struct printbuf bch2_printbuf_init(void)
+{
+	return PRINTBUF;
+}
+
+DEFINE_CLASS(printbuf, struct printbuf,
+	     bch2_printbuf_exit(&_T), bch2_printbuf_init(), void)
+
 /*
  * Returns size remaining of output buffer:
  */
diff --git a/fs/bcachefs/quota.c b/fs/bcachefs/quota.c
index 3d4755d73af7..f241efb1fb50 100644
--- a/fs/bcachefs/quota.c
+++ b/fs/bcachefs/quota.c
@@ -527,7 +527,7 @@ int bch2_fs_quota_read(struct bch_fs *c)
 	struct bch_sb_field_quota *sb_quota = bch2_sb_get_or_create_quota(&c->disk_sb);
 	if (!sb_quota) {
 		mutex_unlock(&c->sb_lock);
-		return -BCH_ERR_ENOSPC_sb_quota;
+		return bch_err_throw(c, ENOSPC_sb_quota);
 	}
 
 	bch2_sb_quota_read(c);
@@ -572,7 +572,7 @@ static int bch2_quota_enable(struct super_block	*sb, unsigned uflags)
 	mutex_lock(&c->sb_lock);
 	sb_quota = bch2_sb_get_or_create_quota(&c->disk_sb);
 	if (!sb_quota) {
-		ret = -BCH_ERR_ENOSPC_sb_quota;
+		ret = bch_err_throw(c, ENOSPC_sb_quota);
 		goto unlock;
 	}
 
@@ -726,7 +726,7 @@ static int bch2_quota_set_info(struct super_block *sb, int type,
 	mutex_lock(&c->sb_lock);
 	sb_quota = bch2_sb_get_or_create_quota(&c->disk_sb);
 	if (!sb_quota) {
-		ret = -BCH_ERR_ENOSPC_sb_quota;
+		ret = bch_err_throw(c, ENOSPC_sb_quota);
 		goto unlock;
 	}
 
diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c
index de1ec9e0caa0..1c345b86b1c0 100644
--- a/fs/bcachefs/rebalance.c
+++ b/fs/bcachefs/rebalance.c
@@ -80,13 +80,12 @@ static inline unsigned bch2_bkey_ptrs_need_move(struct bch_fs *c,
 	unsigned ptr_bit = 1;
 	unsigned rewrite_ptrs = 0;
 
-	rcu_read_lock();
+	guard(rcu)();
 	bkey_for_each_ptr(ptrs, ptr) {
 		if (!ptr->cached && !bch2_dev_in_target(c, ptr->dev, opts->background_target))
 			rewrite_ptrs |= ptr_bit;
 		ptr_bit <<= 1;
 	}
-	rcu_read_unlock();
 
 	return rewrite_ptrs;
 }
@@ -135,12 +134,11 @@ u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k)
 	}
 incompressible:
 	if (opts->background_target) {
-		rcu_read_lock();
+		guard(rcu)();
 		bkey_for_each_ptr_decode(k.k, ptrs, p, entry)
 			if (!p.ptr.cached &&
 			    !bch2_dev_in_target(c, p.ptr.dev, opts->background_target))
 				sectors += p.crc.compressed_size;
-		rcu_read_unlock();
 	}
 
 	return sectors;
@@ -445,7 +443,7 @@ static int do_rebalance_extent(struct moving_context *ctxt,
 		if (bch2_err_matches(ret, ENOMEM)) {
 			/* memory allocation failure, wait for some IO to finish */
 			bch2_move_ctxt_wait_for_io(ctxt);
-			ret = -BCH_ERR_transaction_restart_nested;
+			ret = bch_err_throw(c, transaction_restart_nested);
 		}
 
 		if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
@@ -527,7 +525,7 @@ static void rebalance_wait(struct bch_fs *c)
 		r->state		= BCH_REBALANCE_waiting;
 	}
 
-	bch2_kthread_io_clock_wait(clock, r->wait_iotime_end, MAX_SCHEDULE_TIMEOUT);
+	bch2_kthread_io_clock_wait_once(clock, r->wait_iotime_end, MAX_SCHEDULE_TIMEOUT);
 }
 
 static bool bch2_rebalance_enabled(struct bch_fs *c)
@@ -544,6 +542,7 @@ static int do_rebalance(struct moving_context *ctxt)
 	struct bch_fs_rebalance *r = &c->rebalance;
 	struct btree_iter rebalance_work_iter, extent_iter = {};
 	struct bkey_s_c k;
+	u32 kick = r->kick;
 	int ret = 0;
 
 	bch2_trans_begin(trans);
@@ -593,7 +592,8 @@ static int do_rebalance(struct moving_context *ctxt)
 	if (!ret &&
 	    !kthread_should_stop() &&
 	    !atomic64_read(&r->work_stats.sectors_seen) &&
-	    !atomic64_read(&r->scan_stats.sectors_seen)) {
+	    !atomic64_read(&r->scan_stats.sectors_seen) &&
+	    kick == r->kick) {
 		bch2_moving_ctxt_flush_all(ctxt);
 		bch2_trans_unlock_long(trans);
 		rebalance_wait(c);
@@ -677,11 +677,12 @@ void bch2_rebalance_status_to_text(struct printbuf *out, struct bch_fs *c)
 	}
 	prt_newline(out);
 
-	rcu_read_lock();
-	struct task_struct *t = rcu_dereference(c->rebalance.thread);
-	if (t)
-		get_task_struct(t);
-	rcu_read_unlock();
+	struct task_struct *t;
+	scoped_guard(rcu) {
+		t = rcu_dereference(c->rebalance.thread);
+		if (t)
+			get_task_struct(t);
+	}
 
 	if (t) {
 		bch2_prt_task_backtrace(out, t, 0, GFP_KERNEL);
@@ -794,7 +795,7 @@ static int check_rebalance_work_one(struct btree_trans *trans,
 				     BTREE_ID_extents, POS_MIN,
 				     BTREE_ITER_prefetch|
 				     BTREE_ITER_all_snapshots);
-		return -BCH_ERR_transaction_restart_nested;
+		return bch_err_throw(c, transaction_restart_nested);
 	}
 
 	if (!extent_k.k && !rebalance_k.k)
diff --git a/fs/bcachefs/rebalance.h b/fs/bcachefs/rebalance.h
index 5d9214fe1a22..7a565ea7dbfc 100644
--- a/fs/bcachefs/rebalance.h
+++ b/fs/bcachefs/rebalance.h
@@ -39,13 +39,11 @@ int bch2_set_fs_needs_rebalance(struct bch_fs *);
 
 static inline void bch2_rebalance_wakeup(struct bch_fs *c)
 {
-	struct task_struct *p;
-
-	rcu_read_lock();
-	p = rcu_dereference(c->rebalance.thread);
+	c->rebalance.kick++;
+	guard(rcu)();
+	struct task_struct *p = rcu_dereference(c->rebalance.thread);
 	if (p)
 		wake_up_process(p);
-	rcu_read_unlock();
 }
 
 void bch2_rebalance_status_to_text(struct printbuf *, struct bch_fs *);
diff --git a/fs/bcachefs/rebalance_types.h b/fs/bcachefs/rebalance_types.h
index 33d77286f1d5..c659da149fa3 100644
--- a/fs/bcachefs/rebalance_types.h
+++ b/fs/bcachefs/rebalance_types.h
@@ -18,6 +18,7 @@ enum bch_rebalance_states {
 
 struct bch_fs_rebalance {
 	struct task_struct __rcu	*thread;
+	u32				kick;
 	struct bch_pd_controller pd;
 
 	enum bch_rebalance_states	state;
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 4fca57575565..1e68e61f08e8 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -879,7 +879,7 @@ int bch2_fs_recovery(struct bch_fs *c)
 use_clean:
 		if (!clean) {
 			bch_err(c, "no superblock clean section found");
-			ret = -BCH_ERR_fsck_repair_impossible;
+			ret = bch_err_throw(c, fsck_repair_impossible);
 			goto err;
 
 		}
@@ -1093,10 +1093,6 @@ use_clean:
 out:
 	bch2_flush_fsck_errs(c);
 
-	if (!c->opts.retain_recovery_info) {
-		bch2_journal_keys_put_initial(c);
-		bch2_find_btree_nodes_exit(&c->found_btree_nodes);
-	}
 	if (!IS_ERR(clean))
 		kfree(clean);
 
diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c
index dabb29b08ad0..605588e33fb3 100644
--- a/fs/bcachefs/recovery_passes.c
+++ b/fs/bcachefs/recovery_passes.c
@@ -103,20 +103,20 @@ static void bch2_sb_recovery_passes_to_text(struct printbuf *out,
 		prt_tab(out);
 
 		bch2_pr_time_units(out, le32_to_cpu(i->last_runtime) * NSEC_PER_SEC);
+
+		if (BCH_RECOVERY_PASS_NO_RATELIMIT(i))
+			prt_str(out, " (no ratelimit)");
+
 		prt_newline(out);
 	}
 }
 
-static void bch2_sb_recovery_pass_complete(struct bch_fs *c,
-					   enum bch_recovery_pass pass,
-					   s64 start_time)
+static struct recovery_pass_entry *bch2_sb_recovery_pass_entry(struct bch_fs *c,
+							       enum bch_recovery_pass pass)
 {
 	enum bch_recovery_pass_stable stable = bch2_recovery_pass_to_stable(pass);
-	s64 end_time = ktime_get_real_seconds();
 
-	mutex_lock(&c->sb_lock);
-	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
-	__clear_bit_le64(stable, ext->recovery_passes_required);
+	lockdep_assert_held(&c->sb_lock);
 
 	struct bch_sb_field_recovery_passes *r =
 		bch2_sb_field_get(c->disk_sb.sb, recovery_passes);
@@ -127,15 +127,43 @@ static void bch2_sb_recovery_pass_complete(struct bch_fs *c,
 		r = bch2_sb_field_resize(&c->disk_sb, recovery_passes, u64s);
 		if (!r) {
 			bch_err(c, "error creating recovery_passes sb section");
-			goto out;
+			return NULL;
 		}
 	}
 
-	r->start[stable].last_run	= cpu_to_le64(end_time);
-	r->start[stable].last_runtime	= cpu_to_le32(max(0, end_time - start_time));
-out:
+	return r->start + stable;
+}
+
+static void bch2_sb_recovery_pass_complete(struct bch_fs *c,
+					   enum bch_recovery_pass pass,
+					   s64 start_time)
+{
+	guard(mutex)(&c->sb_lock);
+	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
+	__clear_bit_le64(bch2_recovery_pass_to_stable(pass),
+			 ext->recovery_passes_required);
+
+	struct recovery_pass_entry *e = bch2_sb_recovery_pass_entry(c, pass);
+	if (e) {
+		s64 end_time	= ktime_get_real_seconds();
+		e->last_run	= cpu_to_le64(end_time);
+		e->last_runtime	= cpu_to_le32(max(0, end_time - start_time));
+		SET_BCH_RECOVERY_PASS_NO_RATELIMIT(e, false);
+	}
+
 	bch2_write_super(c);
-	mutex_unlock(&c->sb_lock);
+}
+
+void bch2_recovery_pass_set_no_ratelimit(struct bch_fs *c,
+					 enum bch_recovery_pass pass)
+{
+	guard(mutex)(&c->sb_lock);
+
+	struct recovery_pass_entry *e = bch2_sb_recovery_pass_entry(c, pass);
+	if (e && !BCH_RECOVERY_PASS_NO_RATELIMIT(e)) {
+		SET_BCH_RECOVERY_PASS_NO_RATELIMIT(e, false);
+		bch2_write_super(c);
+	}
 }
 
 static bool bch2_recovery_pass_want_ratelimit(struct bch_fs *c, enum bch_recovery_pass pass)
@@ -157,6 +185,9 @@ static bool bch2_recovery_pass_want_ratelimit(struct bch_fs *c, enum bch_recover
 		 */
 		ret = (u64) le32_to_cpu(i->last_runtime) * 100 >
 			ktime_get_real_seconds() - le64_to_cpu(i->last_run);
+
+		if (BCH_RECOVERY_PASS_NO_RATELIMIT(i))
+			ret = false;
 	}
 
 	return ret;
@@ -315,7 +346,9 @@ int __bch2_run_explicit_recovery_pass(struct bch_fs *c,
 		goto out;
 
 	bool in_recovery = test_bit(BCH_FS_in_recovery, &c->flags);
-	bool rewind = in_recovery && r->curr_pass > pass;
+	bool rewind = in_recovery &&
+		r->curr_pass > pass &&
+		!(r->passes_complete & BIT_ULL(pass));
 	bool ratelimit = flags & RUN_RECOVERY_PASS_ratelimit;
 
 	if (!(in_recovery && (flags & RUN_RECOVERY_PASS_nopersistent))) {
@@ -327,7 +360,7 @@ int __bch2_run_explicit_recovery_pass(struct bch_fs *c,
 	    (!in_recovery || r->curr_pass >= BCH_RECOVERY_PASS_set_may_go_rw)) {
 		prt_printf(out, "need recovery pass %s (%u), but already rw\n",
 			   bch2_recovery_passes[pass], pass);
-		ret = -BCH_ERR_cannot_rewind_recovery;
+		ret = bch_err_throw(c, cannot_rewind_recovery);
 		goto out;
 	}
 
@@ -347,7 +380,7 @@ int __bch2_run_explicit_recovery_pass(struct bch_fs *c,
 		if (rewind) {
 			r->next_pass = pass;
 			r->passes_complete &= (1ULL << pass) >> 1;
-			ret = -BCH_ERR_restart_recovery;
+			ret = bch_err_throw(c, restart_recovery);
 		}
 	} else {
 		prt_printf(out, "scheduling recovery pass %s (%u)%s\n",
@@ -382,6 +415,35 @@ int bch2_run_explicit_recovery_pass(struct bch_fs *c,
 	return ret;
 }
 
+/*
+ * Returns 0 if @pass has run recently, otherwise one of
+ * -BCH_ERR_restart_recovery
+ * -BCH_ERR_recovery_pass_will_run
+ */
+int bch2_require_recovery_pass(struct bch_fs *c,
+			       struct printbuf *out,
+			       enum bch_recovery_pass pass)
+{
+	if (test_bit(BCH_FS_in_recovery, &c->flags) &&
+	    c->recovery.passes_complete & BIT_ULL(pass))
+		return 0;
+
+	guard(mutex)(&c->sb_lock);
+
+	if (bch2_recovery_pass_want_ratelimit(c, pass))
+		return 0;
+
+	enum bch_run_recovery_pass_flags flags = 0;
+	int ret = 0;
+
+	if (recovery_pass_needs_set(c, pass, &flags)) {
+		ret = __bch2_run_explicit_recovery_pass(c, out, pass, flags);
+		bch2_write_super(c);
+	}
+
+	return ret ?: bch_err_throw(c, recovery_pass_will_run);
+}
+
 int bch2_run_print_explicit_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
 {
 	enum bch_run_recovery_pass_flags flags = RUN_RECOVERY_PASS_nopersistent;
diff --git a/fs/bcachefs/recovery_passes.h b/fs/bcachefs/recovery_passes.h
index dc0d2014ff9b..260571c7105e 100644
--- a/fs/bcachefs/recovery_passes.h
+++ b/fs/bcachefs/recovery_passes.h
@@ -10,6 +10,8 @@ u64 bch2_recovery_passes_from_stable(u64 v);
 
 u64 bch2_fsck_recovery_passes(void);
 
+void bch2_recovery_pass_set_no_ratelimit(struct bch_fs *, enum bch_recovery_pass);
+
 enum bch_run_recovery_pass_flags {
 	RUN_RECOVERY_PASS_nopersistent	= BIT(0),
 	RUN_RECOVERY_PASS_ratelimit	= BIT(1),
@@ -24,6 +26,9 @@ int bch2_run_explicit_recovery_pass(struct bch_fs *, struct printbuf *,
 				    enum bch_recovery_pass,
 				    enum bch_run_recovery_pass_flags);
 
+int bch2_require_recovery_pass(struct bch_fs *, struct printbuf *,
+			       enum bch_recovery_pass);
+
 int bch2_run_online_recovery_passes(struct bch_fs *, u64);
 int bch2_run_recovery_passes(struct bch_fs *, enum bch_recovery_pass);
 
diff --git a/fs/bcachefs/recovery_passes_format.h b/fs/bcachefs/recovery_passes_format.h
index c434eafbca19..b63c20558d3d 100644
--- a/fs/bcachefs/recovery_passes_format.h
+++ b/fs/bcachefs/recovery_passes_format.h
@@ -87,6 +87,8 @@ struct recovery_pass_entry {
 	__le32			flags;
 };
 
+LE32_BITMASK(BCH_RECOVERY_PASS_NO_RATELIMIT,	struct recovery_pass_entry, flags, 0, 1)
+
 struct bch_sb_field_recovery_passes {
 	struct bch_sb_field	field;
 	struct recovery_pass_entry start[];
diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c
index 3a13dbcab6ba..a535abd44df3 100644
--- a/fs/bcachefs/reflink.c
+++ b/fs/bcachefs/reflink.c
@@ -312,7 +312,7 @@ static int trans_trigger_reflink_p_segment(struct btree_trans *trans,
 
 	if (!bkey_refcount_c(k)) {
 		if (!(flags & BTREE_TRIGGER_overwrite))
-			ret = -BCH_ERR_missing_indirect_extent;
+			ret = bch_err_throw(c, missing_indirect_extent);
 		goto next;
 	}
 
@@ -612,7 +612,7 @@ s64 bch2_remap_range(struct bch_fs *c,
 	int ret = 0, ret2 = 0;
 
 	if (!enumerated_ref_tryget(&c->writes, BCH_WRITE_REF_reflink))
-		return -BCH_ERR_erofs_no_writes;
+		return bch_err_throw(c, erofs_no_writes);
 
 	bch2_check_set_feature(c, BCH_FEATURE_reflink);
 
@@ -711,7 +711,8 @@ s64 bch2_remap_range(struct bch_fs *c,
 			SET_REFLINK_P_IDX(&dst_p->v, offset);
 
 			if (reflink_p_may_update_opts_field &&
-			    may_change_src_io_path_opts)
+			    may_change_src_io_path_opts &&
+			    REFLINK_P_MAY_UPDATE_OPTIONS(src_p.v))
 				SET_REFLINK_P_MAY_UPDATE_OPTIONS(&dst_p->v, true);
 		} else {
 			BUG();
@@ -847,7 +848,7 @@ int bch2_gc_reflink_start(struct bch_fs *c)
 			struct reflink_gc *r = genradix_ptr_alloc(&c->reflink_gc_table,
 							c->reflink_gc_nr++, GFP_KERNEL);
 			if (!r) {
-				ret = -BCH_ERR_ENOMEM_gc_reflink_start;
+				ret = bch_err_throw(c, ENOMEM_gc_reflink_start);
 				break;
 			}
 
diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c
index 477ef0997949..8383bd7fdb3f 100644
--- a/fs/bcachefs/replicas.c
+++ b/fs/bcachefs/replicas.c
@@ -119,7 +119,7 @@ int bch2_replicas_entry_validate(struct bch_replicas_entry_v1 *r,
 	return 0;
 bad:
 	bch2_replicas_entry_to_text(err, r);
-	return -BCH_ERR_invalid_replicas_entry;
+	return bch_err_throw(c, invalid_replicas_entry);
 }
 
 void bch2_cpu_replicas_to_text(struct printbuf *out,
@@ -311,7 +311,7 @@ static int bch2_mark_replicas_slowpath(struct bch_fs *c,
 	    !__replicas_has_entry(&c->replicas_gc, new_entry)) {
 		new_gc = cpu_replicas_add_entry(c, &c->replicas_gc, new_entry);
 		if (!new_gc.entries) {
-			ret = -BCH_ERR_ENOMEM_cpu_replicas;
+			ret = bch_err_throw(c, ENOMEM_cpu_replicas);
 			goto err;
 		}
 	}
@@ -319,7 +319,7 @@ static int bch2_mark_replicas_slowpath(struct bch_fs *c,
 	if (!__replicas_has_entry(&c->replicas, new_entry)) {
 		new_r = cpu_replicas_add_entry(c, &c->replicas, new_entry);
 		if (!new_r.entries) {
-			ret = -BCH_ERR_ENOMEM_cpu_replicas;
+			ret = bch_err_throw(c, ENOMEM_cpu_replicas);
 			goto err;
 		}
 
@@ -422,7 +422,7 @@ int bch2_replicas_gc_start(struct bch_fs *c, unsigned typemask)
 	if (!c->replicas_gc.entries) {
 		mutex_unlock(&c->sb_lock);
 		bch_err(c, "error allocating c->replicas_gc");
-		return -BCH_ERR_ENOMEM_replicas_gc;
+		return bch_err_throw(c, ENOMEM_replicas_gc);
 	}
 
 	for_each_cpu_replicas_entry(&c->replicas, e)
@@ -458,7 +458,7 @@ retry:
 	new.entries	= kcalloc(nr, new.entry_size, GFP_KERNEL);
 	if (!new.entries) {
 		bch_err(c, "error allocating c->replicas_gc");
-		return -BCH_ERR_ENOMEM_replicas_gc;
+		return bch_err_throw(c, ENOMEM_replicas_gc);
 	}
 
 	mutex_lock(&c->sb_lock);
@@ -622,7 +622,7 @@ static int bch2_cpu_replicas_to_sb_replicas_v0(struct bch_fs *c,
 	sb_r = bch2_sb_field_resize(&c->disk_sb, replicas_v0,
 			DIV_ROUND_UP(bytes, sizeof(u64)));
 	if (!sb_r)
-		return -BCH_ERR_ENOSPC_sb_replicas;
+		return bch_err_throw(c, ENOSPC_sb_replicas);
 
 	bch2_sb_field_delete(&c->disk_sb, BCH_SB_FIELD_replicas);
 	sb_r = bch2_sb_field_get(c->disk_sb.sb, replicas_v0);
@@ -667,7 +667,7 @@ static int bch2_cpu_replicas_to_sb_replicas(struct bch_fs *c,
 	sb_r = bch2_sb_field_resize(&c->disk_sb, replicas,
 			DIV_ROUND_UP(bytes, sizeof(u64)));
 	if (!sb_r)
-		return -BCH_ERR_ENOSPC_sb_replicas;
+		return bch_err_throw(c, ENOSPC_sb_replicas);
 
 	bch2_sb_field_delete(&c->disk_sb, BCH_SB_FIELD_replicas_v0);
 	sb_r = bch2_sb_field_get(c->disk_sb.sb, replicas);
@@ -819,19 +819,18 @@ bool bch2_have_enough_devs(struct bch_fs *c, struct bch_devs_mask devs,
 		if (e->data_type == BCH_DATA_cached)
 			continue;
 
-		rcu_read_lock();
-		for (unsigned i = 0; i < e->nr_devs; i++) {
-			if (e->devs[i] == BCH_SB_MEMBER_INVALID) {
-				nr_failed++;
-				continue;
-			}
+		scoped_guard(rcu)
+			for (unsigned i = 0; i < e->nr_devs; i++) {
+				if (e->devs[i] == BCH_SB_MEMBER_INVALID) {
+					nr_failed++;
+					continue;
+				}
 
-			nr_online += test_bit(e->devs[i], devs.d);
+				nr_online += test_bit(e->devs[i], devs.d);
 
-			struct bch_dev *ca = bch2_dev_rcu_noerror(c, e->devs[i]);
-			nr_failed += !ca || ca->mi.state == BCH_MEMBER_STATE_failed;
-		}
-		rcu_read_unlock();
+				struct bch_dev *ca = bch2_dev_rcu_noerror(c, e->devs[i]);
+				nr_failed += !ca || ca->mi.state == BCH_MEMBER_STATE_failed;
+			}
 
 		if (nr_online + nr_failed == e->nr_devs)
 			continue;
diff --git a/fs/bcachefs/sb-counters_format.h b/fs/bcachefs/sb-counters_format.h
index 7c0c9c842b4e..b868702a431a 100644
--- a/fs/bcachefs/sb-counters_format.h
+++ b/fs/bcachefs/sb-counters_format.h
@@ -26,6 +26,7 @@ enum counters_flags {
 	x(io_move_write_fail,				82,	TYPE_COUNTER)	\
 	x(io_move_start_fail,				39,	TYPE_COUNTER)	\
 	x(io_move_created_rebalance,			83,	TYPE_COUNTER)	\
+	x(io_move_evacuate_bucket,			84,	TYPE_COUNTER)	\
 	x(bucket_invalidate,				3,	TYPE_COUNTER)	\
 	x(bucket_discard,				4,	TYPE_COUNTER)	\
 	x(bucket_discard_fast,				79,	TYPE_COUNTER)	\
diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
index 861fce1630f0..b61f88450a6d 100644
--- a/fs/bcachefs/sb-downgrade.c
+++ b/fs/bcachefs/sb-downgrade.c
@@ -417,7 +417,7 @@ int bch2_sb_downgrade_update(struct bch_fs *c)
 
 	d = bch2_sb_field_resize(&c->disk_sb, downgrade, sb_u64s);
 	if (!d) {
-		ret = -BCH_ERR_ENOSPC_sb_downgrade;
+		ret = bch_err_throw(c, ENOSPC_sb_downgrade);
 		goto out;
 	}
 
diff --git a/fs/bcachefs/sb-errors.c b/fs/bcachefs/sb-errors.c
index 013a96883b4e..48853efdc105 100644
--- a/fs/bcachefs/sb-errors.c
+++ b/fs/bcachefs/sb-errors.c
@@ -78,6 +78,28 @@ const struct bch_sb_field_ops bch_sb_field_ops_errors = {
 	.to_text	= bch2_sb_errors_to_text,
 };
 
+void bch2_fs_errors_to_text(struct printbuf *out, struct bch_fs *c)
+{
+	if (out->nr_tabstops < 1)
+		printbuf_tabstop_push(out, 48);
+	if (out->nr_tabstops < 2)
+		printbuf_tabstop_push(out, 8);
+	if (out->nr_tabstops < 3)
+		printbuf_tabstop_push(out, 16);
+
+	guard(mutex)(&c->fsck_error_counts_lock);
+
+	bch_sb_errors_cpu *e = &c->fsck_error_counts;
+	darray_for_each(*e, i) {
+		bch2_sb_error_id_to_text(out, i->id);
+		prt_tab(out);
+		prt_u64(out, i->nr);
+		prt_tab(out);
+		bch2_prt_datetime(out, i->last_error_time);
+		prt_newline(out);
+	}
+}
+
 void bch2_sb_error_count(struct bch_fs *c, enum bch_sb_error_id err)
 {
 	bch_sb_errors_cpu *e = &c->fsck_error_counts;
diff --git a/fs/bcachefs/sb-errors.h b/fs/bcachefs/sb-errors.h
index b2357b8e6107..e86267264692 100644
--- a/fs/bcachefs/sb-errors.h
+++ b/fs/bcachefs/sb-errors.h
@@ -7,6 +7,7 @@
 extern const char * const bch2_sb_error_strs[];
 
 void bch2_sb_error_id_to_text(struct printbuf *, enum bch_sb_error_id);
+void bch2_fs_errors_to_text(struct printbuf *, struct bch_fs *);
 
 extern const struct bch_sb_field_ops bch_sb_field_ops_errors;
 
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index 0bfb151da9cf..6fdbf265e4c0 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -232,6 +232,7 @@ enum bch_fsck_flags {
 	x(inode_dir_multiple_links,				206,	FSCK_AUTOFIX)	\
 	x(inode_dir_missing_backpointer,			284,	FSCK_AUTOFIX)	\
 	x(inode_dir_unlinked_but_not_empty,			286,	FSCK_AUTOFIX)	\
+	x(inode_dir_has_nonzero_i_size,				319,	FSCK_AUTOFIX)	\
 	x(inode_multiple_links_but_nlink_0,			207,	FSCK_AUTOFIX)	\
 	x(inode_wrong_backpointer,				208,	FSCK_AUTOFIX)	\
 	x(inode_wrong_nlink,					209,	FSCK_AUTOFIX)	\
@@ -243,6 +244,7 @@ enum bch_fsck_flags {
 	x(inode_parent_has_case_insensitive_not_set,		317,	FSCK_AUTOFIX)	\
 	x(vfs_inode_i_blocks_underflow,				311,	FSCK_AUTOFIX)	\
 	x(vfs_inode_i_blocks_not_zero_at_truncate,		313,	FSCK_AUTOFIX)	\
+	x(vfs_bad_inode_rm,					320,	0)		\
 	x(deleted_inode_but_clean,				211,	FSCK_AUTOFIX)	\
 	x(deleted_inode_missing,				212,	FSCK_AUTOFIX)	\
 	x(deleted_inode_is_dir,					213,	FSCK_AUTOFIX)	\
@@ -328,7 +330,7 @@ enum bch_fsck_flags {
 	x(dirent_stray_data_after_cf_name,			305,	0)		\
 	x(rebalance_work_incorrectly_set,			309,	FSCK_AUTOFIX)	\
 	x(rebalance_work_incorrectly_unset,			310,	FSCK_AUTOFIX)	\
-	x(MAX,							319,	0)
+	x(MAX,							321,	0)
 
 enum bch_sb_error_id {
 #define x(t, n, ...) BCH_FSCK_ERR_##t = n,
diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c
index 3398906660a5..363eb0c6eb7c 100644
--- a/fs/bcachefs/sb-members.c
+++ b/fs/bcachefs/sb-members.c
@@ -101,7 +101,7 @@ static int sb_members_v2_resize_entries(struct bch_fs *c)
 
 		mi = bch2_sb_field_resize(&c->disk_sb, members_v2, u64s);
 		if (!mi)
-			return -BCH_ERR_ENOSPC_sb_members_v2;
+			return bch_err_throw(c, ENOSPC_sb_members_v2);
 
 		for (int i = c->disk_sb.sb->nr_devices - 1; i >= 0; --i) {
 			void *dst = (void *) mi->_members + (i * sizeof(struct bch_member));
@@ -378,14 +378,13 @@ void bch2_sb_members_from_cpu(struct bch_fs *c)
 {
 	struct bch_sb_field_members_v2 *mi = bch2_sb_field_get(c->disk_sb.sb, members_v2);
 
-	rcu_read_lock();
+	guard(rcu)();
 	for_each_member_device_rcu(c, ca, NULL) {
 		struct bch_member *m = __bch2_members_v2_get_mut(mi, ca->dev_idx);
 
 		for (unsigned e = 0; e < BCH_MEMBER_ERROR_NR; e++)
 			m->errors[e] = cpu_to_le64(atomic64_read(&ca->errors[e]));
 	}
-	rcu_read_unlock();
 }
 
 void bch2_dev_io_errors_to_text(struct printbuf *out, struct bch_dev *ca)
@@ -443,20 +442,14 @@ void bch2_dev_errors_reset(struct bch_dev *ca)
 
 bool bch2_dev_btree_bitmap_marked(struct bch_fs *c, struct bkey_s_c k)
 {
-	bool ret = true;
-	rcu_read_lock();
+	guard(rcu)();
 	bkey_for_each_ptr(bch2_bkey_ptrs_c(k), ptr) {
 		struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev);
-		if (!ca)
-			continue;
-
-		if (!bch2_dev_btree_bitmap_marked_sectors(ca, ptr->offset, btree_sectors(c))) {
-			ret = false;
-			break;
-		}
+		if (ca &&
+		    !bch2_dev_btree_bitmap_marked_sectors(ca, ptr->offset, btree_sectors(c)))
+			return false;
 	}
-	rcu_read_unlock();
-	return ret;
+	return true;
 }
 
 static void __bch2_dev_btree_bitmap_mark(struct bch_sb_field_members_v2 *mi, unsigned dev,
diff --git a/fs/bcachefs/sb-members.h b/fs/bcachefs/sb-members.h
index 6bd9b86aee5b..8d8a8a857648 100644
--- a/fs/bcachefs/sb-members.h
+++ b/fs/bcachefs/sb-members.h
@@ -28,12 +28,9 @@ static inline struct bch_dev *bch2_dev_rcu(struct bch_fs *, unsigned);
 
 static inline bool bch2_dev_idx_is_online(struct bch_fs *c, unsigned dev)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	struct bch_dev *ca = bch2_dev_rcu(c, dev);
-	bool ret = ca && bch2_dev_is_online(ca);
-	rcu_read_unlock();
-
-	return ret;
+	return ca && bch2_dev_is_online(ca);
 }
 
 static inline bool bch2_dev_is_healthy(struct bch_dev *ca)
@@ -142,12 +139,10 @@ static inline void bch2_dev_put(struct bch_dev *ca)
 
 static inline struct bch_dev *bch2_get_next_dev(struct bch_fs *c, struct bch_dev *ca)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	bch2_dev_put(ca);
 	if ((ca = __bch2_next_dev(c, ca, NULL)))
 		bch2_dev_get(ca);
-	rcu_read_unlock();
-
 	return ca;
 }
 
@@ -166,7 +161,7 @@ static inline struct bch_dev *bch2_get_next_online_dev(struct bch_fs *c,
 						       unsigned state_mask,
 						       int rw, unsigned ref_idx)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	if (ca)
 		enumerated_ref_put(&ca->io_ref[rw], ref_idx);
 
@@ -174,7 +169,6 @@ static inline struct bch_dev *bch2_get_next_online_dev(struct bch_fs *c,
 	       (!((1 << ca->mi.state) & state_mask) ||
 		!enumerated_ref_tryget(&ca->io_ref[rw], ref_idx)))
 		;
-	rcu_read_unlock();
 
 	return ca;
 }
@@ -239,11 +233,10 @@ static inline struct bch_dev *bch2_dev_rcu(struct bch_fs *c, unsigned dev)
 
 static inline struct bch_dev *bch2_dev_tryget_noerror(struct bch_fs *c, unsigned dev)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	struct bch_dev *ca = bch2_dev_rcu_noerror(c, dev);
 	if (ca)
 		bch2_dev_get(ca);
-	rcu_read_unlock();
 	return ca;
 }
 
@@ -299,19 +292,16 @@ static inline struct bch_dev *bch2_dev_get_ioref(struct bch_fs *c, unsigned dev,
 {
 	might_sleep();
 
-	rcu_read_lock();
+	guard(rcu)();
 	struct bch_dev *ca = bch2_dev_rcu(c, dev);
-	if (ca && !enumerated_ref_tryget(&ca->io_ref[rw], ref_idx))
-		ca = NULL;
-	rcu_read_unlock();
+	if (!ca || !enumerated_ref_tryget(&ca->io_ref[rw], ref_idx))
+		return NULL;
 
-	if (ca &&
-	    (ca->mi.state == BCH_MEMBER_STATE_rw ||
-	    (ca->mi.state == BCH_MEMBER_STATE_ro && rw == READ)))
+	if (ca->mi.state == BCH_MEMBER_STATE_rw ||
+	    (ca->mi.state == BCH_MEMBER_STATE_ro && rw == READ))
 		return ca;
 
-	if (ca)
-		enumerated_ref_put(&ca->io_ref[rw], ref_idx);
+	enumerated_ref_put(&ca->io_ref[rw], ref_idx);
 	return NULL;
 }
 
diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c
index 7c403427fbdb..538c324f4765 100644
--- a/fs/bcachefs/six.c
+++ b/fs/bcachefs/six.c
@@ -339,12 +339,9 @@ static inline bool six_owner_running(struct six_lock *lock)
 	 * acquiring the lock and setting the owner field. If we're an RT task
 	 * that will live-lock because we won't let the owner complete.
 	 */
-	rcu_read_lock();
+	guard(rcu)();
 	struct task_struct *owner = READ_ONCE(lock->owner);
-	bool ret = owner ? owner_on_cpu(owner) : !rt_or_dl_task(current);
-	rcu_read_unlock();
-
-	return ret;
+	return owner ? owner_on_cpu(owner) : !rt_or_dl_task(current);
 }
 
 static inline bool six_optimistic_spin(struct six_lock *lock,
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index 00d62d1190ef..23a332d76b32 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -54,7 +54,7 @@ int bch2_snapshot_tree_lookup(struct btree_trans *trans, u32 id,
 					  BTREE_ITER_with_updates, snapshot_tree, s);
 
 	if (bch2_err_matches(ret, ENOENT))
-		ret = -BCH_ERR_ENOENT_snapshot_tree;
+		ret = bch_err_throw(trans->c, ENOENT_snapshot_tree);
 	return ret;
 }
 
@@ -67,7 +67,7 @@ __bch2_snapshot_tree_create(struct btree_trans *trans)
 	struct bkey_i_snapshot_tree *s_t;
 
 	if (ret == -BCH_ERR_ENOSPC_btree_slot)
-		ret = -BCH_ERR_ENOSPC_snapshot_tree;
+		ret = bch_err_throw(trans->c, ENOSPC_snapshot_tree);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -105,11 +105,8 @@ static bool __bch2_snapshot_is_ancestor_early(struct snapshot_table *t, u32 id,
 
 static bool bch2_snapshot_is_ancestor_early(struct bch_fs *c, u32 id, u32 ancestor)
 {
-	rcu_read_lock();
-	bool ret = __bch2_snapshot_is_ancestor_early(rcu_dereference(c->snapshots), id, ancestor);
-	rcu_read_unlock();
-
-	return ret;
+	guard(rcu)();
+	return __bch2_snapshot_is_ancestor_early(rcu_dereference(c->snapshots), id, ancestor);
 }
 
 static inline u32 get_ancestor_below(struct snapshot_table *t, u32 id, u32 ancestor)
@@ -140,13 +137,11 @@ bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor)
 {
 	bool ret;
 
-	rcu_read_lock();
+	guard(rcu)();
 	struct snapshot_table *t = rcu_dereference(c->snapshots);
 
-	if (unlikely(c->recovery.pass_done < BCH_RECOVERY_PASS_check_snapshots)) {
-		ret = __bch2_snapshot_is_ancestor_early(t, id, ancestor);
-		goto out;
-	}
+	if (unlikely(c->recovery.pass_done < BCH_RECOVERY_PASS_check_snapshots))
+		return __bch2_snapshot_is_ancestor_early(t, id, ancestor);
 
 	if (likely(ancestor >= IS_ANCESTOR_BITMAP))
 		while (id && id < ancestor - IS_ANCESTOR_BITMAP)
@@ -157,9 +152,6 @@ bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor)
 		: id == ancestor;
 
 	EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, id, ancestor));
-out:
-	rcu_read_unlock();
-
 	return ret;
 }
 
@@ -293,7 +285,7 @@ static int bch2_snapshot_table_make_room(struct bch_fs *c, u32 id)
 	mutex_lock(&c->snapshot_table_lock);
 	int ret = snapshot_t_mut(c, id)
 		? 0
-		: -BCH_ERR_ENOMEM_mark_snapshot;
+		: bch_err_throw(c, ENOMEM_mark_snapshot);
 	mutex_unlock(&c->snapshot_table_lock);
 	return ret;
 }
@@ -312,7 +304,7 @@ static int __bch2_mark_snapshot(struct btree_trans *trans,
 
 	t = snapshot_t_mut(c, id);
 	if (!t) {
-		ret = -BCH_ERR_ENOMEM_mark_snapshot;
+		ret = bch_err_throw(c, ENOMEM_mark_snapshot);
 		goto err;
 	}
 
@@ -412,10 +404,10 @@ static u32 bch2_snapshot_tree_next(struct bch_fs *c, u32 id)
 u32 bch2_snapshot_oldest_subvol(struct bch_fs *c, u32 snapshot_root,
 				snapshot_id_list *skip)
 {
+	guard(rcu)();
 	u32 id, subvol = 0, s;
 retry:
 	id = snapshot_root;
-	rcu_read_lock();
 	while (id && bch2_snapshot_exists(c, id)) {
 		if (!(skip && snapshot_list_has_id(skip, id))) {
 			s = snapshot_t(c, id)->subvol;
@@ -427,7 +419,6 @@ retry:
 		if (id == snapshot_root)
 			break;
 	}
-	rcu_read_unlock();
 
 	if (!subvol && skip) {
 		skip = NULL;
@@ -617,18 +608,14 @@ static int snapshot_tree_ptr_good(struct btree_trans *trans,
 
 u32 bch2_snapshot_skiplist_get(struct bch_fs *c, u32 id)
 {
-	const struct snapshot_t *s;
-
 	if (!id)
 		return 0;
 
-	rcu_read_lock();
-	s = snapshot_t(c, id);
-	if (s->parent)
-		id = bch2_snapshot_nth_parent(c, id, get_random_u32_below(s->depth));
-	rcu_read_unlock();
-
-	return id;
+	guard(rcu)();
+	const struct snapshot_t *s = snapshot_t(c, id);
+	return s->parent
+		? bch2_snapshot_nth_parent(c, id, get_random_u32_below(s->depth))
+		: id;
 }
 
 static int snapshot_skiplist_good(struct btree_trans *trans, u32 id, struct bch_snapshot s)
@@ -947,10 +934,7 @@ static inline bool same_snapshot(struct snapshot_tree_reconstruct *r, struct bpo
 
 static inline bool snapshot_id_lists_have_common(snapshot_id_list *l, snapshot_id_list *r)
 {
-	darray_for_each(*l, i)
-		if (snapshot_list_has_id(r, *i))
-			return true;
-	return false;
+	return darray_find_p(*l, i, snapshot_list_has_id(r, *i)) != NULL;
 }
 
 static void snapshot_id_list_to_text(struct printbuf *out, snapshot_id_list *s)
@@ -1022,7 +1006,7 @@ int bch2_reconstruct_snapshots(struct bch_fs *c)
 					"snapshot node %u from tree %s missing, recreate?", *id, buf.buf)) {
 				if (t->nr > 1) {
 					bch_err(c, "cannot reconstruct snapshot trees with multiple nodes");
-					ret = -BCH_ERR_fsck_repair_unimplemented;
+					ret = bch_err_throw(c, fsck_repair_unimplemented);
 					goto err;
 				}
 
@@ -1061,24 +1045,73 @@ int __bch2_check_key_has_snapshot(struct btree_trans *trans,
 		ret = bch2_btree_delete_at(trans, iter,
 					   BTREE_UPDATE_internal_snapshot_node) ?: 1;
 
-	/*
-	 * Snapshot missing: we should have caught this with btree_lost_data and
-	 * kicked off reconstruct_snapshots, so if we end up here we have no
-	 * idea what happened:
-	 */
-	if (fsck_err_on(state == SNAPSHOT_ID_empty,
-			trans, bkey_in_missing_snapshot,
-			"key in missing snapshot %s, delete?",
-			(bch2_btree_id_to_text(&buf, iter->btree_id),
-			 prt_char(&buf, ' '),
-			 bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
-		ret = bch2_btree_delete_at(trans, iter,
-					   BTREE_UPDATE_internal_snapshot_node) ?: 1;
+	if (state == SNAPSHOT_ID_empty) {
+		/*
+		 * Snapshot missing: we should have caught this with btree_lost_data and
+		 * kicked off reconstruct_snapshots, so if we end up here we have no
+		 * idea what happened.
+		 *
+		 * Do not delete unless we know that subvolumes and snapshots
+		 * are consistent:
+		 *
+		 * XXX:
+		 *
+		 * We could be smarter here, and instead of using the generic
+		 * recovery pass ratelimiting, track if there have been any
+		 * changes to the snapshots or inodes btrees since those passes
+		 * last ran.
+		 */
+		ret = bch2_require_recovery_pass(c, &buf, BCH_RECOVERY_PASS_check_snapshots) ?: ret;
+		ret = bch2_require_recovery_pass(c, &buf, BCH_RECOVERY_PASS_check_subvols) ?: ret;
+
+		if (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_snapshots))
+			ret = bch2_require_recovery_pass(c, &buf, BCH_RECOVERY_PASS_reconstruct_snapshots) ?: ret;
+
+		unsigned repair_flags = FSCK_CAN_IGNORE | (!ret ? FSCK_CAN_FIX : 0);
+
+		if (__fsck_err(trans, repair_flags, bkey_in_missing_snapshot,
+			     "key in missing snapshot %s, delete?",
+			     (bch2_btree_id_to_text(&buf, iter->btree_id),
+			      prt_char(&buf, ' '),
+			      bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
+			ret = bch2_btree_delete_at(trans, iter,
+						   BTREE_UPDATE_internal_snapshot_node) ?: 1;
+		}
+	}
 fsck_err:
 	printbuf_exit(&buf);
 	return ret;
 }
 
+int __bch2_get_snapshot_overwrites(struct btree_trans *trans,
+				   enum btree_id btree, struct bpos pos,
+				   snapshot_id_list *s)
+{
+	struct bch_fs *c = trans->c;
+	struct btree_iter iter;
+	struct bkey_s_c k;
+	int ret = 0;
+
+	for_each_btree_key_reverse_norestart(trans, iter, btree, bpos_predecessor(pos),
+					     BTREE_ITER_all_snapshots, k, ret) {
+		if (!bkey_eq(k.k->p, pos))
+			break;
+
+		if (!bch2_snapshot_is_ancestor(c, k.k->p.snapshot, pos.snapshot) ||
+		    snapshot_list_has_ancestor(c, s, k.k->p.snapshot))
+			continue;
+
+		ret = snapshot_list_add(c, s, k.k->p.snapshot);
+		if (ret)
+			break;
+	}
+	bch2_trans_iter_exit(trans, &iter);
+	if (ret)
+		darray_exit(s);
+
+	return ret;
+}
+
 /*
  * Mark a snapshot as deleted, for future cleanup:
  */
@@ -1263,7 +1296,7 @@ static int create_snapids(struct btree_trans *trans, u32 parent, u32 tree,
 			goto err;
 
 		if (!k.k || !k.k->p.offset) {
-			ret = -BCH_ERR_ENOSPC_snapshot_create;
+			ret = bch_err_throw(c, ENOSPC_snapshot_create);
 			goto err;
 		}
 
@@ -1399,10 +1432,8 @@ int bch2_snapshot_node_create(struct btree_trans *trans, u32 parent,
 
 static inline u32 interior_delete_has_id(interior_delete_list *l, u32 id)
 {
-	darray_for_each(*l, i)
-		if (i->id == id)
-			return i->live_child;
-	return 0;
+	struct snapshot_interior_delete *i = darray_find_p(*l, i, i->id == id);
+	return i ? i->live_child : 0;
 }
 
 static unsigned __live_child(struct snapshot_table *t, u32 id,
@@ -1434,11 +1465,9 @@ static unsigned live_child(struct bch_fs *c, u32 id)
 {
 	struct snapshot_delete *d = &c->snapshot_delete;
 
-	rcu_read_lock();
-	u32 ret = __live_child(rcu_dereference(c->snapshots), id,
-			       &d->delete_leaves, &d->delete_interior);
-	rcu_read_unlock();
-	return ret;
+	guard(rcu)();
+	return __live_child(rcu_dereference(c->snapshots), id,
+			    &d->delete_leaves, &d->delete_interior);
 }
 
 static bool snapshot_id_dying(struct snapshot_delete *d, unsigned id)
@@ -1695,7 +1724,7 @@ static int check_should_delete_snapshot(struct btree_trans *trans, struct bkey_s
 static inline u32 bch2_snapshot_nth_parent_skip(struct bch_fs *c, u32 id, u32 n,
 						interior_delete_list *skip)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	while (interior_delete_has_id(skip, id))
 		id = __bch2_snapshot_parent(c, id);
 
@@ -1704,7 +1733,6 @@ static inline u32 bch2_snapshot_nth_parent_skip(struct bch_fs *c, u32 id, u32 n,
 			id = __bch2_snapshot_parent(c, id);
 		} while (interior_delete_has_id(skip, id));
 	}
-	rcu_read_unlock();
 
 	return id;
 }
@@ -1870,6 +1898,8 @@ err:
 	d->running = false;
 	mutex_unlock(&d->progress_lock);
 	bch2_trans_put(trans);
+
+	bch2_recovery_pass_set_no_ratelimit(c, BCH_RECOVERY_PASS_check_snapshots);
 out_unlock:
 	mutex_unlock(&d->lock);
 	if (!bch2_err_matches(ret, EROFS))
@@ -1905,7 +1935,7 @@ void bch2_delete_dead_snapshots_async(struct bch_fs *c)
 
 	BUG_ON(!test_bit(BCH_FS_may_go_rw, &c->flags));
 
-	if (!queue_work(c->write_ref_wq, &c->snapshot_delete.work))
+	if (!queue_work(system_long_wq, &c->snapshot_delete.work))
 		enumerated_ref_put(&c->writes, BCH_WRITE_REF_delete_dead_snapshots);
 }
 
diff --git a/fs/bcachefs/snapshot.h b/fs/bcachefs/snapshot.h
index 382a171f5413..6766bf673ed9 100644
--- a/fs/bcachefs/snapshot.h
+++ b/fs/bcachefs/snapshot.h
@@ -46,12 +46,9 @@ static inline const struct snapshot_t *snapshot_t(struct bch_fs *c, u32 id)
 
 static inline u32 bch2_snapshot_tree(struct bch_fs *c, u32 id)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	const struct snapshot_t *s = snapshot_t(c, id);
-	id = s ? s->tree : 0;
-	rcu_read_unlock();
-
-	return id;
+	return s ? s->tree : 0;
 }
 
 static inline u32 __bch2_snapshot_parent_early(struct bch_fs *c, u32 id)
@@ -62,11 +59,8 @@ static inline u32 __bch2_snapshot_parent_early(struct bch_fs *c, u32 id)
 
 static inline u32 bch2_snapshot_parent_early(struct bch_fs *c, u32 id)
 {
-	rcu_read_lock();
-	id = __bch2_snapshot_parent_early(c, id);
-	rcu_read_unlock();
-
-	return id;
+	guard(rcu)();
+	return __bch2_snapshot_parent_early(c, id);
 }
 
 static inline u32 __bch2_snapshot_parent(struct bch_fs *c, u32 id)
@@ -88,20 +82,15 @@ static inline u32 __bch2_snapshot_parent(struct bch_fs *c, u32 id)
 
 static inline u32 bch2_snapshot_parent(struct bch_fs *c, u32 id)
 {
-	rcu_read_lock();
-	id = __bch2_snapshot_parent(c, id);
-	rcu_read_unlock();
-
-	return id;
+	guard(rcu)();
+	return __bch2_snapshot_parent(c, id);
 }
 
 static inline u32 bch2_snapshot_nth_parent(struct bch_fs *c, u32 id, u32 n)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	while (n--)
 		id = __bch2_snapshot_parent(c, id);
-	rcu_read_unlock();
-
 	return id;
 }
 
@@ -110,13 +99,11 @@ u32 bch2_snapshot_skiplist_get(struct bch_fs *, u32);
 
 static inline u32 bch2_snapshot_root(struct bch_fs *c, u32 id)
 {
-	u32 parent;
+	guard(rcu)();
 
-	rcu_read_lock();
+	u32 parent;
 	while ((parent = __bch2_snapshot_parent(c, id)))
 		id = parent;
-	rcu_read_unlock();
-
 	return id;
 }
 
@@ -128,11 +115,8 @@ static inline enum snapshot_id_state __bch2_snapshot_id_state(struct bch_fs *c,
 
 static inline enum snapshot_id_state bch2_snapshot_id_state(struct bch_fs *c, u32 id)
 {
-	rcu_read_lock();
-	enum snapshot_id_state ret = __bch2_snapshot_id_state(c, id);
-	rcu_read_unlock();
-
-	return ret;
+	guard(rcu)();
+	return __bch2_snapshot_id_state(c, id);
 }
 
 static inline bool bch2_snapshot_exists(struct bch_fs *c, u32 id)
@@ -142,12 +126,9 @@ static inline bool bch2_snapshot_exists(struct bch_fs *c, u32 id)
 
 static inline int bch2_snapshot_is_internal_node(struct bch_fs *c, u32 id)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	const struct snapshot_t *s = snapshot_t(c, id);
-	int ret = s ? s->children[0] : -BCH_ERR_invalid_snapshot_node;
-	rcu_read_unlock();
-
-	return ret;
+	return s ? s->children[0] : -BCH_ERR_invalid_snapshot_node;
 }
 
 static inline int bch2_snapshot_is_leaf(struct bch_fs *c, u32 id)
@@ -160,13 +141,8 @@ static inline int bch2_snapshot_is_leaf(struct bch_fs *c, u32 id)
 
 static inline u32 bch2_snapshot_depth(struct bch_fs *c, u32 parent)
 {
-	u32 depth;
-
-	rcu_read_lock();
-	depth = parent ? snapshot_t(c, parent)->depth + 1 : 0;
-	rcu_read_unlock();
-
-	return depth;
+	guard(rcu)();
+	return parent ? snapshot_t(c, parent)->depth + 1 : 0;
 }
 
 bool __bch2_snapshot_is_ancestor(struct bch_fs *, u32, u32);
@@ -180,20 +156,14 @@ static inline bool bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ances
 
 static inline bool bch2_snapshot_has_children(struct bch_fs *c, u32 id)
 {
-	rcu_read_lock();
+	guard(rcu)();
 	const struct snapshot_t *t = snapshot_t(c, id);
-	bool ret = t && (t->children[0]|t->children[1]) != 0;
-	rcu_read_unlock();
-
-	return ret;
+	return t && (t->children[0]|t->children[1]) != 0;
 }
 
 static inline bool snapshot_list_has_id(snapshot_id_list *s, u32 id)
 {
-	darray_for_each(*s, i)
-		if (*i == id)
-			return true;
-	return false;
+	return darray_find(*s, id) != NULL;
 }
 
 static inline bool snapshot_list_has_ancestor(struct bch_fs *c, snapshot_id_list *s, u32 id)
@@ -258,6 +228,25 @@ static inline int bch2_check_key_has_snapshot(struct btree_trans *trans,
 		: __bch2_check_key_has_snapshot(trans, iter, k);
 }
 
+int __bch2_get_snapshot_overwrites(struct btree_trans *,
+				   enum btree_id, struct bpos,
+				   snapshot_id_list *);
+
+/*
+ * Get a list of snapshot IDs that have overwritten a given key:
+ */
+static inline int bch2_get_snapshot_overwrites(struct btree_trans *trans,
+					       enum btree_id btree, struct bpos pos,
+					       snapshot_id_list *s)
+{
+	darray_init(s);
+
+	return bch2_snapshot_has_children(trans->c, pos.snapshot)
+		? __bch2_get_snapshot_overwrites(trans, btree, pos, s)
+		: 0;
+
+}
+
 int bch2_snapshot_node_set_deleted(struct btree_trans *, u32);
 
 int __bch2_key_has_snapshot_overwrites(struct btree_trans *, enum btree_id, struct bpos);
diff --git a/fs/bcachefs/str_hash.c b/fs/bcachefs/str_hash.c
index 0cbf5508a32c..71b735a85026 100644
--- a/fs/bcachefs/str_hash.c
+++ b/fs/bcachefs/str_hash.c
@@ -31,14 +31,15 @@ static int bch2_dirent_has_target(struct btree_trans *trans, struct bkey_s_c_dir
 	}
 }
 
-static noinline int fsck_rename_dirent(struct btree_trans *trans,
-				       struct snapshots_seen *s,
-				       const struct bch_hash_desc desc,
-				       struct bch_hash_info *hash_info,
-				       struct bkey_s_c_dirent old)
+static int bch2_fsck_rename_dirent(struct btree_trans *trans,
+				   struct snapshots_seen *s,
+				   const struct bch_hash_desc desc,
+				   struct bch_hash_info *hash_info,
+				   struct bkey_s_c_dirent old,
+				   bool *updated_before_k_pos)
 {
 	struct qstr old_name = bch2_dirent_get_name(old);
-	struct bkey_i_dirent *new = bch2_trans_kmalloc(trans, bkey_bytes(old.k) + 32);
+	struct bkey_i_dirent *new = bch2_trans_kmalloc(trans, BKEY_U64s_MAX * sizeof(u64));
 	int ret = PTR_ERR_OR_ZERO(new);
 	if (ret)
 		return ret;
@@ -47,28 +48,39 @@ static noinline int fsck_rename_dirent(struct btree_trans *trans,
 	dirent_copy_target(new, old);
 	new->k.p = old.k->p;
 
+	char *renamed_buf = bch2_trans_kmalloc(trans, old_name.len + 20);
+	ret = PTR_ERR_OR_ZERO(renamed_buf);
+	if (ret)
+		return ret;
+
 	for (unsigned i = 0; i < 1000; i++) {
-		unsigned len = sprintf(new->v.d_name, "%.*s.fsck_renamed-%u",
-				       old_name.len, old_name.name, i);
-		unsigned u64s = BKEY_U64s + dirent_val_u64s(len, 0);
+		new->k.u64s = BKEY_U64s_MAX;
 
-		if (u64s > U8_MAX)
-			return -EINVAL;
+		struct qstr renamed_name = (struct qstr) QSTR_INIT(renamed_buf,
+					sprintf(renamed_buf, "%.*s.fsck_renamed-%u",
+						old_name.len, old_name.name, i));
 
-		new->k.u64s = u64s;
+		ret = bch2_dirent_init_name(new, hash_info, &renamed_name, NULL);
+		if (ret)
+			return ret;
 
 		ret = bch2_hash_set_in_snapshot(trans, bch2_dirent_hash_desc, hash_info,
 						(subvol_inum) { 0, old.k->p.inode },
 						old.k->p.snapshot, &new->k_i,
-						BTREE_UPDATE_internal_snapshot_node);
-		if (!bch2_err_matches(ret, EEXIST))
+						BTREE_UPDATE_internal_snapshot_node|
+						STR_HASH_must_create);
+		if (ret && !bch2_err_matches(ret, EEXIST))
+			break;
+		if (!ret) {
+			if (bpos_lt(new->k.p, old.k->p))
+				*updated_before_k_pos = true;
 			break;
+		}
 	}
 
-	if (ret)
-		return ret;
-
-	return bch2_fsck_update_backpointers(trans, s, desc, hash_info, &new->k_i);
+	ret = ret ?: bch2_fsck_update_backpointers(trans, s, desc, hash_info, &new->k_i);
+	bch_err_fn(trans->c, ret);
+	return ret;
 }
 
 static noinline int hash_pick_winner(struct btree_trans *trans,
@@ -186,7 +198,7 @@ int bch2_repair_inode_hash_info(struct btree_trans *trans,
 #endif
 		bch2_print_str(c, KERN_ERR, buf.buf);
 		printbuf_exit(&buf);
-		ret = -BCH_ERR_fsck_repair_unimplemented;
+		ret = bch_err_throw(c, fsck_repair_unimplemented);
 		goto err;
 	}
 
@@ -221,11 +233,115 @@ static noinline int check_inode_hash_info_matches_root(struct btree_trans *trans
 	return ret;
 }
 
+/* Put a str_hash key in its proper location, checking for duplicates */
+int bch2_str_hash_repair_key(struct btree_trans *trans,
+			     struct snapshots_seen *s,
+			     const struct bch_hash_desc *desc,
+			     struct bch_hash_info *hash_info,
+			     struct btree_iter *k_iter, struct bkey_s_c k,
+			     struct btree_iter *dup_iter, struct bkey_s_c dup_k,
+			     bool *updated_before_k_pos)
+{
+	struct bch_fs *c = trans->c;
+	struct printbuf buf = PRINTBUF;
+	bool free_snapshots_seen = false;
+	int ret = 0;
+
+	if (!s) {
+		s = bch2_trans_kmalloc(trans, sizeof(*s));
+		ret = PTR_ERR_OR_ZERO(s);
+		if (ret)
+			goto out;
+
+		s->pos = k_iter->pos;
+		darray_init(&s->ids);
+
+		ret = bch2_get_snapshot_overwrites(trans, desc->btree_id, k_iter->pos, &s->ids);
+		if (ret)
+			goto out;
+
+		free_snapshots_seen = true;
+	}
+
+	if (!dup_k.k) {
+		struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k);
+		ret = PTR_ERR_OR_ZERO(new);
+		if (ret)
+			goto out;
+
+		dup_k = bch2_hash_set_or_get_in_snapshot(trans, dup_iter, *desc, hash_info,
+				       (subvol_inum) { 0, new->k.p.inode },
+				       new->k.p.snapshot, new,
+				       STR_HASH_must_create|
+				       BTREE_ITER_with_updates|
+				       BTREE_UPDATE_internal_snapshot_node);
+		ret = bkey_err(dup_k);
+		if (ret)
+			goto out;
+		if (dup_k.k)
+			goto duplicate_entries;
+
+		if (bpos_lt(new->k.p, k.k->p))
+			*updated_before_k_pos = true;
+
+		ret =   bch2_insert_snapshot_whiteouts(trans, desc->btree_id,
+						       k_iter->pos, new->k.p) ?:
+			bch2_hash_delete_at(trans, *desc, hash_info, k_iter,
+					    BTREE_ITER_with_updates|
+					    BTREE_UPDATE_internal_snapshot_node) ?:
+			bch2_fsck_update_backpointers(trans, s, *desc, hash_info, new) ?:
+			bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?:
+			-BCH_ERR_transaction_restart_commit;
+	} else {
+duplicate_entries:
+		ret = hash_pick_winner(trans, *desc, hash_info, k, dup_k);
+		if (ret < 0)
+			goto out;
+
+		if (!fsck_err(trans, hash_table_key_duplicate,
+			      "duplicate hash table keys%s:\n%s",
+			      ret != 2 ? "" : ", both point to valid inodes",
+			      (printbuf_reset(&buf),
+			       bch2_bkey_val_to_text(&buf, c, k),
+			       prt_newline(&buf),
+			       bch2_bkey_val_to_text(&buf, c, dup_k),
+			       buf.buf)))
+			goto out;
+
+		switch (ret) {
+		case 0:
+			ret = bch2_hash_delete_at(trans, *desc, hash_info, k_iter, 0);
+			break;
+		case 1:
+			ret = bch2_hash_delete_at(trans, *desc, hash_info, dup_iter, 0);
+			break;
+		case 2:
+			ret = bch2_fsck_rename_dirent(trans, s, *desc, hash_info,
+						      bkey_s_c_to_dirent(k),
+						      updated_before_k_pos) ?:
+				bch2_hash_delete_at(trans, *desc, hash_info, k_iter,
+						    BTREE_ITER_with_updates);
+			goto out;
+		}
+
+		ret = bch2_trans_commit(trans, NULL, NULL, 0) ?:
+			-BCH_ERR_transaction_restart_commit;
+	}
+out:
+fsck_err:
+	bch2_trans_iter_exit(trans, dup_iter);
+	printbuf_exit(&buf);
+	if (free_snapshots_seen)
+		darray_exit(&s->ids);
+	return ret;
+}
+
 int __bch2_str_hash_check_key(struct btree_trans *trans,
 			      struct snapshots_seen *s,
 			      const struct bch_hash_desc *desc,
 			      struct bch_hash_info *hash_info,
-			      struct btree_iter *k_iter, struct bkey_s_c hash_k)
+			      struct btree_iter *k_iter, struct bkey_s_c hash_k,
+			      bool *updated_before_k_pos)
 {
 	struct bch_fs *c = trans->c;
 	struct btree_iter iter = {};
@@ -239,24 +355,31 @@ int __bch2_str_hash_check_key(struct btree_trans *trans,
 
 	for_each_btree_key_norestart(trans, iter, desc->btree_id,
 				     SPOS(hash_k.k->p.inode, hash, hash_k.k->p.snapshot),
-				     BTREE_ITER_slots, k, ret) {
+				     BTREE_ITER_slots|
+				     BTREE_ITER_with_updates, k, ret) {
 		if (bkey_eq(k.k->p, hash_k.k->p))
 			break;
 
 		if (k.k->type == desc->key_type &&
-		    !desc->cmp_bkey(k, hash_k))
-			goto duplicate_entries;
+		    !desc->cmp_bkey(k, hash_k)) {
+			ret =	check_inode_hash_info_matches_root(trans, hash_k.k->p.inode,
+								   hash_info) ?:
+				bch2_str_hash_repair_key(trans, s, desc, hash_info,
+							 k_iter, hash_k,
+							 &iter, k, updated_before_k_pos);
+			break;
+		}
 
-		if (bkey_deleted(k.k)) {
-			bch2_trans_iter_exit(trans, &iter);
+		if (bkey_deleted(k.k))
 			goto bad_hash;
-		}
 	}
-out:
 	bch2_trans_iter_exit(trans, &iter);
+out:
+fsck_err:
 	printbuf_exit(&buf);
 	return ret;
 bad_hash:
+	bch2_trans_iter_exit(trans, &iter);
 	/*
 	 * Before doing any repair, check hash_info itself:
 	 */
@@ -265,64 +388,12 @@ bad_hash:
 		goto out;
 
 	if (fsck_err(trans, hash_table_key_wrong_offset,
-		     "hash table key at wrong offset: btree %s inode %llu offset %llu, hashed to %llu\n%s",
-		     bch2_btree_id_str(desc->btree_id), hash_k.k->p.inode, hash_k.k->p.offset, hash,
-		     (printbuf_reset(&buf),
-		      bch2_bkey_val_to_text(&buf, c, hash_k), buf.buf))) {
-		struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, hash_k);
-		if (IS_ERR(new))
-			return PTR_ERR(new);
-
-		k = bch2_hash_set_or_get_in_snapshot(trans, &iter, *desc, hash_info,
-				       (subvol_inum) { 0, hash_k.k->p.inode },
-				       hash_k.k->p.snapshot, new,
-				       STR_HASH_must_create|
-				       BTREE_ITER_with_updates|
-				       BTREE_UPDATE_internal_snapshot_node);
-		ret = bkey_err(k);
-		if (ret)
-			goto out;
-		if (k.k)
-			goto duplicate_entries;
-
-		ret =   bch2_hash_delete_at(trans, *desc, hash_info, k_iter,
-					    BTREE_UPDATE_internal_snapshot_node) ?:
-			bch2_fsck_update_backpointers(trans, s, *desc, hash_info, new) ?:
-			bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc) ?:
-			-BCH_ERR_transaction_restart_nested;
-		goto out;
-	}
-fsck_err:
-	goto out;
-duplicate_entries:
-	ret = hash_pick_winner(trans, *desc, hash_info, hash_k, k);
-	if (ret < 0)
-		goto out;
-
-	if (!fsck_err(trans, hash_table_key_duplicate,
-		      "duplicate hash table keys%s:\n%s",
-		      ret != 2 ? "" : ", both point to valid inodes",
-		      (printbuf_reset(&buf),
-		       bch2_bkey_val_to_text(&buf, c, hash_k),
-		       prt_newline(&buf),
-		       bch2_bkey_val_to_text(&buf, c, k),
-		       buf.buf)))
-		goto out;
-
-	switch (ret) {
-	case 0:
-		ret = bch2_hash_delete_at(trans, *desc, hash_info, k_iter, 0);
-		break;
-	case 1:
-		ret = bch2_hash_delete_at(trans, *desc, hash_info, &iter, 0);
-		break;
-	case 2:
-		ret = fsck_rename_dirent(trans, s, *desc, hash_info, bkey_s_c_to_dirent(hash_k)) ?:
-			bch2_hash_delete_at(trans, *desc, hash_info, k_iter, 0);
-		goto out;
-	}
-
-	ret = bch2_trans_commit(trans, NULL, NULL, 0) ?:
-		-BCH_ERR_transaction_restart_nested;
+		     "hash table key at wrong offset: should be at %llu\n%s",
+		     hash,
+		     (bch2_bkey_val_to_text(&buf, c, hash_k), buf.buf)))
+		ret = bch2_str_hash_repair_key(trans, s, desc, hash_info,
+					       k_iter, hash_k,
+					       &iter, bkey_s_c_null,
+					       updated_before_k_pos);
 	goto out;
 }
diff --git a/fs/bcachefs/str_hash.h b/fs/bcachefs/str_hash.h
index 6762b3627e1b..79d51aef70aa 100644
--- a/fs/bcachefs/str_hash.h
+++ b/fs/bcachefs/str_hash.h
@@ -261,6 +261,7 @@ struct bkey_s_c bch2_hash_set_or_get_in_snapshot(struct btree_trans *trans,
 			   struct bkey_i *insert,
 			   enum btree_iter_update_trigger_flags flags)
 {
+	struct bch_fs *c = trans->c;
 	struct btree_iter slot = {};
 	struct bkey_s_c k;
 	bool found = false;
@@ -288,7 +289,7 @@ struct bkey_s_c bch2_hash_set_or_get_in_snapshot(struct btree_trans *trans,
 	}
 
 	if (!ret)
-		ret = -BCH_ERR_ENOSPC_str_hash_create;
+		ret = bch_err_throw(c, ENOSPC_str_hash_create);
 out:
 	bch2_trans_iter_exit(trans, &slot);
 	bch2_trans_iter_exit(trans, iter);
@@ -300,7 +301,7 @@ not_found:
 		bch2_trans_iter_exit(trans, &slot);
 		return k;
 	} else if (!found && (flags & STR_HASH_must_replace)) {
-		ret = -BCH_ERR_ENOENT_str_hash_set_must_replace;
+		ret = bch_err_throw(c, ENOENT_str_hash_set_must_replace);
 	} else {
 		if (!found && slot.path)
 			swap(*iter, slot);
@@ -328,7 +329,7 @@ int bch2_hash_set_in_snapshot(struct btree_trans *trans,
 		return ret;
 	if (k.k) {
 		bch2_trans_iter_exit(trans, &iter);
-		return -BCH_ERR_EEXIST_str_hash_set;
+		return bch_err_throw(trans->c, EEXIST_str_hash_set);
 	}
 
 	return 0;
@@ -397,17 +398,27 @@ int bch2_hash_delete(struct btree_trans *trans,
 int bch2_repair_inode_hash_info(struct btree_trans *, struct bch_inode_unpacked *);
 
 struct snapshots_seen;
+int bch2_str_hash_repair_key(struct btree_trans *,
+			     struct snapshots_seen *,
+			     const struct bch_hash_desc *,
+			     struct bch_hash_info *,
+			     struct btree_iter *, struct bkey_s_c,
+			     struct btree_iter *, struct bkey_s_c,
+			     bool *);
+
 int __bch2_str_hash_check_key(struct btree_trans *,
 			      struct snapshots_seen *,
 			      const struct bch_hash_desc *,
 			      struct bch_hash_info *,
-			      struct btree_iter *, struct bkey_s_c);
+			      struct btree_iter *, struct bkey_s_c,
+			      bool *);
 
 static inline int bch2_str_hash_check_key(struct btree_trans *trans,
 			    struct snapshots_seen *s,
 			    const struct bch_hash_desc *desc,
 			    struct bch_hash_info *hash_info,
-			    struct btree_iter *k_iter, struct bkey_s_c hash_k)
+			    struct btree_iter *k_iter, struct bkey_s_c hash_k,
+			    bool *updated_before_k_pos)
 {
 	if (hash_k.k->type != desc->key_type)
 		return 0;
@@ -415,7 +426,8 @@ static inline int bch2_str_hash_check_key(struct btree_trans *trans,
 	if (likely(desc->hash_bkey(hash_info, hash_k) == hash_k.k->p.offset))
 		return 0;
 
-	return __bch2_str_hash_check_key(trans, s, desc, hash_info, k_iter, hash_k);
+	return __bch2_str_hash_check_key(trans, s, desc, hash_info, k_iter, hash_k,
+					 updated_before_k_pos);
 }
 
 #endif /* _BCACHEFS_STR_HASH_H */
diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c
index 35c9f86a73c1..020587449123 100644
--- a/fs/bcachefs/subvolume.c
+++ b/fs/bcachefs/subvolume.c
@@ -130,10 +130,20 @@ static int check_subvol(struct btree_trans *trans,
 			     "subvolume %llu points to missing subvolume root %llu:%u",
 			     k.k->p.offset, le64_to_cpu(subvol.v->inode),
 			     le32_to_cpu(subvol.v->snapshot))) {
-			ret = bch2_subvolume_delete(trans, iter->pos.offset);
-			bch_err_msg(c, ret, "deleting subvolume %llu", iter->pos.offset);
-			ret = ret ?: -BCH_ERR_transaction_restart_nested;
-			goto err;
+			/*
+			 * Recreate - any contents that are still disconnected
+			 * will then get reattached under lost+found
+			 */
+			bch2_inode_init_early(c, &inode);
+			bch2_inode_init_late(c, &inode, bch2_current_time(c),
+					     0, 0, S_IFDIR|0700, 0, NULL);
+			inode.bi_inum			= le64_to_cpu(subvol.v->inode);
+			inode.bi_snapshot		= le32_to_cpu(subvol.v->snapshot);
+			inode.bi_subvol			= k.k->p.offset;
+			inode.bi_parent_subvol		= le32_to_cpu(subvol.v->fs_path_parent);
+			ret = __bch2_fsck_write_inode(trans, &inode);
+			if (ret)
+				goto err;
 		}
 	} else {
 		goto err;
@@ -141,13 +151,9 @@ static int check_subvol(struct btree_trans *trans,
 
 	if (!BCH_SUBVOLUME_SNAP(subvol.v)) {
 		u32 snapshot_root = bch2_snapshot_root(c, le32_to_cpu(subvol.v->snapshot));
-		u32 snapshot_tree;
-		struct bch_snapshot_tree st;
-
-		rcu_read_lock();
-		snapshot_tree = snapshot_t(c, snapshot_root)->tree;
-		rcu_read_unlock();
+		u32 snapshot_tree = bch2_snapshot_tree(c, snapshot_root);
 
+		struct bch_snapshot_tree st;
 		ret = bch2_snapshot_tree_lookup(trans, snapshot_tree, &st);
 
 		bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), c,
@@ -259,6 +265,13 @@ void bch2_subvolume_to_text(struct printbuf *out, struct bch_fs *c,
 		prt_printf(out, " creation_parent %u", le32_to_cpu(s.v->creation_parent));
 		prt_printf(out, " fs_parent %u", le32_to_cpu(s.v->fs_path_parent));
 	}
+
+	if (BCH_SUBVOLUME_RO(s.v))
+		prt_printf(out, " ro");
+	if (BCH_SUBVOLUME_SNAP(s.v))
+		prt_printf(out, " snapshot");
+	if (BCH_SUBVOLUME_UNLINKED(s.v))
+		prt_printf(out, " unlinked");
 }
 
 static int subvolume_children_mod(struct btree_trans *trans, struct bpos pos, bool set)
@@ -486,9 +499,12 @@ err:
 
 static int bch2_subvolume_delete(struct btree_trans *trans, u32 subvolid)
 {
-	return bch2_subvolumes_reparent(trans, subvolid) ?:
+	int ret = bch2_subvolumes_reparent(trans, subvolid) ?:
 		commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 			  __bch2_subvolume_delete(trans, subvolid));
+
+	bch2_recovery_pass_set_no_ratelimit(trans->c, BCH_RECOVERY_PASS_check_subvols);
+	return ret;
 }
 
 static void bch2_subvolume_wait_for_pagecache_and_delete(struct work_struct *work)
@@ -597,7 +613,7 @@ int bch2_subvolume_create(struct btree_trans *trans, u64 inode,
 	ret = bch2_bkey_get_empty_slot(trans, &dst_iter,
 				BTREE_ID_subvolumes, POS(0, U32_MAX));
 	if (ret == -BCH_ERR_ENOSPC_btree_slot)
-		ret = -BCH_ERR_ENOSPC_subvolume_create;
+		ret = bch_err_throw(c, ENOSPC_subvolume_create);
 	if (ret)
 		return ret;
 
@@ -703,8 +719,9 @@ static int __bch2_fs_upgrade_for_subvolumes(struct btree_trans *trans)
 		return ret;
 
 	if (!bkey_is_inode(k.k)) {
-		bch_err(trans->c, "root inode not found");
-		ret = -BCH_ERR_ENOENT_inode;
+		struct bch_fs *c = trans->c;
+		bch_err(c, "root inode not found");
+		ret = bch_err_throw(c, ENOENT_inode);
 		goto err;
 	}
 
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index 6687b9235d3c..6c2e1d647403 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -1112,7 +1112,7 @@ int bch2_write_super(struct bch_fs *c)
 		prt_str(&buf, ")");
 		bch2_fs_fatal_error(c, ": %s", buf.buf);
 		printbuf_exit(&buf);
-		ret = -BCH_ERR_sb_not_downgraded;
+		ret = bch_err_throw(c, sb_not_downgraded);
 		goto out;
 	}
 
@@ -1142,7 +1142,7 @@ int bch2_write_super(struct bch_fs *c)
 
 			if (c->opts.errors != BCH_ON_ERROR_continue &&
 			    c->opts.errors != BCH_ON_ERROR_fix_safe) {
-				ret = -BCH_ERR_erofs_sb_err;
+				ret = bch_err_throw(c, erofs_sb_err);
 				bch2_fs_fatal_error(c, "%s", buf.buf);
 			} else {
 				bch_err(c, "%s", buf.buf);
@@ -1161,7 +1161,7 @@ int bch2_write_super(struct bch_fs *c)
 				ca->disk_sb.seq);
 			bch2_fs_fatal_error(c, "%s", buf.buf);
 			printbuf_exit(&buf);
-			ret = -BCH_ERR_erofs_sb_err;
+			ret = bch_err_throw(c, erofs_sb_err);
 		}
 	}
 
@@ -1215,7 +1215,7 @@ int bch2_write_super(struct bch_fs *c)
 				  !can_mount_with_written), c,
 		": Unable to write superblock to sufficient devices (from %ps)",
 		(void *) _RET_IP_))
-		ret = -BCH_ERR_erofs_sb_err;
+		ret = bch_err_throw(c, erofs_sb_err);
 out:
 	/* Make new options visible after they're persistent: */
 	bch2_sb_update(c);
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 11579b74c640..397a69da5a75 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -219,23 +219,17 @@ static int bch2_fs_init_rw(struct bch_fs *);
 
 struct bch_fs *bch2_dev_to_fs(dev_t dev)
 {
-	struct bch_fs *c;
-
-	mutex_lock(&bch_fs_list_lock);
-	rcu_read_lock();
+	guard(mutex)(&bch_fs_list_lock);
+	guard(rcu)();
 
+	struct bch_fs *c;
 	list_for_each_entry(c, &bch_fs_list, list)
 		for_each_member_device_rcu(c, ca, NULL)
 			if (ca->disk_sb.bdev && ca->disk_sb.bdev->bd_dev == dev) {
 				closure_get(&c->cl);
-				goto found;
+				return c;
 			}
-	c = NULL;
-found:
-	rcu_read_unlock();
-	mutex_unlock(&bch_fs_list_lock);
-
-	return c;
+	return NULL;
 }
 
 static struct bch_fs *__bch2_uuid_to_fs(__uuid_t uuid)
@@ -480,16 +474,16 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
 	BUG_ON(!test_bit(BCH_FS_may_go_rw, &c->flags));
 
 	if (WARN_ON(c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info)))
-		return -BCH_ERR_erofs_no_alloc_info;
+		return bch_err_throw(c, erofs_no_alloc_info);
 
 	if (test_bit(BCH_FS_initial_gc_unfixed, &c->flags)) {
 		bch_err(c, "cannot go rw, unfixed btree errors");
-		return -BCH_ERR_erofs_unfixed_errors;
+		return bch_err_throw(c, erofs_unfixed_errors);
 	}
 
 	if (c->sb.features & BIT_ULL(BCH_FEATURE_small_image)) {
 		bch_err(c, "cannot go rw, filesystem is an unresized image file");
-		return -BCH_ERR_erofs_filesystem_full;
+		return bch_err_throw(c, erofs_filesystem_full);
 	}
 
 	if (test_bit(BCH_FS_rw, &c->flags))
@@ -507,13 +501,12 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
 
 	clear_bit(BCH_FS_clean_shutdown, &c->flags);
 
-	rcu_read_lock();
-	for_each_online_member_rcu(c, ca)
-		if (ca->mi.state == BCH_MEMBER_STATE_rw) {
-			bch2_dev_allocator_add(c, ca);
-			enumerated_ref_start(&ca->io_ref[WRITE]);
-		}
-	rcu_read_unlock();
+	scoped_guard(rcu)
+		for_each_online_member_rcu(c, ca)
+			if (ca->mi.state == BCH_MEMBER_STATE_rw) {
+				bch2_dev_allocator_add(c, ca);
+				enumerated_ref_start(&ca->io_ref[WRITE]);
+			}
 
 	bch2_recalc_capacity(c);
 
@@ -571,13 +564,13 @@ int bch2_fs_read_write(struct bch_fs *c)
 {
 	if (c->opts.recovery_pass_last &&
 	    c->opts.recovery_pass_last < BCH_RECOVERY_PASS_journal_replay)
-		return -BCH_ERR_erofs_norecovery;
+		return bch_err_throw(c, erofs_norecovery);
 
 	if (c->opts.nochanges)
-		return -BCH_ERR_erofs_nochanges;
+		return bch_err_throw(c, erofs_nochanges);
 
 	if (c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info))
-		return -BCH_ERR_erofs_no_alloc_info;
+		return bch_err_throw(c, erofs_no_alloc_info);
 
 	return __bch2_fs_read_write(c, false);
 }
@@ -762,7 +755,7 @@ static int bch2_fs_online(struct bch_fs *c)
 	if (c->sb.multi_device &&
 	    __bch2_uuid_to_fs(c->sb.uuid)) {
 		bch_err(c, "filesystem UUID already open");
-		return -BCH_ERR_filesystem_uuid_already_open;
+		return bch_err_throw(c, filesystem_uuid_already_open);
 	}
 
 	ret = bch2_fs_chardev_init(c);
@@ -821,7 +814,7 @@ static int bch2_fs_init_rw(struct bch_fs *c)
 				WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM, 1)) ||
 	    !(c->write_ref_wq = alloc_workqueue("bcachefs_write_ref",
 				WQ_FREEZABLE, 0)))
-		return -BCH_ERR_ENOMEM_fs_other_alloc;
+		return bch_err_throw(c, ENOMEM_fs_other_alloc);
 
 	int ret = bch2_fs_btree_interior_update_init(c) ?:
 		bch2_fs_btree_write_buffer_init(c) ?:
@@ -1002,7 +995,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts *opts,
 	    mempool_init_kvmalloc_pool(&c->btree_bounce_pool, 1,
 				       c->opts.btree_node_size) ||
 	    mempool_init_kmalloc_pool(&c->large_bkey_pool, 1, 2048)) {
-		ret = -BCH_ERR_ENOMEM_fs_other_alloc;
+		ret = bch_err_throw(c, ENOMEM_fs_other_alloc);
 		goto err;
 	}
 
@@ -1038,10 +1031,6 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts *opts,
 		ret = -EINVAL;
 		goto err;
 	}
-	bch_info(c, "Using encoding defined by superblock: utf8-%u.%u.%u",
-		 unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
-		 unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
-		 unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
 #else
 	if (c->sb.features & BIT_ULL(BCH_FEATURE_casefolding)) {
 		printk(KERN_ERR "Cannot mount a filesystem with casefolding on a kernel without CONFIG_UNICODE\n");
@@ -1159,8 +1148,15 @@ int bch2_fs_start(struct bch_fs *c)
 
 	print_mount_opts(c);
 
+#ifdef CONFIG_UNICODE
+	bch_info(c, "Using encoding defined by superblock: utf8-%u.%u.%u",
+		 unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
+		 unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
+		 unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
+#endif
+
 	if (!bch2_fs_may_start(c))
-		return -BCH_ERR_insufficient_devices_to_start;
+		return bch_err_throw(c, insufficient_devices_to_start);
 
 	down_write(&c->state_lock);
 	mutex_lock(&c->sb_lock);
@@ -1171,7 +1167,7 @@ int bch2_fs_start(struct bch_fs *c)
 			sizeof(struct bch_sb_field_ext) / sizeof(u64))) {
 		mutex_unlock(&c->sb_lock);
 		up_write(&c->state_lock);
-		ret = -BCH_ERR_ENOSPC_sb;
+		ret = bch_err_throw(c, ENOSPC_sb);
 		goto err;
 	}
 
@@ -1182,22 +1178,20 @@ int bch2_fs_start(struct bch_fs *c)
 		goto err;
 	}
 
-	rcu_read_lock();
-	for_each_online_member_rcu(c, ca)
-		bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx)->last_mount =
-		cpu_to_le64(now);
-	rcu_read_unlock();
+	scoped_guard(rcu)
+		for_each_online_member_rcu(c, ca)
+			bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx)->last_mount =
+			cpu_to_le64(now);
 
 	/*
 	 * Dno't write superblock yet: recovery might have to downgrade
 	 */
 	mutex_unlock(&c->sb_lock);
 
-	rcu_read_lock();
-	for_each_online_member_rcu(c, ca)
-		if (ca->mi.state == BCH_MEMBER_STATE_rw)
-			bch2_dev_allocator_add(c, ca);
-	rcu_read_unlock();
+	scoped_guard(rcu)
+		for_each_online_member_rcu(c, ca)
+			if (ca->mi.state == BCH_MEMBER_STATE_rw)
+				bch2_dev_allocator_add(c, ca);
 	bch2_recalc_capacity(c);
 	up_write(&c->state_lock);
 
@@ -1215,7 +1209,7 @@ int bch2_fs_start(struct bch_fs *c)
 		goto err;
 
 	if (bch2_fs_init_fault("fs_start")) {
-		ret = -BCH_ERR_injected_fs_start;
+		ret = bch_err_throw(c, injected_fs_start);
 		goto err;
 	}
 
@@ -1242,11 +1236,11 @@ static int bch2_dev_may_add(struct bch_sb *sb, struct bch_fs *c)
 	struct bch_member m = bch2_sb_member_get(sb, sb->dev_idx);
 
 	if (le16_to_cpu(sb->block_size) != block_sectors(c))
-		return -BCH_ERR_mismatched_block_size;
+		return bch_err_throw(c, mismatched_block_size);
 
 	if (le16_to_cpu(m.bucket_size) <
 	    BCH_SB_BTREE_NODE_SIZE(c->disk_sb.sb))
-		return -BCH_ERR_bucket_size_too_small;
+		return bch_err_throw(c, bucket_size_too_small);
 
 	return 0;
 }
@@ -1557,7 +1551,7 @@ static int bch2_dev_alloc(struct bch_fs *c, unsigned dev_idx)
 	bch2_dev_attach(c, ca, dev_idx);
 	return 0;
 err:
-	return -BCH_ERR_ENOMEM_dev_alloc;
+	return bch_err_throw(c, ENOMEM_dev_alloc);
 }
 
 static int __bch2_dev_attach_bdev(struct bch_dev *ca, struct bch_sb_handle *sb)
@@ -1567,13 +1561,13 @@ static int __bch2_dev_attach_bdev(struct bch_dev *ca, struct bch_sb_handle *sb)
 	if (bch2_dev_is_online(ca)) {
 		bch_err(ca, "already have device online in slot %u",
 			sb->sb->dev_idx);
-		return -BCH_ERR_device_already_online;
+		return bch_err_throw(ca->fs, device_already_online);
 	}
 
 	if (get_capacity(sb->bdev->bd_disk) <
 	    ca->mi.bucket_size * ca->mi.nbuckets) {
 		bch_err(ca, "cannot online: device too small");
-		return -BCH_ERR_device_size_too_small;
+		return bch_err_throw(ca->fs, device_size_too_small);
 	}
 
 	BUG_ON(!enumerated_ref_is_zero(&ca->io_ref[READ]));
@@ -1725,7 +1719,7 @@ int __bch2_dev_set_state(struct bch_fs *c, struct bch_dev *ca,
 		return 0;
 
 	if (!bch2_dev_state_allowed(c, ca, new_state, flags))
-		return -BCH_ERR_device_state_not_allowed;
+		return bch_err_throw(c, device_state_not_allowed);
 
 	if (new_state != BCH_MEMBER_STATE_rw)
 		__bch2_dev_read_only(c, ca);
@@ -1778,7 +1772,7 @@ int bch2_dev_remove(struct bch_fs *c, struct bch_dev *ca, int flags)
 
 	if (!bch2_dev_state_allowed(c, ca, BCH_MEMBER_STATE_failed, flags)) {
 		bch_err(ca, "Cannot remove without losing data");
-		ret = -BCH_ERR_device_state_not_allowed;
+		ret = bch_err_throw(c, device_state_not_allowed);
 		goto err;
 	}
 
@@ -1914,7 +1908,7 @@ int bch2_dev_add(struct bch_fs *c, const char *path)
 	if (list_empty(&c->list)) {
 		mutex_lock(&bch_fs_list_lock);
 		if (__bch2_uuid_to_fs(c->sb.uuid))
-			ret = -BCH_ERR_filesystem_uuid_already_open;
+			ret = bch_err_throw(c, filesystem_uuid_already_open);
 		else
 			list_add(&c->list, &bch_fs_list);
 		mutex_unlock(&bch_fs_list_lock);
@@ -2101,7 +2095,7 @@ int bch2_dev_offline(struct bch_fs *c, struct bch_dev *ca, int flags)
 	if (!bch2_dev_state_allowed(c, ca, BCH_MEMBER_STATE_failed, flags)) {
 		bch_err(ca, "Cannot offline required disk");
 		up_write(&c->state_lock);
-		return -BCH_ERR_device_state_not_allowed;
+		return bch_err_throw(c, device_state_not_allowed);
 	}
 
 	__bch2_dev_offline(c, ca);
@@ -2140,7 +2134,7 @@ int bch2_dev_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets)
 	if (nbuckets > BCH_MEMBER_NBUCKETS_MAX) {
 		bch_err(ca, "New device size too big (%llu greater than max %u)",
 			nbuckets, BCH_MEMBER_NBUCKETS_MAX);
-		ret = -BCH_ERR_device_size_too_big;
+		ret = bch_err_throw(c, device_size_too_big);
 		goto err;
 	}
 
@@ -2148,7 +2142,7 @@ int bch2_dev_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets)
 	    get_capacity(ca->disk_sb.bdev->bd_disk) <
 	    ca->mi.bucket_size * nbuckets) {
 		bch_err(ca, "New size larger than device");
-		ret = -BCH_ERR_device_size_too_small;
+		ret = bch_err_throw(c, device_size_too_small);
 		goto err;
 	}
 
@@ -2383,7 +2377,7 @@ struct bch_fs *bch2_fs_open(darray_const_str *devices,
 	}
 
 	if (opts->nochanges && !opts->read_only) {
-		ret = -BCH_ERR_erofs_nochanges;
+		ret = bch_err_throw(c, erofs_nochanges);
 		goto err_print;
 	}
 
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index 1a55196d69f1..05848375cea2 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -26,6 +26,7 @@
 #include "disk_groups.h"
 #include "ec.h"
 #include "enumerated_ref.h"
+#include "error.h"
 #include "inode.h"
 #include "journal.h"
 #include "journal_reclaim.h"
@@ -37,6 +38,7 @@
 #include "rebalance.h"
 #include "recovery_passes.h"
 #include "replicas.h"
+#include "sb-errors.h"
 #include "super-io.h"
 #include "tests.h"
 
@@ -143,6 +145,7 @@ do {									\
 write_attribute(trigger_gc);
 write_attribute(trigger_discards);
 write_attribute(trigger_invalidates);
+write_attribute(trigger_journal_commit);
 write_attribute(trigger_journal_flush);
 write_attribute(trigger_journal_writes);
 write_attribute(trigger_btree_cache_shrink);
@@ -151,6 +154,7 @@ write_attribute(trigger_btree_updates);
 write_attribute(trigger_freelist_wakeup);
 write_attribute(trigger_recalc_capacity);
 write_attribute(trigger_delete_dead_snapshots);
+write_attribute(trigger_emergency_read_only);
 read_attribute(gc_gens_pos);
 
 read_attribute(uuid);
@@ -172,6 +176,7 @@ read_attribute(btree_write_stats);
 
 read_attribute(btree_cache_size);
 read_attribute(compression_stats);
+read_attribute(errors);
 read_attribute(journal_debug);
 read_attribute(btree_cache);
 read_attribute(btree_key_cache);
@@ -353,6 +358,9 @@ SHOW(bch2_fs)
 	if (attr == &sysfs_compression_stats)
 		bch2_compression_stats_to_text(out, c);
 
+	if (attr == &sysfs_errors)
+		bch2_fs_errors_to_text(out, c);
+
 	if (attr == &sysfs_new_stripes)
 		bch2_new_stripes_to_text(out, c);
 
@@ -428,6 +436,9 @@ STORE(bch2_fs)
 	if (attr == &sysfs_trigger_invalidates)
 		bch2_do_invalidates(c);
 
+	if (attr == &sysfs_trigger_journal_commit)
+		bch2_journal_flush(&c->journal);
+
 	if (attr == &sysfs_trigger_journal_flush) {
 		bch2_journal_flush_all_pins(&c->journal);
 		bch2_journal_meta(&c->journal);
@@ -448,6 +459,16 @@ STORE(bch2_fs)
 	if (attr == &sysfs_trigger_delete_dead_snapshots)
 		__bch2_delete_dead_snapshots(c);
 
+	if (attr == &sysfs_trigger_emergency_read_only) {
+		struct printbuf buf = PRINTBUF;
+		bch2_log_msg_start(c, &buf);
+
+		prt_printf(&buf, "shutdown by sysfs\n");
+		bch2_fs_emergency_read_only2(c, &buf);
+		bch2_print_str(c, KERN_ERR, buf.buf);
+		printbuf_exit(&buf);
+	}
+
 #ifdef CONFIG_BCACHEFS_TESTS
 	if (attr == &sysfs_perf_test) {
 		char *tmp = kstrdup(buf, GFP_KERNEL), *p = tmp;
@@ -483,6 +504,7 @@ struct attribute *bch2_fs_files[] = {
 	&sysfs_recovery_status,
 
 	&sysfs_compression_stats,
+	&sysfs_errors,
 
 #ifdef CONFIG_BCACHEFS_TESTS
 	&sysfs_perf_test,
@@ -571,6 +593,7 @@ struct attribute *bch2_fs_internal_files[] = {
 	&sysfs_trigger_gc,
 	&sysfs_trigger_discards,
 	&sysfs_trigger_invalidates,
+	&sysfs_trigger_journal_commit,
 	&sysfs_trigger_journal_flush,
 	&sysfs_trigger_journal_writes,
 	&sysfs_trigger_btree_cache_shrink,
@@ -579,6 +602,7 @@ struct attribute *bch2_fs_internal_files[] = {
 	&sysfs_trigger_freelist_wakeup,
 	&sysfs_trigger_recalc_capacity,
 	&sysfs_trigger_delete_dead_snapshots,
+	&sysfs_trigger_emergency_read_only,
 
 	&sysfs_gc_gens_pos,
 
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index 8cb5b40704fd..dc09532796af 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -199,6 +199,50 @@ DECLARE_EVENT_CLASS(bio,
 		  (unsigned long long)__entry->sector, __entry->nr_sector)
 );
 
+/* errors */
+
+TRACE_EVENT(error_throw,
+	TP_PROTO(struct bch_fs *c, int bch_err, unsigned long ip),
+	TP_ARGS(c, bch_err, ip),
+
+	TP_STRUCT__entry(
+		__field(dev_t,		dev			)
+		__field(int,		err			)
+		__array(char,		err_str, 32		)
+		__array(char,		ip, 32			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= c->dev;
+		__entry->err		= bch_err;
+		strscpy(__entry->err_str, bch2_err_str(bch_err), sizeof(__entry->err_str));
+		snprintf(__entry->ip, sizeof(__entry->ip), "%ps", (void *) ip);
+	),
+
+	TP_printk("%d,%d %s ret %s", MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ip, __entry->err_str)
+);
+
+TRACE_EVENT(error_downcast,
+	TP_PROTO(int bch_err, int std_err, unsigned long ip),
+	TP_ARGS(bch_err, std_err, ip),
+
+	TP_STRUCT__entry(
+		__array(char,		bch_err, 32		)
+		__array(char,		std_err, 32		)
+		__array(char,		ip, 32			)
+	),
+
+	TP_fast_assign(
+		strscpy(__entry->bch_err, bch2_err_str(bch_err), sizeof(__entry->bch_err));
+		strscpy(__entry->std_err, bch2_err_str(std_err), sizeof(__entry->std_err));
+		snprintf(__entry->ip, sizeof(__entry->ip), "%ps", (void *) ip);
+	),
+
+	TP_printk("%s ret %s -> %s %s", __entry->ip,
+		  __entry->bch_err, __entry->std_err, __entry->ip)
+);
+
 /* disk_accounting.c */
 
 TRACE_EVENT(accounting_mem_insert,
@@ -1431,28 +1475,19 @@ DEFINE_EVENT(fs_str, data_update,
 	TP_ARGS(c, str)
 );
 
-DEFINE_EVENT(fs_str, io_move_created_rebalance,
+DEFINE_EVENT(fs_str, io_move_pred,
 	TP_PROTO(struct bch_fs *c, const char *str),
 	TP_ARGS(c, str)
 );
 
-TRACE_EVENT(error_downcast,
-	TP_PROTO(int bch_err, int std_err, unsigned long ip),
-	TP_ARGS(bch_err, std_err, ip),
-
-	TP_STRUCT__entry(
-		__array(char,		bch_err, 32		)
-		__array(char,		std_err, 32		)
-		__array(char,		ip, 32			)
-	),
-
-	TP_fast_assign(
-		strscpy(__entry->bch_err, bch2_err_str(bch_err), sizeof(__entry->bch_err));
-		strscpy(__entry->std_err, bch2_err_str(std_err), sizeof(__entry->std_err));
-		snprintf(__entry->ip, sizeof(__entry->ip), "%ps", (void *) ip);
-	),
+DEFINE_EVENT(fs_str, io_move_created_rebalance,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
+);
 
-	TP_printk("%s -> %s %s", __entry->bch_err, __entry->std_err, __entry->ip)
+DEFINE_EVENT(fs_str, io_move_evacuate_bucket,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 #ifdef CONFIG_BCACHEFS_PATH_TRACEPOINTS
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 653f0ff4b057..85c491fcf1a3 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -64,7 +64,10 @@ static void gfs2_tune_init(struct gfs2_tune *gt)
 
 void free_sbd(struct gfs2_sbd *sdp)
 {
+	struct super_block *sb = sdp->sd_vfs;
+
 	free_percpu(sdp->sd_lkstats);
+	sb->s_fs_info = NULL;
 	kfree(sdp);
 }
 
@@ -1314,7 +1317,6 @@ fail_iput:
 	iput(sdp->sd_inode);
 fail_free:
 	free_sbd(sdp);
-	sb->s_fs_info = NULL;
 	return error;
 }
 
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 748125653d6c..c3c8842920d2 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -764,7 +764,6 @@ fail_reg:
 	fs_err(sdp, "error %d adding sysfs files\n", error);
 	kobject_put(&sdp->sd_kobj);
 	wait_for_completion(&sdp->sd_kobj_unregister);
-	sb->s_fs_info = NULL;
 	return error;
 }
 
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 6d63b958c4bb..cf35ad3f818a 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -180,7 +180,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 	clp->cl_proto = cl_init->proto;
 	clp->cl_nconnect = cl_init->nconnect;
 	clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1;
-	clp->cl_net = get_net(cl_init->net);
+	clp->cl_net = get_net_track(cl_init->net, &clp->cl_ns_tracker, GFP_KERNEL);
 
 #if IS_ENABLED(CONFIG_NFS_LOCALIO)
 	seqlock_init(&clp->cl_boot_lock);
@@ -250,7 +250,7 @@ void nfs_free_client(struct nfs_client *clp)
 	if (!IS_ERR(clp->cl_rpcclient))
 		rpc_shutdown_client(clp->cl_rpcclient);
 
-	put_net(clp->cl_net);
+	put_net_track(clp->cl_net, &clp->cl_ns_tracker);
 	put_nfs_version(clp->cl_nfs_mod);
 	kfree(clp->cl_hostname);
 	kfree(clp->cl_acceptor);
@@ -439,7 +439,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
 			spin_unlock(&nn->nfs_client_lock);
 			new = rpc_ops->init_client(new, cl_init);
 			if (!IS_ERR(new))
-				 nfs_local_probe(new);
+				 nfs_local_probe_async(new);
 			return new;
 		}
 
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 8bdbc4dca89c..10ef46e29b25 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -1021,13 +1021,6 @@ out:
 		nfs_inode_find_state_and_recover(inode, stateid);
 }
 
-void nfs_remove_bad_delegation(struct inode *inode,
-		const nfs4_stateid *stateid)
-{
-	nfs_revoke_delegation(inode, stateid);
-}
-EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation);
-
 void nfs_delegation_mark_returned(struct inode *inode,
 		const nfs4_stateid *stateid)
 {
@@ -1070,6 +1063,24 @@ out_rcu_unlock:
 }
 
 /**
+ * nfs_remove_bad_delegation - handle delegations that are unusable
+ * @inode: inode to process
+ * @stateid: the delegation's stateid
+ *
+ * If the server ACK-ed our FREE_STATEID then clean
+ * up the delegation, else mark and keep the revoked state.
+ */
+void nfs_remove_bad_delegation(struct inode *inode,
+		const nfs4_stateid *stateid)
+{
+	if (stateid && stateid->type == NFS4_FREED_STATEID_TYPE)
+		nfs_delegation_mark_returned(inode, stateid);
+	else
+		nfs_revoke_delegation(inode, stateid);
+}
+EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation);
+
+/**
  * nfs_expire_unused_delegation_types
  * @clp: client to process
  * @flags: delegation types to expire
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index e6909cafab68..df4807460596 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1129,6 +1129,8 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 		nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
 		break;
 	case -NFS4ERR_DELAY:
+		nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
+		fallthrough;
 	case -NFS4ERR_GRACE:
 		rpc_delay(task, FF_LAYOUT_POLL_RETRY_MAX);
 		break;
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 4a304cf17c4b..656d5c50bbce 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -400,7 +400,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
 		 * keep ds_clp even if DS is local, so that if local IO cannot
 		 * proceed somehow, we can fall back to NFS whenever we want.
 		 */
-		nfs_local_probe(ds->ds_clp);
+		nfs_local_probe_async(ds->ds_clp);
 		max_payload =
 			nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient),
 				       NULL);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 119e447758b9..8ab7868807a7 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -557,6 +557,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 			set_nlink(inode, fattr->nlink);
 		else if (fattr_supported & NFS_ATTR_FATTR_NLINK)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_NLINK);
+		else
+			set_nlink(inode, 1);
 		if (fattr->valid & NFS_ATTR_FATTR_OWNER)
 			inode->i_uid = fattr->uid;
 		else if (fattr_supported & NFS_ATTR_FATTR_OWNER)
@@ -633,6 +635,34 @@ nfs_fattr_fixup_delegated(struct inode *inode, struct nfs_fattr *fattr)
 	}
 }
 
+static void nfs_set_timestamps_to_ts(struct inode *inode, struct iattr *attr)
+{
+	unsigned int cache_flags = 0;
+
+	if (attr->ia_valid & ATTR_MTIME_SET) {
+		struct timespec64 ctime = inode_get_ctime(inode);
+		struct timespec64 mtime = inode_get_mtime(inode);
+		struct timespec64 now;
+		int updated = 0;
+
+		now = inode_set_ctime_current(inode);
+		if (!timespec64_equal(&now, &ctime))
+			updated |= S_CTIME;
+
+		inode_set_mtime_to_ts(inode, attr->ia_mtime);
+		if (!timespec64_equal(&now, &mtime))
+			updated |= S_MTIME;
+
+		inode_maybe_inc_iversion(inode, updated);
+		cache_flags |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME;
+	}
+	if (attr->ia_valid & ATTR_ATIME_SET) {
+		inode_set_atime_to_ts(inode, attr->ia_atime);
+		cache_flags |= NFS_INO_INVALID_ATIME;
+	}
+	NFS_I(inode)->cache_validity &= ~cache_flags;
+}
+
 static void nfs_update_timestamps(struct inode *inode, unsigned int ia_valid)
 {
 	enum file_time_flags time_flags = 0;
@@ -701,14 +731,27 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 
 	if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) {
 		spin_lock(&inode->i_lock);
-		nfs_update_timestamps(inode, attr->ia_valid);
+		if (attr->ia_valid & ATTR_MTIME_SET) {
+			nfs_set_timestamps_to_ts(inode, attr);
+			attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET|
+						ATTR_ATIME|ATTR_ATIME_SET);
+		} else {
+			nfs_update_timestamps(inode, attr->ia_valid);
+			attr->ia_valid &= ~(ATTR_MTIME|ATTR_ATIME);
+		}
 		spin_unlock(&inode->i_lock);
-		attr->ia_valid &= ~(ATTR_MTIME | ATTR_ATIME);
 	} else if (nfs_have_delegated_atime(inode) &&
 		   attr->ia_valid & ATTR_ATIME &&
 		   !(attr->ia_valid & ATTR_MTIME)) {
-		nfs_update_delegated_atime(inode);
-		attr->ia_valid &= ~ATTR_ATIME;
+		if (attr->ia_valid & ATTR_ATIME_SET) {
+			spin_lock(&inode->i_lock);
+			nfs_set_timestamps_to_ts(inode, attr);
+			spin_unlock(&inode->i_lock);
+			attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET);
+		} else {
+			nfs_update_delegated_atime(inode);
+			attr->ia_valid &= ~ATTR_ATIME;
+		}
 	}
 
 	/* Optimization: if the end result is no change, don't RPC */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 6655e5f32ec6..69c2c10ee658 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -455,7 +455,6 @@ extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
 
 #if IS_ENABLED(CONFIG_NFS_LOCALIO)
 /* localio.c */
-extern void nfs_local_probe(struct nfs_client *);
 extern void nfs_local_probe_async(struct nfs_client *);
 extern void nfs_local_probe_async_work(struct work_struct *);
 extern struct nfsd_file *nfs_local_open_fh(struct nfs_client *,
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index 4ec952f9f47d..510d0a16cfe9 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -171,7 +171,7 @@ static bool nfs_server_uuid_is_local(struct nfs_client *clp)
  * - called after alloc_client and init_client (so cl_rpcclient exists)
  * - this function is idempotent, it can be called for old or new clients
  */
-void nfs_local_probe(struct nfs_client *clp)
+static void nfs_local_probe(struct nfs_client *clp)
 {
 	/* Disallow localio if disabled via sysfs or AUTH_SYS isn't used */
 	if (!localio_enabled ||
@@ -191,14 +191,16 @@ void nfs_local_probe(struct nfs_client *clp)
 		nfs_localio_enable_client(clp);
 	nfs_uuid_end(&clp->cl_uuid);
 }
-EXPORT_SYMBOL_GPL(nfs_local_probe);
 
 void nfs_local_probe_async_work(struct work_struct *work)
 {
 	struct nfs_client *clp =
 		container_of(work, struct nfs_client, cl_local_probe_work);
 
+	if (!refcount_inc_not_zero(&clp->cl_count))
+		return;
 	nfs_local_probe(clp);
+	nfs_put_client(clp);
 }
 
 void nfs_local_probe_async(struct nfs_client *clp)
@@ -207,14 +209,16 @@ void nfs_local_probe_async(struct nfs_client *clp)
 }
 EXPORT_SYMBOL_GPL(nfs_local_probe_async);
 
-static inline struct nfsd_file *nfs_local_file_get(struct nfsd_file *nf)
+static inline void nfs_local_file_put(struct nfsd_file *localio)
 {
-	return nfs_to->nfsd_file_get(nf);
-}
+	/* nfs_to_nfsd_file_put_local() expects an __rcu pointer
+	 * but we have a __kernel pointer.  It is always safe
+	 * to cast a __kernel pointer to an __rcu pointer
+	 * because the cast only weakens what is known about the pointer.
+	 */
+	struct nfsd_file __rcu *nf = (struct nfsd_file __rcu*) localio;
 
-static inline void nfs_local_file_put(struct nfsd_file *nf)
-{
-	nfs_to->nfsd_file_put(nf);
+	nfs_to_nfsd_file_put_local(&nf);
 }
 
 /*
@@ -226,12 +230,13 @@ static inline void nfs_local_file_put(struct nfsd_file *nf)
 static struct nfsd_file *
 __nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 		    struct nfs_fh *fh, struct nfs_file_localio *nfl,
+		    struct nfsd_file __rcu **pnf,
 		    const fmode_t mode)
 {
 	struct nfsd_file *localio;
 
 	localio = nfs_open_local_fh(&clp->cl_uuid, clp->cl_rpcclient,
-				    cred, fh, nfl, mode);
+				    cred, fh, nfl, pnf, mode);
 	if (IS_ERR(localio)) {
 		int status = PTR_ERR(localio);
 		trace_nfs_local_open_fh(fh, mode, status);
@@ -258,7 +263,7 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 		  struct nfs_fh *fh, struct nfs_file_localio *nfl,
 		  const fmode_t mode)
 {
-	struct nfsd_file *nf, *new, __rcu **pnf;
+	struct nfsd_file *nf, __rcu **pnf;
 
 	if (!nfs_server_is_local(clp))
 		return NULL;
@@ -270,29 +275,9 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 	else
 		pnf = &nfl->ro_file;
 
-	new = NULL;
-	rcu_read_lock();
-	nf = rcu_dereference(*pnf);
-	if (!nf) {
-		rcu_read_unlock();
-		new = __nfs_local_open_fh(clp, cred, fh, nfl, mode);
-		if (IS_ERR(new))
-			return NULL;
-		rcu_read_lock();
-		/* try to swap in the pointer */
-		spin_lock(&clp->cl_uuid.lock);
-		nf = rcu_dereference_protected(*pnf, 1);
-		if (!nf) {
-			nf = new;
-			new = NULL;
-			rcu_assign_pointer(*pnf, nf);
-		}
-		spin_unlock(&clp->cl_uuid.lock);
-	}
-	nf = nfs_local_file_get(nf);
-	rcu_read_unlock();
-	if (new)
-		nfs_to_nfsd_file_put_local(new);
+	nf = __nfs_local_open_fh(clp, cred, fh, nfl, pnf, mode);
+	if (IS_ERR(nf))
+		return NULL;
 	return nf;
 }
 EXPORT_SYMBOL_GPL(nfs_local_open_fh);
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 0282d93c8bcc..aafd15a4afce 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -21,6 +21,7 @@ int nfs42_proc_allocate(struct file *, loff_t, loff_t);
 ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t,
 			struct nl4_server *, nfs4_stateid *, bool);
 int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
+int nfs42_proc_zero_range(struct file *, loff_t, loff_t);
 loff_t nfs42_proc_llseek(struct file *, loff_t, int);
 int nfs42_proc_layoutstats_generic(struct nfs_server *,
 				   struct nfs42_layoutstat_data *);
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 5cf52ece96ac..01c01f45358b 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -146,7 +146,8 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
 
 	err = nfs42_proc_fallocate(&msg, filep, offset, len);
 	if (err == -EOPNOTSUPP)
-		NFS_SERVER(inode)->caps &= ~NFS_CAP_ALLOCATE;
+		NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE |
+					     NFS_CAP_ZERO_RANGE);
 
 	inode_unlock(inode);
 	return err;
@@ -169,7 +170,31 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 	if (err == 0)
 		truncate_pagecache_range(inode, offset, (offset + len) -1);
 	if (err == -EOPNOTSUPP)
-		NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE;
+		NFS_SERVER(inode)->caps &= ~(NFS_CAP_DEALLOCATE |
+					     NFS_CAP_ZERO_RANGE);
+
+	inode_unlock(inode);
+	return err;
+}
+
+int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len)
+{
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ZERO_RANGE],
+	};
+	struct inode *inode = file_inode(filep);
+	int err;
+
+	if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE))
+		return -EOPNOTSUPP;
+
+	inode_lock(inode);
+
+	err = nfs42_proc_fallocate(&msg, filep, offset, len);
+	if (err == 0)
+		truncate_pagecache_range(inode, offset, (offset + len) -1);
+	if (err == -EOPNOTSUPP)
+		NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE;
 
 	inode_unlock(inode);
 	return err;
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index b1b663468249..4cc915d5741d 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -174,6 +174,18 @@
 					 decode_putfh_maxsz + \
 					 decode_deallocate_maxsz + \
 					 decode_getattr_maxsz)
+#define NFS4_enc_zero_range_sz		(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_deallocate_maxsz + \
+					 encode_allocate_maxsz + \
+					 encode_getattr_maxsz)
+#define NFS4_dec_zero_range_sz		(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_deallocate_maxsz + \
+					 decode_allocate_maxsz + \
+					 decode_getattr_maxsz)
 #define NFS4_enc_read_plus_sz		(compound_encode_hdr_maxsz + \
 					 encode_sequence_maxsz + \
 					 encode_putfh_maxsz + \
@@ -649,6 +661,27 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
 }
 
 /*
+ * Encode ZERO_RANGE request
+ */
+static void nfs4_xdr_enc_zero_range(struct rpc_rqst *req,
+				    struct xdr_stream *xdr,
+				    const void *data)
+{
+	const struct nfs42_falloc_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->falloc_fh, &hdr);
+	encode_deallocate(xdr, args, &hdr);
+	encode_allocate(xdr, args, &hdr);
+	encode_getfattr(xdr, args->falloc_bitmask, &hdr);
+	encode_nops(&hdr);
+}
+
+/*
  * Encode READ_PLUS request
  */
 static void nfs4_xdr_enc_read_plus(struct rpc_rqst *req,
@@ -1511,6 +1544,37 @@ out:
 }
 
 /*
+ * Decode ZERO_RANGE request
+ */
+static int nfs4_xdr_dec_zero_range(struct rpc_rqst *rqstp,
+				   struct xdr_stream *xdr,
+				   void *data)
+{
+	struct nfs42_falloc_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_deallocate(xdr, res);
+	if (status)
+		goto out;
+	status = decode_allocate(xdr, res);
+	if (status)
+		goto out;
+	decode_getfattr(xdr, res->falloc_fattr, res->falloc_server);
+out:
+	return status;
+}
+
+/*
  * Decode READ_PLUS request
  */
 static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 7d383d29a995..d3ca91f60fc1 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -67,8 +67,7 @@ struct nfs4_minor_version_ops {
 	void	(*free_lock_state)(struct nfs_server *,
 			struct nfs4_lock_state *);
 	int	(*test_and_free_expired)(struct nfs_server *,
-					 const nfs4_stateid *,
-					 const struct cred *);
+					 nfs4_stateid *, const struct cred *);
 	struct nfs_seqid *
 		(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t);
 	void	(*session_trunk)(struct rpc_clnt *clnt,
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 1cd9652f3c28..5e9d66f3466c 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -225,8 +225,14 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
 	if (!S_ISREG(inode->i_mode))
 		return -EOPNOTSUPP;
 
-	if ((mode != 0) && (mode != (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE)))
+	switch (mode) {
+	case 0:
+	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
+	case FALLOC_FL_ZERO_RANGE:
+		break;
+	default:
 		return -EOPNOTSUPP;
+	}
 
 	ret = inode_newsize_ok(inode, offset + len);
 	if (ret < 0)
@@ -234,6 +240,8 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
 
 	if (mode & FALLOC_FL_PUNCH_HOLE)
 		return nfs42_proc_deallocate(filep, offset, len);
+	else if (mode & FALLOC_FL_ZERO_RANGE)
+		return nfs42_proc_zero_range(filep, offset ,len);
 	return nfs42_proc_allocate(filep, offset, len);
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index b1d2122bd5a7..341740fa293d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -105,7 +105,7 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp,
 		bool is_privileged);
 static int nfs41_test_stateid(struct nfs_server *, const nfs4_stateid *,
 			      const struct cred *);
-static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *,
+static int nfs41_free_stateid(struct nfs_server *, nfs4_stateid *,
 			      const struct cred *, bool);
 #endif
 
@@ -325,14 +325,14 @@ static void nfs4_bitmap_copy_adjust(__u32 *dst, const __u32 *src,
 
 	if (nfs_have_delegated_mtime(inode)) {
 		if (!(cache_validity & NFS_INO_INVALID_ATIME))
-			dst[1] &= ~FATTR4_WORD1_TIME_ACCESS;
+			dst[1] &= ~(FATTR4_WORD1_TIME_ACCESS|FATTR4_WORD1_TIME_ACCESS_SET);
 		if (!(cache_validity & NFS_INO_INVALID_MTIME))
-			dst[1] &= ~FATTR4_WORD1_TIME_MODIFY;
+			dst[1] &= ~(FATTR4_WORD1_TIME_MODIFY|FATTR4_WORD1_TIME_MODIFY_SET);
 		if (!(cache_validity & NFS_INO_INVALID_CTIME))
-			dst[1] &= ~FATTR4_WORD1_TIME_METADATA;
+			dst[1] &= ~(FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY_SET);
 	} else if (nfs_have_delegated_atime(inode)) {
 		if (!(cache_validity & NFS_INO_INVALID_ATIME))
-			dst[1] &= ~FATTR4_WORD1_TIME_ACCESS;
+			dst[1] &= ~(FATTR4_WORD1_TIME_ACCESS|FATTR4_WORD1_TIME_ACCESS_SET);
 	}
 }
 
@@ -2903,16 +2903,14 @@ static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st
 }
 
 static int nfs40_test_and_free_expired_stateid(struct nfs_server *server,
-					       const nfs4_stateid *stateid,
-					       const struct cred *cred)
+					       nfs4_stateid *stateid, const struct cred *cred)
 {
 	return -NFS4ERR_BAD_STATEID;
 }
 
 #if defined(CONFIG_NFS_V4_1)
 static int nfs41_test_and_free_expired_stateid(struct nfs_server *server,
-					       const nfs4_stateid *stateid,
-					       const struct cred *cred)
+					       nfs4_stateid *stateid, const struct cred *cred)
 {
 	int status;
 
@@ -2921,6 +2919,7 @@ static int nfs41_test_and_free_expired_stateid(struct nfs_server *server,
 		break;
 	case NFS4_INVALID_STATEID_TYPE:
 	case NFS4_SPECIAL_STATEID_TYPE:
+	case NFS4_FREED_STATEID_TYPE:
 		return -NFS4ERR_BAD_STATEID;
 	case NFS4_REVOKED_STATEID_TYPE:
 		goto out_free;
@@ -3976,8 +3975,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 		     FATTR4_WORD0_CASE_INSENSITIVE |
 		     FATTR4_WORD0_CASE_PRESERVING;
 	if (minorversion)
-		bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT |
-			     FATTR4_WORD2_OPEN_ARGUMENTS;
+		bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT;
+	if (minorversion > 1)
+		bitmask[2] |= FATTR4_WORD2_OPEN_ARGUMENTS;
 
 	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
 	if (status == 0) {
@@ -5164,13 +5164,15 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_
 }
 
 static struct dentry *nfs4_do_mkdir(struct inode *dir, struct dentry *dentry,
-				    struct nfs4_createdata *data)
+				    struct nfs4_createdata *data, int *statusp)
 {
-	int status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &data->msg,
+	struct dentry *ret;
+
+	*statusp = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &data->msg,
 				    &data->arg.seq_args, &data->res.seq_res, 1);
 
-	if (status)
-		return ERR_PTR(status);
+	if (*statusp)
+		return NULL;
 
 	spin_lock(&dir->i_lock);
 	/* Creating a directory bumps nlink in the parent */
@@ -5179,7 +5181,11 @@ static struct dentry *nfs4_do_mkdir(struct inode *dir, struct dentry *dentry,
 				      data->res.fattr->time_start,
 				      NFS_INO_INVALID_DATA);
 	spin_unlock(&dir->i_lock);
-	return nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr);
+	ret = nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr);
+	if (!IS_ERR(ret))
+		return ret;
+	*statusp = PTR_ERR(ret);
+	return NULL;
 }
 
 static void nfs4_free_createdata(struct nfs4_createdata *data)
@@ -5240,17 +5246,18 @@ static int nfs4_proc_symlink(struct inode *dir, struct dentry *dentry,
 
 static struct dentry *_nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
 				       struct iattr *sattr,
-				       struct nfs4_label *label)
+				       struct nfs4_label *label, int *statusp)
 {
 	struct nfs4_createdata *data;
-	struct dentry *ret = ERR_PTR(-ENOMEM);
+	struct dentry *ret = NULL;
 
+	*statusp = -ENOMEM;
 	data = nfs4_alloc_createdata(dir, &dentry->d_name, sattr, NF4DIR);
 	if (data == NULL)
 		goto out;
 
 	data->arg.label = label;
-	ret = nfs4_do_mkdir(dir, dentry, data);
+	ret = nfs4_do_mkdir(dir, dentry, data, statusp);
 
 	nfs4_free_createdata(data);
 out:
@@ -5273,11 +5280,12 @@ static struct dentry *nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
 	if (!(server->attr_bitmask[2] & FATTR4_WORD2_MODE_UMASK))
 		sattr->ia_mode &= ~current_umask();
 	do {
-		alias = _nfs4_proc_mkdir(dir, dentry, sattr, label);
-		err = PTR_ERR_OR_ZERO(alias);
+		alias = _nfs4_proc_mkdir(dir, dentry, sattr, label, &err);
 		trace_nfs4_mkdir(dir, &dentry->d_name, err);
-		err = nfs4_handle_exception(NFS_SERVER(dir), err,
-				&exception);
+		if (err)
+			alias = ERR_PTR(nfs4_handle_exception(NFS_SERVER(dir),
+							      err,
+							      &exception));
 	} while (exception.retry);
 	nfs4_label_release_security(label);
 
@@ -6211,6 +6219,8 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen,
 	struct nfs_server *server = NFS_SERVER(inode);
 	int ret;
 
+	if (unlikely(NFS_FH(inode)->size == 0))
+		return -ENODATA;
 	if (!nfs4_server_supports_acls(server, type))
 		return -EOPNOTSUPP;
 	ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
@@ -6285,6 +6295,9 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf,
 {
 	struct nfs4_exception exception = { };
 	int err;
+
+	if (unlikely(NFS_FH(inode)->size == 0))
+		return -ENODATA;
 	do {
 		err = __nfs4_proc_set_acl(inode, buf, buflen, type);
 		trace_nfs4_set_acl(inode, err);
@@ -10611,7 +10624,7 @@ static const struct rpc_call_ops nfs41_free_stateid_ops = {
  * Note: this function is always asynchronous.
  */
 static int nfs41_free_stateid(struct nfs_server *server,
-		const nfs4_stateid *stateid,
+		nfs4_stateid *stateid,
 		const struct cred *cred,
 		bool privileged)
 {
@@ -10651,6 +10664,7 @@ static int nfs41_free_stateid(struct nfs_server *server,
 	if (IS_ERR(task))
 		return PTR_ERR(task);
 	rpc_put_task(task);
+	stateid->type = NFS4_FREED_STATEID_TYPE;
 	return 0;
 }
 
@@ -10817,6 +10831,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_OFFLOAD_CANCEL
 		| NFS_CAP_COPY_NOTIFY
 		| NFS_CAP_DEALLOCATE
+		| NFS_CAP_ZERO_RANGE
 		| NFS_CAP_SEEK
 		| NFS_CAP_LAYOUTSTATS
 		| NFS_CAP_CLONE
@@ -10852,7 +10867,7 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
 
 static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 {
-	ssize_t error, error2, error3;
+	ssize_t error, error2, error3, error4;
 	size_t left = size;
 
 	error = generic_listxattr(dentry, list, left);
@@ -10875,8 +10890,16 @@ static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 	error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, left);
 	if (error3 < 0)
 		return error3;
+	if (list) {
+		list += error3;
+		left -= error3;
+	}
+
+	error4 = security_inode_listsecurity(d_inode(dentry), list, left);
+	if (error4 < 0)
+		return error4;
 
-	error += error2 + error3;
+	error += error2 + error3 + error4;
 	if (size && error > size)
 		return -ERANGE;
 	return error;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 55bef5fbfa47..318afde38057 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7711,6 +7711,7 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC42(LISTXATTRS,	enc_listxattrs,		dec_listxattrs),
 	PROC42(REMOVEXATTR,	enc_removexattr,	dec_removexattr),
 	PROC42(READ_PLUS,	enc_read_plus,		dec_read_plus),
+	PROC42(ZERO_RANGE,	enc_zero_range,		dec_zero_range),
 };
 
 static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 91ef486f40b9..b4ccdf78d4dd 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -830,10 +830,16 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 				.servername = clp->cl_hostname,
 				.connect_timeout = connect_timeout,
 				.reconnect_timeout = connect_timeout,
+				.xprtsec = clp->cl_xprtsec,
 			};
 
-			if (da->da_transport != clp->cl_proto)
+			if (da->da_transport != clp->cl_proto &&
+			    clp->cl_proto != XPRT_TRANSPORT_TCP_TLS)
 				continue;
+			if (da->da_transport == XPRT_TRANSPORT_TCP &&
+			    mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS)
+				xprt_args.ident = XPRT_TRANSPORT_TCP_TLS;
+
 			if (da->da_addr.ss_family != clp->cl_addr.ss_family)
 				continue;
 			/* Add this address as an alias */
@@ -841,6 +847,9 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 					rpc_clnt_test_and_add_xprt, NULL);
 			continue;
 		}
+		if (da->da_transport == XPRT_TRANSPORT_TCP &&
+		    mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS)
+			da->da_transport = XPRT_TRANSPORT_TCP_TLS;
 		clp = get_v3_ds_connect(mds_srv,
 				&da->da_addr,
 				da->da_addrlen, da->da_transport,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 81bd1b9aba17..3c1fa320b3f1 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -56,7 +56,8 @@ static int nfs_return_empty_folio(struct folio *folio)
 {
 	folio_zero_segment(folio, 0, folio_size(folio));
 	folio_mark_uptodate(folio);
-	folio_unlock(folio);
+	if (nfs_netfs_folio_unlock(folio))
+		folio_unlock(folio);
 	return 0;
 }
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 9eea9e62afc9..91b5503b6f74 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1052,6 +1052,16 @@ int nfs_reconfigure(struct fs_context *fc)
 	sync_filesystem(sb);
 
 	/*
+	 * The SB_RDONLY flag has been removed from the superblock during
+	 * mounts to prevent interference between different filesystems.
+	 * Similarly, it is also necessary to ignore the SB_RDONLY flag
+	 * during reconfiguration; otherwise, it may also result in the
+	 * creation of redundant superblocks when mounting a directory with
+	 * different rw and ro flags multiple times.
+	 */
+	fc->sb_flags_mask &= ~SB_RDONLY;
+
+	/*
 	 * Userspace mount programs that send binary options generally send
 	 * them populated with default values. We have no way to know which
 	 * ones were explicitly specified. Fall back to legacy behavior and
@@ -1308,8 +1318,17 @@ int nfs_get_tree_common(struct fs_context *fc)
 	if (IS_ERR(server))
 		return PTR_ERR(server);
 
+	/*
+	 * When NFS_MOUNT_UNSHARED is not set, NFS forces the sharing of a
+	 * superblock among each filesystem that mounts sub-directories
+	 * belonging to a single exported root path.
+	 * To prevent interference between different filesystems, the
+	 * SB_RDONLY flag should be removed from the superblock.
+	 */
 	if (server->flags & NFS_MOUNT_UNSHARED)
 		compare_super = NULL;
+	else
+		fc->sb_flags &= ~SB_RDONLY;
 
 	/* -o noac implies -o sync */
 	if (server->flags & NFS_MOUNT_NOAC)
diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c
index 37cb2b776435..545148d42dcc 100644
--- a/fs/nfs/sysfs.c
+++ b/fs/nfs/sysfs.c
@@ -387,6 +387,33 @@ static inline void nfs_sysfs_add_nfsv41_server(struct nfs_server *server)
 }
 #endif /* CONFIG_NFS_V4_1 */
 
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+
+static ssize_t
+localio_show(struct kobject *kobj, struct kobj_attribute *attr,
+				char *buf)
+{
+	struct nfs_server *server = container_of(kobj, struct nfs_server, kobj);
+	bool localio = nfs_server_is_local(server->nfs_client);
+	return sysfs_emit(buf, "%d\n", localio);
+}
+
+static struct kobj_attribute nfs_sysfs_attr_localio = __ATTR_RO(localio);
+
+static void nfs_sysfs_add_nfs_localio_server(struct nfs_server *server)
+{
+	int ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_localio.attr,
+				       nfs_netns_server_namespace(&server->kobj));
+	if (ret < 0)
+		pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n",
+			server->s_sysfs_id, ret);
+}
+#else
+static inline void nfs_sysfs_add_nfs_localio_server(struct nfs_server *server)
+{
+}
+#endif /* IS_ENABLED(CONFIG_NFS_LOCALIO) */
+
 void nfs_sysfs_add_server(struct nfs_server *server)
 {
 	int ret;
@@ -405,6 +432,7 @@ void nfs_sysfs_add_server(struct nfs_server *server)
 			server->s_sysfs_id, ret);
 
 	nfs_sysfs_add_nfsv41_server(server);
+	nfs_sysfs_add_nfs_localio_server(server);
 }
 EXPORT_SYMBOL_GPL(nfs_sysfs_add_server);
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 23df8b214474..374fc6b34c79 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -632,19 +632,19 @@ static void nfs_write_error(struct nfs_page *req, int error)
  * Find an associated nfs write request, and prepare to flush it out
  * May return an error if the user signalled nfs_wait_on_request().
  */
-static int nfs_page_async_flush(struct folio *folio,
-				struct writeback_control *wbc,
-				struct nfs_pageio_descriptor *pgio)
+static int nfs_do_writepage(struct folio *folio, struct writeback_control *wbc,
+		struct nfs_pageio_descriptor *pgio)
 {
 	struct nfs_page *req;
-	int ret = 0;
+	int ret;
+
+	nfs_pageio_cond_complete(pgio, folio->index);
 
 	req = nfs_lock_and_join_requests(folio);
 	if (!req)
-		goto out;
-	ret = PTR_ERR(req);
+		return 0;
 	if (IS_ERR(req))
-		goto out;
+		return PTR_ERR(req);
 
 	nfs_folio_set_writeback(folio);
 	WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags));
@@ -654,7 +654,6 @@ static int nfs_page_async_flush(struct folio *folio,
 	if (nfs_error_is_fatal_on_server(ret))
 		goto out_launder;
 
-	ret = 0;
 	if (!nfs_pageio_add_request(pgio, req)) {
 		ret = pgio->pg_error;
 		/*
@@ -662,28 +661,20 @@ static int nfs_page_async_flush(struct folio *folio,
 		 */
 		if (nfs_error_is_fatal_on_server(ret))
 			goto out_launder;
-		if (wbc->sync_mode == WB_SYNC_NONE)
-			ret = AOP_WRITEPAGE_ACTIVATE;
 		folio_redirty_for_writepage(wbc, folio);
 		nfs_redirty_request(req);
 		pgio->pg_error = 0;
-	} else
-		nfs_add_stats(folio->mapping->host,
-			      NFSIOS_WRITEPAGES, 1);
-out:
-	return ret;
+		return ret;
+	}
+
+	nfs_add_stats(folio->mapping->host, NFSIOS_WRITEPAGES, 1);
+	return 0;
+
 out_launder:
 	nfs_write_error(req, ret);
 	return 0;
 }
 
-static int nfs_do_writepage(struct folio *folio, struct writeback_control *wbc,
-			    struct nfs_pageio_descriptor *pgio)
-{
-	nfs_pageio_cond_complete(pgio, folio->index);
-	return nfs_page_async_flush(folio, wbc, pgio);
-}
-
 /*
  * Write an mmapped page to the server.
  */
@@ -703,17 +694,6 @@ static int nfs_writepage_locked(struct folio *folio,
 	return err;
 }
 
-static int nfs_writepages_callback(struct folio *folio,
-				   struct writeback_control *wbc, void *data)
-{
-	int ret;
-
-	ret = nfs_do_writepage(folio, wbc, data);
-	if (ret != AOP_WRITEPAGE_ACTIVATE)
-		folio_unlock(folio);
-	return ret;
-}
-
 static void nfs_io_completion_commit(void *inode)
 {
 	nfs_commit_inode(inode, 0);
@@ -749,11 +729,15 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 	}
 
 	do {
+		struct folio *folio = NULL;
+
 		nfs_pageio_init_write(&pgio, inode, priority, false,
 				      &nfs_async_write_completion_ops);
 		pgio.pg_io_completion = ioc;
-		err = write_cache_pages(mapping, wbc, nfs_writepages_callback,
-					&pgio);
+		while ((folio = writeback_iter(mapping, wbc, folio, &err))) {
+			err = nfs_do_writepage(folio, wbc, &pgio);
+			folio_unlock(folio);
+		}
 		pgio.pg_error = 0;
 		nfs_pageio_complete(&pgio);
 		if (err == -EAGAIN && mntflags & NFS_MOUNT_SOFTERR)
diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c
index 6a0bdea6d644..05c7c16e37ab 100644
--- a/fs/nfs_common/nfslocalio.c
+++ b/fs/nfs_common/nfslocalio.c
@@ -151,8 +151,7 @@ EXPORT_SYMBOL_GPL(nfs_localio_enable_client);
  */
 static bool nfs_uuid_put(nfs_uuid_t *nfs_uuid)
 {
-	LIST_HEAD(local_files);
-	struct nfs_file_localio *nfl, *tmp;
+	struct nfs_file_localio *nfl;
 
 	spin_lock(&nfs_uuid->lock);
 	if (unlikely(!rcu_access_pointer(nfs_uuid->net))) {
@@ -166,17 +165,42 @@ static bool nfs_uuid_put(nfs_uuid_t *nfs_uuid)
 		nfs_uuid->dom = NULL;
 	}
 
-	list_splice_init(&nfs_uuid->files, &local_files);
-	spin_unlock(&nfs_uuid->lock);
-
 	/* Walk list of files and ensure their last references dropped */
-	list_for_each_entry_safe(nfl, tmp, &local_files, list) {
-		nfs_close_local_fh(nfl);
+
+	while ((nfl = list_first_entry_or_null(&nfs_uuid->files,
+					       struct nfs_file_localio,
+					       list)) != NULL) {
+		/* If nfs_uuid is already NULL, nfs_close_local_fh is
+		 * closing and we must wait, else we unlink and close.
+		 */
+		if (rcu_access_pointer(nfl->nfs_uuid) == NULL) {
+			/* nfs_close_local_fh() is doing the
+			 * close and we must wait. until it unlinks
+			 */
+			wait_var_event_spinlock(nfl,
+						list_first_entry_or_null(
+							&nfs_uuid->files,
+							struct nfs_file_localio,
+							list) != nfl,
+						&nfs_uuid->lock);
+			continue;
+		}
+
+		/* Remove nfl from nfs_uuid->files list */
+		list_del_init(&nfl->list);
+		spin_unlock(&nfs_uuid->lock);
+
+		nfs_to_nfsd_file_put_local(&nfl->ro_file);
+		nfs_to_nfsd_file_put_local(&nfl->rw_file);
 		cond_resched();
-	}
 
-	spin_lock(&nfs_uuid->lock);
-	BUG_ON(!list_empty(&nfs_uuid->files));
+		spin_lock(&nfs_uuid->lock);
+		/* Now we can allow racing nfs_close_local_fh() to
+		 * skip the locking.
+		 */
+		RCU_INIT_POINTER(nfl->nfs_uuid, NULL);
+		wake_up_var_locked(&nfl->nfs_uuid, &nfs_uuid->lock);
+	}
 
 	/* Remove client from nn->local_clients */
 	if (nfs_uuid->list_lock) {
@@ -237,6 +261,7 @@ static void nfs_uuid_add_file(nfs_uuid_t *nfs_uuid, struct nfs_file_localio *nfl
 struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid,
 		   struct rpc_clnt *rpc_clnt, const struct cred *cred,
 		   const struct nfs_fh *nfs_fh, struct nfs_file_localio *nfl,
+		   struct nfsd_file __rcu **pnf,
 		   const fmode_t fmode)
 {
 	struct net *net;
@@ -261,10 +286,9 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid,
 	rcu_read_unlock();
 	/* We have an implied reference to net thanks to nfsd_net_try_get */
 	localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt,
-					     cred, nfs_fh, fmode);
-	if (IS_ERR(localio))
-		nfs_to_nfsd_net_put(net);
-	else
+					     cred, nfs_fh, pnf, fmode);
+	nfs_to_nfsd_net_put(net);
+	if (!IS_ERR(localio))
 		nfs_uuid_add_file(uuid, nfl);
 
 	return localio;
@@ -273,8 +297,6 @@ EXPORT_SYMBOL_GPL(nfs_open_local_fh);
 
 void nfs_close_local_fh(struct nfs_file_localio *nfl)
 {
-	struct nfsd_file *ro_nf = NULL;
-	struct nfsd_file *rw_nf = NULL;
 	nfs_uuid_t *nfs_uuid;
 
 	rcu_read_lock();
@@ -285,28 +307,39 @@ void nfs_close_local_fh(struct nfs_file_localio *nfl)
 		return;
 	}
 
-	ro_nf = rcu_access_pointer(nfl->ro_file);
-	rw_nf = rcu_access_pointer(nfl->rw_file);
-	if (ro_nf || rw_nf) {
-		spin_lock(&nfs_uuid->lock);
-		if (ro_nf)
-			ro_nf = rcu_dereference_protected(xchg(&nfl->ro_file, NULL), 1);
-		if (rw_nf)
-			rw_nf = rcu_dereference_protected(xchg(&nfl->rw_file, NULL), 1);
-
-		/* Remove nfl from nfs_uuid->files list */
-		RCU_INIT_POINTER(nfl->nfs_uuid, NULL);
-		list_del_init(&nfl->list);
+	spin_lock(&nfs_uuid->lock);
+	if (!rcu_access_pointer(nfl->nfs_uuid)) {
+		/* nfs_uuid_put has finished here */
 		spin_unlock(&nfs_uuid->lock);
 		rcu_read_unlock();
-
-		if (ro_nf)
-			nfs_to_nfsd_file_put_local(ro_nf);
-		if (rw_nf)
-			nfs_to_nfsd_file_put_local(rw_nf);
 		return;
 	}
+	if (list_empty(&nfs_uuid->files)) {
+		/* nfs_uuid_put() has started closing files, wait for it
+		 * to finished
+		 */
+		spin_unlock(&nfs_uuid->lock);
+		rcu_read_unlock();
+		wait_var_event(&nfl->nfs_uuid,
+			       rcu_access_pointer(nfl->nfs_uuid) == NULL);
+		return;
+	}
+	/* tell nfs_uuid_put() to wait for us */
+	RCU_INIT_POINTER(nfl->nfs_uuid, NULL);
+	spin_unlock(&nfs_uuid->lock);
 	rcu_read_unlock();
+
+	nfs_to_nfsd_file_put_local(&nfl->ro_file);
+	nfs_to_nfsd_file_put_local(&nfl->rw_file);
+
+	/* Remove nfl from nfs_uuid->files list and signal nfs_uuid_put()
+	 * that we are done.  The moment we drop the spinlock the
+	 * nfs_uuid could be freed.
+	 */
+	spin_lock(&nfs_uuid->lock);
+	list_del_init(&nfl->list);
+	wake_up_var_locked(&nfl->nfs_uuid, &nfs_uuid->lock);
+	spin_unlock(&nfs_uuid->lock);
 }
 EXPORT_SYMBOL_GPL(nfs_close_local_fh);
 
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index ab85e6a2454f..e108b6c705b4 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -378,15 +378,41 @@ nfsd_file_put(struct nfsd_file *nf)
  * the reference of the nfsd_file.
  */
 struct net *
-nfsd_file_put_local(struct nfsd_file *nf)
+nfsd_file_put_local(struct nfsd_file __rcu **pnf)
 {
-	struct net *net = nf->nf_net;
+	struct nfsd_file *nf;
+	struct net *net = NULL;
 
-	nfsd_file_put(nf);
+	nf = unrcu_pointer(xchg(pnf, NULL));
+	if (nf) {
+		net = nf->nf_net;
+		nfsd_file_put(nf);
+	}
 	return net;
 }
 
 /**
+ * nfsd_file_get_local - get nfsd_file reference and reference to net
+ * @nf: nfsd_file of which to put the reference
+ *
+ * Get reference to both the nfsd_file and nf->nf_net.
+ */
+struct nfsd_file *
+nfsd_file_get_local(struct nfsd_file *nf)
+{
+	struct net *net = nf->nf_net;
+
+	if (nfsd_net_try_get(net)) {
+		nf = nfsd_file_get(nf);
+		if (!nf)
+			nfsd_net_put(net);
+	} else {
+		nf = NULL;
+	}
+	return nf;
+}
+
+/**
  * nfsd_file_file - get the backing file of an nfsd_file
  * @nf: nfsd_file of which to access the backing file.
  *
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index 5865f9c72712..722b26c71e45 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -62,7 +62,8 @@ void nfsd_file_cache_shutdown(void);
 int nfsd_file_cache_start_net(struct net *net);
 void nfsd_file_cache_shutdown_net(struct net *net);
 void nfsd_file_put(struct nfsd_file *nf);
-struct net *nfsd_file_put_local(struct nfsd_file *nf);
+struct net *nfsd_file_put_local(struct nfsd_file __rcu **nf);
+struct nfsd_file *nfsd_file_get_local(struct nfsd_file *nf);
 struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
 struct file *nfsd_file_file(struct nfsd_file *nf);
 void nfsd_file_close_inode_sync(struct inode *inode);
diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
index 238647fa379e..80d9ff6608a7 100644
--- a/fs/nfsd/localio.c
+++ b/fs/nfsd/localio.c
@@ -24,21 +24,6 @@
 #include "filecache.h"
 #include "cache.h"
 
-static const struct nfsd_localio_operations nfsd_localio_ops = {
-	.nfsd_net_try_get  = nfsd_net_try_get,
-	.nfsd_net_put  = nfsd_net_put,
-	.nfsd_open_local_fh = nfsd_open_local_fh,
-	.nfsd_file_put_local = nfsd_file_put_local,
-	.nfsd_file_get = nfsd_file_get,
-	.nfsd_file_put = nfsd_file_put,
-	.nfsd_file_file = nfsd_file_file,
-};
-
-void nfsd_localio_ops_init(void)
-{
-	nfs_to = &nfsd_localio_ops;
-}
-
 /**
  * nfsd_open_local_fh - lookup a local filehandle @nfs_fh and map to nfsd_file
  *
@@ -47,6 +32,7 @@ void nfsd_localio_ops_init(void)
  * @rpc_clnt: rpc_clnt that the client established
  * @cred: cred that the client established
  * @nfs_fh: filehandle to lookup
+ * @nfp: place to find the nfsd_file, or store it if it was non-NULL
  * @fmode: fmode_t to use for open
  *
  * This function maps a local fh to a path on a local filesystem.
@@ -57,10 +43,11 @@ void nfsd_localio_ops_init(void)
  * set. Caller (NFS client) is responsible for calling nfsd_net_put and
  * nfsd_file_put (via nfs_to_nfsd_file_put_local).
  */
-struct nfsd_file *
+static struct nfsd_file *
 nfsd_open_local_fh(struct net *net, struct auth_domain *dom,
 		   struct rpc_clnt *rpc_clnt, const struct cred *cred,
-		   const struct nfs_fh *nfs_fh, const fmode_t fmode)
+		   const struct nfs_fh *nfs_fh, struct nfsd_file __rcu **pnf,
+		   const fmode_t fmode)
 {
 	int mayflags = NFSD_MAY_LOCALIO;
 	struct svc_cred rq_cred;
@@ -71,6 +58,15 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom,
 	if (nfs_fh->size > NFS4_FHSIZE)
 		return ERR_PTR(-EINVAL);
 
+	if (!nfsd_net_try_get(net))
+		return ERR_PTR(-ENXIO);
+
+	rcu_read_lock();
+	localio = nfsd_file_get(rcu_dereference(*pnf));
+	rcu_read_unlock();
+	if (localio)
+		return localio;
+
 	/* nfs_fh -> svc_fh */
 	fh_init(&fh, NFS4_FHSIZE);
 	fh.fh_handle.fh_size = nfs_fh->size;
@@ -92,9 +88,47 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom,
 	if (rq_cred.cr_group_info)
 		put_group_info(rq_cred.cr_group_info);
 
+	if (!IS_ERR(localio)) {
+		struct nfsd_file *new;
+		if (!nfsd_net_try_get(net)) {
+			nfsd_file_put(localio);
+			nfsd_net_put(net);
+			return ERR_PTR(-ENXIO);
+		}
+		nfsd_file_get(localio);
+	again:
+		new = unrcu_pointer(cmpxchg(pnf, NULL, RCU_INITIALIZER(localio)));
+		if (new) {
+			/* Some other thread installed an nfsd_file */
+			if (nfsd_file_get(new) == NULL)
+				goto again;
+			/*
+			 * Drop the ref we were going to install and the
+			 * one we were going to return.
+			 */
+			nfsd_file_put(localio);
+			nfsd_file_put(localio);
+			localio = new;
+		}
+	} else
+		nfsd_net_put(net);
+
 	return localio;
 }
-EXPORT_SYMBOL_GPL(nfsd_open_local_fh);
+
+static const struct nfsd_localio_operations nfsd_localio_ops = {
+	.nfsd_net_try_get  = nfsd_net_try_get,
+	.nfsd_net_put  = nfsd_net_put,
+	.nfsd_open_local_fh = nfsd_open_local_fh,
+	.nfsd_file_put_local = nfsd_file_put_local,
+	.nfsd_file_get_local = nfsd_file_get_local,
+	.nfsd_file_file = nfsd_file_file,
+};
+
+void nfsd_localio_ops_init(void)
+{
+	nfs_to = &nfsd_localio_ops;
+}
 
 /*
  * UUID_IS_LOCAL XDR functions
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 34ed242e1063..1e99a35691cd 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -913,7 +913,8 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 	struct ntfs_inode *ni = ntfs_i(inode);
 	u64 valid = ni->i_valid;
 	struct ntfs_sb_info *sbi = ni->mi.sbi;
-	struct page *page, **pages = NULL;
+	struct page **pages = NULL;
+	struct folio *folio;
 	size_t written = 0;
 	u8 frame_bits = NTFS_LZNT_CUNIT + sbi->cluster_bits;
 	u32 frame_size = 1u << frame_bits;
@@ -923,7 +924,6 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 	u64 frame_vbo;
 	pgoff_t index;
 	bool frame_uptodate;
-	struct folio *folio;
 
 	if (frame_size < PAGE_SIZE) {
 		/*
@@ -977,8 +977,7 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 					    pages_per_frame);
 			if (err) {
 				for (ip = 0; ip < pages_per_frame; ip++) {
-					page = pages[ip];
-					folio = page_folio(page);
+					folio = page_folio(pages[ip]);
 					folio_unlock(folio);
 					folio_put(folio);
 				}
@@ -989,10 +988,9 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 		ip = off >> PAGE_SHIFT;
 		off = offset_in_page(valid);
 		for (; ip < pages_per_frame; ip++, off = 0) {
-			page = pages[ip];
-			folio = page_folio(page);
-			zero_user_segment(page, off, PAGE_SIZE);
-			flush_dcache_page(page);
+			folio = page_folio(pages[ip]);
+			folio_zero_segment(folio, off, PAGE_SIZE);
+			flush_dcache_folio(folio);
 			folio_mark_uptodate(folio);
 		}
 
@@ -1001,8 +999,7 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 		ni_unlock(ni);
 
 		for (ip = 0; ip < pages_per_frame; ip++) {
-			page = pages[ip];
-			folio = page_folio(page);
+			folio = page_folio(pages[ip]);
 			folio_mark_uptodate(folio);
 			folio_unlock(folio);
 			folio_put(folio);
@@ -1046,8 +1043,7 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 				if (err) {
 					for (ip = 0; ip < pages_per_frame;
 					     ip++) {
-						page = pages[ip];
-						folio = page_folio(page);
+						folio = page_folio(pages[ip]);
 						folio_unlock(folio);
 						folio_put(folio);
 					}
@@ -1065,10 +1061,10 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 		for (;;) {
 			size_t cp, tail = PAGE_SIZE - off;
 
-			page = pages[ip];
-			cp = copy_page_from_iter_atomic(page, off,
+			folio = page_folio(pages[ip]);
+			cp = copy_folio_from_iter_atomic(folio, off,
 							min(tail, bytes), from);
-			flush_dcache_page(page);
+			flush_dcache_folio(folio);
 
 			copied += cp;
 			bytes -= cp;
@@ -1088,9 +1084,8 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 		ni_unlock(ni);
 
 		for (ip = 0; ip < pages_per_frame; ip++) {
-			page = pages[ip];
-			ClearPageDirty(page);
-			folio = page_folio(page);
+			folio = page_folio(pages[ip]);
+			folio_clear_dirty(folio);
 			folio_mark_uptodate(folio);
 			folio_unlock(folio);
 			folio_put(folio);
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 89d2dbbb742c..5200a0f3cafc 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -155,6 +155,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
 	struct cached_fids *cfids;
 	const char *npath;
 	int retries = 0, cur_sleep = 1;
+	__le32 lease_flags = 0;
 
 	if (cifs_sb->root == NULL)
 		return -ENOENT;
@@ -201,6 +202,8 @@ replay_again:
 	}
 	spin_unlock(&cfids->cfid_list_lock);
 
+	pfid = &cfid->fid;
+
 	/*
 	 * Skip any prefix paths in @path as lookup_noperm_positive_unlocked() ends up
 	 * calling ->lookup() which already adds those through
@@ -222,6 +225,25 @@ replay_again:
 			rc = -ENOENT;
 			goto out;
 		}
+		if (dentry->d_parent && server->dialect >= SMB30_PROT_ID) {
+			struct cached_fid *parent_cfid;
+
+			spin_lock(&cfids->cfid_list_lock);
+			list_for_each_entry(parent_cfid, &cfids->entries, entry) {
+				if (parent_cfid->dentry == dentry->d_parent) {
+					cifs_dbg(FYI, "found a parent cached file handle\n");
+					if (parent_cfid->has_lease && parent_cfid->time) {
+						lease_flags
+							|= SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE;
+						memcpy(pfid->parent_lease_key,
+						       parent_cfid->fid.lease_key,
+						       SMB2_LEASE_KEY_SIZE);
+					}
+					break;
+				}
+			}
+			spin_unlock(&cfids->cfid_list_lock);
+		}
 	}
 	cfid->dentry = dentry;
 	cfid->tcon = tcon;
@@ -236,7 +258,6 @@ replay_again:
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
-	pfid = &cfid->fid;
 	server->ops->new_lease_key(pfid);
 
 	memset(rqst, 0, sizeof(rqst));
@@ -256,6 +277,7 @@ replay_again:
 				   FILE_READ_EA,
 		.disposition = FILE_OPEN,
 		.fid = pfid,
+		.lease_flags = lease_flags,
 		.replay = !!(retries),
 	};
 
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index fb04e263611c..0a5266ecfd15 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -70,7 +70,6 @@ bool require_gcm_256; /* false by default */
 bool enable_negotiate_signing; /* false by default */
 unsigned int global_secflags = CIFSSEC_DEF;
 /* unsigned int ntlmv2_support = 0; */
-unsigned int sign_CIFS_PDUs = 1;
 
 /*
  * Global transaction id (XID) information
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 3b32116b0b49..ad7dd16db3e9 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -556,7 +556,7 @@ struct smb_version_operations {
 	void (*set_oplock_level)(struct cifsInodeInfo *cinode, __u32 oplock, __u16 epoch,
 				 bool *purge_cache);
 	/* create lease context buffer for CREATE request */
-	char * (*create_lease_buf)(u8 *lease_key, u8 oplock);
+	char * (*create_lease_buf)(u8 *lease_key, u8 oplock, u8 *parent_lease_key, __le32 le_flags);
 	/* parse lease context buffer and return oplock/epoch info */
 	__u8 (*parse_lease_buf)(void *buf, __u16 *epoch, char *lkey);
 	ssize_t (*copychunk_range)(const unsigned int,
@@ -773,6 +773,7 @@ struct TCP_Server_Info {
 	char workstation_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL];
 	__u32 sequence_number; /* for signing, protected by srv_mutex */
 	__u32 reconnect_instance; /* incremented on each reconnect */
+	__le32 session_key_id; /* retrieved from negotiate response and send in session setup request */
 	struct session_key session_key;
 	unsigned long lstrp; /* when we got last response from this server */
 	struct cifs_secmech secmech; /* crypto sec mech functs, descriptors */
@@ -1441,6 +1442,7 @@ struct cifs_open_parms {
 	bool reconnect:1;
 	bool replay:1; /* indicates that this open is for a replay */
 	struct kvec *ea_cctx;
+	__le32 lease_flags;
 };
 
 struct cifs_fid {
@@ -1448,6 +1450,7 @@ struct cifs_fid {
 	__u64 persistent_fid;	/* persist file id for smb2 */
 	__u64 volatile_fid;	/* volatile file id for smb2 */
 	__u8 lease_key[SMB2_LEASE_KEY_SIZE];	/* lease key for smb2 */
+	__u8 parent_lease_key[SMB2_LEASE_KEY_SIZE];
 	__u8 create_guid[16];
 	__u32 access;
 	struct cifs_pending_open *pending_open;
@@ -1988,8 +1991,7 @@ require use of the stronger protocol */
  * TCP_Server_Info->		TCP_Server_Info			cifs_get_tcp_session
  * reconnect_mutex
  * TCP_Server_Info->srv_mutex	TCP_Server_Info			cifs_get_tcp_session
- * cifs_ses->session_mutex		cifs_ses		sesInfoAlloc
- *				cifs_tcon
+ * cifs_ses->session_mutex	cifs_ses			sesInfoAlloc
  * cifs_tcon->open_file_lock	cifs_tcon->openFileList		tconInfoAlloc
  *				cifs_tcon->pending_opens
  * cifs_tcon->stat_lock		cifs_tcon->bytes_read		tconInfoAlloc
@@ -2008,21 +2010,25 @@ require use of the stronger protocol */
  *				->oplock_credits
  *				->reconnect_instance
  * cifs_ses->ses_lock		(anything that is not protected by another lock and can change)
+ *								sesInfoAlloc
  * cifs_ses->iface_lock		cifs_ses->iface_list		sesInfoAlloc
  *				->iface_count
  *				->iface_last_update
- * cifs_ses->chan_lock		cifs_ses->chans
+ * cifs_ses->chan_lock		cifs_ses->chans			sesInfoAlloc
  *				->chans_need_reconnect
  *				->chans_in_reconnect
  * cifs_tcon->tc_lock		(anything that is not protected by another lock and can change)
+ *								tcon_info_alloc
  * inode->i_rwsem, taken by fs/netfs/locking.c e.g. should be taken before cifsInodeInfo locks
  * cifsInodeInfo->open_file_lock	cifsInodeInfo->openFileList	cifs_alloc_inode
  * cifsInodeInfo->writers_lock	cifsInodeInfo->writers		cifsInodeInfo_alloc
  * cifsInodeInfo->lock_sem	cifsInodeInfo->llist		cifs_init_once
  *				->can_cache_brlcks
  * cifsInodeInfo->deferred_lock	cifsInodeInfo->deferred_closes	cifsInodeInfo_alloc
- * cached_fids->cfid_list_lock	cifs_tcon->cfids->entries	 init_cached_dirs
- * cifsFileInfo->fh_mutex		cifsFileInfo			cifs_new_fileinfo
+ * cached_fids->cfid_list_lock	cifs_tcon->cfids->entries	init_cached_dirs
+ * cached_fid->fid_lock		(anything that is not protected by another lock and can change)
+ *								init_cached_dir
+ * cifsFileInfo->fh_mutex	cifsFileInfo			cifs_new_fileinfo
  * cifsFileInfo->file_info_lock	cifsFileInfo->count		cifs_new_fileinfo
  *				->invalidHandle			initiate_cifs_search
  *				->oplock_break_cancelled
diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h
index 1b79fe07476f..d9cf7db0ac35 100644
--- a/fs/smb/client/cifspdu.h
+++ b/fs/smb/client/cifspdu.h
@@ -597,7 +597,7 @@ typedef union smb_com_session_setup_andx {
 		__le16 MaxBufferSize;
 		__le16 MaxMpxCount;
 		__le16 VcNumber;
-		__u32 SessionKey;
+		__le32 SessionKey;
 		__le16 SecurityBlobLength;
 		__u32 Reserved;
 		__le32 Capabilities;	/* see below */
@@ -616,7 +616,7 @@ typedef union smb_com_session_setup_andx {
 		__le16 MaxBufferSize;
 		__le16 MaxMpxCount;
 		__le16 VcNumber;
-		__u32 SessionKey;
+		__le32 SessionKey;
 		__le16 CaseInsensitivePasswordLength; /* ASCII password len */
 		__le16 CaseSensitivePasswordLength; /* Unicode password length*/
 		__u32 Reserved;	/* see below */
@@ -654,7 +654,7 @@ typedef union smb_com_session_setup_andx {
 		__le16 MaxBufferSize;
 		__le16 MaxMpxCount;
 		__le16 VcNumber;
-		__u32 SessionKey;
+		__le32 SessionKey;
 		__le16 PasswordLength;
 		__u32 Reserved; /* encrypt key len and offset */
 		__le16 ByteCount;
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 477792c07d45..7216fcec79e8 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -498,6 +498,7 @@ CIFSSMBNegotiate(const unsigned int xid,
 	server->max_rw = le32_to_cpu(pSMBr->MaxRawSize);
 	cifs_dbg(NOISY, "Max buf = %d\n", ses->server->maxBuf);
 	server->capabilities = le32_to_cpu(pSMBr->Capabilities);
+	server->session_key_id = pSMBr->SessionKey;
 	server->timeAdj = (int)(__s16)le16_to_cpu(pSMBr->ServerTimeZone);
 	server->timeAdj *= 60;
 
@@ -2753,10 +2754,10 @@ int cifs_query_reparse_point(const unsigned int xid,
 
 	io_req->TotalParameterCount = 0;
 	io_req->TotalDataCount = 0;
-	io_req->MaxParameterCount = cpu_to_le32(2);
+	io_req->MaxParameterCount = cpu_to_le32(0);
 	/* BB find exact data count max from sess structure BB */
 	io_req->MaxDataCount = cpu_to_le32(CIFSMaxBufSize & 0xFFFFFF00);
-	io_req->MaxSetupCount = 4;
+	io_req->MaxSetupCount = 1;
 	io_req->Reserved = 0;
 	io_req->ParameterOffset = 0;
 	io_req->DataCount = 0;
@@ -2783,6 +2784,22 @@ int cifs_query_reparse_point(const unsigned int xid,
 		goto error;
 	}
 
+	/* SetupCount must be 1, otherwise offset to ByteCount is incorrect. */
+	if (io_rsp->SetupCount != 1) {
+		rc = -EIO;
+		goto error;
+	}
+
+	/*
+	 * ReturnedDataLen is output length of executed IOCTL.
+	 * DataCount is output length transferred over network.
+	 * Check that we have full FSCTL_GET_REPARSE_POINT buffer.
+	 */
+	if (data_count != le16_to_cpu(io_rsp->ReturnedDataLen)) {
+		rc = -EIO;
+		goto error;
+	}
+
 	end = 2 + get_bcc(&io_rsp->hdr) + (__u8 *)&io_rsp->ByteCount;
 	start = (__u8 *)&io_rsp->hdr.Protocol + data_offset;
 	if (start >= end) {
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 6bf04d9a5491..024817d40c5f 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -377,6 +377,13 @@ static int __cifs_reconnect(struct TCP_Server_Info *server,
 	if (!cifs_tcp_ses_needs_reconnect(server, 1))
 		return 0;
 
+	/*
+	 * if smb session has been marked for reconnect, also reconnect all
+	 * connections. This way, the other connections do not end up bad.
+	 */
+	if (mark_smb_session)
+		cifs_signal_cifsd_for_reconnect(server, mark_smb_session);
+
 	cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session);
 
 	cifs_abort_connection(server);
@@ -385,7 +392,8 @@ static int __cifs_reconnect(struct TCP_Server_Info *server,
 		try_to_freeze();
 		cifs_server_lock(server);
 
-		if (!cifs_swn_set_server_dstaddr(server)) {
+		if (!cifs_swn_set_server_dstaddr(server) &&
+		    !SERVER_IS_CHAN(server)) {
 			/* resolve the hostname again to make sure that IP address is up-to-date */
 			rc = reconn_set_ipaddr_from_hostname(server);
 			cifs_dbg(FYI, "%s: reconn_set_ipaddr_from_hostname: rc=%d\n", __func__, rc);
diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index d1e95632ac54..1c6e5389c51f 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -23,6 +23,7 @@
 #include "fs_context.h"
 #include "cifs_ioctl.h"
 #include "fscache.h"
+#include "cached_dir.h"
 
 static void
 renew_parental_timestamps(struct dentry *direntry)
@@ -190,6 +191,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifs_open_parms oparms;
 	int rdwr_for_fscache = 0;
+	__le32 lease_flags = 0;
 
 	*oplock = 0;
 	if (tcon->ses->server->oplocks)
@@ -312,6 +314,26 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 		create_options |= CREATE_OPTION_READONLY;
 
 retry_open:
+	if (tcon->cfids && direntry->d_parent && server->dialect >= SMB30_PROT_ID) {
+		struct cached_fid *parent_cfid;
+
+		spin_lock(&tcon->cfids->cfid_list_lock);
+		list_for_each_entry(parent_cfid, &tcon->cfids->entries, entry) {
+			if (parent_cfid->dentry == direntry->d_parent) {
+				cifs_dbg(FYI, "found a parent cached file handle\n");
+				if (parent_cfid->has_lease && parent_cfid->time) {
+					lease_flags
+						|= SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE;
+					memcpy(fid->parent_lease_key,
+					       parent_cfid->fid.lease_key,
+					       SMB2_LEASE_KEY_SIZE);
+				}
+				break;
+			}
+		}
+		spin_unlock(&tcon->cfids->cfid_list_lock);
+	}
+
 	oparms = (struct cifs_open_parms) {
 		.tcon = tcon,
 		.cifs_sb = cifs_sb,
@@ -320,6 +342,7 @@ retry_open:
 		.disposition = disposition,
 		.path = full_path,
 		.fid = fid,
+		.lease_flags = lease_flags,
 		.mode = mode,
 	};
 	rc = server->ops->open(xid, &oparms, oplock, buf);
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index 7b6ed9b23e71..e77017f47084 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -326,6 +326,14 @@ check_smb_hdr(struct smb_hdr *smb)
 	if (smb->Command == SMB_COM_LOCKING_ANDX)
 		return 0;
 
+	/*
+	 * Windows NT server returns error resposne (e.g. STATUS_DELETE_PENDING
+	 * or STATUS_OBJECT_NAME_NOT_FOUND or ERRDOS/ERRbadfile or any other)
+	 * for some TRANS2 requests without the RESPONSE flag set in header.
+	 */
+	if (smb->Command == SMB_COM_TRANSACTION2 && smb->Status.CifsError != 0)
+		return 0;
+
 	cifs_dbg(VFS, "Server sent request, not response. mid=%u\n",
 		 get_mid(smb));
 	return 1;
diff --git a/fs/smb/client/namespace.c b/fs/smb/client/namespace.c
index 778daf11f1db..52a520349cb7 100644
--- a/fs/smb/client/namespace.c
+++ b/fs/smb/client/namespace.c
@@ -146,6 +146,9 @@ static char *automount_fullpath(struct dentry *dentry, void *page)
 	}
 	spin_unlock(&tcon->tc_lock);
 
+	if (unlikely(!page))
+		return ERR_PTR(-ENOMEM);
+
 	s = dentry_path_raw(dentry, page, PATH_MAX);
 	if (IS_ERR(s))
 		return s;
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index b3fa9ee26912..ec0db32c7d98 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -445,6 +445,10 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 
 	ses->chans[chan_index].iface = iface;
 	spin_unlock(&ses->chan_lock);
+
+	spin_lock(&server->srv_lock);
+	memcpy(&server->dstaddr, &iface->sockaddr, sizeof(server->dstaddr));
+	spin_unlock(&server->srv_lock);
 }
 
 static int
@@ -628,6 +632,7 @@ static __u32 cifs_ssetup_hdr(struct cifs_ses *ses,
 					USHRT_MAX));
 	pSMB->req.MaxMpxCount = cpu_to_le16(server->maxReq);
 	pSMB->req.VcNumber = cpu_to_le16(1);
+	pSMB->req.SessionKey = server->session_key_id;
 
 	/* Now no need to set SMBFLG_CASELESS or obsolete CANONICAL PATH */
 
@@ -1684,22 +1689,22 @@ _sess_auth_rawntlmssp_assemble_req(struct sess_data *sess_data)
 	pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base;
 
 	capabilities = cifs_ssetup_hdr(ses, server, pSMB);
-	if ((pSMB->req.hdr.Flags2 & SMBFLG2_UNICODE) == 0) {
-		cifs_dbg(VFS, "NTLMSSP requires Unicode support\n");
-		return -ENOSYS;
-	}
-
 	pSMB->req.hdr.Flags2 |= SMBFLG2_EXT_SEC;
 	capabilities |= CAP_EXTENDED_SECURITY;
 	pSMB->req.Capabilities |= cpu_to_le32(capabilities);
 
 	bcc_ptr = sess_data->iov[2].iov_base;
-	/* unicode strings must be word aligned */
-	if (!IS_ALIGNED(sess_data->iov[0].iov_len + sess_data->iov[1].iov_len, 2)) {
-		*bcc_ptr = 0;
-		bcc_ptr++;
+
+	if (pSMB->req.hdr.Flags2 & SMBFLG2_UNICODE) {
+		/* unicode strings must be word aligned */
+		if (!IS_ALIGNED(sess_data->iov[0].iov_len + sess_data->iov[1].iov_len, 2)) {
+			*bcc_ptr = 0;
+			bcc_ptr++;
+		}
+		unicode_oslm_strings(&bcc_ptr, sess_data->nls_cp);
+	} else {
+		ascii_oslm_strings(&bcc_ptr, sess_data->nls_cp);
 	}
-	unicode_oslm_strings(&bcc_ptr, sess_data->nls_cp);
 
 	sess_data->iov[2].iov_len = (long) bcc_ptr -
 					(long) sess_data->iov[2].iov_base;
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 2fe8eeb98535..bab9f567d9b7 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -4069,7 +4069,7 @@ map_oplock_to_lease(u8 oplock)
 }
 
 static char *
-smb2_create_lease_buf(u8 *lease_key, u8 oplock)
+smb2_create_lease_buf(u8 *lease_key, u8 oplock, u8 *parent_lease_key, __le32 flags)
 {
 	struct create_lease *buf;
 
@@ -4095,7 +4095,7 @@ smb2_create_lease_buf(u8 *lease_key, u8 oplock)
 }
 
 static char *
-smb3_create_lease_buf(u8 *lease_key, u8 oplock)
+smb3_create_lease_buf(u8 *lease_key, u8 oplock, u8 *parent_lease_key, __le32 flags)
 {
 	struct create_lease_v2 *buf;
 
@@ -4105,6 +4105,9 @@ smb3_create_lease_buf(u8 *lease_key, u8 oplock)
 
 	memcpy(&buf->lcontext.LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE);
 	buf->lcontext.LeaseState = map_oplock_to_lease(oplock);
+	buf->lcontext.LeaseFlags = flags;
+	if (flags & SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE)
+		memcpy(&buf->lcontext.ParentLeaseKey, parent_lease_key, SMB2_LEASE_KEY_SIZE);
 
 	buf->ccontext.DataOffset = cpu_to_le16(offsetof
 					(struct create_lease_v2, lcontext));
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 399185ca7cac..0c320d06809c 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -2392,11 +2392,16 @@ static int
 add_lease_context(struct TCP_Server_Info *server,
 		  struct smb2_create_req *req,
 		  struct kvec *iov,
-		  unsigned int *num_iovec, u8 *lease_key, __u8 *oplock)
+		  unsigned int *num_iovec,
+		  u8 *lease_key,
+		  __u8 *oplock,
+		  u8 *parent_lease_key,
+		  __le32 flags)
 {
 	unsigned int num = *num_iovec;
 
-	iov[num].iov_base = server->ops->create_lease_buf(lease_key, *oplock);
+	iov[num].iov_base = server->ops->create_lease_buf(lease_key, *oplock,
+							  parent_lease_key, flags);
 	if (iov[num].iov_base == NULL)
 		return -ENOMEM;
 	iov[num].iov_len = server->vals->create_lease_size;
@@ -3069,7 +3074,9 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
 		req->RequestedOplockLevel = *oplock; /* no srv lease support */
 	else {
 		rc = add_lease_context(server, req, iov, &n_iov,
-				       oparms->fid->lease_key, oplock);
+				       oparms->fid->lease_key, oplock,
+				       oparms->fid->parent_lease_key,
+				       oparms->lease_flags);
 		if (rc)
 			return rc;
 	}
@@ -5917,71 +5924,6 @@ posix_qfsinf_exit:
 }
 
 int
-SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
-	      u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata)
-{
-	struct smb_rqst rqst;
-	struct smb2_query_info_rsp *rsp = NULL;
-	struct kvec iov;
-	struct kvec rsp_iov;
-	int rc = 0;
-	int resp_buftype;
-	struct cifs_ses *ses = tcon->ses;
-	struct TCP_Server_Info *server;
-	struct smb2_fs_full_size_info *info = NULL;
-	int flags = 0;
-	int retries = 0, cur_sleep = 1;
-
-replay_again:
-	/* reinitialize for possible replay */
-	flags = 0;
-	server = cifs_pick_channel(ses);
-
-	rc = build_qfs_info_req(&iov, tcon, server,
-				FS_FULL_SIZE_INFORMATION,
-				sizeof(struct smb2_fs_full_size_info),
-				persistent_fid, volatile_fid);
-	if (rc)
-		return rc;
-
-	if (smb3_encryption_required(tcon))
-		flags |= CIFS_TRANSFORM_REQ;
-
-	memset(&rqst, 0, sizeof(struct smb_rqst));
-	rqst.rq_iov = &iov;
-	rqst.rq_nvec = 1;
-
-	if (retries)
-		smb2_set_replay(server, &rqst);
-
-	rc = cifs_send_recv(xid, ses, server,
-			    &rqst, &resp_buftype, flags, &rsp_iov);
-	free_qfs_info_req(&iov);
-	if (rc) {
-		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
-		goto qfsinf_exit;
-	}
-	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
-
-	info = (struct smb2_fs_full_size_info *)(
-		le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
-	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
-			       le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
-			       sizeof(struct smb2_fs_full_size_info));
-	if (!rc)
-		smb2_copy_fs_info_to_kstatfs(info, fsdata);
-
-qfsinf_exit:
-	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
-
-	if (is_replayable_error(rc) &&
-	    smb2_should_replay(tcon, &retries, &cur_sleep))
-		goto replay_again;
-
-	return rc;
-}
-
-int
 SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	      u64 persistent_fid, u64 volatile_fid, int level)
 {
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 4662c7e2d259..035aa1624053 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -259,9 +259,6 @@ extern int smb2_handle_cancelled_close(struct cifs_tcon *tcon,
 				       __u64 volatile_fid);
 extern int smb2_handle_cancelled_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server);
 void smb2_cancelled_close_fid(struct work_struct *work);
-extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
-			 u64 persistent_file_id, u64 volatile_file_id,
-			 struct kstatfs *FSData);
 extern int SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 			 u64 persistent_file_id, u64 volatile_file_id,
 			 struct kstatfs *FSData);
diff --git a/fs/smb/server/Kconfig b/fs/smb/server/Kconfig
index cf70e96ad4de..4a23a5e7e8fe 100644
--- a/fs/smb/server/Kconfig
+++ b/fs/smb/server/Kconfig
@@ -11,6 +11,7 @@ config SMB_SERVER
 	select CRYPTO_HMAC
 	select CRYPTO_ECB
 	select CRYPTO_LIB_DES
+	select CRYPTO_LIB_SHA256
 	select CRYPTO_SHA256
 	select CRYPTO_CMAC
 	select CRYPTO_SHA512
diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c
index b3d121052408..d99871c21451 100644
--- a/fs/smb/server/auth.c
+++ b/fs/smb/server/auth.c
@@ -979,40 +979,6 @@ out:
 	return rc;
 }
 
-int ksmbd_gen_sd_hash(struct ksmbd_conn *conn, char *sd_buf, int len,
-		      __u8 *pi_hash)
-{
-	int rc;
-	struct ksmbd_crypto_ctx *ctx = NULL;
-
-	ctx = ksmbd_crypto_ctx_find_sha256();
-	if (!ctx) {
-		ksmbd_debug(AUTH, "could not alloc sha256\n");
-		return -ENOMEM;
-	}
-
-	rc = crypto_shash_init(CRYPTO_SHA256(ctx));
-	if (rc) {
-		ksmbd_debug(AUTH, "could not init shashn");
-		goto out;
-	}
-
-	rc = crypto_shash_update(CRYPTO_SHA256(ctx), sd_buf, len);
-	if (rc) {
-		ksmbd_debug(AUTH, "could not update with n\n");
-		goto out;
-	}
-
-	rc = crypto_shash_final(CRYPTO_SHA256(ctx), pi_hash);
-	if (rc) {
-		ksmbd_debug(AUTH, "Could not generate hash err : %d\n", rc);
-		goto out;
-	}
-out:
-	ksmbd_release_crypto_ctx(ctx);
-	return rc;
-}
-
 static int ksmbd_get_encryption_key(struct ksmbd_work *work, __u64 ses_id,
 				    int enc, u8 *key)
 {
diff --git a/fs/smb/server/auth.h b/fs/smb/server/auth.h
index 362b6159a6cf..6879a1bd1b91 100644
--- a/fs/smb/server/auth.h
+++ b/fs/smb/server/auth.h
@@ -66,6 +66,4 @@ int ksmbd_gen_smb311_encryptionkey(struct ksmbd_conn *conn,
 				   struct ksmbd_session *sess);
 int ksmbd_gen_preauth_integrity_hash(struct ksmbd_conn *conn, char *buf,
 				     __u8 *pi_hash);
-int ksmbd_gen_sd_hash(struct ksmbd_conn *conn, char *sd_buf, int len,
-		      __u8 *pi_hash);
 #endif
diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h
index 14620e147dda..6efed923bd68 100644
--- a/fs/smb/server/connection.h
+++ b/fs/smb/server/connection.h
@@ -108,6 +108,7 @@ struct ksmbd_conn {
 	__le16				signing_algorithm;
 	bool				binding;
 	atomic_t			refcnt;
+	bool				is_aapl;
 };
 
 struct ksmbd_conn_ops {
diff --git a/fs/smb/server/crypto_ctx.c b/fs/smb/server/crypto_ctx.c
index ce733dc9a4a3..80bd68c8635e 100644
--- a/fs/smb/server/crypto_ctx.c
+++ b/fs/smb/server/crypto_ctx.c
@@ -75,9 +75,6 @@ static struct shash_desc *alloc_shash_desc(int id)
 	case CRYPTO_SHASH_CMACAES:
 		tfm = crypto_alloc_shash("cmac(aes)", 0, 0);
 		break;
-	case CRYPTO_SHASH_SHA256:
-		tfm = crypto_alloc_shash("sha256", 0, 0);
-		break;
 	case CRYPTO_SHASH_SHA512:
 		tfm = crypto_alloc_shash("sha512", 0, 0);
 		break;
@@ -198,11 +195,6 @@ struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_cmacaes(void)
 	return ____crypto_shash_ctx_find(CRYPTO_SHASH_CMACAES);
 }
 
-struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha256(void)
-{
-	return ____crypto_shash_ctx_find(CRYPTO_SHASH_SHA256);
-}
-
 struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha512(void)
 {
 	return ____crypto_shash_ctx_find(CRYPTO_SHASH_SHA512);
diff --git a/fs/smb/server/crypto_ctx.h b/fs/smb/server/crypto_ctx.h
index 4a367c62f653..ac64801d52d3 100644
--- a/fs/smb/server/crypto_ctx.h
+++ b/fs/smb/server/crypto_ctx.h
@@ -13,7 +13,6 @@ enum {
 	CRYPTO_SHASH_HMACMD5	= 0,
 	CRYPTO_SHASH_HMACSHA256,
 	CRYPTO_SHASH_CMACAES,
-	CRYPTO_SHASH_SHA256,
 	CRYPTO_SHASH_SHA512,
 	CRYPTO_SHASH_MAX,
 };
@@ -39,14 +38,12 @@ struct ksmbd_crypto_ctx {
 #define CRYPTO_HMACMD5(c)	((c)->desc[CRYPTO_SHASH_HMACMD5])
 #define CRYPTO_HMACSHA256(c)	((c)->desc[CRYPTO_SHASH_HMACSHA256])
 #define CRYPTO_CMACAES(c)	((c)->desc[CRYPTO_SHASH_CMACAES])
-#define CRYPTO_SHA256(c)	((c)->desc[CRYPTO_SHASH_SHA256])
 #define CRYPTO_SHA512(c)	((c)->desc[CRYPTO_SHASH_SHA512])
 
 #define CRYPTO_HMACMD5_TFM(c)	((c)->desc[CRYPTO_SHASH_HMACMD5]->tfm)
 #define CRYPTO_HMACSHA256_TFM(c)\
 				((c)->desc[CRYPTO_SHASH_HMACSHA256]->tfm)
 #define CRYPTO_CMACAES_TFM(c)	((c)->desc[CRYPTO_SHASH_CMACAES]->tfm)
-#define CRYPTO_SHA256_TFM(c)	((c)->desc[CRYPTO_SHASH_SHA256]->tfm)
 #define CRYPTO_SHA512_TFM(c)	((c)->desc[CRYPTO_SHASH_SHA512]->tfm)
 
 #define CRYPTO_GCM(c)		((c)->ccmaes[CRYPTO_AEAD_AES_GCM])
@@ -57,7 +54,6 @@ struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_hmacmd5(void);
 struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_hmacsha256(void);
 struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_cmacaes(void);
 struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha512(void);
-struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha256(void);
 struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_gcm(void);
 struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_ccm(void);
 void ksmbd_crypto_destroy(void);
diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c
index ab533c602987..8c9c49c3a0a4 100644
--- a/fs/smb/server/server.c
+++ b/fs/smb/server/server.c
@@ -631,6 +631,5 @@ MODULE_SOFTDEP("pre: sha512");
 MODULE_SOFTDEP("pre: aead2");
 MODULE_SOFTDEP("pre: ccm");
 MODULE_SOFTDEP("pre: gcm");
-MODULE_SOFTDEP("pre: crc32");
 module_init(ksmbd_server_init)
 module_exit(ksmbd_server_exit)
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 8d414239b3fe..1a308171b599 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -2874,7 +2874,7 @@ int smb2_open(struct ksmbd_work *work)
 	int req_op_level = 0, open_flags = 0, may_flags = 0, file_info = 0;
 	int rc = 0;
 	int contxt_cnt = 0, query_disk_id = 0;
-	int maximal_access_ctxt = 0, posix_ctxt = 0;
+	bool maximal_access_ctxt = false, posix_ctxt = false;
 	int s_type = 0;
 	int next_off = 0;
 	char *name = NULL;
@@ -2903,6 +2903,27 @@ int smb2_open(struct ksmbd_work *work)
 		return create_smb2_pipe(work);
 	}
 
+	if (req->CreateContextsOffset && tcon->posix_extensions) {
+		context = smb2_find_context_vals(req, SMB2_CREATE_TAG_POSIX, 16);
+		if (IS_ERR(context)) {
+			rc = PTR_ERR(context);
+			goto err_out2;
+		} else if (context) {
+			struct create_posix *posix = (struct create_posix *)context;
+
+			if (le16_to_cpu(context->DataOffset) +
+				le32_to_cpu(context->DataLength) <
+			    sizeof(struct create_posix) - 4) {
+				rc = -EINVAL;
+				goto err_out2;
+			}
+			ksmbd_debug(SMB, "get posix context\n");
+
+			posix_mode = le32_to_cpu(posix->Mode);
+			posix_ctxt = true;
+		}
+	}
+
 	if (req->NameLength) {
 		name = smb2_get_name((char *)req + le16_to_cpu(req->NameOffset),
 				     le16_to_cpu(req->NameLength),
@@ -2925,9 +2946,11 @@ int smb2_open(struct ksmbd_work *work)
 				goto err_out2;
 		}
 
-		rc = ksmbd_validate_filename(name);
-		if (rc < 0)
-			goto err_out2;
+		if (posix_ctxt == false) {
+			rc = ksmbd_validate_filename(name);
+			if (rc < 0)
+				goto err_out2;
+		}
 
 		if (ksmbd_share_veto_filename(share, name)) {
 			rc = -ENOENT;
@@ -3085,28 +3108,6 @@ int smb2_open(struct ksmbd_work *work)
 			rc = -EBADF;
 			goto err_out2;
 		}
-
-		if (tcon->posix_extensions) {
-			context = smb2_find_context_vals(req,
-							 SMB2_CREATE_TAG_POSIX, 16);
-			if (IS_ERR(context)) {
-				rc = PTR_ERR(context);
-				goto err_out2;
-			} else if (context) {
-				struct create_posix *posix =
-					(struct create_posix *)context;
-				if (le16_to_cpu(context->DataOffset) +
-				    le32_to_cpu(context->DataLength) <
-				    sizeof(struct create_posix) - 4) {
-					rc = -EINVAL;
-					goto err_out2;
-				}
-				ksmbd_debug(SMB, "get posix context\n");
-
-				posix_mode = le32_to_cpu(posix->Mode);
-				posix_ctxt = 1;
-			}
-		}
 	}
 
 	if (ksmbd_override_fsids(work)) {
@@ -3539,6 +3540,15 @@ int smb2_open(struct ksmbd_work *work)
 			ksmbd_debug(SMB, "get query on disk id context\n");
 			query_disk_id = 1;
 		}
+
+		if (conn->is_aapl == false) {
+			context = smb2_find_context_vals(req, SMB2_CREATE_AAPL, 4);
+			if (IS_ERR(context)) {
+				rc = PTR_ERR(context);
+				goto err_out1;
+			} else if (context)
+				conn->is_aapl = true;
+		}
 	}
 
 	rc = ksmbd_vfs_getattr(&path, &stat);
@@ -3978,7 +3988,10 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level,
 		if (dinfo->EaSize)
 			dinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE;
 		dinfo->Reserved = 0;
-		dinfo->UniqueId = cpu_to_le64(ksmbd_kstat->kstat->ino);
+		if (conn->is_aapl)
+			dinfo->UniqueId = 0;
+		else
+			dinfo->UniqueId = cpu_to_le64(ksmbd_kstat->kstat->ino);
 		if (d_info->hide_dot_file && d_info->name[0] == '.')
 			dinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE;
 		memcpy(dinfo->FileName, conv_name, conv_len);
@@ -3995,7 +4008,10 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level,
 			smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode);
 		if (fibdinfo->EaSize)
 			fibdinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE;
-		fibdinfo->UniqueId = cpu_to_le64(ksmbd_kstat->kstat->ino);
+		if (conn->is_aapl)
+			fibdinfo->UniqueId = 0;
+		else
+			fibdinfo->UniqueId = cpu_to_le64(ksmbd_kstat->kstat->ino);
 		fibdinfo->ShortNameLength = 0;
 		fibdinfo->Reserved = 0;
 		fibdinfo->Reserved2 = cpu_to_le16(0);
diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h
index 17a0b18a8406..16ae8a10490b 100644
--- a/fs/smb/server/smb2pdu.h
+++ b/fs/smb/server/smb2pdu.h
@@ -63,6 +63,9 @@ struct preauth_integrity_info {
 
 #define SMB2_SESSION_TIMEOUT		(10 * HZ)
 
+/* Apple Defined Contexts */
+#define SMB2_CREATE_AAPL		"AAPL"
+
 struct create_durable_req_v2 {
 	struct create_context_hdr ccontext;
 	__u8   Name[8];
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index baf0d3031a44..ba45e809555a 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -4,6 +4,7 @@
  *   Copyright (C) 2018 Samsung Electronics Co., Ltd.
  */
 
+#include <crypto/sha2.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/filelock.h>
@@ -1476,11 +1477,7 @@ int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn,
 	acl.sd_buf = (char *)pntsd;
 	acl.sd_size = len;
 
-	rc = ksmbd_gen_sd_hash(conn, acl.sd_buf, acl.sd_size, acl.hash);
-	if (rc) {
-		pr_err("failed to generate hash for ndr acl\n");
-		return rc;
-	}
+	sha256(acl.sd_buf, acl.sd_size, acl.hash);
 
 	smb_acl = ksmbd_vfs_make_xattr_posix_acl(idmap, inode,
 						 ACL_TYPE_ACCESS);
@@ -1495,12 +1492,7 @@ int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn,
 		goto out;
 	}
 
-	rc = ksmbd_gen_sd_hash(conn, acl_ndr.data, acl_ndr.offset,
-			       acl.posix_acl_hash);
-	if (rc) {
-		pr_err("failed to generate hash for ndr acl\n");
-		goto out;
-	}
+	sha256(acl_ndr.data, acl_ndr.offset, acl.posix_acl_hash);
 
 	rc = ndr_encode_v4_ntacl(&sd_ndr, &acl);
 	if (rc) {
@@ -1557,11 +1549,7 @@ int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn,
 		goto out_free;
 	}
 
-	rc = ksmbd_gen_sd_hash(conn, acl_ndr.data, acl_ndr.offset, cmp_hash);
-	if (rc) {
-		pr_err("failed to generate hash for ndr acl\n");
-		goto out_free;
-	}
+	sha256(acl_ndr.data, acl_ndr.offset, cmp_hash);
 
 	if (memcmp(cmp_hash, acl.posix_acl_hash, XATTR_SD_HASH_SIZE)) {
 		pr_err("hash value diff\n");
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index ccccb1cbf7df..a729b77983fa 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -236,10 +236,6 @@ int hv_common_cpu_init(unsigned int cpu);
 int hv_common_cpu_die(unsigned int cpu);
 void hv_identify_partition_type(void);
 
-void *hv_alloc_hyperv_page(void);
-void *hv_alloc_hyperv_zeroed_page(void);
-void hv_free_hyperv_page(void *addr);
-
 /**
  * hv_cpu_number_to_vp_number() - Map CPU to VP.
  * @cpu_number: CPU number in Linux terms
@@ -378,4 +374,10 @@ static inline int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u3
 }
 #endif /* CONFIG_MSHV_ROOT */
 
+#if IS_ENABLED(CONFIG_HYPERV_VTL_MODE)
+u8 __init get_vtl(void);
+#else
+static inline u8 get_vtl(void) { return 0; }
+#endif
+
 #endif
diff --git a/include/asm-generic/simd.h b/include/asm-generic/simd.h
index ac29a22eb7cf..70c8716ad32a 100644
--- a/include/asm-generic/simd.h
+++ b/include/asm-generic/simd.h
@@ -4,6 +4,7 @@
 
 #include <linux/compiler_attributes.h>
 #include <linux/preempt.h>
+#include <linux/sched.h>
 #include <linux/types.h>
 
 /*
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 88a42973fa47..1fff717cae51 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -58,6 +58,11 @@
  *    Defaults to flushing at tlb_end_vma() to reset the range; helps when
  *    there's large holes between the VMAs.
  *
+ *  - tlb_free_vmas()
+ *
+ *    tlb_free_vmas() marks the start of unlinking of one or more vmas
+ *    and freeing page-tables.
+ *
  *  - tlb_remove_table()
  *
  *    tlb_remove_table() is the basic primitive to free page-table directories
@@ -464,7 +469,12 @@ tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma)
 	 */
 	tlb->vma_huge = is_vm_hugetlb_page(vma);
 	tlb->vma_exec = !!(vma->vm_flags & VM_EXEC);
-	tlb->vma_pfn  = !!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP));
+
+	/*
+	 * Track if there's at least one VM_PFNMAP/VM_MIXEDMAP vma
+	 * in the tracked range, see tlb_free_vmas().
+	 */
+	tlb->vma_pfn |= !!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP));
 }
 
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
@@ -548,22 +558,38 @@ static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *
 
 static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 {
+	if (tlb->fullmm || IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS))
+		return;
+
+	/*
+	 * Do a TLB flush and reset the range at VMA boundaries; this avoids
+	 * the ranges growing with the unused space between consecutive VMAs,
+	 * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on
+	 * this.
+	 */
+	tlb_flush_mmu_tlbonly(tlb);
+}
+
+static inline void tlb_free_vmas(struct mmu_gather *tlb)
+{
 	if (tlb->fullmm)
 		return;
 
 	/*
 	 * VM_PFNMAP is more fragile because the core mm will not track the
-	 * page mapcount -- there might not be page-frames for these PFNs after
-	 * all. Force flush TLBs for such ranges to avoid munmap() vs
-	 * unmap_mapping_range() races.
+	 * page mapcount -- there might not be page-frames for these PFNs
+	 * after all.
+	 *
+	 * Specifically() there is a race between munmap() and
+	 * unmap_mapping_range(), where munmap() will unlink the VMA, such
+	 * that unmap_mapping_range() will no longer observe the VMA and
+	 * no-op, without observing the TLBI, returning prematurely.
+	 *
+	 * So if we're about to unlink such a VMA, and we have pending
+	 * TLBI for such a vma, flush things now.
 	 */
-	if (tlb->vma_pfn || !IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS)) {
-		/*
-		 * Do a TLB flush and reset the range at VMA boundaries; this avoids
-		 * the ranges growing with the unused space between consecutive VMAs.
-		 */
+	if (tlb->vma_pfn)
 		tlb_flush_mmu_tlbonly(tlb);
-	}
 }
 
 /*
diff --git a/include/cxl/features.h b/include/cxl/features.h
index 5f7f842765a5..b9297693dae7 100644
--- a/include/cxl/features.h
+++ b/include/cxl/features.h
@@ -64,7 +64,7 @@ struct cxl_features_state {
 struct cxl_mailbox;
 struct cxl_memdev;
 #ifdef CONFIG_CXL_FEATURES
-inline struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds);
+struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds);
 int devm_cxl_setup_features(struct cxl_dev_state *cxlds);
 int devm_cxl_setup_fwctl(struct device *host, struct cxl_memdev *cxlmd);
 #else
diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h
index 68606fa5fe73..1be7f6a02304 100644
--- a/include/hyperv/hvgdk_mini.h
+++ b/include/hyperv/hvgdk_mini.h
@@ -475,7 +475,7 @@ union hv_vp_assist_msr_contents {	 /* HV_REGISTER_VP_ASSIST_PAGE */
 #define HVCALL_CREATE_PORT				0x0095
 #define HVCALL_CONNECT_PORT				0x0096
 #define HVCALL_START_VP					0x0099
-#define HVCALL_GET_VP_ID_FROM_APIC_ID			0x009a
+#define HVCALL_GET_VP_INDEX_FROM_APIC_ID			0x009a
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE	0x00af
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST	0x00b0
 #define HVCALL_SIGNAL_EVENT_DIRECT			0x00c0
@@ -1228,7 +1228,7 @@ struct hv_send_ipi {	 /* HV_INPUT_SEND_SYNTHETIC_CLUSTER_IPI */
 	u64 cpu_mask;
 } __packed;
 
-#define	HV_X64_VTL_MASK			GENMASK(3, 0)
+#define	HV_VTL_MASK			GENMASK(3, 0)
 
 /* Hyper-V memory host visibility */
 enum hv_mem_host_visibility {
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index f4b3d442b7df..f102c0fe3431 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -335,8 +335,11 @@ int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity
 int acpi_gsi_to_irq (u32 gsi, unsigned int *irq);
 int acpi_isa_irq_to_gsi (unsigned isa_irq, u32 *gsi);
 
+typedef struct fwnode_handle *(*acpi_gsi_domain_disp_fn)(u32);
+
 void acpi_set_irq_model(enum acpi_irq_model_id model,
-			struct fwnode_handle *(*)(u32));
+			acpi_gsi_domain_disp_fn fn);
+acpi_gsi_domain_disp_fn acpi_get_gsi_dispatcher(void);
 void acpi_set_gsi_to_irq_fallback(u32 (*)(u32));
 
 struct irq_domain *acpi_irq_create_hierarchy(unsigned int flags,
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index a3863da1510e..784ebe4607a4 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -7,6 +7,11 @@
 
 #include <linux/args.h>
 #include <linux/init.h>
+
+#ifndef __ASSEMBLY__
+#include <linux/uuid.h>
+#endif
+
 #include <uapi/linux/const.h>
 
 /*
@@ -107,10 +112,10 @@
 			   ARM_SMCCC_FUNC_QUERY_CALL_UID)
 
 /* KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74 */
-#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0	0xb66fb428U
-#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1	0xe911c52eU
-#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2	0x564bcaa9U
-#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3	0x743a004dU
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM UUID_INIT(\
+	0xb66fb428, 0xc52e, 0xe911, \
+	0xa9, 0xca, 0x4b, 0x56, \
+	0x4d, 0x00, 0x3a, 0x74)
 
 /* KVM "vendor specific" services */
 #define ARM_SMCCC_KVM_FUNC_FEATURES		0
@@ -348,6 +353,57 @@ s32 arm_smccc_get_soc_id_version(void);
  */
 s32 arm_smccc_get_soc_id_revision(void);
 
+#ifndef __ASSEMBLY__
+
+/*
+ * Returns whether a specific hypervisor UUID is advertised for the
+ * Vendor Specific Hypervisor Service range.
+ */
+bool arm_smccc_hypervisor_has_uuid(const uuid_t *uuid);
+
+static inline uuid_t smccc_res_to_uuid(u32 r0, u32 r1, u32 r2, u32 r3)
+{
+	uuid_t uuid = {
+		.b = {
+			[0]  = (r0 >> 0)  & 0xff,
+			[1]  = (r0 >> 8)  & 0xff,
+			[2]  = (r0 >> 16) & 0xff,
+			[3]  = (r0 >> 24) & 0xff,
+
+			[4]  = (r1 >> 0)  & 0xff,
+			[5]  = (r1 >> 8)  & 0xff,
+			[6]  = (r1 >> 16) & 0xff,
+			[7]  = (r1 >> 24) & 0xff,
+
+			[8]  = (r2 >> 0)  & 0xff,
+			[9]  = (r2 >> 8)  & 0xff,
+			[10] = (r2 >> 16) & 0xff,
+			[11] = (r2 >> 24) & 0xff,
+
+			[12] = (r3 >> 0)  & 0xff,
+			[13] = (r3 >> 8)  & 0xff,
+			[14] = (r3 >> 16) & 0xff,
+			[15] = (r3 >> 24) & 0xff,
+		},
+	};
+
+	return uuid;
+}
+
+static inline u32 smccc_uuid_to_reg(const uuid_t *uuid, int reg)
+{
+	u32 val = 0;
+
+	val |= (u32)(uuid->b[4 * reg + 0] << 0);
+	val |= (u32)(uuid->b[4 * reg + 1] << 8);
+	val |= (u32)(uuid->b[4 * reg + 2] << 16);
+	val |= (u32)(uuid->b[4 * reg + 3] << 24);
+
+	return val;
+}
+
+#endif /* !__ASSEMBLY__ */
+
 /**
  * struct arm_smccc_res - Result from SMC/HVC call
  * @a0-a3 result values from registers 0 to 3
diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index f5652e5a9060..10e626db7eee 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -12,7 +12,6 @@
 #include <linux/device.h>
 #include <linux/fb.h>
 #include <linux/mutex.h>
-#include <linux/notifier.h>
 #include <linux/types.h>
 
 /**
@@ -279,11 +278,6 @@ struct backlight_device {
 	const struct backlight_ops *ops;
 
 	/**
-	 * @fb_notif: The framebuffer notifier block
-	 */
-	struct notifier_block fb_notif;
-
-	/**
 	 * @entry: List entry of all registered backlight devices
 	 */
 	struct list_head entry;
@@ -294,15 +288,7 @@ struct backlight_device {
 	struct device dev;
 
 	/**
-	 * @fb_bl_on: The state of individual fbdev's.
-	 *
-	 * Multiple fbdev's may share one backlight device. The fb_bl_on
-	 * records the state of the individual fbdev.
-	 */
-	bool fb_bl_on[FB_MAX];
-
-	/**
-	 * @use_count: The number of uses of fb_bl_on.
+	 * @use_count: The number of unblanked displays.
 	 */
 	int use_count;
 };
@@ -408,6 +394,22 @@ struct backlight_device *backlight_device_get_by_type(enum backlight_type type);
 int backlight_device_set_brightness(struct backlight_device *bd,
 				    unsigned long brightness);
 
+#if IS_REACHABLE(CONFIG_BACKLIGHT_CLASS_DEVICE)
+void backlight_notify_blank(struct backlight_device *bd,
+			    struct device *display_dev,
+			    bool fb_on, bool prev_fb_on);
+void backlight_notify_blank_all(struct device *display_dev,
+				bool fb_on, bool prev_fb_on);
+#else
+static inline void backlight_notify_blank(struct backlight_device *bd,
+					  struct device *display_dev,
+					  bool fb_on, bool prev_fb_on)
+{ }
+static inline void backlight_notify_blank_all(struct device *display_dev,
+					      bool fb_on, bool prev_fb_on)
+{ }
+#endif
+
 #define to_backlight_device(obj) container_of(obj, struct backlight_device, dev)
 
 /**
diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h
index 63928f173223..6d9a53db54b6 100644
--- a/include/linux/bitfield.h
+++ b/include/linux/bitfield.h
@@ -8,6 +8,7 @@
 #define _LINUX_BITFIELD_H
 
 #include <linux/build_bug.h>
+#include <linux/typecheck.h>
 #include <asm/byteorder.h>
 
 /*
@@ -38,8 +39,7 @@
  *	  FIELD_PREP(REG_FIELD_D, 0x40);
  *
  * Modify:
- *  reg &= ~REG_FIELD_C;
- *  reg |= FIELD_PREP(REG_FIELD_C, c);
+ *  FIELD_MODIFY(REG_FIELD_C, &reg, c);
  */
 
 #define __bf_shf(x) (__builtin_ffsll(x) - 1)
@@ -156,6 +156,23 @@
 		(typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask));	\
 	})
 
+/**
+ * FIELD_MODIFY() - modify a bitfield element
+ * @_mask: shifted mask defining the field's length and position
+ * @_reg_p: pointer to the memory that should be updated
+ * @_val: value to store in the bitfield
+ *
+ * FIELD_MODIFY() modifies the set of bits in @_reg_p specified by @_mask,
+ * by replacing them with the bitfield value passed in as @_val.
+ */
+#define FIELD_MODIFY(_mask, _reg_p, _val)						\
+	({										\
+		typecheck_pointer(_reg_p);						\
+		__BF_FIELD_CHECK(_mask, *(_reg_p), _val, "FIELD_MODIFY: ");		\
+		*(_reg_p) &= ~(_mask);							\
+		*(_reg_p) |= (((typeof(_mask))(_val) << __bf_shf(_mask)) & (_mask));	\
+	})
+
 extern void __compiletime_error("value doesn't fit into mask")
 __field_overflow(void);
 extern void __compiletime_error("bad bitfield mask")
diff --git a/include/linux/bitmap-str.h b/include/linux/bitmap-str.h
index 17caeca94cab..53d3e1b32d3d 100644
--- a/include/linux/bitmap-str.h
+++ b/include/linux/bitmap-str.h
@@ -2,12 +2,14 @@
 #ifndef __LINUX_BITMAP_STR_H
 #define __LINUX_BITMAP_STR_H
 
+#include <linux/types.h>
+
 int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits);
 int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits);
-extern int bitmap_print_bitmask_to_buf(char *buf, const unsigned long *maskp,
-					int nmaskbits, loff_t off, size_t count);
-extern int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp,
-					int nmaskbits, loff_t off, size_t count);
+int bitmap_print_bitmask_to_buf(char *buf, const unsigned long *maskp, int nmaskbits,
+				loff_t off, size_t count);
+int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp, int nmaskbits,
+			     loff_t off, size_t count);
 int bitmap_parse(const char *buf, unsigned int buflen, unsigned long *dst, int nbits);
 int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits);
 int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen,
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index c1cb53cf2f0f..9be2d50da09a 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -8,7 +8,6 @@
 
 #include <uapi/linux/kernel.h>
 
-#define BITS_PER_TYPE(type)	(sizeof(type) * BITS_PER_BYTE)
 #define BITS_TO_LONGS(nr)	__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
 #define BITS_TO_U64(nr)		__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u64))
 #define BITS_TO_U32(nr)		__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32))
diff --git a/include/linux/bits.h b/include/linux/bits.h
index 14fd0ca9a6cd..7ad056219115 100644
--- a/include/linux/bits.h
+++ b/include/linux/bits.h
@@ -12,6 +12,7 @@
 #define BIT_ULL_MASK(nr)	(ULL(1) << ((nr) % BITS_PER_LONG_LONG))
 #define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
 #define BITS_PER_BYTE		8
+#define BITS_PER_TYPE(type)	(sizeof(type) * BITS_PER_BYTE)
 
 /*
  * Create a contiguous bitmask starting at bit position @l and ending at
@@ -19,16 +20,68 @@
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
 #if !defined(__ASSEMBLY__)
+
+/*
+ * Missing asm support
+ *
+ * GENMASK_U*() and BIT_U*() depend on BITS_PER_TYPE() which relies on sizeof(),
+ * something not available in asm. Nevertheless, fixed width integers is a C
+ * concept. Assembly code can rely on the long and long long versions instead.
+ */
+
 #include <linux/build_bug.h>
 #include <linux/compiler.h>
+#include <linux/overflow.h>
+
 #define GENMASK_INPUT_CHECK(h, l) BUILD_BUG_ON_ZERO(const_true((l) > (h)))
-#else
+
+/*
+ * Generate a mask for the specified type @t. Additional checks are made to
+ * guarantee the value returned fits in that type, relying on
+ * -Wshift-count-overflow compiler check to detect incompatible arguments.
+ * For example, all these create build errors or warnings:
+ *
+ * - GENMASK(15, 20): wrong argument order
+ * - GENMASK(72, 15): doesn't fit unsigned long
+ * - GENMASK_U32(33, 15): doesn't fit in a u32
+ */
+#define GENMASK_TYPE(t, h, l)					\
+	((t)(GENMASK_INPUT_CHECK(h, l) +			\
+	     (type_max(t) << (l) &				\
+	      type_max(t) >> (BITS_PER_TYPE(t) - 1 - (h)))))
+
+#define GENMASK_U8(h, l)	GENMASK_TYPE(u8, h, l)
+#define GENMASK_U16(h, l)	GENMASK_TYPE(u16, h, l)
+#define GENMASK_U32(h, l)	GENMASK_TYPE(u32, h, l)
+#define GENMASK_U64(h, l)	GENMASK_TYPE(u64, h, l)
+
+/*
+ * Fixed-type variants of BIT(), with additional checks like GENMASK_TYPE(). The
+ * following examples generate compiler warnings due to -Wshift-count-overflow:
+ *
+ * - BIT_U8(8)
+ * - BIT_U32(-1)
+ * - BIT_U32(40)
+ */
+#define BIT_INPUT_CHECK(type, nr) \
+	BUILD_BUG_ON_ZERO(const_true((nr) >= BITS_PER_TYPE(type)))
+
+#define BIT_TYPE(type, nr) ((type)(BIT_INPUT_CHECK(type, nr) + BIT_ULL(nr)))
+
+#define BIT_U8(nr)	BIT_TYPE(u8, nr)
+#define BIT_U16(nr)	BIT_TYPE(u16, nr)
+#define BIT_U32(nr)	BIT_TYPE(u32, nr)
+#define BIT_U64(nr)	BIT_TYPE(u64, nr)
+
+#else /* defined(__ASSEMBLY__) */
+
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
  * disable the input check if that is the case.
  */
 #define GENMASK_INPUT_CHECK(h, l) 0
-#endif
+
+#endif /* !defined(__ASSEMBLY__) */
 
 #define GENMASK(h, l) \
 	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 332b56f323d9..a59880c809c7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1456,6 +1456,13 @@ static inline bool bdev_is_zone_start(struct block_device *bdev,
 	return bdev_offset_from_zone_start(bdev, sector) == 0;
 }
 
+/* Check whether @sector is a multiple of the zone size. */
+static inline bool bdev_is_zone_aligned(struct block_device *bdev,
+					sector_t sector)
+{
+	return bdev_is_zone_start(bdev, sector);
+}
+
 /**
  * bdev_zone_is_seq - check if a sector belongs to a sequential write zone
  * @bdev:	block device to check
diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h
index 3aa3640f8c18..2cfbb4c65c78 100644
--- a/include/linux/build_bug.h
+++ b/include/linux/build_bug.h
@@ -4,17 +4,17 @@
 
 #include <linux/compiler.h>
 
-#ifdef __CHECKER__
-#define BUILD_BUG_ON_ZERO(e) (0)
-#else /* __CHECKER__ */
 /*
  * Force a compilation error if condition is true, but also produce a
  * result (of value 0 and type int), so the expression can be used
  * e.g. in a structure initializer (or where-ever else comma expressions
  * aren't permitted).
+ *
+ * Take an error message as an optional second argument. If omitted,
+ * default to the stringification of the tested expression.
  */
-#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); })))
-#endif /* __CHECKER__ */
+#define BUILD_BUG_ON_ZERO(e, ...) \
+	__BUILD_BUG_ON_ZERO_MSG(e, ##__VA_ARGS__, #e " is true")
 
 /* Force a compilation error if a constant expression is not a power of 2 */
 #define __BUILD_BUG_ON_NOT_POWER_OF_2(n)	\
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 27725f1ab5ab..6f04a1d8c720 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -192,9 +192,9 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 })
 
 #ifdef __CHECKER__
-#define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0)
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) (0)
 #else /* __CHECKER__ */
-#define __BUILD_BUG_ON_ZERO_MSG(e, msg) ((int)sizeof(struct {_Static_assert(!(e), msg);}))
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) ((int)sizeof(struct {_Static_assert(!(e), msg);}))
 #endif /* __CHECKER__ */
 
 /* &a[0] degrades to a pointer: a different type from an array */
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 6a569c7534db..7ae80a7ca81e 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -626,22 +626,6 @@ static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
 }
 
 /**
- * cpumask_assign_cpu - assign a cpu in a cpumask
- * @cpu: cpu number (< nr_cpu_ids)
- * @dstp: the cpumask pointer
- * @bool: the value to assign
- */
-static __always_inline void cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value)
-{
-	assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value);
-}
-
-static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value)
-{
-	__assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value);
-}
-
-/**
  * cpumask_test_cpu - test for a cpu in a cpumask
  * @cpu: cpu number (< nr_cpu_ids)
  * @cpumask: the cpumask pointer
@@ -1141,6 +1125,9 @@ void init_cpu_possible(const struct cpumask *src);
 #define assign_cpu(cpu, mask, val)	\
 	assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
 
+#define __assign_cpu(cpu, mask, val)	\
+	__assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
+
 #define set_cpu_possible(cpu, possible)	assign_cpu((cpu), &__cpu_possible_mask, (possible))
 #define set_cpu_enabled(cpu, enabled)	assign_cpu((cpu), &__cpu_enabled_mask, (enabled))
 #define set_cpu_present(cpu, present)	assign_cpu((cpu), &__cpu_present_mask, (present))
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index bcc6d7b69470..cb95951547ab 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -93,7 +93,14 @@ typedef void (*dm_status_fn) (struct dm_target *ti, status_type_t status_type,
 typedef int (*dm_message_fn) (struct dm_target *ti, unsigned int argc, char **argv,
 			      char *result, unsigned int maxlen);
 
-typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev);
+/*
+ * Called with *forward == true. If it remains true, the ioctl should be
+ * forwarded to bdev. If it is reset to false, the target already fully handled
+ * the ioctl and the return value is the return value for the whole ioctl.
+ */
+typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev,
+				    unsigned int cmd, unsigned long arg,
+				    bool *forward);
 
 #ifdef CONFIG_BLK_DEV_ZONED
 typedef int (*dm_report_zones_fn) (struct dm_target *ti,
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 451f9c152c99..fa32f2aca22f 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -745,9 +745,16 @@ static inline int edac_ecs_get_desc(struct device *ecs_dev,
 #endif /* CONFIG_EDAC_ECS */
 
 enum edac_mem_repair_type {
+	EDAC_REPAIR_PPR,
+	EDAC_REPAIR_CACHELINE_SPARING,
+	EDAC_REPAIR_ROW_SPARING,
+	EDAC_REPAIR_BANK_SPARING,
+	EDAC_REPAIR_RANK_SPARING,
 	EDAC_REPAIR_MAX
 };
 
+extern const char * const edac_repair_type[];
+
 enum edac_mem_repair_cmd {
 	EDAC_DO_MEM_REPAIR = 1,
 };
diff --git a/include/linux/fb.h b/include/linux/fb.h
index cd653862ab99..05cc251035da 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -129,18 +129,12 @@ struct fb_cursor_user {
  * Register/unregister for framebuffer events
  */
 
-/*	The resolution of the passed in fb_info about to change */
-#define FB_EVENT_MODE_CHANGE		0x01
-
 #ifdef CONFIG_GUMSTIX_AM200EPD
 /* only used by mach-pxa/am200epd.c */
 #define FB_EVENT_FB_REGISTERED          0x05
 #define FB_EVENT_FB_UNREGISTERED        0x06
 #endif
 
-/*      A display blank is requested       */
-#define FB_EVENT_BLANK                  0x09
-
 struct fb_event {
 	struct fb_info *info;
 	void *data;
@@ -472,6 +466,8 @@ struct fb_info {
 	struct list_head modelist;      /* mode list */
 	struct fb_videomode *mode;	/* current mode */
 
+	int blank; /* current blanking; see FB_BLANK_ constants */
+
 #if IS_ENABLED(CONFIG_FB_BACKLIGHT)
 	/* assigned backlight device */
 	/* set before framebuffer registration,
@@ -756,11 +752,15 @@ extern void fb_bl_default_curve(struct fb_info *fb_info, u8 off, u8 min, u8 max)
 
 #if IS_ENABLED(CONFIG_FB_BACKLIGHT)
 struct backlight_device *fb_bl_device(struct fb_info *info);
+void fb_bl_notify_blank(struct fb_info *info, int old_blank);
 #else
 static inline struct backlight_device *fb_bl_device(struct fb_info *info)
 {
 	return NULL;
 }
+
+static inline void fb_bl_notify_blank(struct fb_info *info, int old_blank)
+{ }
 #endif
 
 static inline struct lcd_device *fb_lcd_device(struct fb_info *info)
diff --git a/include/linux/hid.h b/include/linux/hid.h
index ef9a90ca0fbd..568a9d8c749b 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -357,6 +357,7 @@ struct hid_item {
  * | @HID_QUIRK_INPUT_PER_APP:
  * | @HID_QUIRK_X_INVERT:
  * | @HID_QUIRK_Y_INVERT:
+ * | @HID_QUIRK_IGNORE_MOUSE:
  * | @HID_QUIRK_SKIP_OUTPUT_REPORTS:
  * | @HID_QUIRK_SKIP_OUTPUT_REPORT_ID:
  * | @HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP:
@@ -382,6 +383,7 @@ struct hid_item {
 #define HID_QUIRK_INPUT_PER_APP			BIT(11)
 #define HID_QUIRK_X_INVERT			BIT(12)
 #define HID_QUIRK_Y_INVERT			BIT(13)
+#define HID_QUIRK_IGNORE_MOUSE			BIT(14)
 #define HID_QUIRK_SKIP_OUTPUT_REPORTS		BIT(16)
 #define HID_QUIRK_SKIP_OUTPUT_REPORT_ID		BIT(17)
 #define HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP	BIT(18)
@@ -740,8 +742,9 @@ struct hid_descriptor {
 	__le16 bcdHID;
 	__u8  bCountryCode;
 	__u8  bNumDescriptors;
+	struct hid_class_descriptor rpt_desc;
 
-	struct hid_class_descriptor desc[1];
+	struct hid_class_descriptor opt_descs[];
 } __attribute__ ((packed));
 
 #define HID_DEVICE(b, g, ven, prod)					\
@@ -792,6 +795,8 @@ struct hid_usage_id {
  * @suspend: invoked on suspend (NULL means nop)
  * @resume: invoked on resume if device was not reset (NULL means nop)
  * @reset_resume: invoked on resume if device was reset (NULL means nop)
+ * @on_hid_hw_open: invoked when hid core opens first instance (NULL means nop)
+ * @on_hid_hw_close: invoked when hid core closes last instance (NULL means nop)
  *
  * probe should return -errno on error, or 0 on success. During probe,
  * input will not be passed to raw_event unless hid_device_io_start is
@@ -847,6 +852,8 @@ struct hid_driver {
 	int (*suspend)(struct hid_device *hdev, pm_message_t message);
 	int (*resume)(struct hid_device *hdev);
 	int (*reset_resume)(struct hid_device *hdev);
+	void (*on_hid_hw_open)(struct hid_device *hdev);
+	void (*on_hid_hw_close)(struct hid_device *hdev);
 
 /* private: */
 	struct device_driver driver;
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index b52ac40d5830..a59c5c3e95fb 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1276,6 +1276,8 @@ static inline void *hv_get_drvdata(struct hv_device *dev)
 	return dev_get_drvdata(&dev->device);
 }
 
+struct device *hv_get_vmbus_root_device(void);
+
 struct hv_ring_buffer_debug_info {
 	u32 current_interrupt_mask;
 	u32 current_read_index;
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 420c7f9aa6ee..ce377f7fb912 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -111,6 +111,8 @@
 
 /* bits unique to S1G beacon */
 #define IEEE80211_S1G_BCN_NEXT_TBTT	0x100
+#define IEEE80211_S1G_BCN_CSSID		0x200
+#define IEEE80211_S1G_BCN_ANO		0x400
 
 /* see 802.11ah-2016 9.9 NDP CMAC frames */
 #define IEEE80211_S1G_1MHZ_NDP_BITS	25
@@ -153,9 +155,6 @@
 
 #define IEEE80211_ANO_NETTYPE_WILD              15
 
-/* bits unique to S1G beacon */
-#define IEEE80211_S1G_BCN_NEXT_TBTT    0x100
-
 /* control extension - for IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTL_EXT */
 #define IEEE80211_CTL_EXT_POLL		0x2000
 #define IEEE80211_CTL_EXT_SPR		0x3000
@@ -628,6 +627,42 @@ static inline bool ieee80211_is_s1g_beacon(__le16 fc)
 }
 
 /**
+ * ieee80211_s1g_has_next_tbtt - check if IEEE80211_S1G_BCN_NEXT_TBTT
+ * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame contains the variable-length
+ *	next TBTT field
+ */
+static inline bool ieee80211_s1g_has_next_tbtt(__le16 fc)
+{
+	return ieee80211_is_s1g_beacon(fc) &&
+		(fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT));
+}
+
+/**
+ * ieee80211_s1g_has_ano - check if IEEE80211_S1G_BCN_ANO
+ * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame contains the variable-length
+ *	ANO field
+ */
+static inline bool ieee80211_s1g_has_ano(__le16 fc)
+{
+	return ieee80211_is_s1g_beacon(fc) &&
+		(fc & cpu_to_le16(IEEE80211_S1G_BCN_ANO));
+}
+
+/**
+ * ieee80211_s1g_has_cssid - check if IEEE80211_S1G_BCN_CSSID
+ * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame contains the variable-length
+ *	compressed SSID field
+ */
+static inline bool ieee80211_s1g_has_cssid(__le16 fc)
+{
+	return ieee80211_is_s1g_beacon(fc) &&
+		(fc & cpu_to_le16(IEEE80211_S1G_BCN_CSSID));
+}
+
+/**
  * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon
  * @fc: frame control bytes in little-endian byteorder
  * Return: whether or not the frame is an S1G short beacon,
@@ -1245,16 +1280,40 @@ struct ieee80211_ext {
 			u8 change_seq;
 			u8 variable[0];
 		} __packed s1g_beacon;
-		struct {
-			u8 sa[ETH_ALEN];
-			__le32 timestamp;
-			u8 change_seq;
-			u8 next_tbtt[3];
-			u8 variable[0];
-		} __packed s1g_short_beacon;
 	} u;
 } __packed __aligned(2);
 
+/**
+ * ieee80211_s1g_optional_len - determine length of optional S1G beacon fields
+ * @fc: frame control bytes in little-endian byteorder
+ * Return: total length in bytes of the optional fixed-length fields
+ *
+ * S1G beacons may contain up to three optional fixed-length fields that
+ * precede the variable-length elements. Whether these fields are present
+ * is indicated by flags in the frame control field.
+ *
+ * From IEEE 802.11-2024 section 9.3.4.3:
+ *  - Next TBTT field may be 0 or 3 bytes
+ *  - Short SSID field may be 0 or 4 bytes
+ *  - Access Network Options (ANO) field may be 0 or 1 byte
+ */
+static inline size_t
+ieee80211_s1g_optional_len(__le16 fc)
+{
+	size_t len = 0;
+
+	if (ieee80211_s1g_has_next_tbtt(fc))
+		len += 3;
+
+	if (ieee80211_s1g_has_cssid(fc))
+		len += 4;
+
+	if (ieee80211_s1g_has_ano(fc))
+		len += 1;
+
+	return len;
+}
+
 #define IEEE80211_TWT_CONTROL_NDP			BIT(0)
 #define IEEE80211_TWT_CONTROL_RESP_MODE			BIT(1)
 #define IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST	BIT(3)
diff --git a/include/linux/irqchip/irq-renesas-rzv2h.h b/include/linux/irqchip/irq-renesas-rzv2h.h
new file mode 100644
index 000000000000..618a60d2eac0
--- /dev/null
+++ b/include/linux/irqchip/irq-renesas-rzv2h.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Renesas RZ/V2H(P) Interrupt Control Unit (ICU)
+ *
+ * Copyright (C) 2025 Renesas Electronics Corporation.
+ */
+
+#ifndef __LINUX_IRQ_RENESAS_RZV2H
+#define __LINUX_IRQ_RENESAS_RZV2H
+
+#include <linux/platform_device.h>
+
+#define RZV2H_ICU_DMAC_REQ_NO_DEFAULT		0x3ff
+
+#ifdef CONFIG_RENESAS_RZV2H_ICU
+void rzv2h_icu_register_dma_req(struct platform_device *icu_dev, u8 dmac_index, u8 dmac_channel,
+				u16 req_no);
+#else
+static inline void rzv2h_icu_register_dma_req(struct platform_device *icu_dev, u8 dmac_index,
+					      u8 dmac_channel, u16 req_no) { }
+#endif
+
+#endif /* __LINUX_IRQ_RENESAS_RZV2H */
diff --git a/include/linux/lcd.h b/include/linux/lcd.h
index c3ccdff4519a..d4fa03722b72 100644
--- a/include/linux/lcd.h
+++ b/include/linux/lcd.h
@@ -11,7 +11,6 @@
 
 #include <linux/device.h>
 #include <linux/mutex.h>
-#include <linux/notifier.h>
 
 #define LCD_POWER_ON			(0)
 #define LCD_POWER_REDUCED		(1) // deprecated; don't use in new code
@@ -79,8 +78,11 @@ struct lcd_device {
 	const struct lcd_ops *ops;
 	/* Serialise access to set_power method */
 	struct mutex update_lock;
-	/* The framebuffer notifier block */
-	struct notifier_block fb_notif;
+
+	/**
+	 * @entry: List entry of all registered lcd devices
+	 */
+	struct list_head entry;
 
 	struct device dev;
 };
@@ -125,6 +127,19 @@ extern void lcd_device_unregister(struct lcd_device *ld);
 extern void devm_lcd_device_unregister(struct device *dev,
 	struct lcd_device *ld);
 
+#if IS_REACHABLE(CONFIG_LCD_CLASS_DEVICE)
+void lcd_notify_blank_all(struct device *display_dev, int power);
+void lcd_notify_mode_change_all(struct device *display_dev,
+				unsigned int width, unsigned int height);
+#else
+static inline void lcd_notify_blank_all(struct device *display_dev, int power)
+{}
+
+static inline void lcd_notify_mode_change_all(struct device *display_dev,
+					      unsigned int width, unsigned int height)
+{}
+#endif
+
 #define to_lcd_device(obj) container_of(obj, struct lcd_device, dev)
 
 static inline void * lcd_get_data(struct lcd_device *ld_dev)
diff --git a/include/linux/led-class-flash.h b/include/linux/led-class-flash.h
index 36df927ec4b7..21ec856c36bc 100644
--- a/include/linux/led-class-flash.h
+++ b/include/linux/led-class-flash.h
@@ -45,6 +45,8 @@ struct led_flash_ops {
 	int (*timeout_set)(struct led_classdev_flash *fled_cdev, u32 timeout);
 	/* get the flash LED fault */
 	int (*fault_get)(struct led_classdev_flash *fled_cdev, u32 *fault);
+	/* set flash duration */
+	int (*duration_set)(struct led_classdev_flash *fled_cdev, u32 duration);
 };
 
 /*
@@ -75,6 +77,9 @@ struct led_classdev_flash {
 	/* flash timeout value in microseconds along with its constraints */
 	struct led_flash_setting timeout;
 
+	/* flash timeout value in microseconds along with its constraints */
+	struct led_flash_setting duration;
+
 	/* LED Flash class sysfs groups */
 	const struct attribute_group *sysfs_groups[LED_FLASH_SYSFS_GROUPS_SIZE];
 };
@@ -209,4 +214,15 @@ int led_set_flash_timeout(struct led_classdev_flash *fled_cdev, u32 timeout);
  */
 int led_get_flash_fault(struct led_classdev_flash *fled_cdev, u32 *fault);
 
+/**
+ * led_set_flash_duration - set flash LED duration
+ * @fled_cdev: the flash LED to set
+ * @timeout: the flash duration to set it to
+ *
+ * Set the flash strobe duration.
+ *
+ * Returns: 0 on success or negative error value on failure
+ */
+int led_set_flash_duration(struct led_classdev_flash *fled_cdev, u32 duration);
+
 #endif	/* __LINUX_FLASH_LEDS_H_INCLUDED */
diff --git a/include/linux/leds.h b/include/linux/leds.h
index 98f9719c924c..b3f0aa081064 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -640,6 +640,12 @@ static inline void ledtrig_flash_ctrl(bool on) {}
 static inline void ledtrig_torch_ctrl(bool on) {}
 #endif
 
+#if IS_REACHABLE(CONFIG_LEDS_TRIGGER_BACKLIGHT)
+void ledtrig_backlight_blank(bool blank);
+#else
+static inline void ledtrig_backlight_blank(bool blank) {}
+#endif
+
 /*
  * Generic LED platform data for describing LED names and default triggers.
  */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index e5695998acb0..31be45fd47a6 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -41,17 +41,6 @@
  */
 #undef ATA_IRQ_TRAP		/* define to ack screaming irqs */
 
-
-#define ata_print_version_once(dev, version)			\
-({								\
-	static bool __print_once;				\
-								\
-	if (!__print_once) {					\
-		__print_once = true;				\
-		ata_print_version(dev, version);		\
-	}							\
-})
-
 /* defines only for the constants which don't work well as enums */
 #define ATA_TAG_POISON		0xfafbfcfdU
 
@@ -1593,7 +1582,11 @@ do {								\
 #define ata_dev_dbg(dev, fmt, ...)				\
 	ata_dev_printk(debug, dev, fmt, ##__VA_ARGS__)
 
-void ata_print_version(const struct device *dev, const char *version);
+static inline void ata_print_version_once(const struct device *dev,
+					  const char *version)
+{
+	dev_dbg_once(dev, "version %s\n", version);
+}
 
 /*
  * ata_eh_info helpers
@@ -1625,6 +1618,8 @@ static inline void ata_port_desc_misc(struct ata_port *ap, int irq)
 {
 	ata_port_desc(ap, "irq %d", irq);
 	ata_port_desc(ap, "lpm-pol %d", ap->target_lpm_policy);
+	if (ap->pflags & ATA_PFLAG_EXTERNAL)
+		ata_port_desc(ap, "ext");
 }
 
 static inline bool ata_tag_internal(unsigned int tag)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f7848f73f41c..87b6688f124a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -113,6 +113,12 @@ struct mem_cgroup_per_node {
 	CACHELINE_PADDING(_pad2_);
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 	struct mem_cgroup_reclaim_iter	iter;
+
+#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+	/* slab stats for nmi context */
+	atomic_t		slab_reclaimable;
+	atomic_t		slab_unreclaimable;
+#endif
 };
 
 struct mem_cgroup_threshold {
@@ -236,6 +242,10 @@ struct mem_cgroup {
 	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
 	atomic_long_t		memory_events_local[MEMCG_NR_MEMORY_EVENTS];
 
+#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+	/* MEMCG_KMEM for nmi context */
+	atomic_t		kmem_stat;
+#endif
 	/*
 	 * Hint of reclaim pressure for socket memroy management. Note
 	 * that this indicator should NOT be used in legacy cgroup mode
diff --git a/include/linux/mfd/aat2870.h b/include/linux/mfd/aat2870.h
index 2445842d482d..c7a3c53eba68 100644
--- a/include/linux/mfd/aat2870.h
+++ b/include/linux/mfd/aat2870.h
@@ -133,9 +133,6 @@ struct aat2870_data {
 	int (*read)(struct aat2870_data *aat2870, u8 addr, u8 *val);
 	int (*write)(struct aat2870_data *aat2870, u8 addr, u8 val);
 	int (*update)(struct aat2870_data *aat2870, u8 addr, u8 mask, u8 val);
-
-	/* for debugfs */
-	struct dentry *dentry_root;
 };
 
 struct aat2870_subdev_info {
diff --git a/include/linux/mfd/bcm590xx.h b/include/linux/mfd/bcm590xx.h
index 6b8791da6119..5a5783abd47b 100644
--- a/include/linux/mfd/bcm590xx.h
+++ b/include/linux/mfd/bcm590xx.h
@@ -13,6 +13,26 @@
 #include <linux/i2c.h>
 #include <linux/regmap.h>
 
+/* PMU ID register values; also used as device type */
+#define BCM590XX_PMUID_BCM59054		0x54
+#define BCM590XX_PMUID_BCM59056		0x56
+
+/* Known chip revision IDs */
+#define BCM59054_REV_DIGITAL_A1		1
+#define BCM59054_REV_ANALOG_A1		2
+
+#define BCM59056_REV_DIGITAL_A0		1
+#define BCM59056_REV_ANALOG_A0		1
+
+#define BCM59056_REV_DIGITAL_B0		2
+#define BCM59056_REV_ANALOG_B0		2
+
+/* regmap types */
+enum bcm590xx_regmap_type {
+	BCM590XX_REGMAP_PRI,
+	BCM590XX_REGMAP_SEC,
+};
+
 /* max register address */
 #define BCM590XX_MAX_REGISTER_PRI	0xe7
 #define BCM590XX_MAX_REGISTER_SEC	0xf0
@@ -23,7 +43,13 @@ struct bcm590xx {
 	struct i2c_client *i2c_sec;
 	struct regmap *regmap_pri;
 	struct regmap *regmap_sec;
-	unsigned int id;
+
+	/* PMU ID value; also used as device type */
+	u8 pmu_id;
+
+	/* Chip revision, read from PMUREV reg */
+	u8 rev_digital;
+	u8 rev_analog;
 };
 
 #endif /*  __LINUX_MFD_BCM590XX_H */
diff --git a/include/linux/mfd/max14577-private.h b/include/linux/mfd/max14577-private.h
index a21374f8ad26..dd51a37fa37f 100644
--- a/include/linux/mfd/max14577-private.h
+++ b/include/linux/mfd/max14577-private.h
@@ -2,7 +2,7 @@
 /*
  * max14577-private.h - Common API for the Maxim 14577/77836 internal sub chip
  *
- * Copyright (C) 2014 Samsung Electrnoics
+ * Copyright (C) 2014 Samsung Electronics
  * Chanwoo Choi <cw00.choi@samsung.com>
  * Krzysztof Kozlowski <krzk@kernel.org>
  */
diff --git a/include/linux/mfd/max14577.h b/include/linux/mfd/max14577.h
index 8b3ef891ba42..0fda5c2e745a 100644
--- a/include/linux/mfd/max14577.h
+++ b/include/linux/mfd/max14577.h
@@ -2,7 +2,7 @@
 /*
  * max14577.h - Driver for the Maxim 14577/77836
  *
- * Copyright (C) 2014 Samsung Electrnoics
+ * Copyright (C) 2014 Samsung Electronics
  * Chanwoo Choi <cw00.choi@samsung.com>
  * Krzysztof Kozlowski <krzk@kernel.org>
  *
diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h
index ea635d12a741..e6b8b4014dc0 100644
--- a/include/linux/mfd/max77686-private.h
+++ b/include/linux/mfd/max77686-private.h
@@ -2,7 +2,7 @@
 /*
  * max77686-private.h - Voltage regulator driver for the Maxim 77686/802
  *
- *  Copyright (C) 2012 Samsung Electrnoics
+ *  Copyright (C) 2012 Samsung Electronics
  *  Chiwoong Byun <woong.byun@samsung.com>
  */
 
diff --git a/include/linux/mfd/max77686.h b/include/linux/mfd/max77686.h
index d0fb510875e6..7c4624acd1db 100644
--- a/include/linux/mfd/max77686.h
+++ b/include/linux/mfd/max77686.h
@@ -2,7 +2,7 @@
 /*
  * max77686.h - Driver for the Maxim 77686/802
  *
- *  Copyright (C) 2012 Samsung Electrnoics
+ *  Copyright (C) 2012 Samsung Electronics
  *  Chiwoong Byun <woong.byun@samsung.com>
  *
  * This driver is based on max8997.h
diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index c324d548619e..8e7c35b5ea1c 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -2,7 +2,7 @@
 /*
  * max77693-private.h - Voltage regulator driver for the Maxim 77693
  *
- *  Copyright (C) 2012 Samsung Electrnoics
+ *  Copyright (C) 2012 Samsung Electronics
  *  SangYoung Son <hello.son@samsung.com>
  *
  * This program is not provided / owned by Maxim Integrated Products.
diff --git a/include/linux/mfd/max77693.h b/include/linux/mfd/max77693.h
index c67c16ba8649..8e77ebeb7cf1 100644
--- a/include/linux/mfd/max77693.h
+++ b/include/linux/mfd/max77693.h
@@ -2,7 +2,7 @@
 /*
  * max77693.h - Driver for the Maxim 77693
  *
- *  Copyright (C) 2012 Samsung Electrnoics
+ *  Copyright (C) 2012 Samsung Electronics
  *  SangYoung Son <hello.son@samsung.com>
  *
  * This program is not provided / owned by Maxim Integrated Products.
diff --git a/include/linux/mfd/max8997-private.h b/include/linux/mfd/max8997-private.h
index f70eea0f2264..261c0aae7d00 100644
--- a/include/linux/mfd/max8997-private.h
+++ b/include/linux/mfd/max8997-private.h
@@ -2,7 +2,7 @@
 /*
  * max8997-private.h - Voltage regulator driver for the Maxim 8997
  *
- *  Copyright (C) 2010 Samsung Electrnoics
+ *  Copyright (C) 2010 Samsung Electronics
  *  MyungJoo Ham <myungjoo.ham@samsung.com>
  */
 
diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h
index 5c2cc1103437..fb36e1386069 100644
--- a/include/linux/mfd/max8997.h
+++ b/include/linux/mfd/max8997.h
@@ -2,7 +2,7 @@
 /*
  * max8997.h - Driver for the Maxim 8997/8966
  *
- *  Copyright (C) 2009-2010 Samsung Electrnoics
+ *  Copyright (C) 2009-2010 Samsung Electronics
  *  MyungJoo Ham <myungjoo.ham@samsung.com>
  *
  * This driver is based on max8998.h
diff --git a/include/linux/mfd/max8998-private.h b/include/linux/mfd/max8998-private.h
index 6deb5f577602..d77dc18db6eb 100644
--- a/include/linux/mfd/max8998-private.h
+++ b/include/linux/mfd/max8998-private.h
@@ -2,7 +2,7 @@
 /*
  * max8998-private.h - Voltage regulator driver for the Maxim 8998
  *
- *  Copyright (C) 2009-2010 Samsung Electrnoics
+ *  Copyright (C) 2009-2010 Samsung Electronics
  *  Kyungmin Park <kyungmin.park@samsung.com>
  *  Marek Szyprowski <m.szyprowski@samsung.com>
  */
diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h
index a054e55c8646..5473f1983e31 100644
--- a/include/linux/mfd/max8998.h
+++ b/include/linux/mfd/max8998.h
@@ -2,7 +2,7 @@
 /*
  * max8998.h - Voltage regulator driver for the Maxim 8998
  *
- *  Copyright (C) 2009-2010 Samsung Electrnoics
+ *  Copyright (C) 2009-2010 Samsung Electronics
  *  Kyungmin Park <kyungmin.park@samsung.com>
  *  Marek Szyprowski <m.szyprowski@samsung.com>
  */
diff --git a/include/linux/mfd/rohm-bd96801.h b/include/linux/mfd/rohm-bd96801.h
index e2d9e10b6364..68c8ac8ad409 100644
--- a/include/linux/mfd/rohm-bd96801.h
+++ b/include/linux/mfd/rohm-bd96801.h
@@ -40,7 +40,9 @@
  * INTB status registers are at range 0x5c ... 0x63
  */
 #define BD96801_REG_INT_SYS_ERRB1	0x52
+#define BD96801_REG_INT_BUCK2_ERRB	0x56
 #define BD96801_REG_INT_SYS_INTB	0x5c
+#define BD96801_REG_INT_BUCK2_INTB	0x5e
 #define BD96801_REG_INT_LDO7_INTB	0x63
 
 /* MASK registers */
diff --git a/include/linux/mfd/rohm-bd96802.h b/include/linux/mfd/rohm-bd96802.h
new file mode 100644
index 000000000000..bf4b77944edf
--- /dev/null
+++ b/include/linux/mfd/rohm-bd96802.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2025 ROHM Semiconductors
+ *
+ * The digital interface of trhe BD96802 PMIC is a reduced version of the
+ * BD96801. Hence the BD96801 definitions are used for registers and masks
+ * while this header only holds the IRQ definitions - mainly to avoid gaps in
+ * IRQ numbers caused by the lack of some BUCKs / LDOs and their respective
+ * IRQs.
+ */
+
+#ifndef __LINUX_MFD_BD96802_H__
+#define __LINUX_MFD_BD96802_H__
+
+/* ERRB IRQs */
+enum {
+	/* Reg 0x52, 0x53, 0x54 - ERRB system IRQs */
+	BD96802_OTP_ERR_STAT,
+	BD96802_DBIST_ERR_STAT,
+	BD96802_EEP_ERR_STAT,
+	BD96802_ABIST_ERR_STAT,
+	BD96802_PRSTB_ERR_STAT,
+	BD96802_DRMOS1_ERR_STAT,
+	BD96802_DRMOS2_ERR_STAT,
+	BD96802_SLAVE_ERR_STAT,
+	BD96802_VREF_ERR_STAT,
+	BD96802_TSD_ERR_STAT,
+	BD96802_UVLO_ERR_STAT,
+	BD96802_OVLO_ERR_STAT,
+	BD96802_OSC_ERR_STAT,
+	BD96802_PON_ERR_STAT,
+	BD96802_POFF_ERR_STAT,
+	BD96802_CMD_SHDN_ERR_STAT,
+	BD96802_INT_SHDN_ERR_STAT,
+
+	/* Reg 0x55 BUCK1 ERR IRQs */
+	BD96802_BUCK1_PVIN_ERR_STAT,
+	BD96802_BUCK1_OVP_ERR_STAT,
+	BD96802_BUCK1_UVP_ERR_STAT,
+	BD96802_BUCK1_SHDN_ERR_STAT,
+
+	/* Reg 0x56 BUCK2 ERR IRQs */
+	BD96802_BUCK2_PVIN_ERR_STAT,
+	BD96802_BUCK2_OVP_ERR_STAT,
+	BD96802_BUCK2_UVP_ERR_STAT,
+	BD96802_BUCK2_SHDN_ERR_STAT,
+};
+
+/* INTB IRQs */
+enum {
+	/* Reg 0x5c (System INTB) */
+	BD96802_TW_STAT,
+	BD96802_WDT_ERR_STAT,
+	BD96802_I2C_ERR_STAT,
+	BD96802_CHIP_IF_ERR_STAT,
+
+	/* Reg 0x5d (BUCK1 INTB) */
+	BD96802_BUCK1_OCPH_STAT,
+	BD96802_BUCK1_OCPL_STAT,
+	BD96802_BUCK1_OCPN_STAT,
+	BD96802_BUCK1_OVD_STAT,
+	BD96802_BUCK1_UVD_STAT,
+	BD96802_BUCK1_TW_CH_STAT,
+
+	/* Reg 0x5e (BUCK2 INTB) */
+	BD96802_BUCK2_OCPH_STAT,
+	BD96802_BUCK2_OCPL_STAT,
+	BD96802_BUCK2_OCPN_STAT,
+	BD96802_BUCK2_OVD_STAT,
+	BD96802_BUCK2_UVD_STAT,
+	BD96802_BUCK2_TW_CH_STAT,
+};
+
+#endif
diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h
index e7d4e6afe388..579e8dcfcca4 100644
--- a/include/linux/mfd/rohm-generic.h
+++ b/include/linux/mfd/rohm-generic.h
@@ -17,6 +17,9 @@ enum rohm_chip_type {
 	ROHM_CHIP_TYPE_BD71837,
 	ROHM_CHIP_TYPE_BD71847,
 	ROHM_CHIP_TYPE_BD96801,
+	ROHM_CHIP_TYPE_BD96802,
+	ROHM_CHIP_TYPE_BD96805,
+	ROHM_CHIP_TYPE_BD96806,
 	ROHM_CHIP_TYPE_AMOUNT
 };
 
diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h
index f35314458fd2..d785e101fe79 100644
--- a/include/linux/mfd/samsung/core.h
+++ b/include/linux/mfd/samsung/core.h
@@ -39,6 +39,7 @@ enum sec_device_type {
 	S5M8767X,
 	S2DOS05,
 	S2MPA01,
+	S2MPG10,
 	S2MPS11X,
 	S2MPS13X,
 	S2MPS14X,
@@ -66,15 +67,11 @@ struct sec_pmic_dev {
 	struct regmap *regmap_pmic;
 	struct i2c_client *i2c;
 
-	unsigned long device_type;
+	int device_type;
 	int irq;
 	struct regmap_irq_chip_data *irq_data;
 };
 
-int sec_irq_init(struct sec_pmic_dev *sec_pmic);
-void sec_irq_exit(struct sec_pmic_dev *sec_pmic);
-int sec_irq_resume(struct sec_pmic_dev *sec_pmic);
-
 struct sec_platform_data {
 	struct sec_regulator_data	*regulators;
 	struct sec_opmode_data		*opmode;
diff --git a/include/linux/mfd/samsung/irq.h b/include/linux/mfd/samsung/irq.h
index 978f7af66f74..b4805cbd949b 100644
--- a/include/linux/mfd/samsung/irq.h
+++ b/include/linux/mfd/samsung/irq.h
@@ -57,6 +57,109 @@ enum s2mpa01_irq {
 #define S2MPA01_IRQ_B24_TSD_MASK	(1 << 4)
 #define S2MPA01_IRQ_B35_TSD_MASK	(1 << 5)
 
+enum s2mpg10_irq {
+	/* PMIC */
+	S2MPG10_IRQ_PWRONF,
+	S2MPG10_IRQ_PWRONR,
+	S2MPG10_IRQ_JIGONBF,
+	S2MPG10_IRQ_JIGONBR,
+	S2MPG10_IRQ_ACOKBF,
+	S2MPG10_IRQ_ACOKBR,
+	S2MPG10_IRQ_PWRON1S,
+	S2MPG10_IRQ_MRB,
+#define S2MPG10_IRQ_PWRONF_MASK		BIT(0)
+#define S2MPG10_IRQ_PWRONR_MASK		BIT(1)
+#define S2MPG10_IRQ_JIGONBF_MASK	BIT(2)
+#define S2MPG10_IRQ_JIGONBR_MASK	BIT(3)
+#define S2MPG10_IRQ_ACOKBF_MASK		BIT(4)
+#define S2MPG10_IRQ_ACOKBR_MASK		BIT(5)
+#define S2MPG10_IRQ_PWRON1S_MASK	BIT(6)
+#define S2MPG10_IRQ_MRB_MASK		BIT(7)
+
+	S2MPG10_IRQ_RTC60S,
+	S2MPG10_IRQ_RTCA1,
+	S2MPG10_IRQ_RTCA0,
+	S2MPG10_IRQ_RTC1S,
+	S2MPG10_IRQ_WTSR_COLDRST,
+	S2MPG10_IRQ_WTSR,
+	S2MPG10_IRQ_WRST,
+	S2MPG10_IRQ_SMPL,
+#define S2MPG10_IRQ_RTC60S_MASK		BIT(0)
+#define S2MPG10_IRQ_RTCA1_MASK		BIT(1)
+#define S2MPG10_IRQ_RTCA0_MASK		BIT(2)
+#define S2MPG10_IRQ_RTC1S_MASK		BIT(3)
+#define S2MPG10_IRQ_WTSR_COLDRST_MASK	BIT(4)
+#define S2MPG10_IRQ_WTSR_MASK		BIT(5)
+#define S2MPG10_IRQ_WRST_MASK		BIT(6)
+#define S2MPG10_IRQ_SMPL_MASK		BIT(7)
+
+	S2MPG10_IRQ_120C,
+	S2MPG10_IRQ_140C,
+	S2MPG10_IRQ_TSD,
+	S2MPG10_IRQ_PIF_TIMEOUT1,
+	S2MPG10_IRQ_PIF_TIMEOUT2,
+	S2MPG10_IRQ_SPD_PARITY_ERR,
+	S2MPG10_IRQ_SPD_ABNORMAL_STOP,
+	S2MPG10_IRQ_PMETER_OVERF,
+#define S2MPG10_IRQ_INT120C_MASK		BIT(0)
+#define S2MPG10_IRQ_INT140C_MASK		BIT(1)
+#define S2MPG10_IRQ_TSD_MASK			BIT(2)
+#define S2MPG10_IRQ_PIF_TIMEOUT1_MASK		BIT(3)
+#define S2MPG10_IRQ_PIF_TIMEOUT2_MASK		BIT(4)
+#define S2MPG10_IRQ_SPD_PARITY_ERR_MASK		BIT(5)
+#define S2MPG10_IRQ_SPD_ABNORMAL_STOP_MASK	BIT(6)
+#define S2MPG10_IRQ_PMETER_OVERF_MASK		BIT(7)
+
+	S2MPG10_IRQ_OCP_B1M,
+	S2MPG10_IRQ_OCP_B2M,
+	S2MPG10_IRQ_OCP_B3M,
+	S2MPG10_IRQ_OCP_B4M,
+	S2MPG10_IRQ_OCP_B5M,
+	S2MPG10_IRQ_OCP_B6M,
+	S2MPG10_IRQ_OCP_B7M,
+	S2MPG10_IRQ_OCP_B8M,
+#define S2MPG10_IRQ_OCP_B1M_MASK	BIT(0)
+#define S2MPG10_IRQ_OCP_B2M_MASK	BIT(1)
+#define S2MPG10_IRQ_OCP_B3M_MASK	BIT(2)
+#define S2MPG10_IRQ_OCP_B4M_MASK	BIT(3)
+#define S2MPG10_IRQ_OCP_B5M_MASK	BIT(4)
+#define S2MPG10_IRQ_OCP_B6M_MASK	BIT(5)
+#define S2MPG10_IRQ_OCP_B7M_MASK	BIT(6)
+#define S2MPG10_IRQ_OCP_B8M_MASK	BIT(7)
+
+	S2MPG10_IRQ_OCP_B9M,
+	S2MPG10_IRQ_OCP_B10M,
+	S2MPG10_IRQ_WLWP_ACC,
+	S2MPG10_IRQ_SMPL_TIMEOUT,
+	S2MPG10_IRQ_WTSR_TIMEOUT,
+	S2MPG10_IRQ_SPD_SRP_PKT_RST,
+#define S2MPG10_IRQ_OCP_B9M_MASK		BIT(0)
+#define S2MPG10_IRQ_OCP_B10M_MASK		BIT(1)
+#define S2MPG10_IRQ_WLWP_ACC_MASK		BIT(2)
+#define S2MPG10_IRQ_SMPL_TIMEOUT_MASK		BIT(5)
+#define S2MPG10_IRQ_WTSR_TIMEOUT_MASK		BIT(6)
+#define S2MPG10_IRQ_SPD_SRP_PKT_RST_MASK	BIT(7)
+
+	S2MPG10_IRQ_PWR_WARN_CH0,
+	S2MPG10_IRQ_PWR_WARN_CH1,
+	S2MPG10_IRQ_PWR_WARN_CH2,
+	S2MPG10_IRQ_PWR_WARN_CH3,
+	S2MPG10_IRQ_PWR_WARN_CH4,
+	S2MPG10_IRQ_PWR_WARN_CH5,
+	S2MPG10_IRQ_PWR_WARN_CH6,
+	S2MPG10_IRQ_PWR_WARN_CH7,
+#define S2MPG10_IRQ_PWR_WARN_CH0_MASK	BIT(0)
+#define S2MPG10_IRQ_PWR_WARN_CH1_MASK	BIT(1)
+#define S2MPG10_IRQ_PWR_WARN_CH2_MASK	BIT(2)
+#define S2MPG10_IRQ_PWR_WARN_CH3_MASK	BIT(3)
+#define S2MPG10_IRQ_PWR_WARN_CH4_MASK	BIT(4)
+#define S2MPG10_IRQ_PWR_WARN_CH5_MASK	BIT(5)
+#define S2MPG10_IRQ_PWR_WARN_CH6_MASK	BIT(6)
+#define S2MPG10_IRQ_PWR_WARN_CH7_MASK	BIT(7)
+
+	S2MPG10_IRQ_NR,
+};
+
 enum s2mps11_irq {
 	S2MPS11_IRQ_PWRONF,
 	S2MPS11_IRQ_PWRONR,
diff --git a/include/linux/mfd/samsung/rtc.h b/include/linux/mfd/samsung/rtc.h
index 0204decfc9aa..51c4239a1fa6 100644
--- a/include/linux/mfd/samsung/rtc.h
+++ b/include/linux/mfd/samsung/rtc.h
@@ -72,6 +72,37 @@ enum s2mps_rtc_reg {
 	S2MPS_RTC_REG_MAX,
 };
 
+enum s2mpg10_rtc_reg {
+	S2MPG10_RTC_CTRL,
+	S2MPG10_RTC_UPDATE,
+	S2MPG10_RTC_SMPL,
+	S2MPG10_RTC_WTSR,
+	S2MPG10_RTC_CAP_SEL,
+	S2MPG10_RTC_MSEC,
+	S2MPG10_RTC_SEC,
+	S2MPG10_RTC_MIN,
+	S2MPG10_RTC_HOUR,
+	S2MPG10_RTC_WEEK,
+	S2MPG10_RTC_DAY,
+	S2MPG10_RTC_MON,
+	S2MPG10_RTC_YEAR,
+	S2MPG10_RTC_A0SEC,
+	S2MPG10_RTC_A0MIN,
+	S2MPG10_RTC_A0HOUR,
+	S2MPG10_RTC_A0WEEK,
+	S2MPG10_RTC_A0DAY,
+	S2MPG10_RTC_A0MON,
+	S2MPG10_RTC_A0YEAR,
+	S2MPG10_RTC_A1SEC,
+	S2MPG10_RTC_A1MIN,
+	S2MPG10_RTC_A1HOUR,
+	S2MPG10_RTC_A1WEEK,
+	S2MPG10_RTC_A1DAY,
+	S2MPG10_RTC_A1MON,
+	S2MPG10_RTC_A1YEAR,
+	S2MPG10_RTC_OSC_CTRL,
+};
+
 #define RTC_I2C_ADDR		(0x0C >> 1)
 
 #define HOUR_12			(1 << 7)
@@ -124,10 +155,16 @@ enum s2mps_rtc_reg {
 #define ALARM_ENABLE_SHIFT	7
 #define ALARM_ENABLE_MASK	(1 << ALARM_ENABLE_SHIFT)
 
+/* WTSR & SMPL registers */
 #define SMPL_ENABLE_SHIFT	7
 #define SMPL_ENABLE_MASK	(1 << SMPL_ENABLE_SHIFT)
 
 #define WTSR_ENABLE_SHIFT	6
 #define WTSR_ENABLE_MASK	(1 << WTSR_ENABLE_SHIFT)
 
+#define S2MPG10_WTSR_COLDTIMER	GENMASK(6, 5)
+#define S2MPG10_WTSR_COLDRST	BIT(4)
+#define S2MPG10_WTSR_WTSRT	GENMASK(3, 1)
+#define S2MPG10_WTSR_WTSR_EN	BIT(0)
+
 #endif /*  __LINUX_MFD_SEC_RTC_H */
diff --git a/include/linux/mfd/samsung/s2mpg10.h b/include/linux/mfd/samsung/s2mpg10.h
new file mode 100644
index 000000000000..9f5919b89a3c
--- /dev/null
+++ b/include/linux/mfd/samsung/s2mpg10.h
@@ -0,0 +1,454 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright 2015 Samsung Electronics
+ * Copyright 2020 Google Inc
+ * Copyright 2025 Linaro Ltd.
+ */
+
+#ifndef __LINUX_MFD_S2MPG10_H
+#define __LINUX_MFD_S2MPG10_H
+
+/* Common registers (type 0x000) */
+enum s2mpg10_common_reg {
+	S2MPG10_COMMON_CHIPID,
+	S2MPG10_COMMON_INT,
+	S2MPG10_COMMON_INT_MASK,
+	S2MPG10_COMMON_SPD_CTRL1 = 0x0a,
+	S2MPG10_COMMON_SPD_CTRL2,
+	S2MPG10_COMMON_SPD_CTRL3,
+	S2MPG10_COMMON_MON1SEL = 0x1a,
+	S2MPG10_COMMON_MON2SEL,
+	S2MPG10_COMMON_MONR,
+	S2MPG10_COMMON_DEBUG_CTRL1,
+	S2MPG10_COMMON_DEBUG_CTRL2,
+	S2MPG10_COMMON_DEBUG_CTRL3,
+	S2MPG10_COMMON_DEBUG_CTRL4,
+	S2MPG10_COMMON_DEBUG_CTRL5,
+	S2MPG10_COMMON_DEBUG_CTRL6,
+	S2MPG10_COMMON_DEBUG_CTRL7,
+	S2MPG10_COMMON_DEBUG_CTRL8,
+	S2MPG10_COMMON_TEST_MODE1,
+	S2MPG10_COMMON_TEST_MODE2,
+	S2MPG10_COMMON_SPD_DEBUG1,
+	S2MPG10_COMMON_SPD_DEBUG2,
+	S2MPG10_COMMON_SPD_DEBUG3,
+	S2MPG10_COMMON_SPD_DEBUG4,
+};
+
+/* For S2MPG10_COMMON_INT and S2MPG10_COMMON_INT_MASK */
+#define S2MPG10_COMMON_INT_SRC       GENMASK(7, 0)
+#define S2MPG10_COMMON_INT_SRC_PMIC  BIT(0)
+
+/* PMIC registers (type 0x100) */
+enum s2mpg10_pmic_reg {
+	S2MPG10_PMIC_INT1,
+	S2MPG10_PMIC_INT2,
+	S2MPG10_PMIC_INT3,
+	S2MPG10_PMIC_INT4,
+	S2MPG10_PMIC_INT5,
+	S2MPG10_PMIC_INT6,
+	S2MPG10_PMIC_INT1M,
+	S2MPG10_PMIC_INT2M,
+	S2MPG10_PMIC_INT3M,
+	S2MPG10_PMIC_INT4M,
+	S2MPG10_PMIC_INT5M,
+	S2MPG10_PMIC_INT6M,
+	S2MPG10_PMIC_STATUS1,
+	S2MPG10_PMIC_STATUS2,
+	S2MPG10_PMIC_PWRONSRC,
+	S2MPG10_PMIC_OFFSRC,
+	S2MPG10_PMIC_BU_CHG,
+	S2MPG10_PMIC_RTCBUF,
+	S2MPG10_PMIC_COMMON_CTRL1,
+	S2MPG10_PMIC_COMMON_CTRL2,
+	S2MPG10_PMIC_COMMON_CTRL3,
+	S2MPG10_PMIC_COMMON_CTRL4,
+	S2MPG10_PMIC_SMPL_WARN_CTRL,
+	S2MPG10_PMIC_MIMICKING_CTRL,
+	S2MPG10_PMIC_B1M_CTRL,
+	S2MPG10_PMIC_B1M_OUT1,
+	S2MPG10_PMIC_B1M_OUT2,
+	S2MPG10_PMIC_B2M_CTRL,
+	S2MPG10_PMIC_B2M_OUT1,
+	S2MPG10_PMIC_B2M_OUT2,
+	S2MPG10_PMIC_B3M_CTRL,
+	S2MPG10_PMIC_B3M_OUT1,
+	S2MPG10_PMIC_B3M_OUT2,
+	S2MPG10_PMIC_B4M_CTRL,
+	S2MPG10_PMIC_B4M_OUT1,
+	S2MPG10_PMIC_B4M_OUT2,
+	S2MPG10_PMIC_B5M_CTRL,
+	S2MPG10_PMIC_B5M_OUT1,
+	S2MPG10_PMIC_B5M_OUT2,
+	S2MPG10_PMIC_B6M_CTRL,
+	S2MPG10_PMIC_B6M_OUT1,
+	S2MPG10_PMIC_B6M_OUT2,
+	S2MPG10_PMIC_B7M_CTRL,
+	S2MPG10_PMIC_B7M_OUT1,
+	S2MPG10_PMIC_B7M_OUT2,
+	S2MPG10_PMIC_B8M_CTRL,
+	S2MPG10_PMIC_B8M_OUT1,
+	S2MPG10_PMIC_B8M_OUT2,
+	S2MPG10_PMIC_B9M_CTRL,
+	S2MPG10_PMIC_B9M_OUT1,
+	S2MPG10_PMIC_B9M_OUT2,
+	S2MPG10_PMIC_B10M_CTRL,
+	S2MPG10_PMIC_B10M_OUT1,
+	S2MPG10_PMIC_B10M_OUT2,
+	S2MPG10_PMIC_BUCK1M_USONIC,
+	S2MPG10_PMIC_BUCK2M_USONIC,
+	S2MPG10_PMIC_BUCK3M_USONIC,
+	S2MPG10_PMIC_BUCK4M_USONIC,
+	S2MPG10_PMIC_BUCK5M_USONIC,
+	S2MPG10_PMIC_BUCK6M_USONIC,
+	S2MPG10_PMIC_BUCK7M_USONIC,
+	S2MPG10_PMIC_BUCK8M_USONIC,
+	S2MPG10_PMIC_BUCK9M_USONIC,
+	S2MPG10_PMIC_BUCK10M_USONIC,
+	S2MPG10_PMIC_L1M_CTRL,
+	S2MPG10_PMIC_L2M_CTRL,
+	S2MPG10_PMIC_L3M_CTRL,
+	S2MPG10_PMIC_L4M_CTRL,
+	S2MPG10_PMIC_L5M_CTRL,
+	S2MPG10_PMIC_L6M_CTRL,
+	S2MPG10_PMIC_L7M_CTRL,
+	S2MPG10_PMIC_L8M_CTRL,
+	S2MPG10_PMIC_L9M_CTRL,
+	S2MPG10_PMIC_L10M_CTRL,
+	S2MPG10_PMIC_L11M_CTRL1,
+	S2MPG10_PMIC_L11M_CTRL2,
+	S2MPG10_PMIC_L12M_CTRL1,
+	S2MPG10_PMIC_L12M_CTRL2,
+	S2MPG10_PMIC_L13M_CTRL1,
+	S2MPG10_PMIC_L13M_CTRL2,
+	S2MPG10_PMIC_L14M_CTRL,
+	S2MPG10_PMIC_L15M_CTRL1,
+	S2MPG10_PMIC_L15M_CTRL2,
+	S2MPG10_PMIC_L16M_CTRL,
+	S2MPG10_PMIC_L17M_CTRL,
+	S2MPG10_PMIC_L18M_CTRL,
+	S2MPG10_PMIC_L19M_CTRL,
+	S2MPG10_PMIC_L20M_CTRL,
+	S2MPG10_PMIC_L21M_CTRL,
+	S2MPG10_PMIC_L22M_CTRL,
+	S2MPG10_PMIC_L23M_CTRL,
+	S2MPG10_PMIC_L24M_CTRL,
+	S2MPG10_PMIC_L25M_CTRL,
+	S2MPG10_PMIC_L26M_CTRL,
+	S2MPG10_PMIC_L27M_CTRL,
+	S2MPG10_PMIC_L28M_CTRL,
+	S2MPG10_PMIC_L29M_CTRL,
+	S2MPG10_PMIC_L30M_CTRL,
+	S2MPG10_PMIC_L31M_CTRL,
+	S2MPG10_PMIC_LDO_CTRL1,
+	S2MPG10_PMIC_LDO_CTRL2,
+	S2MPG10_PMIC_LDO_DSCH1,
+	S2MPG10_PMIC_LDO_DSCH2,
+	S2MPG10_PMIC_LDO_DSCH3,
+	S2MPG10_PMIC_LDO_DSCH4,
+	S2MPG10_PMIC_LDO_BUCK7M_HLIMIT,
+	S2MPG10_PMIC_LDO_BUCK7M_LLIMIT,
+	S2MPG10_PMIC_LDO_LDO21M_HLIMIT,
+	S2MPG10_PMIC_LDO_LDO21M_LLIMIT,
+	S2MPG10_PMIC_LDO_LDO11M_HLIMIT,
+	S2MPG10_PMIC_DVS_RAMP1,
+	S2MPG10_PMIC_DVS_RAMP2,
+	S2MPG10_PMIC_DVS_RAMP3,
+	S2MPG10_PMIC_DVS_RAMP4,
+	S2MPG10_PMIC_DVS_RAMP5,
+	S2MPG10_PMIC_DVS_RAMP6,
+	S2MPG10_PMIC_DVS_SYNC_CTRL1,
+	S2MPG10_PMIC_DVS_SYNC_CTRL2,
+	S2MPG10_PMIC_DVS_SYNC_CTRL3,
+	S2MPG10_PMIC_DVS_SYNC_CTRL4,
+	S2MPG10_PMIC_DVS_SYNC_CTRL5,
+	S2MPG10_PMIC_DVS_SYNC_CTRL6,
+	S2MPG10_PMIC_OFF_CTRL1,
+	S2MPG10_PMIC_OFF_CTRL2,
+	S2MPG10_PMIC_OFF_CTRL3,
+	S2MPG10_PMIC_OFF_CTRL4,
+	S2MPG10_PMIC_SEQ_CTRL1,
+	S2MPG10_PMIC_SEQ_CTRL2,
+	S2MPG10_PMIC_SEQ_CTRL3,
+	S2MPG10_PMIC_SEQ_CTRL4,
+	S2MPG10_PMIC_SEQ_CTRL5,
+	S2MPG10_PMIC_SEQ_CTRL6,
+	S2MPG10_PMIC_SEQ_CTRL7,
+	S2MPG10_PMIC_SEQ_CTRL8,
+	S2MPG10_PMIC_SEQ_CTRL9,
+	S2MPG10_PMIC_SEQ_CTRL10,
+	S2MPG10_PMIC_SEQ_CTRL11,
+	S2MPG10_PMIC_SEQ_CTRL12,
+	S2MPG10_PMIC_SEQ_CTRL13,
+	S2MPG10_PMIC_SEQ_CTRL14,
+	S2MPG10_PMIC_SEQ_CTRL15,
+	S2MPG10_PMIC_SEQ_CTRL16,
+	S2MPG10_PMIC_SEQ_CTRL17,
+	S2MPG10_PMIC_SEQ_CTRL18,
+	S2MPG10_PMIC_SEQ_CTRL19,
+	S2MPG10_PMIC_SEQ_CTRL20,
+	S2MPG10_PMIC_SEQ_CTRL21,
+	S2MPG10_PMIC_SEQ_CTRL22,
+	S2MPG10_PMIC_SEQ_CTRL23,
+	S2MPG10_PMIC_SEQ_CTRL24,
+	S2MPG10_PMIC_SEQ_CTRL25,
+	S2MPG10_PMIC_SEQ_CTRL26,
+	S2MPG10_PMIC_SEQ_CTRL27,
+	S2MPG10_PMIC_SEQ_CTRL28,
+	S2MPG10_PMIC_SEQ_CTRL29,
+	S2MPG10_PMIC_SEQ_CTRL30,
+	S2MPG10_PMIC_SEQ_CTRL31,
+	S2MPG10_PMIC_SEQ_CTRL32,
+	S2MPG10_PMIC_SEQ_CTRL33,
+	S2MPG10_PMIC_SEQ_CTRL34,
+	S2MPG10_PMIC_SEQ_CTRL35,
+	S2MPG10_PMIC_OFF_SEQ_CTRL1,
+	S2MPG10_PMIC_OFF_SEQ_CTRL2,
+	S2MPG10_PMIC_OFF_SEQ_CTRL3,
+	S2MPG10_PMIC_OFF_SEQ_CTRL4,
+	S2MPG10_PMIC_OFF_SEQ_CTRL5,
+	S2MPG10_PMIC_OFF_SEQ_CTRL6,
+	S2MPG10_PMIC_OFF_SEQ_CTRL7,
+	S2MPG10_PMIC_OFF_SEQ_CTRL8,
+	S2MPG10_PMIC_OFF_SEQ_CTRL9,
+	S2MPG10_PMIC_OFF_SEQ_CTRL10,
+	S2MPG10_PMIC_OFF_SEQ_CTRL11,
+	S2MPG10_PMIC_OFF_SEQ_CTRL12,
+	S2MPG10_PMIC_OFF_SEQ_CTRL13,
+	S2MPG10_PMIC_OFF_SEQ_CTRL14,
+	S2MPG10_PMIC_OFF_SEQ_CTRL15,
+	S2MPG10_PMIC_OFF_SEQ_CTRL16,
+	S2MPG10_PMIC_OFF_SEQ_CTRL17,
+	S2MPG10_PMIC_OFF_SEQ_CTRL18,
+	S2MPG10_PMIC_PCTRLSEL1,
+	S2MPG10_PMIC_PCTRLSEL2,
+	S2MPG10_PMIC_PCTRLSEL3,
+	S2MPG10_PMIC_PCTRLSEL4,
+	S2MPG10_PMIC_PCTRLSEL5,
+	S2MPG10_PMIC_PCTRLSEL6,
+	S2MPG10_PMIC_PCTRLSEL7,
+	S2MPG10_PMIC_PCTRLSEL8,
+	S2MPG10_PMIC_PCTRLSEL9,
+	S2MPG10_PMIC_PCTRLSEL10,
+	S2MPG10_PMIC_PCTRLSEL11,
+	S2MPG10_PMIC_PCTRLSEL12,
+	S2MPG10_PMIC_PCTRLSEL13,
+	S2MPG10_PMIC_DCTRLSEL1,
+	S2MPG10_PMIC_DCTRLSEL2,
+	S2MPG10_PMIC_DCTRLSEL3,
+	S2MPG10_PMIC_DCTRLSEL4,
+	S2MPG10_PMIC_DCTRLSEL5,
+	S2MPG10_PMIC_DCTRLSEL6,
+	S2MPG10_PMIC_DCTRLSEL7,
+	S2MPG10_PMIC_GPIO_CTRL1,
+	S2MPG10_PMIC_GPIO_CTRL2,
+	S2MPG10_PMIC_GPIO_CTRL3,
+	S2MPG10_PMIC_GPIO_CTRL4,
+	S2MPG10_PMIC_GPIO_CTRL5,
+	S2MPG10_PMIC_GPIO_CTRL6,
+	S2MPG10_PMIC_GPIO_CTRL7,
+	S2MPG10_PMIC_B2M_OCP_WARN,
+	S2MPG10_PMIC_B2M_OCP_WARN_X,
+	S2MPG10_PMIC_B2M_OCP_WARN_Y,
+	S2MPG10_PMIC_B2M_OCP_WARN_Z,
+	S2MPG10_PMIC_B3M_OCP_WARN,
+	S2MPG10_PMIC_B3M_OCP_WARN_X,
+	S2MPG10_PMIC_B3M_OCP_WARN_Y,
+	S2MPG10_PMIC_B3M_OCP_WARN_Z,
+	S2MPG10_PMIC_B10M_OCP_WARN,
+	S2MPG10_PMIC_B10M_OCP_WARN_X,
+	S2MPG10_PMIC_B10M_OCP_WARN_Y,
+	S2MPG10_PMIC_B10M_OCP_WARN_Z,
+	S2MPG10_PMIC_B2M_SOFT_OCP_WARN,
+	S2MPG10_PMIC_B2M_SOFT_OCP_WARN_X,
+	S2MPG10_PMIC_B2M_SOFT_OCP_WARN_Y,
+	S2MPG10_PMIC_B2M_SOFT_OCP_WARN_Z,
+	S2MPG10_PMIC_B3M_SOFT_OCP_WARN,
+	S2MPG10_PMIC_B3M_SOFT_OCP_WARN_X,
+	S2MPG10_PMIC_B3M_SOFT_OCP_WARN_Y,
+	S2MPG10_PMIC_B3M_SOFT_OCP_WARN_Z,
+	S2MPG10_PMIC_B10M_SOFT_OCP_WARN,
+	S2MPG10_PMIC_B10M_SOFT_OCP_WARN_X,
+	S2MPG10_PMIC_B10M_SOFT_OCP_WARN_Y,
+	S2MPG10_PMIC_B10M_SOFT_OCP_WARN_Z,
+	S2MPG10_PMIC_BUCK_OCP_EN1,
+	S2MPG10_PMIC_BUCK_OCP_EN2,
+	S2MPG10_PMIC_BUCK_OCP_PD_EN1,
+	S2MPG10_PMIC_BUCK_OCP_PD_EN2,
+	S2MPG10_PMIC_BUCK_OCP_CTRL1,
+	S2MPG10_PMIC_BUCK_OCP_CTRL2,
+	S2MPG10_PMIC_BUCK_OCP_CTRL3,
+	S2MPG10_PMIC_BUCK_OCP_CTRL4,
+	S2MPG10_PMIC_BUCK_OCP_CTRL5,
+	S2MPG10_PMIC_PIF_CTRL,
+	S2MPG10_PMIC_BUCK_HR_MODE1,
+	S2MPG10_PMIC_BUCK_HR_MODE2,
+	S2MPG10_PMIC_FAULTOUT_CTRL,
+	S2MPG10_PMIC_LDO_SENSE1,
+	S2MPG10_PMIC_LDO_SENSE2,
+	S2MPG10_PMIC_LDO_SENSE3,
+	S2MPG10_PMIC_LDO_SENSE4,
+};
+
+/* Meter registers (type 0xa00) */
+enum s2mpg10_meter_reg {
+	S2MPG10_METER_CTRL1,
+	S2MPG10_METER_CTRL2,
+	S2MPG10_METER_CTRL3,
+	S2MPG10_METER_CTRL4,
+	S2MPG10_METER_BUCKEN1,
+	S2MPG10_METER_BUCKEN2,
+	S2MPG10_METER_MUXSEL0,
+	S2MPG10_METER_MUXSEL1,
+	S2MPG10_METER_MUXSEL2,
+	S2MPG10_METER_MUXSEL3,
+	S2MPG10_METER_MUXSEL4,
+	S2MPG10_METER_MUXSEL5,
+	S2MPG10_METER_MUXSEL6,
+	S2MPG10_METER_MUXSEL7,
+	S2MPG10_METER_LPF_C0_0,
+	S2MPG10_METER_LPF_C0_1,
+	S2MPG10_METER_LPF_C0_2,
+	S2MPG10_METER_LPF_C0_3,
+	S2MPG10_METER_LPF_C0_4,
+	S2MPG10_METER_LPF_C0_5,
+	S2MPG10_METER_LPF_C0_6,
+	S2MPG10_METER_LPF_C0_7,
+	S2MPG10_METER_PWR_WARN0,
+	S2MPG10_METER_PWR_WARN1,
+	S2MPG10_METER_PWR_WARN2,
+	S2MPG10_METER_PWR_WARN3,
+	S2MPG10_METER_PWR_WARN4,
+	S2MPG10_METER_PWR_WARN5,
+	S2MPG10_METER_PWR_WARN6,
+	S2MPG10_METER_PWR_WARN7,
+	S2MPG10_METER_PWR_HYS1,
+	S2MPG10_METER_PWR_HYS2,
+	S2MPG10_METER_PWR_HYS3,
+	S2MPG10_METER_PWR_HYS4,
+	S2MPG10_METER_ACC_DATA_CH0_1 = 0x40,
+	S2MPG10_METER_ACC_DATA_CH0_2,
+	S2MPG10_METER_ACC_DATA_CH0_3,
+	S2MPG10_METER_ACC_DATA_CH0_4,
+	S2MPG10_METER_ACC_DATA_CH0_5,
+	S2MPG10_METER_ACC_DATA_CH0_6,
+	S2MPG10_METER_ACC_DATA_CH1_1,
+	S2MPG10_METER_ACC_DATA_CH1_2,
+	S2MPG10_METER_ACC_DATA_CH1_3,
+	S2MPG10_METER_ACC_DATA_CH1_4,
+	S2MPG10_METER_ACC_DATA_CH1_5,
+	S2MPG10_METER_ACC_DATA_CH1_6,
+	S2MPG10_METER_ACC_DATA_CH2_1,
+	S2MPG10_METER_ACC_DATA_CH2_2,
+	S2MPG10_METER_ACC_DATA_CH2_3,
+	S2MPG10_METER_ACC_DATA_CH2_4,
+	S2MPG10_METER_ACC_DATA_CH2_5,
+	S2MPG10_METER_ACC_DATA_CH2_6,
+	S2MPG10_METER_ACC_DATA_CH3_1,
+	S2MPG10_METER_ACC_DATA_CH3_2,
+	S2MPG10_METER_ACC_DATA_CH3_3,
+	S2MPG10_METER_ACC_DATA_CH3_4,
+	S2MPG10_METER_ACC_DATA_CH3_5,
+	S2MPG10_METER_ACC_DATA_CH3_6,
+	S2MPG10_METER_ACC_DATA_CH4_1,
+	S2MPG10_METER_ACC_DATA_CH4_2,
+	S2MPG10_METER_ACC_DATA_CH4_3,
+	S2MPG10_METER_ACC_DATA_CH4_4,
+	S2MPG10_METER_ACC_DATA_CH4_5,
+	S2MPG10_METER_ACC_DATA_CH4_6,
+	S2MPG10_METER_ACC_DATA_CH5_1,
+	S2MPG10_METER_ACC_DATA_CH5_2,
+	S2MPG10_METER_ACC_DATA_CH5_3,
+	S2MPG10_METER_ACC_DATA_CH5_4,
+	S2MPG10_METER_ACC_DATA_CH5_5,
+	S2MPG10_METER_ACC_DATA_CH5_6,
+	S2MPG10_METER_ACC_DATA_CH6_1,
+	S2MPG10_METER_ACC_DATA_CH6_2,
+	S2MPG10_METER_ACC_DATA_CH6_3,
+	S2MPG10_METER_ACC_DATA_CH6_4,
+	S2MPG10_METER_ACC_DATA_CH6_5,
+	S2MPG10_METER_ACC_DATA_CH6_6,
+	S2MPG10_METER_ACC_DATA_CH7_1,
+	S2MPG10_METER_ACC_DATA_CH7_2,
+	S2MPG10_METER_ACC_DATA_CH7_3,
+	S2MPG10_METER_ACC_DATA_CH7_4,
+	S2MPG10_METER_ACC_DATA_CH7_5,
+	S2MPG10_METER_ACC_DATA_CH7_6,
+	S2MPG10_METER_ACC_COUNT_1,
+	S2MPG10_METER_ACC_COUNT_2,
+	S2MPG10_METER_ACC_COUNT_3,
+	S2MPG10_METER_LPF_DATA_CH0_1,
+	S2MPG10_METER_LPF_DATA_CH0_2,
+	S2MPG10_METER_LPF_DATA_CH0_3,
+	S2MPG10_METER_LPF_DATA_CH1_1,
+	S2MPG10_METER_LPF_DATA_CH1_2,
+	S2MPG10_METER_LPF_DATA_CH1_3,
+	S2MPG10_METER_LPF_DATA_CH2_1,
+	S2MPG10_METER_LPF_DATA_CH2_2,
+	S2MPG10_METER_LPF_DATA_CH2_3,
+	S2MPG10_METER_LPF_DATA_CH3_1,
+	S2MPG10_METER_LPF_DATA_CH3_2,
+	S2MPG10_METER_LPF_DATA_CH3_3,
+	S2MPG10_METER_LPF_DATA_CH4_1,
+	S2MPG10_METER_LPF_DATA_CH4_2,
+	S2MPG10_METER_LPF_DATA_CH4_3,
+	S2MPG10_METER_LPF_DATA_CH5_1,
+	S2MPG10_METER_LPF_DATA_CH5_2,
+	S2MPG10_METER_LPF_DATA_CH5_3,
+	S2MPG10_METER_LPF_DATA_CH6_1,
+	S2MPG10_METER_LPF_DATA_CH6_2,
+	S2MPG10_METER_LPF_DATA_CH6_3,
+	S2MPG10_METER_LPF_DATA_CH7_1,
+	S2MPG10_METER_LPF_DATA_CH7_2,
+	S2MPG10_METER_LPF_DATA_CH7_3,
+	S2MPG10_METER_DSM_TRIM_OFFSET = 0xee,
+	S2MPG10_METER_BUCK_METER_TRIM3 = 0xf1,
+};
+
+/* S2MPG10 regulator IDs */
+enum s2mpg10_regulators {
+	S2MPG10_LDO1,
+	S2MPG10_LDO2,
+	S2MPG10_LDO3,
+	S2MPG10_LDO4,
+	S2MPG10_LDO5,
+	S2MPG10_LDO6,
+	S2MPG10_LDO7,
+	S2MPG10_LDO8,
+	S2MPG10_LDO9,
+	S2MPG10_LDO10,
+	S2MPG10_LDO11,
+	S2MPG10_LDO12,
+	S2MPG10_LDO13,
+	S2MPG10_LDO14,
+	S2MPG10_LDO15,
+	S2MPG10_LDO16,
+	S2MPG10_LDO17,
+	S2MPG10_LDO18,
+	S2MPG10_LDO19,
+	S2MPG10_LDO20,
+	S2MPG10_LDO21,
+	S2MPG10_LDO22,
+	S2MPG10_LDO23,
+	S2MPG10_LDO24,
+	S2MPG10_LDO25,
+	S2MPG10_LDO26,
+	S2MPG10_LDO27,
+	S2MPG10_LDO28,
+	S2MPG10_LDO29,
+	S2MPG10_LDO30,
+	S2MPG10_LDO31,
+	S2MPG10_BUCK1,
+	S2MPG10_BUCK2,
+	S2MPG10_BUCK3,
+	S2MPG10_BUCK4,
+	S2MPG10_BUCK5,
+	S2MPG10_BUCK6,
+	S2MPG10_BUCK7,
+	S2MPG10_BUCK8,
+	S2MPG10_BUCK9,
+	S2MPG10_BUCK10,
+	S2MPG10_REGULATOR_MAX,
+};
+
+#endif /* __LINUX_MFD_S2MPG10_H */
diff --git a/include/linux/mfd/stm32-lptimer.h b/include/linux/mfd/stm32-lptimer.h
index 06d3f11dc3c9..a592c8dc716d 100644
--- a/include/linux/mfd/stm32-lptimer.h
+++ b/include/linux/mfd/stm32-lptimer.h
@@ -17,20 +17,30 @@
 #define STM32_LPTIM_IER		0x08	/* Interrupt Enable Reg      */
 #define STM32_LPTIM_CFGR	0x0C	/* Configuration Reg         */
 #define STM32_LPTIM_CR		0x10	/* Control Reg               */
-#define STM32_LPTIM_CMP		0x14	/* Compare Reg               */
+#define STM32_LPTIM_CMP		0x14	/* Compare Reg (MP25 CCR1)   */
 #define STM32_LPTIM_ARR		0x18	/* Autoreload Reg            */
 #define STM32_LPTIM_CNT		0x1C	/* Counter Reg               */
+#define STM32_LPTIM_CCMR1	0x2C	/* Capture/Compare Mode MP25 */
+#define STM32_LPTIM_CCR2	0x34	/* Compare Reg2 MP25         */
+
+#define STM32_LPTIM_HWCFGR2	0x3EC	/* Hardware configuration register 2 - MP25 */
+#define STM32_LPTIM_HWCFGR1	0x3F0	/* Hardware configuration register 1 - MP15 */
+#define STM32_LPTIM_VERR	0x3F4	/* Version identification register - MP15 */
 
 /* STM32_LPTIM_ISR - bit fields */
+#define STM32_LPTIM_DIEROK_ARROK	(BIT(24) | BIT(4)) /* MP25 */
+#define STM32_LPTIM_CMP2_ARROK		(BIT(19) | BIT(4))
 #define STM32_LPTIM_CMPOK_ARROK		GENMASK(4, 3)
 #define STM32_LPTIM_ARROK		BIT(4)
 #define STM32_LPTIM_CMPOK		BIT(3)
 
 /* STM32_LPTIM_ICR - bit fields */
-#define STM32_LPTIM_ARRMCF		BIT(1)
+#define STM32_LPTIM_DIEROKCF_ARROKCF	(BIT(24) | BIT(4)) /* MP25 */
+#define STM32_LPTIM_CMP2OKCF_ARROKCF	(BIT(19) | BIT(4))
 #define STM32_LPTIM_CMPOKCF_ARROKCF	GENMASK(4, 3)
+#define STM32_LPTIM_ARRMCF		BIT(1)
 
-/* STM32_LPTIM_IER - bit flieds */
+/* STM32_LPTIM_IER - bit fields */
 #define STM32_LPTIM_ARRMIE	BIT(1)
 
 /* STM32_LPTIM_CR - bit fields */
@@ -53,16 +63,37 @@
 /* STM32_LPTIM_ARR */
 #define STM32_LPTIM_MAX_ARR	0xFFFF
 
+/* STM32_LPTIM_CCMR1 */
+#define STM32_LPTIM_CC2P	GENMASK(19, 18)
+#define STM32_LPTIM_CC2E	BIT(17)
+#define STM32_LPTIM_CC2SEL	BIT(16)
+#define STM32_LPTIM_CC1P	GENMASK(3, 2)
+#define STM32_LPTIM_CC1E	BIT(1)
+#define STM32_LPTIM_CC1SEL	BIT(0)
+
+/* STM32_LPTIM_HWCFGR1 */
+#define STM32_LPTIM_HWCFGR1_ENCODER	BIT(16)
+
+/* STM32_LPTIM_HWCFGR2 */
+#define STM32_LPTIM_HWCFGR2_CHAN_NUM	GENMASK(3, 0)
+
+/* STM32_LPTIM_VERR */
+#define STM32_LPTIM_VERR_23	0x23	/* STM32MP25 */
+
 /**
  * struct stm32_lptimer - STM32 Low-Power Timer data assigned by parent device
  * @clk: clock reference for this instance
  * @regmap: register map reference for this instance
  * @has_encoder: indicates this Low-Power Timer supports encoder mode
+ * @num_cc_chans: indicates the number of capture/compare channels
+ * @version: indicates the major and minor revision of the controller
  */
 struct stm32_lptimer {
 	struct clk *clk;
 	struct regmap *regmap;
 	bool has_encoder;
+	unsigned int num_cc_chans;
+	u32 version;
 };
 
 #endif
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9e221ffcb868..0ef2ba0c667a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1276,9 +1276,9 @@ vm_fault_t finish_fault(struct vm_fault *vmf);
  * the page's disk buffers. PG_private must be set to tell the VM to call
  * into the filesystem to release these pages.
  *
- * A page may belong to an inode's memory mapping. In this case, page->mapping
- * is the pointer to the inode, and page->index is the file offset of the page,
- * in units of PAGE_SIZE.
+ * A folio may belong to an inode's memory mapping. In this case,
+ * folio->mapping points to the inode, and folio->index is the file
+ * offset of the folio, in units of PAGE_SIZE.
  *
  * If pagecache pages are not associated with an inode, they are said to be
  * anonymous pages. These may become associated with the swapcache, and in that
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index d3cffd8828c9..d6b91e8a66d6 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -108,7 +108,7 @@ struct page {
 			/* See page-flags.h for PAGE_MAPPING_FLAGS */
 			struct address_space *mapping;
 			union {
-				pgoff_t index;		/* Our offset within mapping. */
+				pgoff_t __folio_index;		/* Our offset within mapping. */
 				unsigned long share;	/* share count for fsdax */
 			};
 			/**
@@ -489,7 +489,7 @@ FOLIO_MATCH(flags, flags);
 FOLIO_MATCH(lru, lru);
 FOLIO_MATCH(mapping, mapping);
 FOLIO_MATCH(compound_head, lru);
-FOLIO_MATCH(index, index);
+FOLIO_MATCH(__folio_index, index);
 FOLIO_MATCH(private, private);
 FOLIO_MATCH(_mapcount, _mapcount);
 FOLIO_MATCH(_refcount, _refcount);
@@ -590,7 +590,7 @@ TABLE_MATCH(flags, __page_flags);
 TABLE_MATCH(compound_head, pt_list);
 TABLE_MATCH(compound_head, _pt_pad_1);
 TABLE_MATCH(mapping, __page_mapping);
-TABLE_MATCH(index, pt_index);
+TABLE_MATCH(__folio_index, pt_index);
 TABLE_MATCH(rcu_head, pt_rcu_head);
 TABLE_MATCH(page_type, __page_type);
 TABLE_MATCH(_refcount, __page_refcount);
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index bc2402a45741..d1094c2d5fb6 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -654,9 +654,6 @@ static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
 #define pmdp_clear_flush_young_notify pmdp_clear_flush_young
 #define ptep_clear_young_notify ptep_test_and_clear_young
 #define pmdp_clear_young_notify pmdp_test_and_clear_young
-#define	ptep_clear_flush_notify ptep_clear_flush
-#define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush
-#define pudp_huge_clear_flush_notify pudp_huge_clear_flush
 
 static inline void mmu_notifier_synchronize(void)
 {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 28066b4ced81..283913d42d7b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -37,6 +37,22 @@
 
 #define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1)
 
+/* Defines the order for the number of pages that have a migrate type. */
+#ifndef CONFIG_PAGE_BLOCK_ORDER
+#define PAGE_BLOCK_ORDER MAX_PAGE_ORDER
+#else
+#define PAGE_BLOCK_ORDER CONFIG_PAGE_BLOCK_ORDER
+#endif /* CONFIG_PAGE_BLOCK_ORDER */
+
+/*
+ * The MAX_PAGE_ORDER, which defines the max order of pages to be allocated
+ * by the buddy allocator, has to be larger or equal to the PAGE_BLOCK_ORDER,
+ * which defines the order for the number of pages that can have a migrate type
+ */
+#if (PAGE_BLOCK_ORDER > MAX_PAGE_ORDER)
+#error MAX_PAGE_ORDER must be >= PAGE_BLOCK_ORDER
+#endif
+
 /*
  * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed
  * costly to service.  That is between allocation orders which should
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index d8cad844870a..e947af6a3684 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -72,6 +72,7 @@ struct nfs4_stateid_struct {
 		NFS4_LAYOUT_STATEID_TYPE,
 		NFS4_PNFS_DS_STATEID_TYPE,
 		NFS4_REVOKED_STATEID_TYPE,
+		NFS4_FREED_STATEID_TYPE,
 	} type;
 };
 
@@ -678,6 +679,7 @@ enum {
 	NFSPROC4_CLNT_SEEK,
 	NFSPROC4_CLNT_ALLOCATE,
 	NFSPROC4_CLNT_DEALLOCATE,
+	NFSPROC4_CLNT_ZERO_RANGE,
 	NFSPROC4_CLNT_LAYOUTSTATS,
 	NFSPROC4_CLNT_CLONE,
 	NFSPROC4_CLNT_COPY,
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index ee03f3cef30c..63141320c2a8 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -125,6 +125,7 @@ struct nfs_client {
 	 */
 	char			cl_ipaddr[48];
 	struct net		*cl_net;
+	netns_tracker		cl_ns_tracker;
 	struct list_head	pending_cb_stateids;
 	struct rcu_head		rcu;
 
@@ -303,6 +304,7 @@ struct nfs_server {
 #define NFS_CAP_CASE_PRESERVING	(1U << 7)
 #define NFS_CAP_REBOOT_LAYOUTRETURN	(1U << 8)
 #define NFS_CAP_OFFLOAD_STATUS	(1U << 9)
+#define NFS_CAP_ZERO_RANGE	(1U << 10)
 #define NFS_CAP_OPEN_XOR	(1U << 12)
 #define NFS_CAP_DELEGTIME	(1U << 13)
 #define NFS_CAP_POSIX_LOCK	(1U << 14)
diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
index 9aa8a43843d7..5c7c92659e73 100644
--- a/include/linux/nfslocalio.h
+++ b/include/linux/nfslocalio.h
@@ -50,10 +50,6 @@ void nfs_localio_invalidate_clients(struct list_head *nn_local_clients,
 				    spinlock_t *nn_local_clients_lock);
 
 /* localio needs to map filehandle -> struct nfsd_file */
-extern struct nfsd_file *
-nfsd_open_local_fh(struct net *, struct auth_domain *, struct rpc_clnt *,
-		   const struct cred *, const struct nfs_fh *,
-		   const fmode_t) __must_hold(rcu);
 void nfs_close_local_fh(struct nfs_file_localio *);
 
 struct nfsd_localio_operations {
@@ -64,10 +60,10 @@ struct nfsd_localio_operations {
 						struct rpc_clnt *,
 						const struct cred *,
 						const struct nfs_fh *,
+						struct nfsd_file __rcu **pnf,
 						const fmode_t);
-	struct net *(*nfsd_file_put_local)(struct nfsd_file *);
-	struct nfsd_file *(*nfsd_file_get)(struct nfsd_file *);
-	void (*nfsd_file_put)(struct nfsd_file *);
+	struct net *(*nfsd_file_put_local)(struct nfsd_file __rcu **);
+	struct nfsd_file *(*nfsd_file_get_local)(struct nfsd_file *);
 	struct file *(*nfsd_file_file)(struct nfsd_file *);
 } ____cacheline_aligned;
 
@@ -77,6 +73,7 @@ extern const struct nfsd_localio_operations *nfs_to;
 struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *,
 		   struct rpc_clnt *, const struct cred *,
 		   const struct nfs_fh *, struct nfs_file_localio *,
+		   struct nfsd_file __rcu **pnf,
 		   const fmode_t);
 
 static inline void nfs_to_nfsd_net_put(struct net *net)
@@ -91,16 +88,19 @@ static inline void nfs_to_nfsd_net_put(struct net *net)
 	rcu_read_unlock();
 }
 
-static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio)
+static inline void nfs_to_nfsd_file_put_local(struct nfsd_file __rcu **localio)
 {
 	/*
-	 * Must not hold RCU otherwise nfsd_file_put() can easily trigger:
-	 * "Voluntary context switch within RCU read-side critical section!"
-	 * by scheduling deep in underlying filesystem (e.g. XFS).
+	 * Either *localio must be guaranteed to be non-NULL, or caller
+	 * must prevent nfsd shutdown from completing as nfs_close_local_fh()
+	 * does by blocking the nfs_uuid from being finally put.
 	 */
-	struct net *net = nfs_to->nfsd_file_put_local(localio);
+	struct net *net;
 
-	nfs_to_nfsd_net_put(net);
+	net = nfs_to->nfsd_file_put_local(localio);
+
+	if (net)
+		nfs_to_nfsd_net_put(net);
 }
 
 #else   /* CONFIG_NFS_LOCALIO */
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index f0ac0633366b..f08ae71585fa 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -39,9 +39,6 @@
  * int nodes_full(mask)			Is mask full (all bits sets)?
  * int nodes_weight(mask)		Hamming weight - number of set bits
  *
- * void nodes_shift_right(dst, src, n)	Shift right
- * void nodes_shift_left(dst, src, n)	Shift left
- *
  * unsigned int first_node(mask)	Number lowest set bit, or MAX_NUMNODES
  * unsigend int next_node(node, mask)	Next node past 'node', or MAX_NUMNODES
  * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first,
@@ -247,22 +244,6 @@ static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int n
 	return bitmap_weight(srcp->bits, nbits);
 }
 
-#define nodes_shift_right(dst, src, n) \
-			__nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES)
-static __always_inline void __nodes_shift_right(nodemask_t *dstp,
-					const nodemask_t *srcp, int n, int nbits)
-{
-	bitmap_shift_right(dstp->bits, srcp->bits, n, nbits);
-}
-
-#define nodes_shift_left(dst, src, n) \
-			__nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES)
-static __always_inline void __nodes_shift_left(nodemask_t *dstp,
-					const nodemask_t *srcp, int n, int nbits)
-{
-	bitmap_shift_left(dstp->bits, srcp->bits, n, nbits);
-}
-
 /* FIXME: better would be to fix all architectures to never return
           > MAX_NUMNODES, then the silly min_ts could be dropped. */
 
@@ -541,6 +522,7 @@ static __always_inline int node_random(const nodemask_t *maskp)
 
 #define for_each_node(node)	   for_each_node_state(node, N_POSSIBLE)
 #define for_each_online_node(node) for_each_node_state(node, N_ONLINE)
+#define for_each_node_with_cpus(node)	for_each_node_state(node, N_CPU)
 
 /*
  * For nodemask scratch area.
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index fc6b9c87cb0a..e73a4292ef02 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -41,18 +41,18 @@ extern unsigned int pageblock_order;
  * Huge pages are a constant size, but don't exceed the maximum allocation
  * granularity.
  */
-#define pageblock_order		MIN_T(unsigned int, HUGETLB_PAGE_ORDER, MAX_PAGE_ORDER)
+#define pageblock_order		MIN_T(unsigned int, HUGETLB_PAGE_ORDER, PAGE_BLOCK_ORDER)
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
 #elif defined(CONFIG_TRANSPARENT_HUGEPAGE)
 
-#define pageblock_order		MIN_T(unsigned int, HPAGE_PMD_ORDER, MAX_PAGE_ORDER)
+#define pageblock_order		MIN_T(unsigned int, HPAGE_PMD_ORDER, PAGE_BLOCK_ORDER)
 
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-/* If huge pages are not used, group by MAX_ORDER_NR_PAGES */
-#define pageblock_order		MAX_PAGE_ORDER
+/* If huge pages are not used, group by PAGE_BLOCK_ORDER */
+#define pageblock_order		PAGE_BLOCK_ORDER
 
 #endif /* CONFIG_HUGETLB_PAGE */
 
diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h
index 3a10f8cfc3ad..d930651473b4 100644
--- a/include/linux/pci-ecam.h
+++ b/include/linux/pci-ecam.h
@@ -93,10 +93,4 @@ extern const struct pci_ecam_ops al_pcie_ops;	/* Amazon Annapurna Labs PCIe */
 extern const struct pci_ecam_ops tegra194_pcie_ops; /* Tegra194 PCIe */
 extern const struct pci_ecam_ops loongson_pci_ecam_ops; /* Loongson PCIe */
 #endif
-
-#if IS_ENABLED(CONFIG_PCI_HOST_COMMON)
-/* for DT-based PCI controllers that support ECAM */
-int pci_host_common_probe(struct platform_device *pdev);
-void pci_host_common_remove(struct platform_device *pdev);
-#endif
 #endif
diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h
index 82837008b56f..4286bfdbfdfa 100644
--- a/include/linux/pci-epc.h
+++ b/include/linux/pci-epc.h
@@ -100,10 +100,10 @@ struct pci_epc_ops {
 	void	(*unmap_addr)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			      phys_addr_t addr);
 	int	(*set_msi)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-			   u8 interrupts);
+			   u8 nr_irqs);
 	int	(*get_msi)(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
 	int	(*set_msix)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-			    u16 interrupts, enum pci_barno, u32 offset);
+			    u16 nr_irqs, enum pci_barno, u32 offset);
 	int	(*get_msix)(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
 	int	(*raise_irq)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			     unsigned int type, u16 interrupt_num);
@@ -286,11 +286,10 @@ int pci_epc_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 		     u64 pci_addr, size_t size);
 void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			phys_addr_t phys_addr);
-int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-		    u8 interrupts);
+int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u8 nr_irqs);
 int pci_epc_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
-int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-		     u16 interrupts, enum pci_barno, u32 offset);
+int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u16 nr_irqs,
+		     enum pci_barno, u32 offset);
 int pci_epc_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
 int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			phys_addr_t phys_addr, u8 interrupt_num,
diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h
index 879d19cebd4f..749cee0bcf2c 100644
--- a/include/linux/pci-epf.h
+++ b/include/linux/pci-epf.h
@@ -114,6 +114,8 @@ struct pci_epf_driver {
  * @phys_addr: physical address that should be mapped to the BAR
  * @addr: virtual address corresponding to the @phys_addr
  * @size: the size of the address space present in BAR
+ * @aligned_size: the size actually allocated to accommodate the iATU alignment
+ *                requirement
  * @barno: BAR number
  * @flags: flags that are set for the BAR
  */
@@ -121,6 +123,7 @@ struct pci_epf_bar {
 	dma_addr_t	phys_addr;
 	void		*addr;
 	size_t		size;
+	size_t		aligned_size;
 	enum pci_barno	barno;
 	int		flags;
 };
diff --git a/include/linux/pci.h b/include/linux/pci.h
index b231cbc67a35..05e68f35f392 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -348,7 +348,7 @@ struct pci_dev {
 	u8		hdr_type;	/* PCI header type (`multi' flag masked out) */
 #ifdef CONFIG_PCIEAER
 	u16		aer_cap;	/* AER capability offset */
-	struct aer_stats *aer_stats;	/* AER stats for this device */
+	struct aer_info	*aer_info;	/* AER info for this device */
 #endif
 #ifdef CONFIG_PCIEPORTBUS
 	struct rcec_ea	*rcec_ea;	/* RCEC cached endpoint association */
@@ -425,8 +425,6 @@ struct pci_dev {
 	struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */
 	struct resource driver_exclusive_resource;	 /* driver exclusive resource ranges */
 
-	bool		match_driver;		/* Skip attaching driver */
-
 	unsigned int	transparent:1;		/* Subtractive decode bridge */
 	unsigned int	io_window:1;		/* Bridge has I/O window */
 	unsigned int	pref_window:1;		/* Bridge has pref mem window */
@@ -1141,9 +1139,6 @@ resource_size_t pcibios_align_resource(void *, const struct resource *,
 				resource_size_t,
 				resource_size_t);
 
-/* Weak but can be overridden by arch */
-void pci_fixup_cardbus(struct pci_bus *);
-
 /* Generic PCI functions used internally */
 
 void pcibios_resource_to_bus(struct pci_bus *bus, struct pci_bus_region *region,
@@ -1850,6 +1845,14 @@ static inline bool pcie_aspm_support_enabled(void) { return false; }
 static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; }
 #endif
 
+#ifdef CONFIG_HOTPLUG_PCI
+void pci_hp_ignore_link_change(struct pci_dev *pdev);
+void pci_hp_unignore_link_change(struct pci_dev *pdev);
+#else
+static inline void pci_hp_ignore_link_change(struct pci_dev *pdev) { }
+static inline void pci_hp_unignore_link_change(struct pci_dev *pdev) { }
+#endif
+
 #ifdef CONFIG_PCIEAER
 bool pci_aer_available(void);
 #else
@@ -1858,6 +1861,39 @@ static inline bool pci_aer_available(void) { return false; }
 
 bool pci_ats_disabled(void);
 
+#define PCIE_PTM_CONTEXT_UPDATE_AUTO 0
+#define PCIE_PTM_CONTEXT_UPDATE_MANUAL 1
+
+struct pcie_ptm_ops {
+	int (*check_capability)(void *drvdata);
+	int (*context_update_write)(void *drvdata, u8 mode);
+	int (*context_update_read)(void *drvdata, u8 *mode);
+	int (*context_valid_write)(void *drvdata, bool valid);
+	int (*context_valid_read)(void *drvdata, bool *valid);
+	int (*local_clock_read)(void *drvdata, u64 *clock);
+	int (*master_clock_read)(void *drvdata, u64 *clock);
+	int (*t1_read)(void *drvdata, u64 *clock);
+	int (*t2_read)(void *drvdata, u64 *clock);
+	int (*t3_read)(void *drvdata, u64 *clock);
+	int (*t4_read)(void *drvdata, u64 *clock);
+
+	bool (*context_update_visible)(void *drvdata);
+	bool (*context_valid_visible)(void *drvdata);
+	bool (*local_clock_visible)(void *drvdata);
+	bool (*master_clock_visible)(void *drvdata);
+	bool (*t1_visible)(void *drvdata);
+	bool (*t2_visible)(void *drvdata);
+	bool (*t3_visible)(void *drvdata);
+	bool (*t4_visible)(void *drvdata);
+};
+
+struct pci_ptm_debugfs {
+	struct dentry *debugfs;
+	const struct pcie_ptm_ops *ops;
+	struct mutex lock;
+	void *pdata;
+};
+
 #ifdef CONFIG_PCIE_PTM
 int pci_enable_ptm(struct pci_dev *dev, u8 *granularity);
 void pci_disable_ptm(struct pci_dev *dev);
@@ -1870,6 +1906,18 @@ static inline bool pcie_ptm_enabled(struct pci_dev *dev)
 { return false; }
 #endif
 
+#if IS_ENABLED(CONFIG_DEBUG_FS) && IS_ENABLED(CONFIG_PCIE_PTM)
+struct pci_ptm_debugfs *pcie_ptm_create_debugfs(struct device *dev, void *pdata,
+						const struct pcie_ptm_ops *ops);
+void pcie_ptm_destroy_debugfs(struct pci_ptm_debugfs *ptm_debugfs);
+#else
+static inline struct pci_ptm_debugfs
+*pcie_ptm_create_debugfs(struct device *dev, void *pdata,
+			 const struct pcie_ptm_ops *ops) { return NULL; }
+static inline void
+pcie_ptm_destroy_debugfs(struct pci_ptm_debugfs *ptm_debugfs) { }
+#endif
+
 void pci_cfg_access_lock(struct pci_dev *dev);
 bool pci_cfg_access_trylock(struct pci_dev *dev);
 void pci_cfg_access_unlock(struct pci_dev *dev);
@@ -2324,7 +2372,6 @@ void pcim_iounmap(struct pci_dev *pdev, void __iomem *addr);
 void __iomem * const *pcim_iomap_table(struct pci_dev *pdev);
 int pcim_request_region(struct pci_dev *pdev, int bar, const char *name);
 int pcim_iomap_regions(struct pci_dev *pdev, int mask, const char *name);
-void pcim_iounmap_regions(struct pci_dev *pdev, int mask);
 void __iomem *pcim_iomap_range(struct pci_dev *pdev, int bar,
 				unsigned long offset, unsigned long len);
 
@@ -2696,9 +2743,6 @@ void pci_uevent_ers(struct pci_dev *pdev, enum  pci_ers_result err_type);
 
 #include <linux/dma-mapping.h>
 
-#define pci_printk(level, pdev, fmt, arg...) \
-	dev_printk(level, &(pdev)->dev, fmt, ##arg)
-
 #define pci_emerg(pdev, fmt, arg...)	dev_emerg(&(pdev)->dev, fmt, ##arg)
 #define pci_alert(pdev, fmt, arg...)	dev_alert(&(pdev)->dev, fmt, ##arg)
 #define pci_crit(pdev, fmt, arg...)	dev_crit(&(pdev)->dev, fmt, ##arg)
diff --git a/include/linux/phy/phy-hdmi.h b/include/linux/phy/phy-hdmi.h
new file mode 100644
index 000000000000..f0ec963c6e84
--- /dev/null
+++ b/include/linux/phy/phy-hdmi.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2022,2024 NXP
+ */
+
+#ifndef __PHY_HDMI_H_
+#define __PHY_HDMI_H_
+
+/**
+ * struct phy_configure_opts_hdmi - HDMI configuration set
+ * @tmds_char_rate: HDMI TMDS Character Rate in Hertz.
+ * @bpc: Bits per color channel.
+ *
+ * This structure is used to represent the configuration state of a HDMI phy.
+ */
+struct phy_configure_opts_hdmi {
+	unsigned long long tmds_char_rate;
+	unsigned int bpc;
+};
+
+#endif /* __PHY_HDMI_H_ */
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index e63e6e70e860..437769e061b7 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -17,6 +17,7 @@
 #include <linux/regulator/consumer.h>
 
 #include <linux/phy/phy-dp.h>
+#include <linux/phy/phy-hdmi.h>
 #include <linux/phy/phy-lvds.h>
 #include <linux/phy/phy-mipi-dphy.h>
 
@@ -42,7 +43,8 @@ enum phy_mode {
 	PHY_MODE_MIPI_DPHY,
 	PHY_MODE_SATA,
 	PHY_MODE_LVDS,
-	PHY_MODE_DP
+	PHY_MODE_DP,
+	PHY_MODE_HDMI,
 };
 
 enum phy_media {
@@ -60,11 +62,14 @@ enum phy_media {
  *		the DisplayPort protocol.
  * @lvds:	Configuration set applicable for phys supporting
  *		the LVDS phy mode.
+ * @hdmi:	Configuration set applicable for phys supporting
+ *		the HDMI phy mode.
  */
 union phy_configure_opts {
 	struct phy_configure_opts_mipi_dphy	mipi_dphy;
 	struct phy_configure_opts_dp		dp;
 	struct phy_configure_opts_lvds		lvds;
+	struct phy_configure_opts_hdmi		hdmi;
 };
 
 /**
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 756b842dcd30..e7cb70fcc0af 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -470,6 +470,8 @@ static inline int pm_runtime_put(struct device *dev)
 	return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC);
 }
 
+DEFINE_FREE(pm_runtime_put, struct device *, if (_T) pm_runtime_put(_T))
+
 /**
  * __pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0.
  * @dev: Target device.
diff --git a/include/linux/property.h b/include/linux/property.h
index e214ecd241eb..bc5bfc98176b 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -208,7 +208,12 @@ DEFINE_FREE(fwnode_handle, struct fwnode_handle *, fwnode_handle_put(_T))
 int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index);
 int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name);
 
-unsigned int device_get_child_node_count(const struct device *dev);
+unsigned int fwnode_get_child_node_count(const struct fwnode_handle *fwnode);
+
+static inline unsigned int device_get_child_node_count(const struct device *dev)
+{
+	return fwnode_get_child_node_count(dev_fwnode(dev));
+}
 
 static inline int device_property_read_u8(const struct device *dev,
 					  const char *propname, u8 *val)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index aa9c5be7a632..4f78a64beb52 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -548,6 +548,10 @@ struct sched_statistics {
 	u64				nr_failed_migrations_running;
 	u64				nr_failed_migrations_hot;
 	u64				nr_forced_migrations;
+#ifdef CONFIG_NUMA_BALANCING
+	u64				numa_task_migrated;
+	u64				numa_task_swapped;
+#endif
 
 	u64				nr_wakeups;
 	u64				nr_wakeups_sync;
diff --git a/include/linux/sm501.h b/include/linux/sm501.h
index 2f3488b2875d..bcda27a46e7a 100644
--- a/include/linux/sm501.h
+++ b/include/linux/sm501.h
@@ -12,9 +12,6 @@ extern int sm501_unit_power(struct device *dev,
 extern unsigned long sm501_set_clock(struct device *dev,
 				     int clksrc, unsigned long freq);
 
-extern unsigned long sm501_find_clock(struct device *dev,
-				      int clksrc, unsigned long req_freq);
-
 /* sm501_misc_control
  *
  * Modify the SM501's MISC_CONTROL register
diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h
index 0d5a17ea8fb8..1a2c0e0838f9 100644
--- a/include/linux/soc/samsung/exynos-regs-pmu.h
+++ b/include/linux/soc/samsung/exynos-regs-pmu.h
@@ -55,6 +55,8 @@
 #define EXYNOS4_MIPI_PHY_SRESETN		(1 << 1)
 #define EXYNOS4_MIPI_PHY_MRESETN		(1 << 2)
 #define EXYNOS4_MIPI_PHY_RESET_MASK		(3 << 1)
+/* USB PHY enable bit, valid for Exynos7870 */
+#define EXYNOS7870_USB2PHY_ENABLE		(1 << 1)
 
 #define S5P_INFORM0				0x0800
 #define S5P_INFORM1				0x0804
@@ -185,6 +187,9 @@
 /* Only for S5Pv210 */
 #define S5PV210_EINT_WAKEUP_MASK	0xC004
 
+/* Only for Exynos2200 */
+#define EXYNOS2200_PHY_CTRL_USB20	0x72C
+
 /* Only for Exynos4210 */
 #define S5P_CMU_CLKSTOP_LCD1_LOWPWR	0x1154
 #define S5P_CMU_RESET_LCD1_LOWPWR	0x1174
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 2362f621d94c..0832776262ac 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -8,6 +8,7 @@
 #include <linux/bug.h>
 #include <linux/completion.h>
 #include <linux/device.h>
+#include <linux/idr.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/lockdep_types.h>
@@ -50,6 +51,7 @@ struct sdw_slave;
 
 #define SDW_FRAME_CTRL_BITS		48
 #define SDW_MAX_DEVICES			11
+#define SDW_FW_MAX_DEVICES		16
 
 #define SDW_MAX_PORTS			15
 #define SDW_VALID_PORT_RANGE(n)		((n) < SDW_MAX_PORTS && (n) >= 1)
@@ -630,6 +632,7 @@ struct sdw_slave_ops {
  * struct sdw_slave - SoundWire Slave
  * @id: MIPI device ID
  * @dev: Linux device
+ * @index: internal ID for this slave
  * @irq: IRQ number
  * @status: Status reported by the Slave
  * @bus: Bus handle
@@ -661,6 +664,7 @@ struct sdw_slave_ops {
 struct sdw_slave {
 	struct sdw_slave_id id;
 	struct device dev;
+	int index;
 	int irq;
 	enum sdw_slave_status status;
 	struct sdw_bus *bus;
@@ -968,6 +972,7 @@ struct sdw_stream_runtime {
  * @md: Master device
  * @bus_lock_key: bus lock key associated to @bus_lock
  * @bus_lock: bus lock
+ * @slave_ida: IDA for allocating internal slave IDs
  * @slaves: list of Slaves on this bus
  * @msg_lock_key: message lock key associated to @msg_lock
  * @msg_lock: message lock
@@ -1010,6 +1015,7 @@ struct sdw_bus {
 	struct sdw_master_device *md;
 	struct lock_class_key bus_lock_key;
 	struct mutex bus_lock;
+	struct ida slave_ida;
 	struct list_head slaves;
 	struct lock_class_key msg_lock_key;
 	struct mutex msg_lock;
diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h
index dc6ebaee3d18..9c9435009537 100644
--- a/include/linux/soundwire/sdw_intel.h
+++ b/include/linux/soundwire/sdw_intel.h
@@ -189,6 +189,9 @@
 #define SDW_SHIM3_INTEL_VS_ACTMCTL_DOAISE2	BIT(14)
 #define SDW_SHIM3_INTEL_VS_ACTMCTL_CLDE		BIT(15)
 
+/* ACE3+ Mic privacy control and status register */
+#define SDW_SHIM2_INTEL_VS_PVCCS		0x10
+
 /**
  * struct sdw_intel_stream_params_data: configuration passed during
  * the @params_stream callback, e.g. for interaction with DSP
@@ -331,6 +334,7 @@ struct sdw_intel_ctx {
  * @shim_base: sdw shim base.
  * @alh_base: sdw alh base.
  * @ext: extended HDaudio link support
+ * @mic_privacy: ACE version supports microphone privacy
  * @hbus: hdac_bus pointer, needed for power management
  * @eml_lock: mutex protecting shared registers in the HDaudio multi-link
  * space
@@ -349,6 +353,7 @@ struct sdw_intel_res {
 	u32 shim_base;
 	u32 alh_base;
 	bool ext;
+	bool mic_privacy;
 	struct hdac_bus *hbus;
 	struct mutex *eml_lock;
 };
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 81b952649d35..f46d1fb8f71a 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -30,6 +30,8 @@
 #define RPC_MAXCWND(xprt)	((xprt)->max_reqs << RPC_CWNDSHIFT)
 #define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd)
 
+#define RPC_GSS_SEQNO_ARRAY_SIZE 3U
+
 enum rpc_display_format_t {
 	RPC_DISPLAY_ADDR = 0,
 	RPC_DISPLAY_PORT,
@@ -66,7 +68,8 @@ struct rpc_rqst {
 	struct rpc_cred *	rq_cred;	/* Bound cred */
 	__be32			rq_xid;		/* request XID */
 	int			rq_cong;	/* has incremented xprt->cong */
-	u32			rq_seqno;	/* gss seq no. used on req. */
+	u32			rq_seqnos[RPC_GSS_SEQNO_ARRAY_SIZE];	/* past gss req seq nos. */
+	unsigned int		rq_seqno_count;	/* number of entries in rq_seqnos */
 	int			rq_enc_pages_num;
 	struct page		**rq_enc_pages;	/* scratch pages for use by
 						   gss privacy code */
@@ -119,6 +122,18 @@ struct rpc_rqst {
 #define rq_svec			rq_snd_buf.head
 #define rq_slen			rq_snd_buf.len
 
+static inline int xprt_rqst_add_seqno(struct rpc_rqst *req, u32 seqno)
+{
+	if (likely(req->rq_seqno_count < RPC_GSS_SEQNO_ARRAY_SIZE))
+		req->rq_seqno_count++;
+
+	/* Shift array to make room for the newest element at the beginning */
+	memmove(&req->rq_seqnos[1], &req->rq_seqnos[0],
+		(RPC_GSS_SEQNO_ARRAY_SIZE - 1) * sizeof(req->rq_seqnos[0]));
+	req->rq_seqnos[0] = seqno;
+	return 0;
+}
+
 /* RPC transport layer security policies */
 enum xprtsec_policies {
 	RPC_XPRTSEC_NONE = 0,
diff --git a/include/linux/topology.h b/include/linux/topology.h
index cd6b4bdc9cfd..33b7fda97d39 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -29,6 +29,7 @@
 
 #include <linux/arch_topology.h>
 #include <linux/cpumask.h>
+#include <linux/nodemask.h>
 #include <linux/bitops.h>
 #include <linux/mmzone.h>
 #include <linux/smp.h>
@@ -39,10 +40,6 @@
 #define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node))
 #endif
 
-#define for_each_node_with_cpus(node)			\
-	for_each_online_node(node)			\
-		if (nr_cpus_node(node))
-
 int arch_update_cpu_topology(void);
 
 /* Conform to ACPI 2.0 SLIT distance definitions */
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 393d0622cc28..2e86c653186c 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -182,8 +182,6 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
 	return ret;
 }
 
-size_t copy_page_from_iter_atomic(struct page *page, size_t offset,
-				  size_t bytes, struct iov_iter *i);
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
 void iov_iter_revert(struct iov_iter *i, size_t bytes);
 size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes);
@@ -193,6 +191,8 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
 size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
+size_t copy_folio_from_iter_atomic(struct folio *folio, size_t offset,
+		size_t bytes, struct iov_iter *i);
 
 size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
@@ -210,12 +210,6 @@ static inline size_t copy_folio_from_iter(struct folio *folio, size_t offset,
 	return copy_page_from_iter(&folio->page, offset, bytes, i);
 }
 
-static inline size_t copy_folio_from_iter_atomic(struct folio *folio,
-		size_t offset, size_t bytes, struct iov_iter *i)
-{
-	return copy_page_from_iter_atomic(&folio->page, offset, bytes, i);
-}
-
 size_t copy_page_to_iter_nofault(struct page *page, unsigned offset,
 				 size_t bytes, struct iov_iter *i);
 
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 9e15a088ba38..91a3ce9a2687 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -66,6 +66,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		NUMA_HINT_FAULTS,
 		NUMA_HINT_FAULTS_LOCAL,
 		NUMA_PAGE_MIGRATE,
+		NUMA_TASK_MIGRATE,
+		NUMA_TASK_SWAP,
 #endif
 #ifdef CONFIG_MIGRATION
 		PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
diff --git a/include/net/checksum.h b/include/net/checksum.h
index e57986b173f8..3cbab35de5ab 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -152,7 +152,7 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
 			       const __be32 *from, const __be32 *to,
 			       bool pseudohdr);
 void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb,
-				     __wsum diff, bool pseudohdr);
+				     __wsum diff, bool pseudohdr, bool ipv6);
 
 static __always_inline
 void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb,
diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
index 86fe6aecff1e..76b56f78abb0 100644
--- a/include/trace/events/fs_dax.h
+++ b/include/trace/events/fs_dax.h
@@ -102,54 +102,6 @@ DEFINE_EVENT(dax_pmd_load_hole_class, name, \
 DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole);
 DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole_fallback);
 
-DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
-	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
-		long length, pfn_t pfn, void *radix_entry),
-	TP_ARGS(inode, vmf, length, pfn, radix_entry),
-	TP_STRUCT__entry(
-		__field(unsigned long, ino)
-		__field(unsigned long, vm_flags)
-		__field(unsigned long, address)
-		__field(long, length)
-		__field(u64, pfn_val)
-		__field(void *, radix_entry)
-		__field(dev_t, dev)
-		__field(int, write)
-	),
-	TP_fast_assign(
-		__entry->dev = inode->i_sb->s_dev;
-		__entry->ino = inode->i_ino;
-		__entry->vm_flags = vmf->vma->vm_flags;
-		__entry->address = vmf->address;
-		__entry->write = vmf->flags & FAULT_FLAG_WRITE;
-		__entry->length = length;
-		__entry->pfn_val = pfn.val;
-		__entry->radix_entry = radix_entry;
-	),
-	TP_printk("dev %d:%d ino %#lx %s %s address %#lx length %#lx "
-			"pfn %#llx %s radix_entry %#lx",
-		MAJOR(__entry->dev),
-		MINOR(__entry->dev),
-		__entry->ino,
-		__entry->vm_flags & VM_SHARED ? "shared" : "private",
-		__entry->write ? "write" : "read",
-		__entry->address,
-		__entry->length,
-		__entry->pfn_val & ~PFN_FLAGS_MASK,
-		__print_flags_u64(__entry->pfn_val & PFN_FLAGS_MASK, "|",
-			PFN_FLAGS_TRACE),
-		(unsigned long)__entry->radix_entry
-	)
-)
-
-#define DEFINE_PMD_INSERT_MAPPING_EVENT(name) \
-DEFINE_EVENT(dax_pmd_insert_mapping_class, name, \
-	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
-		long length, pfn_t pfn, void *radix_entry), \
-	TP_ARGS(inode, vmf, length, pfn, radix_entry))
-
-DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping);
-
 DECLARE_EVENT_CLASS(dax_pte_fault_class,
 	TP_PROTO(struct inode *inode, struct vm_fault *vmf, int result),
 	TP_ARGS(inode, vmf, result),
@@ -194,36 +146,6 @@ DEFINE_PTE_FAULT_EVENT(dax_load_hole);
 DEFINE_PTE_FAULT_EVENT(dax_insert_pfn_mkwrite_no_entry);
 DEFINE_PTE_FAULT_EVENT(dax_insert_pfn_mkwrite);
 
-TRACE_EVENT(dax_insert_mapping,
-	TP_PROTO(struct inode *inode, struct vm_fault *vmf, void *radix_entry),
-	TP_ARGS(inode, vmf, radix_entry),
-	TP_STRUCT__entry(
-		__field(unsigned long, ino)
-		__field(unsigned long, vm_flags)
-		__field(unsigned long, address)
-		__field(void *, radix_entry)
-		__field(dev_t, dev)
-		__field(int, write)
-	),
-	TP_fast_assign(
-		__entry->dev = inode->i_sb->s_dev;
-		__entry->ino = inode->i_ino;
-		__entry->vm_flags = vmf->vma->vm_flags;
-		__entry->address = vmf->address;
-		__entry->write = vmf->flags & FAULT_FLAG_WRITE;
-		__entry->radix_entry = radix_entry;
-	),
-	TP_printk("dev %d:%d ino %#lx %s %s address %#lx radix_entry %#lx",
-		MAJOR(__entry->dev),
-		MINOR(__entry->dev),
-		__entry->ino,
-		__entry->vm_flags & VM_SHARED ? "shared" : "private",
-		__entry->write ? "write" : "read",
-		__entry->address,
-		(unsigned long)__entry->radix_entry
-	)
-)
-
 DECLARE_EVENT_CLASS(dax_writeback_range_class,
 	TP_PROTO(struct inode *inode, pgoff_t start_index, pgoff_t end_index),
 	TP_ARGS(inode, start_index, end_index),
diff --git a/include/trace/events/irq_matrix.h b/include/trace/events/irq_matrix.h
index 267d4cbbf360..93244078b4e6 100644
--- a/include/trace/events/irq_matrix.h
+++ b/include/trace/events/irq_matrix.h
@@ -138,14 +138,6 @@ DEFINE_EVENT(irq_matrix_global_update, irq_matrix_assign_system,
 	TP_ARGS(bit, matrix)
 );
 
-DEFINE_EVENT(irq_matrix_cpu, irq_matrix_alloc_reserved,
-
-	TP_PROTO(int bit, unsigned int cpu,
-		 struct irq_matrix *matrix, struct cpumap *cmap),
-
-	TP_ARGS(bit, cpu, matrix, cmap)
-);
-
 DEFINE_EVENT(irq_matrix_cpu, irq_matrix_reserve_managed,
 
 	TP_PROTO(int bit, unsigned int cpu,
diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h
index b0b6300a0cab..8aeae06cf434 100644
--- a/include/trace/events/rpcgss.h
+++ b/include/trace/events/rpcgss.h
@@ -409,7 +409,7 @@ TRACE_EVENT(rpcgss_seqno,
 		__entry->task_id = task->tk_pid;
 		__entry->client_id = task->tk_client->cl_clid;
 		__entry->xid = be32_to_cpu(rqst->rq_xid);
-		__entry->seqno = rqst->rq_seqno;
+		__entry->seqno = *rqst->rq_seqnos;
 	),
 
 	TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x seqno=%u",
@@ -440,7 +440,7 @@ TRACE_EVENT(rpcgss_need_reencode,
 		__entry->client_id = task->tk_client->cl_clid;
 		__entry->xid = be32_to_cpu(task->tk_rqstp->rq_xid);
 		__entry->seq_xmit = seq_xmit;
-		__entry->seqno = task->tk_rqstp->rq_seqno;
+		__entry->seqno = *task->tk_rqstp->rq_seqnos;
 		__entry->ret = ret;
 	),
 
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 81f795150097..aad697da1580 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1098,7 +1098,7 @@ TRACE_EVENT(xprt_transmit,
 		__entry->client_id = rqst->rq_task->tk_client ?
 			rqst->rq_task->tk_client->cl_clid : -1;
 		__entry->xid = be32_to_cpu(rqst->rq_xid);
-		__entry->seqno = rqst->rq_seqno;
+		__entry->seqno = *rqst->rq_seqnos;
 		__entry->status = status;
 	),
 
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index a7e5452b5d21..d3ef86c97ae3 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -379,32 +379,6 @@ TRACE_EVENT(mem_connect,
 	)
 );
 
-TRACE_EVENT(mem_return_failed,
-
-	TP_PROTO(const struct xdp_mem_info *mem,
-		 const struct page *page),
-
-	TP_ARGS(mem, page),
-
-	TP_STRUCT__entry(
-		__field(const struct page *,	page)
-		__field(u32,		mem_id)
-		__field(u32,		mem_type)
-	),
-
-	TP_fast_assign(
-		__entry->page		= page;
-		__entry->mem_id		= mem->id;
-		__entry->mem_type	= mem->type;
-	),
-
-	TP_printk("mem_id=%d mem_type=%s page=%p",
-		  __entry->mem_id,
-		  __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB),
-		  __entry->page
-	)
-);
-
 TRACE_EVENT(bpf_xdp_link_attach_failed,
 
 	TP_PROTO(const char *msg),
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 85180e4aaa5a..0b4a2f124d11 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2056,6 +2056,7 @@ union bpf_attr {
  * 		for updates resulting in a null checksum the value is set to
  * 		**CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates
  * 		that the modified header field is part of the pseudo-header.
+ * 		Flag **BPF_F_IPV6** should be set for IPv6 packets.
  *
  * 		This helper works in combination with **bpf_csum_diff**\ (),
  * 		which does not update the checksum in-place, but offers more
@@ -6072,6 +6073,7 @@ enum {
 	BPF_F_PSEUDO_HDR		= (1ULL << 4),
 	BPF_F_MARK_MANGLED_0		= (1ULL << 5),
 	BPF_F_MARK_ENFORCE		= (1ULL << 6),
+	BPF_F_IPV6			= (1ULL << 7),
 };
 
 /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index b08c7378164d..3225e025e30e 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -258,10 +258,12 @@ enum {
 	DM_DEV_SET_GEOMETRY_CMD,
 	DM_DEV_ARM_POLL_CMD,
 	DM_GET_TARGET_VERSION_CMD,
+	DM_MPATH_PROBE_PATHS_CMD,
 };
 
 #define DM_IOCTL 0xfd
 
+/* Control device ioctls */
 #define DM_VERSION       _IOWR(DM_IOCTL, DM_VERSION_CMD, struct dm_ioctl)
 #define DM_REMOVE_ALL    _IOWR(DM_IOCTL, DM_REMOVE_ALL_CMD, struct dm_ioctl)
 #define DM_LIST_DEVICES  _IOWR(DM_IOCTL, DM_LIST_DEVICES_CMD, struct dm_ioctl)
@@ -285,10 +287,13 @@ enum {
 #define DM_TARGET_MSG	 _IOWR(DM_IOCTL, DM_TARGET_MSG_CMD, struct dm_ioctl)
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
+/* Block device ioctls */
+#define DM_MPATH_PROBE_PATHS _IO(DM_IOCTL, DM_MPATH_PROBE_PATHS_CMD)
+
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	49
+#define DM_VERSION_MINOR	50
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2025-01-17)"
+#define DM_VERSION_EXTRA	"-ioctl (2025-04-28)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index ba326710f9c8..a3a3e942dedf 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -750,7 +750,8 @@
 #define PCI_EXT_CAP_ID_NPEM	0x29	/* Native PCIe Enclosure Management */
 #define PCI_EXT_CAP_ID_PL_32GT  0x2A    /* Physical Layer 32.0 GT/s */
 #define PCI_EXT_CAP_ID_DOE	0x2E	/* Data Object Exchange */
-#define PCI_EXT_CAP_ID_MAX	PCI_EXT_CAP_ID_DOE
+#define PCI_EXT_CAP_ID_PL_64GT	0x31	/* Physical Layer 64.0 GT/s */
+#define PCI_EXT_CAP_ID_MAX	PCI_EXT_CAP_ID_PL_64GT
 
 #define PCI_EXT_CAP_DSN_SIZEOF	12
 #define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40
@@ -1144,12 +1145,21 @@
 #define PCI_DLF_CAP		0x04	/* Capabilities Register */
 #define  PCI_DLF_EXCHANGE_ENABLE	0x80000000  /* Data Link Feature Exchange Enable */
 
+/* Secondary PCIe Capability 8.0 GT/s */
+#define PCI_SECPCI_LE_CTRL	0x0c /* Lane Equalization Control Register */
+
 /* Physical Layer 16.0 GT/s */
 #define PCI_PL_16GT_LE_CTRL	0x20	/* Lane Equalization Control Register */
 #define  PCI_PL_16GT_LE_CTRL_DSP_TX_PRESET_MASK		0x0000000F
 #define  PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_MASK		0x000000F0
 #define  PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_SHIFT	4
 
+/* Physical Layer 32.0 GT/s */
+#define PCI_PL_32GT_LE_CTRL	0x20	/* Lane Equalization Control Register */
+
+/* Physical Layer 64.0 GT/s */
+#define PCI_PL_64GT_LE_CTRL	0x20	/* Lane Equalization Control Register */
+
 /* Native PCIe Enclosure Management */
 #define PCI_NPEM_CAP     0x04 /* NPEM capability register */
 #define  PCI_NPEM_CAP_CAPABLE     0x00000001 /* NPEM Capable */
diff --git a/init/Kconfig b/init/Kconfig
index 20716189fe68..af4c2f085455 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -136,6 +136,9 @@ config LD_CAN_USE_KEEP_IN_OVERLAY
 config RUSTC_HAS_COERCE_POINTEE
 	def_bool RUSTC_VERSION >= 108400
 
+config RUSTC_HAS_SPAN_FILE
+	def_bool RUSTC_VERSION >= 108800
+
 config RUSTC_HAS_UNNECESSARY_TRANSMUTES
 	def_bool RUSTC_VERSION >= 108800
 
@@ -992,6 +995,20 @@ config MEMCG
 	help
 	  Provides control over the memory footprint of tasks in a cgroup.
 
+config MEMCG_NMI_UNSAFE
+	bool
+	depends on MEMCG
+	depends on HAVE_NMI
+	depends on !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && !ARCH_HAVE_NMI_SAFE_CMPXCHG
+	default y
+
+config MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+	bool
+	depends on MEMCG
+	depends on HAVE_NMI
+	depends on !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && ARCH_HAVE_NMI_SAFE_CMPXCHG
+	default y
+
 config MEMCG_V1
 	bool "Legacy cgroup v1 memory controller"
 	depends on MEMCG
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index ce4752ab9e09..cbeaa499a96a 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -47,8 +47,20 @@ static spinlock_t *ss_rstat_lock(struct cgroup_subsys *ss)
 
 static raw_spinlock_t *ss_rstat_cpu_lock(struct cgroup_subsys *ss, int cpu)
 {
-	if (ss)
+	if (ss) {
+		/*
+		 * Depending on config, the subsystem per-cpu lock type may be an
+		 * empty struct. In enviromnents where this is the case, allocation
+		 * of this field is not performed in ss_rstat_init(). Avoid a
+		 * cpu-based offset relative to NULL by returning early. When the
+		 * lock type is zero in size, the corresponding lock functions are
+		 * no-ops so passing them NULL is acceptable.
+		 */
+		if (sizeof(*ss->rstat_ss_cpu_lock) == 0)
+			return NULL;
+
 		return per_cpu_ptr(ss->rstat_ss_cpu_lock, cpu);
+	}
 
 	return per_cpu_ptr(&rstat_base_cpu_lock, cpu);
 }
@@ -510,20 +522,15 @@ int __init ss_rstat_init(struct cgroup_subsys *ss)
 {
 	int cpu;
 
-#ifdef CONFIG_SMP
 	/*
-	 * On uniprocessor machines, arch_spinlock_t is defined as an empty
-	 * struct. Avoid allocating a size of zero by having this block
-	 * excluded in this case. It's acceptable to leave the subsystem locks
-	 * unitialized since the associated lock functions are no-ops in the
-	 * non-smp case.
+	 * Depending on config, the subsystem per-cpu lock type may be an empty
+	 * struct. Avoid allocating a size of zero in this case.
 	 */
-	if (ss) {
+	if (ss && sizeof(*ss->rstat_ss_cpu_lock)) {
 		ss->rstat_ss_cpu_lock = alloc_percpu(raw_spinlock_t);
 		if (!ss->rstat_ss_cpu_lock)
 			return -ENOMEM;
 	}
-#endif
 
 	spin_lock_init(ss_rstat_lock(ss));
 	for_each_possible_cpu(cpu)
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 19a2c65f3d37..565f9717c6ca 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -531,7 +531,7 @@ static u64 get_inode_sequence_number(struct inode *inode)
  *
  * For shared mappings (when @fshared), the key is:
  *
- *   ( inode->i_sequence, page->index, offset_within_page )
+ *   ( inode->i_sequence, page offset within mapping, offset_within_page )
  *
  * [ also see get_inode_sequence_number() ]
  *
diff --git a/kernel/module/internal.h b/kernel/module/internal.h
index 626cf8668a7e..8d74b0a21c82 100644
--- a/kernel/module/internal.h
+++ b/kernel/module/internal.h
@@ -322,8 +322,11 @@ int module_enable_rodata_ro(const struct module *mod);
 int module_enable_rodata_ro_after_init(const struct module *mod);
 int module_enable_data_nx(const struct module *mod);
 int module_enable_text_rox(const struct module *mod);
-int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
-				char *secstrings, struct module *mod);
+int module_enforce_rwx_sections(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
+				const char *secstrings,
+				const struct module *mod);
+void module_mark_ro_after_init(const Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
+			       const char *secstrings);
 
 #ifdef CONFIG_MODULE_SIG
 int module_sig_check(struct load_info *info, int flags);
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 5c6ab20240a6..3d64e69cc03e 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1562,12 +1562,11 @@ static void __layout_sections(struct module *mod, struct load_info *info, bool i
 {
 	unsigned int m, i;
 
+	/*
+	 * { Mask of required section header flags,
+	 *   Mask of excluded section header flags }
+	 */
 	static const unsigned long masks[][2] = {
-		/*
-		 * NOTE: all executable code must be the first section
-		 * in this array; otherwise modify the text_size
-		 * finder in the two loops below
-		 */
 		{ SHF_EXECINSTR | SHF_ALLOC, ARCH_SHF_SMALL },
 		{ SHF_ALLOC, SHF_WRITE | ARCH_SHF_SMALL },
 		{ SHF_RO_AFTER_INIT | SHF_ALLOC, ARCH_SHF_SMALL },
@@ -2768,7 +2767,6 @@ core_param(module_blacklist, module_blacklist, charp, 0400);
 static struct module *layout_and_allocate(struct load_info *info, int flags)
 {
 	struct module *mod;
-	unsigned int ndx;
 	int err;
 
 	/* Allow arches to frob section contents and sizes.  */
@@ -2786,22 +2784,11 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
 	info->sechdrs[info->index.pcpu].sh_flags &= ~(unsigned long)SHF_ALLOC;
 
 	/*
-	 * Mark ro_after_init section with SHF_RO_AFTER_INIT so that
-	 * layout_sections() can put it in the right place.
+	 * Mark relevant sections as SHF_RO_AFTER_INIT so layout_sections() can
+	 * put them in the right place.
 	 * Note: ro_after_init sections also have SHF_{WRITE,ALLOC} set.
 	 */
-	ndx = find_sec(info, ".data..ro_after_init");
-	if (ndx)
-		info->sechdrs[ndx].sh_flags |= SHF_RO_AFTER_INIT;
-	/*
-	 * Mark the __jump_table section as ro_after_init as well: these data
-	 * structures are never modified, with the exception of entries that
-	 * refer to code in the __init section, which are annotated as such
-	 * at module load time.
-	 */
-	ndx = find_sec(info, "__jump_table");
-	if (ndx)
-		info->sechdrs[ndx].sh_flags |= SHF_RO_AFTER_INIT;
+	module_mark_ro_after_init(info->hdr, info->sechdrs, info->secstrings);
 
 	/*
 	 * Determine total sizes, and put offsets in sh_entsize.  For now
diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c
index 03f4142cfbf4..8fd438529fbc 100644
--- a/kernel/module/strict_rwx.c
+++ b/kernel/module/strict_rwx.c
@@ -87,8 +87,9 @@ int module_enable_data_nx(const struct module *mod)
 	return 0;
 }
 
-int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
-				char *secstrings, struct module *mod)
+int module_enforce_rwx_sections(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
+				const char *secstrings,
+				const struct module *mod)
 {
 	const unsigned long shf_wx = SHF_WRITE | SHF_EXECINSTR;
 	int i;
@@ -106,3 +107,45 @@ int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 
 	return 0;
 }
+
+static const char *const ro_after_init[] = {
+	/*
+	 * Section .data..ro_after_init holds data explicitly annotated by
+	 * __ro_after_init.
+	 */
+	".data..ro_after_init",
+
+	/*
+	 * Section __jump_table holds data structures that are never modified,
+	 * with the exception of entries that refer to code in the __init
+	 * section, which are marked as such at module load time.
+	 */
+	"__jump_table",
+
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+	/*
+	 * Section .static_call_sites holds data structures that need to be
+	 * sorted and processed at module load time but are never modified
+	 * afterwards.
+	 */
+	".static_call_sites",
+#endif
+};
+
+void module_mark_ro_after_init(const Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
+			       const char *secstrings)
+{
+	int i, j;
+
+	for (i = 1; i < hdr->e_shnum; i++) {
+		Elf_Shdr *shdr = &sechdrs[i];
+
+		for (j = 0; j < ARRAY_SIZE(ro_after_init); j++) {
+			if (strcmp(secstrings + shdr->sh_name,
+				   ro_after_init[j]) == 0) {
+				shdr->sh_flags |= SHF_RO_AFTER_INIT;
+				break;
+			}
+		}
+	}
+}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 62b3416f5e43..dce50fa57471 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3362,6 +3362,10 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 #ifdef CONFIG_NUMA_BALANCING
 static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
+	__schedstat_inc(p->stats.numa_task_swapped);
+	count_vm_numa_event(NUMA_TASK_SWAP);
+	count_memcg_event_mm(p->mm, NUMA_TASK_SWAP);
+
 	if (task_on_rq_queued(p)) {
 		struct rq *src_rq, *dst_rq;
 		struct rq_flags srf, drf;
@@ -7930,8 +7934,9 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
 	if (!cpumask_test_cpu(target_cpu, p->cpus_ptr))
 		return -EINVAL;
 
-	/* TODO: This is not properly updating schedstats */
-
+	__schedstat_inc(p->stats.numa_task_migrated);
+	count_vm_numa_event(NUMA_TASK_MIGRATE);
+	count_memcg_event_mm(p->mm, NUMA_TASK_MIGRATE);
 	trace_sched_move_numa(p, curr_cpu, target_cpu);
 	return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
 }
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 557246880a7e..9d71baf08075 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1210,6 +1210,10 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		P_SCHEDSTAT(nr_failed_migrations_running);
 		P_SCHEDSTAT(nr_failed_migrations_hot);
 		P_SCHEDSTAT(nr_forced_migrations);
+#ifdef CONFIG_NUMA_BALANCING
+		P_SCHEDSTAT(numa_task_migrated);
+		P_SCHEDSTAT(numa_task_swapped);
+#endif
 		P_SCHEDSTAT(nr_wakeups);
 		P_SCHEDSTAT(nr_wakeups_sync);
 		P_SCHEDSTAT(nr_wakeups_migrate);
diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index 66da03cc0b33..6d29d3cbc670 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -138,6 +138,7 @@ found:
 		goto retry;
 }
 
+#ifdef CONFIG_NUMA
 /*
  * Tracks nodes that have not yet been visited when searching for an idle
  * CPU across all available nodes.
@@ -186,6 +187,13 @@ static s32 pick_idle_cpu_from_online_nodes(const struct cpumask *cpus_allowed, i
 
 	return cpu;
 }
+#else
+static inline s32
+pick_idle_cpu_from_online_nodes(const struct cpumask *cpus_allowed, int node, u64 flags)
+{
+	return -EBUSY;
+}
+#endif
 
 /*
  * Find an idle CPU in the system, starting from @node.
@@ -447,11 +455,18 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
 	const struct cpumask *llc_cpus = NULL, *numa_cpus = NULL;
 	const struct cpumask *allowed = cpus_allowed ?: p->cpus_ptr;
 	int node = scx_cpu_node_if_enabled(prev_cpu);
+	bool is_prev_allowed;
 	s32 cpu;
 
 	preempt_disable();
 
 	/*
+	 * Check whether @prev_cpu is still within the allowed set. If not,
+	 * we can still try selecting a nearby CPU.
+	 */
+	is_prev_allowed = cpumask_test_cpu(prev_cpu, allowed);
+
+	/*
 	 * Determine the subset of CPUs usable by @p within @cpus_allowed.
 	 */
 	if (allowed != p->cpus_ptr) {
@@ -465,21 +480,6 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
 			cpu = -EBUSY;
 			goto out_enable;
 		}
-
-		/*
-		 * If @prev_cpu is not in the allowed CPUs, skip topology
-		 * optimizations and try to pick any idle CPU usable by the
-		 * task.
-		 *
-		 * If %SCX_OPS_BUILTIN_IDLE_PER_NODE is enabled, prioritize
-		 * the current node, as it may optimize some waker->wakee
-		 * workloads.
-		 */
-		if (!cpumask_test_cpu(prev_cpu, allowed)) {
-			node = scx_cpu_node_if_enabled(smp_processor_id());
-			cpu = scx_pick_idle_cpu(allowed, node, flags);
-			goto out_enable;
-		}
 	}
 
 	/*
@@ -525,7 +525,7 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
 		 * then avoid a migration.
 		 */
 		cpu = smp_processor_id();
-		if (cpus_share_cache(cpu, prev_cpu) &&
+		if (is_prev_allowed && cpus_share_cache(cpu, prev_cpu) &&
 		    scx_idle_test_and_clear_cpu(prev_cpu)) {
 			cpu = prev_cpu;
 			goto out_unlock;
@@ -562,7 +562,8 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
 		/*
 		 * Keep using @prev_cpu if it's part of a fully idle core.
 		 */
-		if (cpumask_test_cpu(prev_cpu, idle_cpumask(node)->smt) &&
+		if (is_prev_allowed &&
+		    cpumask_test_cpu(prev_cpu, idle_cpumask(node)->smt) &&
 		    scx_idle_test_and_clear_cpu(prev_cpu)) {
 			cpu = prev_cpu;
 			goto out_unlock;
@@ -611,7 +612,7 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
 	/*
 	 * Use @prev_cpu if it's idle.
 	 */
-	if (scx_idle_test_and_clear_cpu(prev_cpu)) {
+	if (is_prev_allowed && scx_idle_test_and_clear_cpu(prev_cpu)) {
 		cpu = prev_cpu;
 		goto out_unlock;
 	}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b4326827e326..7a14da5396fb 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2273,7 +2273,8 @@ static bool task_numa_compare(struct task_numa_env *env,
 
 	rcu_read_lock();
 	cur = rcu_dereference(dst_rq->curr);
-	if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur)))
+	if (cur && ((cur->flags & (PF_EXITING | PF_KTHREAD)) ||
+		    !cur->mm))
 		cur = NULL;
 
 	/*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1af952cba48d..a7291685902e 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -7438,9 +7438,10 @@ void ftrace_release_mod(struct module *mod)
 
 	mutex_lock(&ftrace_lock);
 
-	if (ftrace_disabled)
-		goto out_unlock;
-
+	/*
+	 * To avoid the UAF problem after the module is unloaded, the
+	 * 'mod_map' resource needs to be released unconditionally.
+	 */
 	list_for_each_entry_safe(mod_map, n, &ftrace_mod_maps, list) {
 		if (mod_map->mod == mod) {
 			list_del_rcu(&mod_map->list);
@@ -7449,6 +7450,9 @@ void ftrace_release_mod(struct module *mod)
 		}
 	}
 
+	if (ftrace_disabled)
+		goto out_unlock;
+
 	/*
 	 * Each module has its own ftrace_pages, remove
 	 * them from the list.
@@ -7627,6 +7631,9 @@ allocate_ftrace_mod_map(struct module *mod,
 {
 	struct ftrace_mod_map *mod_map;
 
+	if (ftrace_disabled)
+		return NULL;
+
 	mod_map = kmalloc(sizeof(*mod_map), GFP_KERNEL);
 	if (!mod_map)
 		return NULL;
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index d9e19fb2dcf3..969d4ad510df 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -457,38 +457,35 @@ size_t iov_iter_zero(size_t bytes, struct iov_iter *i)
 }
 EXPORT_SYMBOL(iov_iter_zero);
 
-size_t copy_page_from_iter_atomic(struct page *page, size_t offset,
+size_t copy_folio_from_iter_atomic(struct folio *folio, size_t offset,
 		size_t bytes, struct iov_iter *i)
 {
 	size_t n, copied = 0;
-	bool uses_kmap = IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) ||
-			 PageHighMem(page);
 
-	if (!page_copy_sane(page, offset, bytes))
+	if (!page_copy_sane(&folio->page, offset, bytes))
 		return 0;
 	if (WARN_ON_ONCE(!i->data_source))
 		return 0;
 
 	do {
-		char *p;
+		char *to = kmap_local_folio(folio, offset);
 
 		n = bytes - copied;
-		if (uses_kmap) {
-			page += offset / PAGE_SIZE;
-			offset %= PAGE_SIZE;
-			n = min_t(size_t, n, PAGE_SIZE - offset);
-		}
-
-		p = kmap_atomic(page) + offset;
-		n = __copy_from_iter(p, n, i);
-		kunmap_atomic(p);
+		if (folio_test_partial_kmap(folio) &&
+		    n > PAGE_SIZE - offset_in_page(offset))
+			n = PAGE_SIZE - offset_in_page(offset);
+
+		pagefault_disable();
+		n = __copy_from_iter(to, n, i);
+		pagefault_enable();
+		kunmap_local(to);
 		copied += n;
 		offset += n;
-	} while (uses_kmap && copied != bytes && n > 0);
+	} while (copied != bytes && n > 0);
 
 	return copied;
 }
-EXPORT_SYMBOL(copy_page_from_iter_atomic);
+EXPORT_SYMBOL(copy_folio_from_iter_atomic);
 
 static void iov_iter_bvec_advance(struct iov_iter *i, size_t size)
 {
diff --git a/lib/tests/test_bits.c b/lib/tests/test_bits.c
index c7b38d91e1f1..47325b41515f 100644
--- a/lib/tests/test_bits.c
+++ b/lib/tests/test_bits.c
@@ -5,6 +5,26 @@
 
 #include <kunit/test.h>
 #include <linux/bits.h>
+#include <linux/types.h>
+
+#define assert_type(t, x) _Generic(x, t: x, default: 0)
+
+static_assert(assert_type(u8, BIT_U8(0)) == 1u);
+static_assert(assert_type(u16, BIT_U16(0)) == 1u);
+static_assert(assert_type(u32, BIT_U32(0)) == 1u);
+static_assert(assert_type(u64, BIT_U64(0)) == 1ull);
+
+static_assert(assert_type(u8, BIT_U8(7)) == 0x80u);
+static_assert(assert_type(u16, BIT_U16(15)) == 0x8000u);
+static_assert(assert_type(u32, BIT_U32(31)) == 0x80000000u);
+static_assert(assert_type(u64, BIT_U64(63)) == 0x8000000000000000ull);
+
+static_assert(assert_type(unsigned long, GENMASK(31, 0)) == U32_MAX);
+static_assert(assert_type(unsigned long long, GENMASK_ULL(63, 0)) == U64_MAX);
+static_assert(assert_type(u8, GENMASK_U8(7, 0)) == U8_MAX);
+static_assert(assert_type(u16, GENMASK_U16(15, 0)) == U16_MAX);
+static_assert(assert_type(u32, GENMASK_U32(31, 0)) == U32_MAX);
+static_assert(assert_type(u64, GENMASK_U64(63, 0)) == U64_MAX);
 
 
 static void genmask_test(struct kunit *test)
@@ -14,11 +34,21 @@ static void genmask_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, 6ul, GENMASK(2, 1));
 	KUNIT_EXPECT_EQ(test, 0xFFFFFFFFul, GENMASK(31, 0));
 
+	KUNIT_EXPECT_EQ(test, 1u, GENMASK_U8(0, 0));
+	KUNIT_EXPECT_EQ(test, 3u, GENMASK_U16(1, 0));
+	KUNIT_EXPECT_EQ(test, 0x10000, GENMASK_U32(16, 16));
+
 #ifdef TEST_GENMASK_FAILURES
 	/* these should fail compilation */
 	GENMASK(0, 1);
 	GENMASK(0, 10);
 	GENMASK(9, 10);
+
+	GENMASK_U32(0, 31);
+	GENMASK_U64(64, 0);
+	GENMASK_U32(32, 0);
+	GENMASK_U16(16, 0);
+	GENMASK_U8(8, 0);
 #endif
 
 
diff --git a/mm/Kconfig b/mm/Kconfig
index bd08e151fa1b..f8bb8f070d0d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -993,6 +993,40 @@ config CMA_AREAS
 
 	  If unsure, leave the default value "8" in UMA and "20" in NUMA.
 
+#
+# Select this config option from the architecture Kconfig, if available, to set
+# the max page order for physically contiguous allocations.
+#
+config ARCH_FORCE_MAX_ORDER
+	int
+
+#
+# When ARCH_FORCE_MAX_ORDER is not defined,
+# the default page block order is MAX_PAGE_ORDER (10) as per
+# include/linux/mmzone.h.
+#
+config PAGE_BLOCK_ORDER
+	int "Page Block Order"
+	range 1 10 if ARCH_FORCE_MAX_ORDER = 0
+	default 10 if ARCH_FORCE_MAX_ORDER = 0
+	range 1 ARCH_FORCE_MAX_ORDER if ARCH_FORCE_MAX_ORDER != 0
+	default ARCH_FORCE_MAX_ORDER if ARCH_FORCE_MAX_ORDER != 0
+	help
+	  The page block order refers to the power of two number of pages that
+	  are physically contiguous and can have a migrate type associated to
+	  them. The maximum size of the page block order is limited by
+	  ARCH_FORCE_MAX_ORDER.
+
+	  This config allows overriding the default page block order when the
+	  page block order is required to be smaller than ARCH_FORCE_MAX_ORDER
+	  or MAX_PAGE_ORDER.
+
+	  Reducing pageblock order can negatively impact THP generation
+	  success rate. If your workloads uses THP heavily, please use this
+	  option with caution.
+
+	  Don't change if unsure.
+
 config MEM_SOFT_DIRTY
 	bool "Track memory changes"
 	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig
index c213cf8b5638..551745df011b 100644
--- a/mm/damon/Kconfig
+++ b/mm/damon/Kconfig
@@ -4,6 +4,7 @@ menu "Data Access Monitoring"
 
 config DAMON
 	bool "DAMON: Data Access Monitoring Framework"
+	default y
 	help
 	  This builds a framework that allows kernel subsystems to monitor
 	  access frequency of each memory region. The information can be useful
@@ -28,6 +29,7 @@ config DAMON_VADDR
 	bool "Data access monitoring operations for virtual address spaces"
 	depends on DAMON && MMU
 	select PAGE_IDLE_FLAG
+	default DAMON
 	help
 	  This builds the default data access monitoring operations for DAMON
 	  that work for virtual address spaces.
@@ -36,6 +38,7 @@ config DAMON_PADDR
 	bool "Data access monitoring operations for the physical address space"
 	depends on DAMON && MMU
 	select PAGE_IDLE_FLAG
+	default DAMON
 	help
 	  This builds the default data access monitoring operations for DAMON
 	  that works for the physical address space.
@@ -55,6 +58,7 @@ config DAMON_VADDR_KUNIT_TEST
 config DAMON_SYSFS
 	bool "DAMON sysfs interface"
 	depends on DAMON && SYSFS
+	default DAMON
 	help
 	  This builds the sysfs interface for DAMON.  The user space can use
 	  the interface for arbitrary data access monitoring.
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 0bb71e2ab713..b217e0120e09 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1093,9 +1093,17 @@ static int damon_commit_targets(
 			if (err)
 				return err;
 		} else {
+			struct damos *s;
+
 			if (damon_target_has_pid(dst))
 				put_pid(dst_target->pid);
 			damon_destroy_target(dst_target);
+			damon_for_each_scheme(s, dst) {
+				if (s->quota.charge_target_from == dst_target) {
+					s->quota.charge_target_from = NULL;
+					s->quota.charge_addr_from = 0;
+				}
+			}
 		}
 	}
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 48c944e2c163..bada249b9fb7 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -142,7 +142,7 @@ static void page_cache_delete(struct address_space *mapping,
 	xas_init_marks(&xas);
 
 	folio->mapping = NULL;
-	/* Leave page->index set: truncation lookup relies upon it */
+	/* Leave folio->index set: truncation lookup relies upon it */
 	mapping->nrpages -= nr;
 }
 
@@ -949,7 +949,7 @@ unlock:
 	return 0;
 error:
 	folio->mapping = NULL;
-	/* Leave page->index set: truncation relies upon it */
+	/* Leave folio->index set: truncation relies upon it */
 	folio_put_refs(folio, nr);
 	return xas_error(&xas);
 }
diff --git a/mm/gup.c b/mm/gup.c
index 329c5f7acc7a..e065a49842a8 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -3299,7 +3299,7 @@ static unsigned long gup_fast(unsigned long start, unsigned long end,
 	 * include/asm-generic/tlb.h for more details.
 	 *
 	 * We do not adopt an rcu_read_lock() here as we also want to block IPIs
-	 * that come from THPs splitting.
+	 * that come from callers of tlb_remove_table_sync_one().
 	 */
 	local_irq_save(flags);
 	gup_fast_pgd_range(start, end, gup_flags, pages, &nr_pinned);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 32ab14aa4074..f0b1d53079f9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3741,7 +3741,7 @@ static void __init report_hugepages(void)
 
 		string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
 		pr_info("HugeTLB: registered %s page size, pre-allocated %ld pages\n",
-			buf, h->free_huge_pages);
+			buf, h->nr_huge_pages);
 		if (nrinvalid)
 			pr_info("HugeTLB: %s page size: %lu invalid page%s discarded\n",
 					buf, nrinvalid, nrinvalid > 1 ? "s" : "");
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index cdf5a581368b..15203ea7d007 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -548,19 +548,6 @@ static void release_pte_pages(pte_t *pte, pte_t *_pte,
 	}
 }
 
-static bool is_refcount_suitable(struct folio *folio)
-{
-	int expected_refcount = folio_mapcount(folio);
-
-	if (!folio_test_anon(folio) || folio_test_swapcache(folio))
-		expected_refcount += folio_nr_pages(folio);
-
-	if (folio_test_private(folio))
-		expected_refcount++;
-
-	return folio_ref_count(folio) == expected_refcount;
-}
-
 static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 					unsigned long address,
 					pte_t *pte,
@@ -652,7 +639,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		 * but not from this process. The other process cannot write to
 		 * the page, only trigger CoW.
 		 */
-		if (!is_refcount_suitable(folio)) {
+		if (folio_expected_ref_count(folio) != folio_ref_count(folio)) {
 			folio_unlock(folio);
 			result = SCAN_PAGE_COUNT;
 			goto out;
@@ -1402,7 +1389,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 		 * has excessive GUP pins (i.e. 512).  Anyway the same check
 		 * will be done again later the risk seems low.
 		 */
-		if (!is_refcount_suitable(folio)) {
+		if (folio_expected_ref_count(folio) != folio_ref_count(folio)) {
 			result = SCAN_PAGE_COUNT;
 			goto out_unmap;
 		}
@@ -2293,6 +2280,17 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 			continue;
 		}
 
+		if (!folio_try_get(folio)) {
+			xas_reset(&xas);
+			continue;
+		}
+
+		if (unlikely(folio != xas_reload(&xas))) {
+			folio_put(folio);
+			xas_reset(&xas);
+			continue;
+		}
+
 		if (folio_order(folio) == HPAGE_PMD_ORDER &&
 		    folio->index == start) {
 			/* Maybe PMD-mapped */
@@ -2303,23 +2301,27 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 			 * it's safe to skip LRU and refcount checks before
 			 * returning.
 			 */
+			folio_put(folio);
 			break;
 		}
 
 		node = folio_nid(folio);
 		if (hpage_collapse_scan_abort(node, cc)) {
 			result = SCAN_SCAN_ABORT;
+			folio_put(folio);
 			break;
 		}
 		cc->node_load[node]++;
 
 		if (!folio_test_lru(folio)) {
 			result = SCAN_PAGE_LRU;
+			folio_put(folio);
 			break;
 		}
 
-		if (!is_refcount_suitable(folio)) {
+		if (folio_expected_ref_count(folio) + 1 != folio_ref_count(folio)) {
 			result = SCAN_PAGE_COUNT;
+			folio_put(folio);
 			break;
 		}
 
@@ -2331,6 +2333,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 		 */
 
 		present += folio_nr_pages(folio);
+		folio_put(folio);
 
 		if (need_resched()) {
 			xas_pause(&xas);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b90aa3075950..902da8a9c643 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -474,6 +474,8 @@ static const unsigned int memcg_vm_event_stat[] = {
 	NUMA_PAGE_MIGRATE,
 	NUMA_PTE_UPDATES,
 	NUMA_HINT_FAULTS,
+	NUMA_TASK_MIGRATE,
+	NUMA_TASK_SWAP,
 #endif
 };
 
@@ -531,7 +533,7 @@ struct memcg_vmstats {
 	unsigned long		events_pending[NR_MEMCG_EVENTS];
 
 	/* Stats updates since the last flush */
-	atomic64_t		stats_updates;
+	atomic_t		stats_updates;
 };
 
 /*
@@ -557,7 +559,7 @@ static u64 flush_last_time;
 
 static bool memcg_vmstats_needs_flush(struct memcg_vmstats *vmstats)
 {
-	return atomic64_read(&vmstats->stats_updates) >
+	return atomic_read(&vmstats->stats_updates) >
 		MEMCG_CHARGE_BATCH * num_online_cpus();
 }
 
@@ -571,7 +573,9 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val,
 	if (!val)
 		return;
 
-	css_rstat_updated(&memcg->css, cpu);
+	/* TODO: add to cgroup update tree once it is nmi-safe. */
+	if (!in_nmi())
+		css_rstat_updated(&memcg->css, cpu);
 	statc_pcpu = memcg->vmstats_percpu;
 	for (; statc_pcpu; statc_pcpu = statc->parent_pcpu) {
 		statc = this_cpu_ptr(statc_pcpu);
@@ -589,7 +593,7 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val,
 			continue;
 
 		stats_updates = this_cpu_xchg(statc_pcpu->stats_updates, 0);
-		atomic64_add(stats_updates, &statc->vmstats->stats_updates);
+		atomic_add(stats_updates, &statc->vmstats->stats_updates);
 	}
 }
 
@@ -597,7 +601,7 @@ static void __mem_cgroup_flush_stats(struct mem_cgroup *memcg, bool force)
 {
 	bool needs_flush = memcg_vmstats_needs_flush(memcg->vmstats);
 
-	trace_memcg_flush_stats(memcg, atomic64_read(&memcg->vmstats->stats_updates),
+	trace_memcg_flush_stats(memcg, atomic_read(&memcg->vmstats->stats_updates),
 		force, needs_flush);
 
 	if (!force && !needs_flush)
@@ -2513,17 +2517,47 @@ static void commit_charge(struct folio *folio, struct mem_cgroup *memcg)
 	folio->memcg_data = (unsigned long)memcg;
 }
 
+#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+static inline void account_slab_nmi_safe(struct mem_cgroup *memcg,
+					 struct pglist_data *pgdat,
+					 enum node_stat_item idx, int nr)
+{
+	struct lruvec *lruvec;
+
+	if (likely(!in_nmi())) {
+		lruvec = mem_cgroup_lruvec(memcg, pgdat);
+		mod_memcg_lruvec_state(lruvec, idx, nr);
+	} else {
+		struct mem_cgroup_per_node *pn = memcg->nodeinfo[pgdat->node_id];
+
+		/* TODO: add to cgroup update tree once it is nmi-safe. */
+		if (idx == NR_SLAB_RECLAIMABLE_B)
+			atomic_add(nr, &pn->slab_reclaimable);
+		else
+			atomic_add(nr, &pn->slab_unreclaimable);
+	}
+}
+#else
+static inline void account_slab_nmi_safe(struct mem_cgroup *memcg,
+					 struct pglist_data *pgdat,
+					 enum node_stat_item idx, int nr)
+{
+	struct lruvec *lruvec;
+
+	lruvec = mem_cgroup_lruvec(memcg, pgdat);
+	mod_memcg_lruvec_state(lruvec, idx, nr);
+}
+#endif
+
 static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
 				       struct pglist_data *pgdat,
 				       enum node_stat_item idx, int nr)
 {
 	struct mem_cgroup *memcg;
-	struct lruvec *lruvec;
 
 	rcu_read_lock();
 	memcg = obj_cgroup_memcg(objcg);
-	lruvec = mem_cgroup_lruvec(memcg, pgdat);
-	mod_memcg_lruvec_state(lruvec, idx, nr);
+	account_slab_nmi_safe(memcg, pgdat, idx, nr);
 	rcu_read_unlock();
 }
 
@@ -2648,6 +2682,9 @@ __always_inline struct obj_cgroup *current_obj_cgroup(void)
 	struct mem_cgroup *memcg;
 	struct obj_cgroup *objcg;
 
+	if (IS_ENABLED(CONFIG_MEMCG_NMI_UNSAFE) && in_nmi())
+		return NULL;
+
 	if (in_task()) {
 		memcg = current->active_memcg;
 		if (unlikely(memcg))
@@ -2710,6 +2747,23 @@ struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio)
 	return objcg;
 }
 
+#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+static inline void account_kmem_nmi_safe(struct mem_cgroup *memcg, int val)
+{
+	if (likely(!in_nmi())) {
+		mod_memcg_state(memcg, MEMCG_KMEM, val);
+	} else {
+		/* TODO: add to cgroup update tree once it is nmi-safe. */
+		atomic_add(val, &memcg->kmem_stat);
+	}
+}
+#else
+static inline void account_kmem_nmi_safe(struct mem_cgroup *memcg, int val)
+{
+	mod_memcg_state(memcg, MEMCG_KMEM, val);
+}
+#endif
+
 /*
  * obj_cgroup_uncharge_pages: uncharge a number of kernel pages from a objcg
  * @objcg: object cgroup to uncharge
@@ -2722,7 +2776,7 @@ static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
 
 	memcg = get_mem_cgroup_from_objcg(objcg);
 
-	mod_memcg_state(memcg, MEMCG_KMEM, -nr_pages);
+	account_kmem_nmi_safe(memcg, -nr_pages);
 	memcg1_account_kmem(memcg, -nr_pages);
 	if (!mem_cgroup_is_root(memcg))
 		refill_stock(memcg, nr_pages);
@@ -2750,7 +2804,7 @@ static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp,
 	if (ret)
 		goto out;
 
-	mod_memcg_state(memcg, MEMCG_KMEM, nr_pages);
+	account_kmem_nmi_safe(memcg, nr_pages);
 	memcg1_account_kmem(memcg, nr_pages);
 out:
 	css_put(&memcg->css);
@@ -3961,6 +4015,53 @@ static void mem_cgroup_stat_aggregate(struct aggregate_control *ac)
 	}
 }
 
+#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+static void flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent,
+			    int cpu)
+{
+	int nid;
+
+	if (atomic_read(&memcg->kmem_stat)) {
+		int kmem = atomic_xchg(&memcg->kmem_stat, 0);
+		int index = memcg_stats_index(MEMCG_KMEM);
+
+		memcg->vmstats->state[index] += kmem;
+		if (parent)
+			parent->vmstats->state_pending[index] += kmem;
+	}
+
+	for_each_node_state(nid, N_MEMORY) {
+		struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
+		struct lruvec_stats *lstats = pn->lruvec_stats;
+		struct lruvec_stats *plstats = NULL;
+
+		if (parent)
+			plstats = parent->nodeinfo[nid]->lruvec_stats;
+
+		if (atomic_read(&pn->slab_reclaimable)) {
+			int slab = atomic_xchg(&pn->slab_reclaimable, 0);
+			int index = memcg_stats_index(NR_SLAB_RECLAIMABLE_B);
+
+			lstats->state[index] += slab;
+			if (plstats)
+				plstats->state_pending[index] += slab;
+		}
+		if (atomic_read(&pn->slab_unreclaimable)) {
+			int slab = atomic_xchg(&pn->slab_unreclaimable, 0);
+			int index = memcg_stats_index(NR_SLAB_UNRECLAIMABLE_B);
+
+			lstats->state[index] += slab;
+			if (plstats)
+				plstats->state_pending[index] += slab;
+		}
+	}
+}
+#else
+static void flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent,
+			    int cpu)
+{}
+#endif
+
 static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
@@ -3969,6 +4070,8 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 	struct aggregate_control ac;
 	int nid;
 
+	flush_nmi_stats(memcg, parent, cpu);
+
 	statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
 
 	ac = (struct aggregate_control) {
@@ -4018,8 +4121,8 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 	}
 	WRITE_ONCE(statc->stats_updates, 0);
 	/* We are in a per-cpu loop here, only do the atomic write once */
-	if (atomic64_read(&memcg->vmstats->stats_updates))
-		atomic64_set(&memcg->vmstats->stats_updates, 0);
+	if (atomic_read(&memcg->vmstats->stats_updates))
+		atomic_set(&memcg->vmstats->stats_updates, 0);
 }
 
 static void mem_cgroup_fork(struct task_struct *task)
diff --git a/mm/memory.c b/mm/memory.c
index 5cb48f262ab0..8eba595056fe 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -358,6 +358,8 @@ void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 {
 	struct unlink_vma_file_batch vb;
 
+	tlb_free_vmas(tlb);
+
 	do {
 		unsigned long addr = vma->vm_start;
 		struct vm_area_struct *next;
@@ -4668,8 +4670,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 
 		/*
 		 * KSM sometimes has to copy on read faults, for example, if
-		 * page->index of !PageKSM() pages would be nonlinear inside the
-		 * anon VMA -- PageKSM() is lost on actual swapout.
+		 * folio->index of non-ksm folios would be nonlinear inside the
+		 * anon VMA -- the ksm flag is lost on actual swapout.
 		 */
 		folio = ksm_might_need_to_copy(folio, vma, vmf->address);
 		if (unlikely(!folio)) {
diff --git a/mm/mm_init.c b/mm/mm_init.c
index f0bd0830daad..f2944748f526 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1509,7 +1509,7 @@ static inline void setup_usemap(struct zone *zone) {}
 /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
 void __init set_pageblock_order(void)
 {
-	unsigned int order = MAX_PAGE_ORDER;
+	unsigned int order = PAGE_BLOCK_ORDER;
 
 	/* Check that pageblock_nr_pages has not already been setup */
 	if (pageblock_order)
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index db7ba4a725d6..b49cc6385f1f 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -424,6 +424,7 @@ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 #ifdef CONFIG_MMU_GATHER_PAGE_SIZE
 	tlb->page_size = 0;
 #endif
+	tlb->vma_pfn = 0;
 
 	__tlb_reset_range(tlb);
 	inc_tlb_flush_pending(tlb->mm);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index b603a59cf8f7..b8eea5b3c064 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2565,11 +2565,11 @@ struct folio *writeback_iter(struct address_space *mapping,
 	if (!folio) {
 		/*
 		 * To avoid deadlocks between range_cyclic writeback and callers
-		 * that hold pages in PageWriteback to aggregate I/O until
+		 * that hold folios in writeback to aggregate I/O until
 		 * the writeback iteration finishes, we do not loop back to the
-		 * start of the file.  Doing so causes a page lock/page
+		 * start of the file.  Doing so causes a folio lock/folio
 		 * writeback access order inversion - we should only ever lock
-		 * multiple pages in ascending page->index order, and looping
+		 * multiple folios in ascending folio->index order, and looping
 		 * back to the start of the file violates that rule and causes
 		 * deadlocks.
 		 */
diff --git a/mm/shmem.c b/mm/shmem.c
index 858cee02ca49..0c5fb4ffa03a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1446,8 +1446,6 @@ static int shmem_unuse_swap_entries(struct inode *inode,
 	for (i = 0; i < folio_batch_count(fbatch); i++) {
 		struct folio *folio = fbatch->folios[i];
 
-		if (!xa_is_value(folio))
-			continue;
 		error = shmem_swapin_folio(inode, indices[i], &folio, SGP_CACHE,
 					mapping_gfp_mask(mapping), NULL, NULL);
 		if (error == 0) {
@@ -1505,6 +1503,7 @@ int shmem_unuse(unsigned int type)
 		return 0;
 
 	mutex_lock(&shmem_swaplist_mutex);
+start_over:
 	list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) {
 		if (!info->swapped) {
 			list_del_init(&info->swaplist);
@@ -1523,13 +1522,15 @@ int shmem_unuse(unsigned int type)
 		cond_resched();
 
 		mutex_lock(&shmem_swaplist_mutex);
-		next = list_next_entry(info, swaplist);
-		if (!info->swapped)
-			list_del_init(&info->swaplist);
 		if (atomic_dec_and_test(&info->stop_eviction))
 			wake_up_var(&info->stop_eviction);
 		if (error)
 			break;
+		if (list_empty(&info->swaplist))
+			goto start_over;
+		next = list_next_entry(info, swaplist);
+		if (!info->swapped)
+			list_del_init(&info->swaplist);
 	}
 	mutex_unlock(&shmem_swaplist_mutex);
 
@@ -1643,8 +1644,8 @@ try_split:
 		BUG_ON(folio_mapped(folio));
 		return swap_writeout(folio, wbc);
 	}
-
-	list_del_init(&info->swaplist);
+	if (!info->swapped)
+		list_del_init(&info->swaplist);
 	mutex_unlock(&shmem_swaplist_mutex);
 	if (nr_pages > 1)
 		goto try_split;
@@ -2331,6 +2332,8 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 		 */
 		split_order = shmem_split_large_entry(inode, index, swap, gfp);
 		if (split_order < 0) {
+			folio_put(folio);
+			folio = NULL;
 			error = split_order;
 			goto failed;
 		}
@@ -5805,12 +5808,12 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name,
 	if (size < 0 || size > MAX_LFS_FILESIZE)
 		return ERR_PTR(-EINVAL);
 
-	if (shmem_acct_size(flags, size))
-		return ERR_PTR(-ENOMEM);
-
 	if (is_idmapped_mnt(mnt))
 		return ERR_PTR(-EINVAL);
 
+	if (shmem_acct_size(flags, size))
+		return ERR_PTR(-ENOMEM);
+
 	inode = shmem_get_inode(&nop_mnt_idmap, mnt->mnt_sb, NULL,
 				S_IFREG | S_IRWXUGO, 0, flags);
 	if (IS_ERR(inode)) {
diff --git a/mm/slub.c b/mm/slub.c
index be8b09e09d30..31e11ef256f9 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2084,10 +2084,11 @@ prepare_slab_obj_exts_hook(struct kmem_cache *s, gfp_t flags, void *p)
 
 	slab = virt_to_slab(p);
 	if (!slab_obj_exts(slab) &&
-	    WARN(alloc_slab_obj_exts(slab, s, flags, false),
-		 "%s, %s: Failed to create slab extension vector!\n",
-		 __func__, s->name))
+	    alloc_slab_obj_exts(slab, s, flags, false)) {
+		pr_warn_once("%s, %s: Failed to create slab extension vector!\n",
+			     __func__, s->name);
 		return NULL;
+	}
 
 	return slab_obj_exts(slab) + obj_to_index(s, slab, p);
 }
@@ -4968,14 +4969,16 @@ static gfp_t kmalloc_gfp_adjust(gfp_t flags, size_t size)
 	 * We want to attempt a large physically contiguous block first because
 	 * it is less likely to fragment multiple larger blocks and therefore
 	 * contribute to a long term fragmentation less than vmalloc fallback.
-	 * However make sure that larger requests are not too disruptive - no
-	 * OOM killer and no allocation failure warnings as we have a fallback.
+	 * However make sure that larger requests are not too disruptive - i.e.
+	 * do not direct reclaim unless physically continuous memory is preferred
+	 * (__GFP_RETRY_MAYFAIL mode). We still kick in kswapd/kcompactd to
+	 * start working in the background
 	 */
 	if (size > PAGE_SIZE) {
 		flags |= __GFP_NOWARN;
 
 		if (!(flags & __GFP_RETRY_MAYFAIL))
-			flags |= __GFP_NORETRY;
+			flags &= ~__GFP_DIRECT_RECLAIM;
 
 		/* nofail semantic is implemented by the vmalloc fallback */
 		flags &= ~__GFP_NOFAIL;
diff --git a/mm/truncate.c b/mm/truncate.c
index f2aaf99f2990..91eb92a5ce4f 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -425,7 +425,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 		for (i = 0; i < folio_batch_count(&fbatch); i++) {
 			struct folio *folio = fbatch.folios[i];
 
-			/* We rely upon deletion not changing page->index */
+			/* We rely upon deletion not changing folio->index */
 
 			if (xa_is_value(folio))
 				continue;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index d888c248d99f..6f740f070b3d 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1347,6 +1347,8 @@ const char * const vmstat_text[] = {
 	"numa_hint_faults",
 	"numa_hint_faults_local",
 	"numa_pages_migrated",
+	"numa_task_migrated",
+	"numa_task_swapped",
 #endif
 #ifdef CONFIG_MIGRATION
 	"pgmigrate_success",
diff --git a/mm/zpdesc.h b/mm/zpdesc.h
index 57e7a4d6c6ca..d3df316e5bb7 100644
--- a/mm/zpdesc.h
+++ b/mm/zpdesc.h
@@ -54,8 +54,8 @@ struct zpdesc {
 ZPDESC_MATCH(flags, flags);
 ZPDESC_MATCH(lru, lru);
 ZPDESC_MATCH(mapping, movable_ops);
-ZPDESC_MATCH(index, next);
-ZPDESC_MATCH(index, handle);
+ZPDESC_MATCH(__folio_index, next);
+ZPDESC_MATCH(__folio_index, handle);
 ZPDESC_MATCH(private, zspage);
 ZPDESC_MATCH(page_type, first_obj_offset);
 ZPDESC_MATCH(_refcount, _refcount);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 042d3ac3b4a3..a5bde5db58ef 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4870,7 +4870,8 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn,
 
 	if (!smp_sufficient_security(conn->hcon, pchan->sec_level,
 				     SMP_ALLOW_STK)) {
-		result = L2CAP_CR_LE_AUTHENTICATION;
+		result = pchan->sec_level == BT_SECURITY_MEDIUM ?
+			L2CAP_CR_LE_ENCRYPTION : L2CAP_CR_LE_AUTHENTICATION;
 		chan = NULL;
 		goto response_unlock;
 	}
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 261926dccc7e..14a9462fced5 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2566,7 +2566,8 @@ static int mgmt_hci_cmd_sync(struct sock *sk, struct hci_dev *hdev,
 	struct mgmt_pending_cmd *cmd;
 	int err;
 
-	if (len < sizeof(*cp))
+	if (len != (offsetof(struct mgmt_cp_hci_cmd_sync, params) +
+		    le16_to_cpu(cp->params_len)))
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_HCI_CMD_SYNC,
 				       MGMT_STATUS_INVALID_PARAMS);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 2b514d95c528..be97c440ecd5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9968,6 +9968,7 @@ int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
 
 	return dev->netdev_ops->ndo_bpf(dev, bpf);
 }
+EXPORT_SYMBOL_GPL(netif_xdp_propagate);
 
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode)
 {
@@ -10498,7 +10499,7 @@ static void dev_index_release(struct net *net, int ifindex)
 static bool from_cleanup_net(void)
 {
 #ifdef CONFIG_NET_NS
-	return current == cleanup_net_task;
+	return current == READ_ONCE(cleanup_net_task);
 #else
 	return false;
 #endif
diff --git a/net/core/devmem.h b/net/core/devmem.h
index e7ba77050b8f..0a3b28ba5c13 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -170,8 +170,9 @@ static inline void __net_devmem_dmabuf_binding_free(struct work_struct *wq)
 }
 
 static inline struct net_devmem_dmabuf_binding *
-net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
+net_devmem_bind_dmabuf(struct net_device *dev,
 		       enum dma_data_direction direction,
+		       unsigned int dmabuf_fd,
 		       struct netdev_nl_sock *priv,
 		       struct netlink_ext_ack *extack)
 {
diff --git a/net/core/filter.c b/net/core/filter.c
index ab456bf1056e..327ca73f9cd7 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1968,10 +1968,11 @@ BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset,
 	bool is_pseudo = flags & BPF_F_PSEUDO_HDR;
 	bool is_mmzero = flags & BPF_F_MARK_MANGLED_0;
 	bool do_mforce = flags & BPF_F_MARK_ENFORCE;
+	bool is_ipv6   = flags & BPF_F_IPV6;
 	__sum16 *ptr;
 
 	if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_MARK_ENFORCE |
-			       BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK)))
+			       BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK | BPF_F_IPV6)))
 		return -EINVAL;
 	if (unlikely(offset > 0xffff || offset & 1))
 		return -EFAULT;
@@ -1987,7 +1988,7 @@ BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset,
 		if (unlikely(from != 0))
 			return -EINVAL;
 
-		inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo);
+		inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo, is_ipv6);
 		break;
 	case 2:
 		inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 42ee7fce3d95..ae54f26709ca 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -654,7 +654,7 @@ static void cleanup_net(struct work_struct *work)
 	struct net *net, *tmp, *last;
 	LIST_HEAD(net_exit_list);
 
-	cleanup_net_task = current;
+	WRITE_ONCE(cleanup_net_task, current);
 
 	/* Atomically snapshot the list of namespaces to cleanup */
 	net_kill_list = llist_del_all(&cleanup_list);
@@ -704,7 +704,7 @@ static void cleanup_net(struct work_struct *work)
 		put_user_ns(net->user_ns);
 		net_passive_dec(net);
 	}
-	cleanup_net_task = NULL;
+	WRITE_ONCE(cleanup_net_task, NULL);
 }
 
 /**
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 4011eb305cee..ba7cf3e3c32f 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -153,9 +153,9 @@ u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats)
 EXPORT_SYMBOL(page_pool_ethtool_stats_get);
 
 #else
-#define alloc_stat_inc(pool, __stat)
-#define recycle_stat_inc(pool, __stat)
-#define recycle_stat_add(pool, __stat, val)
+#define alloc_stat_inc(...)	do { } while (0)
+#define recycle_stat_inc(...)	do { } while (0)
+#define recycle_stat_add(...)	do { } while (0)
 #endif
 
 static bool page_pool_producer_lock(struct page_pool *pool)
@@ -741,19 +741,16 @@ void page_pool_return_page(struct page_pool *pool, netmem_ref netmem)
 
 static bool page_pool_recycle_in_ring(struct page_pool *pool, netmem_ref netmem)
 {
-	int ret;
-	/* BH protection not needed if current is softirq */
-	if (in_softirq())
-		ret = ptr_ring_produce(&pool->ring, (__force void *)netmem);
-	else
-		ret = ptr_ring_produce_bh(&pool->ring, (__force void *)netmem);
+	bool in_softirq, ret;
 
-	if (!ret) {
+	/* BH protection not needed if current is softirq */
+	in_softirq = page_pool_producer_lock(pool);
+	ret = !__ptr_ring_produce(&pool->ring, (__force void *)netmem);
+	if (ret)
 		recycle_stat_inc(pool, ring);
-		return true;
-	}
+	page_pool_producer_unlock(pool, in_softirq);
 
-	return false;
+	return ret;
 }
 
 /* Only allow direct recycling in special circumstances, into the
@@ -1150,10 +1147,14 @@ static void page_pool_scrub(struct page_pool *pool)
 
 static int page_pool_release(struct page_pool *pool)
 {
+	bool in_softirq;
 	int inflight;
 
 	page_pool_scrub(pool);
 	inflight = page_pool_inflight(pool, true);
+	/* Acquire producer lock to make sure producers have exited. */
+	in_softirq = page_pool_producer_lock(pool);
+	page_pool_producer_unlock(pool, in_softirq);
 	if (!inflight)
 		__page_pool_destroy(pool);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f9a35bdc58ad..c57692eb8da9 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3671,7 +3671,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 	if (tb[IFLA_LINKMODE])
 		dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]);
 	if (tb[IFLA_GROUP])
-		dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
+		netif_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
 	if (tb[IFLA_GSO_MAX_SIZE])
 		netif_set_gso_max_size(dev, nla_get_u32(tb[IFLA_GSO_MAX_SIZE]));
 	if (tb[IFLA_GSO_MAX_SEGS])
diff --git a/net/core/sock.c b/net/core/sock.c
index 341979874459..3b409bc8ef6d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3284,16 +3284,16 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind)
 {
 	struct mem_cgroup *memcg = mem_cgroup_sockets_enabled ? sk->sk_memcg : NULL;
 	struct proto *prot = sk->sk_prot;
-	bool charged = false;
+	bool charged = true;
 	long allocated;
 
 	sk_memory_allocated_add(sk, amt);
 	allocated = sk_memory_allocated(sk);
 
 	if (memcg) {
-		if (!mem_cgroup_charge_skmem(memcg, amt, gfp_memcg_charge()))
+		charged = mem_cgroup_charge_skmem(memcg, amt, gfp_memcg_charge());
+		if (!charged)
 			goto suppress_allocation;
-		charged = true;
 	}
 
 	/* Under limit. */
@@ -3378,7 +3378,7 @@ suppress_allocation:
 
 	sk_memory_allocated_sub(sk, amt);
 
-	if (charged)
+	if (memcg && charged)
 		mem_cgroup_uncharge_skmem(memcg, amt);
 
 	return 0;
diff --git a/net/core/utils.c b/net/core/utils.c
index e47feeaa5a49..5e63b0ea21f3 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -473,11 +473,11 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
 EXPORT_SYMBOL(inet_proto_csum_replace16);
 
 void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb,
-				     __wsum diff, bool pseudohdr)
+				     __wsum diff, bool pseudohdr, bool ipv6)
 {
 	if (skb->ip_summed != CHECKSUM_PARTIAL) {
 		csum_replace_by_diff(sum, diff);
-		if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr)
+		if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr && !ipv6)
 			skb->csum = ~csum_sub(diff, skb->csum);
 	} else if (pseudohdr) {
 		*sum = ~csum_fold(csum_add(diff, csum_unfold(*sum)));
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 8c3c068728e5..fe75821623a4 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -257,7 +257,7 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb,
 	int source_port;
 	u8 *brcm_tag;
 
-	if (unlikely(!pskb_may_pull(skb, BRCM_LEG_PORT_ID)))
+	if (unlikely(!pskb_may_pull(skb, BRCM_LEG_TAG_LEN + VLAN_HLEN)))
 		return NULL;
 
 	brcm_tag = dsa_etype_header_pos_rx(skb);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 9c775f8aa438..85b5aa82d7d7 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -495,6 +495,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 	bool copy_dtor;
 	__sum16 check;
 	__be16 newlen;
+	int ret = 0;
 
 	mss = skb_shinfo(gso_skb)->gso_size;
 	if (gso_skb->len <= sizeof(*uh) + mss)
@@ -523,6 +524,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 		if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size)
 			return __udp_gso_segment_list(gso_skb, features, is_ipv6);
 
+		ret = __skb_linearize(gso_skb);
+		if (ret)
+			return ERR_PTR(ret);
+
 		 /* Setup csum, as fraglist skips this in udp4_gro_receive. */
 		gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head;
 		gso_skb->csum_offset = offsetof(struct udphdr, check);
diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c
index 95e9146918cc..b8d43ed4689d 100644
--- a/net/ipv6/ila/ila_common.c
+++ b/net/ipv6/ila/ila_common.c
@@ -86,7 +86,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb,
 
 			diff = get_csum_diff(ip6h, p);
 			inet_proto_csum_replace_by_diff(&th->check, skb,
-							diff, true);
+							diff, true, true);
 		}
 		break;
 	case NEXTHDR_UDP:
@@ -97,7 +97,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb,
 			if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
 				diff = get_csum_diff(ip6h, p);
 				inet_proto_csum_replace_by_diff(&uh->check, skb,
-								diff, true);
+								diff, true, true);
 				if (!uh->check)
 					uh->check = CSUM_MANGLED_0;
 			}
@@ -111,7 +111,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb,
 
 			diff = get_csum_diff(ip6h, p);
 			inet_proto_csum_replace_by_diff(&ih->icmp6_cksum, skb,
-							diff, true);
+							diff, true, true);
 		}
 		break;
 	}
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index ac1dbd492c22..a11a02b4ba95 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -1644,10 +1644,8 @@ static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = {
 	[SEG6_LOCAL_SRH]	= { .type = NLA_BINARY },
 	[SEG6_LOCAL_TABLE]	= { .type = NLA_U32 },
 	[SEG6_LOCAL_VRFTABLE]	= { .type = NLA_U32 },
-	[SEG6_LOCAL_NH4]	= { .type = NLA_BINARY,
-				    .len = sizeof(struct in_addr) },
-	[SEG6_LOCAL_NH6]	= { .type = NLA_BINARY,
-				    .len = sizeof(struct in6_addr) },
+	[SEG6_LOCAL_NH4]	= NLA_POLICY_EXACT_LEN(sizeof(struct in_addr)),
+	[SEG6_LOCAL_NH6]	= NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
 	[SEG6_LOCAL_IIF]	= { .type = NLA_U32 },
 	[SEG6_LOCAL_OIF]	= { .type = NLA_U32 },
 	[SEG6_LOCAL_BPF]	= { .type = NLA_NESTED },
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index b84150dbfe8c..948909a242d6 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7220,11 +7220,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
 	bssid = ieee80211_get_bssid(hdr, len, sdata->vif.type);
 	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
 		struct ieee80211_ext *ext = (void *) mgmt;
-
-		if (ieee80211_is_s1g_short_beacon(ext->frame_control))
-			variable = ext->u.s1g_short_beacon.variable;
-		else
-			variable = ext->u.s1g_beacon.variable;
+		variable = ext->u.s1g_beacon.variable +
+			   ieee80211_s1g_optional_len(ext->frame_control);
 	}
 
 	baselen = (u8 *) variable - (u8 *) mgmt;
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 7b8da40a912d..cd8385ecafd9 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -276,6 +276,7 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 	struct ieee80211_mgmt *mgmt = (void *)skb->data;
 	struct ieee80211_bss *bss;
 	struct ieee80211_channel *channel;
+	struct ieee80211_ext *ext;
 	size_t min_hdr_len = offsetof(struct ieee80211_mgmt,
 				      u.probe_resp.variable);
 
@@ -285,12 +286,10 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 		return;
 
 	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
-		if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
-			min_hdr_len = offsetof(struct ieee80211_ext,
-					       u.s1g_short_beacon.variable);
-		else
-			min_hdr_len = offsetof(struct ieee80211_ext,
-					       u.s1g_beacon);
+		ext = (struct ieee80211_ext *)mgmt;
+		min_hdr_len =
+			offsetof(struct ieee80211_ext, u.s1g_beacon.variable) +
+			ieee80211_s1g_optional_len(ext->frame_control);
 	}
 
 	if (skb->len < min_hdr_len)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index aad84aabd7f1..f391cd267922 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -248,7 +248,7 @@ static noinline bool
 nf_nat_used_tuple_new(const struct nf_conntrack_tuple *tuple,
 		      const struct nf_conn *ignored_ct)
 {
-	static const unsigned long uses_nat = IPS_NAT_MASK | IPS_SEQ_ADJUST_BIT;
+	static const unsigned long uses_nat = IPS_NAT_MASK | IPS_SEQ_ADJUST;
 	const struct nf_conntrack_tuple_hash *thash;
 	const struct nf_conntrack_zone *zone;
 	struct nf_conn *ct;
@@ -287,8 +287,14 @@ nf_nat_used_tuple_new(const struct nf_conntrack_tuple *tuple,
 	zone = nf_ct_zone(ignored_ct);
 
 	thash = nf_conntrack_find_get(net, zone, tuple);
-	if (unlikely(!thash)) /* clashing entry went away */
-		return false;
+	if (unlikely(!thash)) {
+		struct nf_conntrack_tuple reply;
+
+		nf_ct_invert_tuple(&reply, tuple);
+		thash = nf_conntrack_find_get(net, zone, &reply);
+		if (!thash) /* clashing entry went away */
+			return false;
+	}
 
 	ct = nf_ct_tuplehash_to_ctrack(thash);
 
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index c15db28c5ebc..be7c16c79f71 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1114,6 +1114,25 @@ bool nft_pipapo_avx2_estimate(const struct nft_set_desc *desc, u32 features,
 }
 
 /**
+ * pipapo_resmap_init_avx2() - Initialise result map before first use
+ * @m:		Matching data, including mapping table
+ * @res_map:	Result map
+ *
+ * Like pipapo_resmap_init() but do not set start map bits covered by the first field.
+ */
+static inline void pipapo_resmap_init_avx2(const struct nft_pipapo_match *m, unsigned long *res_map)
+{
+	const struct nft_pipapo_field *f = m->f;
+	int i;
+
+	/* Starting map doesn't need to be set to all-ones for this implementation,
+	 * but we do need to zero the remaining bits, if any.
+	 */
+	for (i = f->bsize; i < m->bsize_max; i++)
+		res_map[i] = 0ul;
+}
+
+/**
  * nft_pipapo_avx2_lookup() - Lookup function for AVX2 implementation
  * @net:	Network namespace
  * @set:	nftables API set representation
@@ -1171,7 +1190,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	res  = scratch->map + (map_index ? m->bsize_max : 0);
 	fill = scratch->map + (map_index ? 0 : m->bsize_max);
 
-	/* Starting map doesn't need to be set for this implementation */
+	pipapo_resmap_init_avx2(m, res);
 
 	nft_pipapo_avx2_prepare();
 
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index 6ea16138582c..33b77084a4e5 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -1165,8 +1165,10 @@ int netlbl_conn_setattr(struct sock *sk,
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
-		if (sk->sk_family != AF_INET6)
-			return -EAFNOSUPPORT;
+		if (sk->sk_family != AF_INET6) {
+			ret_val = -EAFNOSUPPORT;
+			goto conn_setattr_return;
+		}
 
 		addr6 = (struct sockaddr_in6 *)addr;
 		entry = netlbl_domhsh_getentry_af6(secattr->domain,
diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c
index 1f7c136d6d0e..0a260df45d25 100644
--- a/net/rxrpc/insecure.c
+++ b/net/rxrpc/insecure.c
@@ -45,8 +45,9 @@ static void none_free_call_crypto(struct rxrpc_call *call)
 static bool none_validate_challenge(struct rxrpc_connection *conn,
 				    struct sk_buff *skb)
 {
-	return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
-				rxrpc_eproto_rxnull_challenge);
+	rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+			 rxrpc_eproto_rxnull_challenge);
+	return true;
 }
 
 static int none_sendmsg_respond_to_challenge(struct sk_buff *challenge,
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 369310909fc9..0fa244f16876 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1545,6 +1545,7 @@ static int gss_marshal(struct rpc_task *task, struct xdr_stream *xdr)
 	struct kvec	iov;
 	struct xdr_buf	verf_buf;
 	int status;
+	u32 seqno;
 
 	/* Credential */
 
@@ -1556,15 +1557,16 @@ static int gss_marshal(struct rpc_task *task, struct xdr_stream *xdr)
 	cred_len = p++;
 
 	spin_lock(&ctx->gc_seq_lock);
-	req->rq_seqno = (ctx->gc_seq < MAXSEQ) ? ctx->gc_seq++ : MAXSEQ;
+	seqno = (ctx->gc_seq < MAXSEQ) ? ctx->gc_seq++ : MAXSEQ;
+	xprt_rqst_add_seqno(req, seqno);
 	spin_unlock(&ctx->gc_seq_lock);
-	if (req->rq_seqno == MAXSEQ)
+	if (*req->rq_seqnos == MAXSEQ)
 		goto expired;
 	trace_rpcgss_seqno(task);
 
 	*p++ = cpu_to_be32(RPC_GSS_VERSION);
 	*p++ = cpu_to_be32(ctx->gc_proc);
-	*p++ = cpu_to_be32(req->rq_seqno);
+	*p++ = cpu_to_be32(*req->rq_seqnos);
 	*p++ = cpu_to_be32(gss_cred->gc_service);
 	p = xdr_encode_netobj(p, &ctx->gc_wire_ctx);
 	*cred_len = cpu_to_be32((p - (cred_len + 1)) << 2);
@@ -1678,17 +1680,31 @@ gss_refresh_null(struct rpc_task *task)
 	return 0;
 }
 
+static u32
+gss_validate_seqno_mic(struct gss_cl_ctx *ctx, u32 seqno, __be32 *seq, __be32 *p, u32 len)
+{
+	struct kvec iov;
+	struct xdr_buf verf_buf;
+	struct xdr_netobj mic;
+
+	*seq = cpu_to_be32(seqno);
+	iov.iov_base = seq;
+	iov.iov_len = 4;
+	xdr_buf_from_iov(&iov, &verf_buf);
+	mic.data = (u8 *)p;
+	mic.len = len;
+	return gss_verify_mic(ctx->gc_gss_ctx, &verf_buf, &mic);
+}
+
 static int
 gss_validate(struct rpc_task *task, struct xdr_stream *xdr)
 {
 	struct rpc_cred *cred = task->tk_rqstp->rq_cred;
 	struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
 	__be32		*p, *seq = NULL;
-	struct kvec	iov;
-	struct xdr_buf	verf_buf;
-	struct xdr_netobj mic;
 	u32		len, maj_stat;
 	int		status;
+	int		i = 1; /* don't recheck the first item */
 
 	p = xdr_inline_decode(xdr, 2 * sizeof(*p));
 	if (!p)
@@ -1705,13 +1721,10 @@ gss_validate(struct rpc_task *task, struct xdr_stream *xdr)
 	seq = kmalloc(4, GFP_KERNEL);
 	if (!seq)
 		goto validate_failed;
-	*seq = cpu_to_be32(task->tk_rqstp->rq_seqno);
-	iov.iov_base = seq;
-	iov.iov_len = 4;
-	xdr_buf_from_iov(&iov, &verf_buf);
-	mic.data = (u8 *)p;
-	mic.len = len;
-	maj_stat = gss_verify_mic(ctx->gc_gss_ctx, &verf_buf, &mic);
+	maj_stat = gss_validate_seqno_mic(ctx, task->tk_rqstp->rq_seqnos[0], seq, p, len);
+	/* RFC 2203 5.3.3.1 - compute the checksum of each sequence number in the cache */
+	while (unlikely(maj_stat == GSS_S_BAD_SIG && i < task->tk_rqstp->rq_seqno_count))
+		maj_stat = gss_validate_seqno_mic(ctx, task->tk_rqstp->rq_seqnos[i], seq, p, len);
 	if (maj_stat == GSS_S_CONTEXT_EXPIRED)
 		clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags);
 	if (maj_stat)
@@ -1750,7 +1763,7 @@ gss_wrap_req_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx,
 	if (!p)
 		goto wrap_failed;
 	integ_len = p++;
-	*p = cpu_to_be32(rqstp->rq_seqno);
+	*p = cpu_to_be32(*rqstp->rq_seqnos);
 
 	if (rpcauth_wrap_req_encode(task, xdr))
 		goto wrap_failed;
@@ -1847,7 +1860,7 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx,
 	if (!p)
 		goto wrap_failed;
 	opaque_len = p++;
-	*p = cpu_to_be32(rqstp->rq_seqno);
+	*p = cpu_to_be32(*rqstp->rq_seqnos);
 
 	if (rpcauth_wrap_req_encode(task, xdr))
 		goto wrap_failed;
@@ -2001,7 +2014,7 @@ gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred,
 	offset = rcv_buf->len - xdr_stream_remaining(xdr);
 	if (xdr_stream_decode_u32(xdr, &seqno))
 		goto unwrap_failed;
-	if (seqno != rqstp->rq_seqno)
+	if (seqno != *rqstp->rq_seqnos)
 		goto bad_seqno;
 	if (xdr_buf_subsegment(rcv_buf, &gss_data, offset, len))
 		goto unwrap_failed;
@@ -2045,7 +2058,7 @@ unwrap_failed:
 	trace_rpcgss_unwrap_failed(task);
 	goto out;
 bad_seqno:
-	trace_rpcgss_bad_seqno(task, rqstp->rq_seqno, seqno);
+	trace_rpcgss_bad_seqno(task, *rqstp->rq_seqnos, seqno);
 	goto out;
 bad_mic:
 	trace_rpcgss_verify_mic(task, maj_stat);
@@ -2077,7 +2090,7 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred,
 	if (maj_stat != GSS_S_COMPLETE)
 		goto bad_unwrap;
 	/* gss_unwrap decrypted the sequence number */
-	if (be32_to_cpup(p++) != rqstp->rq_seqno)
+	if (be32_to_cpup(p++) != *rqstp->rq_seqnos)
 		goto bad_seqno;
 
 	/* gss_unwrap redacts the opaque blob from the head iovec.
@@ -2093,7 +2106,7 @@ unwrap_failed:
 	trace_rpcgss_unwrap_failed(task);
 	return -EIO;
 bad_seqno:
-	trace_rpcgss_bad_seqno(task, rqstp->rq_seqno, be32_to_cpup(--p));
+	trace_rpcgss_bad_seqno(task, *rqstp->rq_seqnos, be32_to_cpup(--p));
 	return -EIO;
 bad_unwrap:
 	trace_rpcgss_unwrap(task, maj_stat);
@@ -2118,14 +2131,14 @@ gss_xmit_need_reencode(struct rpc_task *task)
 	if (!ctx)
 		goto out;
 
-	if (gss_seq_is_newer(req->rq_seqno, READ_ONCE(ctx->gc_seq)))
+	if (gss_seq_is_newer(*req->rq_seqnos, READ_ONCE(ctx->gc_seq)))
 		goto out_ctx;
 
 	seq_xmit = READ_ONCE(ctx->gc_seq_xmit);
-	while (gss_seq_is_newer(req->rq_seqno, seq_xmit)) {
+	while (gss_seq_is_newer(*req->rq_seqnos, seq_xmit)) {
 		u32 tmp = seq_xmit;
 
-		seq_xmit = cmpxchg(&ctx->gc_seq_xmit, tmp, req->rq_seqno);
+		seq_xmit = cmpxchg(&ctx->gc_seq_xmit, tmp, *req->rq_seqnos);
 		if (seq_xmit == tmp) {
 			ret = false;
 			goto out_ctx;
@@ -2134,7 +2147,7 @@ gss_xmit_need_reencode(struct rpc_task *task)
 
 	win = ctx->gc_win;
 	if (win > 0)
-		ret = !gss_seq_is_newer(req->rq_seqno, seq_xmit - win);
+		ret = !gss_seq_is_newer(*req->rq_seqnos, seq_xmit - win);
 
 out_ctx:
 	gss_put_ctx(ctx);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 6f75862d9782..21426c3049d3 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2771,8 +2771,13 @@ out_verifier:
 	case -EPROTONOSUPPORT:
 		goto out_err;
 	case -EACCES:
-		/* Re-encode with a fresh cred */
-		fallthrough;
+		/* possible RPCSEC_GSS out-of-sequence event (RFC2203),
+		 * reset recv state and keep waiting, don't retransmit
+		 */
+		task->tk_rqstp->rq_reply_bytes_recvd = 0;
+		task->tk_status = xprt_request_enqueue_receive(task);
+		task->tk_action = call_transmit_status;
+		return -EBADMSG;
 	default:
 		goto out_garbage;
 	}
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 0eab15465511..d5e0cdcad9e0 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1365,7 +1365,7 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
 				INIT_LIST_HEAD(&req->rq_xmit2);
 				goto out;
 			}
-		} else if (!req->rq_seqno) {
+		} else if (req->rq_seqno_count == 0) {
 			list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) {
 				if (pos->rq_task->tk_owner != task->tk_owner)
 					continue;
@@ -1898,6 +1898,7 @@ xprt_request_init(struct rpc_task *task)
 	req->rq_snd_buf.bvec = NULL;
 	req->rq_rcv_buf.bvec = NULL;
 	req->rq_release_snd_buf = NULL;
+	req->rq_seqno_count = 0;
 	xprt_init_majortimeo(task, req, task->tk_client->cl_timeout);
 
 	trace_xprt_reserve(req);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 83cc095846d3..04ff66758fc3 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2726,20 +2726,14 @@ static void xs_tcp_tls_setup_socket(struct work_struct *work)
 	if (status)
 		goto out_close;
 	xprt_release_write(lower_xprt, NULL);
-
 	trace_rpc_socket_connect(upper_xprt, upper_transport->sock, 0);
-	if (!xprt_test_and_set_connected(upper_xprt)) {
-		upper_xprt->connect_cookie++;
-		clear_bit(XPRT_SOCK_CONNECTING, &upper_transport->sock_state);
-		xprt_clear_connecting(upper_xprt);
-
-		upper_xprt->stat.connect_count++;
-		upper_xprt->stat.connect_time += (long)jiffies -
-					   upper_xprt->stat.connect_start;
-		xs_run_error_worker(upper_transport, XPRT_SOCK_WAKE_PENDING);
-	}
 	rpc_shutdown_client(lower_clnt);
 
+	/* Check for ingress data that arrived before the socket's
+	 * ->data_ready callback was set up.
+	 */
+	xs_poll_check_readable(upper_transport);
+
 out_unlock:
 	current_restore_flags(pflags, PF_MEMALLOC);
 	upper_transport->clnt = NULL;
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index f4cfe88670f5..ea5bb131ebd0 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -818,7 +818,11 @@ static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb,
 	}
 
 	/* Get net to avoid freed tipc_crypto when delete namespace */
-	get_net(aead->crypto->net);
+	if (!maybe_get_net(aead->crypto->net)) {
+		tipc_bearer_put(b);
+		rc = -ENODEV;
+		goto exit;
+	}
 
 	/* Now, do encrypt */
 	rc = crypto_aead_encrypt(req);
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index ddd3a97f6609..e8a4fe44ec2d 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -3250,6 +3250,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
 	const u8 *ie;
 	size_t ielen;
 	u64 tsf;
+	size_t s1g_optional_len;
 
 	if (WARN_ON(!mgmt))
 		return NULL;
@@ -3264,12 +3265,11 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
 
 	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
 		ext = (void *) mgmt;
-		if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
-			min_hdr_len = offsetof(struct ieee80211_ext,
-					       u.s1g_short_beacon.variable);
-		else
-			min_hdr_len = offsetof(struct ieee80211_ext,
-					       u.s1g_beacon.variable);
+		s1g_optional_len =
+			ieee80211_s1g_optional_len(ext->frame_control);
+		min_hdr_len =
+			offsetof(struct ieee80211_ext, u.s1g_beacon.variable) +
+			s1g_optional_len;
 	} else {
 		/* same for beacons */
 		min_hdr_len = offsetof(struct ieee80211_mgmt,
@@ -3285,11 +3285,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
 		const struct ieee80211_s1g_bcn_compat_ie *compat;
 		const struct element *elem;
 
-		if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
-			ie = ext->u.s1g_short_beacon.variable;
-		else
-			ie = ext->u.s1g_beacon.variable;
-
+		ie = ext->u.s1g_beacon.variable + s1g_optional_len;
 		elem = cfg80211_find_elem(WLAN_EID_S1G_BCN_COMPAT, ie, ielen);
 		if (!elem)
 			return NULL;
diff --git a/rust/Makefile b/rust/Makefile
index 3aca903a7d08..27dec7904c3a 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -60,6 +60,8 @@ endif
 core-cfgs = \
     --cfg no_fp_fmt_parse
 
+core-edition := $(if $(call rustc-min-version,108700),2024,2021)
+
 # `rustc` recognizes `--remap-path-prefix` since 1.26.0, but `rustdoc` only
 # since Rust 1.81.0. Moreover, `rustdoc` ICEs on out-of-tree builds since Rust
 # 1.82.0 (https://github.com/rust-lang/rust/issues/138520). Thus workaround both
@@ -106,8 +108,8 @@ rustdoc-macros: $(src)/macros/lib.rs FORCE
 
 # Starting with Rust 1.82.0, skipping `-Wrustdoc::unescaped_backticks` should
 # not be needed -- see https://github.com/rust-lang/rust/pull/128307.
-rustdoc-core: private skip_flags = -Wrustdoc::unescaped_backticks
-rustdoc-core: private rustc_target_flags = $(core-cfgs)
+rustdoc-core: private skip_flags = --edition=2021 -Wrustdoc::unescaped_backticks
+rustdoc-core: private rustc_target_flags = --edition=$(core-edition) $(core-cfgs)
 rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs FORCE
 	+$(call if_changed,rustdoc)
 
@@ -273,7 +275,7 @@ bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \
 	-fzero-call-used-regs=% -fno-stack-clash-protection \
 	-fno-inline-functions-called-once -fsanitize=bounds-strict \
 	-fstrict-flex-arrays=% -fmin-function-alignment=% \
-	-fzero-init-padding-bits=% \
+	-fzero-init-padding-bits=% -mno-fdpic \
 	--param=% --param asan-%
 
 # Derived from `scripts/Makefile.clang`.
@@ -402,7 +404,8 @@ quiet_cmd_rustc_procmacro = $(RUSTC_OR_CLIPPY_QUIET) P $@
 		-Clink-args='$(call escsq,$(KBUILD_PROCMACROLDFLAGS))' \
 		--emit=dep-info=$(depfile) --emit=link=$@ --extern proc_macro \
 		--crate-type proc-macro \
-		--crate-name $(patsubst lib%.$(libmacros_extension),%,$(notdir $@)) $<
+		--crate-name $(patsubst lib%.$(libmacros_extension),%,$(notdir $@)) \
+		@$(objtree)/include/generated/rustc_cfg $<
 
 # Procedural macros can only be used with the `rustc` that compiled it.
 $(obj)/$(libmacros_name): $(src)/macros/lib.rs FORCE
@@ -416,7 +419,7 @@ quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L
       cmd_rustc_library = \
 	OBJTREE=$(abspath $(objtree)) \
 	$(if $(skip_clippy),$(RUSTC),$(RUSTC_OR_CLIPPY)) \
-		$(filter-out $(skip_flags),$(rust_flags) $(rustc_target_flags)) \
+		$(filter-out $(skip_flags),$(rust_flags)) $(rustc_target_flags) \
 		--emit=dep-info=$(depfile) --emit=obj=$@ \
 		--emit=metadata=$(dir $@)$(patsubst %.o,lib%.rmeta,$(notdir $@)) \
 		--crate-type rlib -L$(objtree)/$(obj) \
@@ -427,7 +430,7 @@ quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L
 
 rust-analyzer:
 	$(Q)MAKEFLAGS= $(srctree)/scripts/generate_rust_analyzer.py \
-		--cfgs='core=$(core-cfgs)' \
+		--cfgs='core=$(core-cfgs)' $(core-edition) \
 		$(realpath $(srctree)) $(realpath $(objtree)) \
 		$(rustc_sysroot) $(RUST_LIB_SRC) $(if $(KBUILD_EXTMOD),$(srcroot)) \
 		> rust-project.json
@@ -483,15 +486,16 @@ $(obj)/helpers/helpers.o: $(src)/helpers/helpers.c $(recordmcount_source) FORCE
 $(obj)/exports.o: private skip_gendwarfksyms = 1
 
 $(obj)/core.o: private skip_clippy = 1
-$(obj)/core.o: private skip_flags = -Wunreachable_pub
+$(obj)/core.o: private skip_flags = --edition=2021 -Wunreachable_pub
 $(obj)/core.o: private rustc_objcopy = $(foreach sym,$(redirect-intrinsics),--redefine-sym $(sym)=__rust$(sym))
-$(obj)/core.o: private rustc_target_flags = $(core-cfgs)
+$(obj)/core.o: private rustc_target_flags = --edition=$(core-edition) $(core-cfgs)
 $(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs \
     $(wildcard $(objtree)/include/config/RUSTC_VERSION_TEXT) FORCE
 	+$(call if_changed_rule,rustc_library)
 ifneq ($(or $(CONFIG_X86_64),$(CONFIG_X86_32)),)
 $(obj)/core.o: scripts/target.json
 endif
+KCOV_INSTRUMENT_core.o := n
 
 $(obj)/compiler_builtins.o: private skip_gendwarfksyms = 1
 $(obj)/compiler_builtins.o: private rustc_objcopy = -w -W '__*'
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index a5a6fb45d405..bc494745f67b 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -6,6 +6,28 @@
  * Sorted alphabetically.
  */
 
+/*
+ * First, avoid forward references to `enum` types.
+ *
+ * This workarounds a `bindgen` issue with them:
+ * <https://github.com/rust-lang/rust-bindgen/issues/3179>.
+ *
+ * Without this, the generated Rust type may be the wrong one (`i32`) or
+ * the proper one (typically `c_uint`) depending on how the headers are
+ * included, which in turn may depend on the particular kernel configuration
+ * or the architecture.
+ *
+ * The alternative would be to use casts and likely an
+ * `#[allow(clippy::unnecessary_cast)]` in the Rust source files. Instead,
+ * this approach allows us to keep the correct code in the source files and
+ * simply remove this section when the issue is fixed upstream and we bump
+ * the minimum `bindgen` version.
+ *
+ * This workaround may not be possible in some cases, depending on how the C
+ * headers are set up.
+ */
+#include <linux/hrtimer_types.h>
+
 #include <drm/drm_device.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
@@ -48,6 +70,7 @@
 #include <linux/tracepoint.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <linux/xarray.h>
 #include <trace/events/rust_sample.h>
 
 #if defined(CONFIG_DRM_PANIC_SCREEN_QR_CODE)
@@ -67,3 +90,8 @@ const gfp_t RUST_CONST_HELPER___GFP_HIGHMEM = ___GFP_HIGHMEM;
 const gfp_t RUST_CONST_HELPER___GFP_NOWARN = ___GFP_NOWARN;
 const blk_features_t RUST_CONST_HELPER_BLK_FEAT_ROTATIONAL = BLK_FEAT_ROTATIONAL;
 const fop_flags_t RUST_CONST_HELPER_FOP_UNSIGNED_OFFSET = FOP_UNSIGNED_OFFSET;
+
+const xa_mark_t RUST_CONST_HELPER_XA_PRESENT = XA_PRESENT;
+
+const gfp_t RUST_CONST_HELPER_XA_FLAGS_ALLOC = XA_FLAGS_ALLOC;
+const gfp_t RUST_CONST_HELPER_XA_FLAGS_ALLOC1 = XA_FLAGS_ALLOC1;
diff --git a/rust/ffi.rs b/rust/ffi.rs
index 584f75b49862..d60aad792af4 100644
--- a/rust/ffi.rs
+++ b/rust/ffi.rs
@@ -17,7 +17,7 @@ macro_rules! alias {
 
         // Check size compatibility with `core`.
         const _: () = assert!(
-            core::mem::size_of::<$name>() == core::mem::size_of::<core::ffi::$name>()
+            ::core::mem::size_of::<$name>() == ::core::mem::size_of::<::core::ffi::$name>()
         );
     )*}
 }
diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index 805307018f0e..0f1b5d115985 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -43,3 +43,4 @@
 #include "vmalloc.c"
 #include "wait.c"
 #include "workqueue.c"
+#include "xarray.c"
diff --git a/rust/helpers/xarray.c b/rust/helpers/xarray.c
new file mode 100644
index 000000000000..60b299f11451
--- /dev/null
+++ b/rust/helpers/xarray.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/xarray.h>
+
+int rust_helper_xa_err(void *entry)
+{
+	return xa_err(entry);
+}
+
+void rust_helper_xa_init_flags(struct xarray *xa, gfp_t flags)
+{
+	return xa_init_flags(xa, flags);
+}
+
+int rust_helper_xa_trylock(struct xarray *xa)
+{
+	return xa_trylock(xa);
+}
+
+void rust_helper_xa_lock(struct xarray *xa)
+{
+	return xa_lock(xa);
+}
+
+void rust_helper_xa_unlock(struct xarray *xa)
+{
+	return xa_unlock(xa);
+}
diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs
index fc9c9c41cd79..a2c49e5494d3 100644
--- a/rust/kernel/alloc.rs
+++ b/rust/kernel/alloc.rs
@@ -94,10 +94,10 @@ pub mod flags {
     ///
     /// A lower watermark is applied to allow access to "atomic reserves". The current
     /// implementation doesn't support NMI and few other strict non-preemptive contexts (e.g.
-    /// raw_spin_lock). The same applies to [`GFP_NOWAIT`].
+    /// `raw_spin_lock`). The same applies to [`GFP_NOWAIT`].
     pub const GFP_ATOMIC: Flags = Flags(bindings::GFP_ATOMIC);
 
-    /// Typical for kernel-internal allocations. The caller requires ZONE_NORMAL or a lower zone
+    /// Typical for kernel-internal allocations. The caller requires `ZONE_NORMAL` or a lower zone
     /// for direct access but can direct reclaim.
     pub const GFP_KERNEL: Flags = Flags(bindings::GFP_KERNEL);
 
diff --git a/rust/kernel/alloc/allocator_test.rs b/rust/kernel/alloc/allocator_test.rs
index c37d4c0c64e9..d19c06ef0498 100644
--- a/rust/kernel/alloc/allocator_test.rs
+++ b/rust/kernel/alloc/allocator_test.rs
@@ -4,7 +4,7 @@
 //! of those types (e.g. `CString`) use kernel allocators for instantiation.
 //!
 //! In order to allow userspace test cases to make use of such types as well, implement the
-//! `Cmalloc` allocator within the allocator_test module and type alias all kernel allocators to
+//! `Cmalloc` allocator within the `allocator_test` module and type alias all kernel allocators to
 //! `Cmalloc`. The `Cmalloc` allocator uses libc's `realloc()` function as allocator backend.
 
 #![allow(missing_docs)]
diff --git a/rust/kernel/alloc/kbox.rs b/rust/kernel/alloc/kbox.rs
index b77d32f3a58b..c386ff771d50 100644
--- a/rust/kernel/alloc/kbox.rs
+++ b/rust/kernel/alloc/kbox.rs
@@ -57,12 +57,50 @@ use pin_init::{InPlaceWrite, Init, PinInit, ZeroableOption};
 /// assert!(KVBox::<Huge>::new_uninit(GFP_KERNEL).is_ok());
 /// ```
 ///
+/// [`Box`]es can also be used to store trait objects by coercing their type:
+///
+/// ```
+/// trait FooTrait {}
+///
+/// struct FooStruct;
+/// impl FooTrait for FooStruct {}
+///
+/// let _ = KBox::new(FooStruct, GFP_KERNEL)? as KBox<dyn FooTrait>;
+/// # Ok::<(), Error>(())
+/// ```
+///
 /// # Invariants
 ///
 /// `self.0` is always properly aligned and either points to memory allocated with `A` or, for
 /// zero-sized types, is a dangling, well aligned pointer.
 #[repr(transparent)]
-pub struct Box<T: ?Sized, A: Allocator>(NonNull<T>, PhantomData<A>);
+#[cfg_attr(CONFIG_RUSTC_HAS_COERCE_POINTEE, derive(core::marker::CoercePointee))]
+pub struct Box<#[cfg_attr(CONFIG_RUSTC_HAS_COERCE_POINTEE, pointee)] T: ?Sized, A: Allocator>(
+    NonNull<T>,
+    PhantomData<A>,
+);
+
+// This is to allow coercion from `Box<T, A>` to `Box<U, A>` if `T` can be converted to the
+// dynamically-sized type (DST) `U`.
+#[cfg(not(CONFIG_RUSTC_HAS_COERCE_POINTEE))]
+impl<T, U, A> core::ops::CoerceUnsized<Box<U, A>> for Box<T, A>
+where
+    T: ?Sized + core::marker::Unsize<U>,
+    U: ?Sized,
+    A: Allocator,
+{
+}
+
+// This is to allow `Box<U, A>` to be dispatched on when `Box<T, A>` can be coerced into `Box<U,
+// A>`.
+#[cfg(not(CONFIG_RUSTC_HAS_COERCE_POINTEE))]
+impl<T, U, A> core::ops::DispatchFromDyn<Box<U, A>> for Box<T, A>
+where
+    T: ?Sized + core::marker::Unsize<U>,
+    U: ?Sized,
+    A: Allocator,
+{
+}
 
 /// Type alias for [`Box`] with a [`Kmalloc`] allocator.
 ///
@@ -101,7 +139,7 @@ pub type VBox<T> = Box<T, super::allocator::Vmalloc>;
 pub type KVBox<T> = Box<T, super::allocator::KVmalloc>;
 
 // SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee:
-// https://doc.rust-lang.org/stable/std/option/index.html#representation).
+// <https://doc.rust-lang.org/stable/std/option/index.html#representation>).
 unsafe impl<T, A: Allocator> ZeroableOption for Box<T, A> {}
 
 // SAFETY: `Box` is `Send` if `T` is `Send` because the `Box` owns a `T`.
@@ -360,68 +398,70 @@ where
     }
 }
 
-impl<T: 'static, A> ForeignOwnable for Box<T, A>
+// SAFETY: The `into_foreign` function returns a pointer that is well-aligned.
+unsafe impl<T: 'static, A> ForeignOwnable for Box<T, A>
 where
     A: Allocator,
 {
+    type PointedTo = T;
     type Borrowed<'a> = &'a T;
     type BorrowedMut<'a> = &'a mut T;
 
-    fn into_foreign(self) -> *mut crate::ffi::c_void {
-        Box::into_raw(self).cast()
+    fn into_foreign(self) -> *mut Self::PointedTo {
+        Box::into_raw(self)
     }
 
-    unsafe fn from_foreign(ptr: *mut crate::ffi::c_void) -> Self {
+    unsafe fn from_foreign(ptr: *mut Self::PointedTo) -> Self {
         // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous
         // call to `Self::into_foreign`.
-        unsafe { Box::from_raw(ptr.cast()) }
+        unsafe { Box::from_raw(ptr) }
     }
 
-    unsafe fn borrow<'a>(ptr: *mut crate::ffi::c_void) -> &'a T {
+    unsafe fn borrow<'a>(ptr: *mut Self::PointedTo) -> &'a T {
         // SAFETY: The safety requirements of this method ensure that the object remains alive and
         // immutable for the duration of 'a.
-        unsafe { &*ptr.cast() }
+        unsafe { &*ptr }
     }
 
-    unsafe fn borrow_mut<'a>(ptr: *mut crate::ffi::c_void) -> &'a mut T {
-        let ptr = ptr.cast();
+    unsafe fn borrow_mut<'a>(ptr: *mut Self::PointedTo) -> &'a mut T {
         // SAFETY: The safety requirements of this method ensure that the pointer is valid and that
         // nothing else will access the value for the duration of 'a.
         unsafe { &mut *ptr }
     }
 }
 
-impl<T: 'static, A> ForeignOwnable for Pin<Box<T, A>>
+// SAFETY: The `into_foreign` function returns a pointer that is well-aligned.
+unsafe impl<T: 'static, A> ForeignOwnable for Pin<Box<T, A>>
 where
     A: Allocator,
 {
+    type PointedTo = T;
     type Borrowed<'a> = Pin<&'a T>;
     type BorrowedMut<'a> = Pin<&'a mut T>;
 
-    fn into_foreign(self) -> *mut crate::ffi::c_void {
+    fn into_foreign(self) -> *mut Self::PointedTo {
         // SAFETY: We are still treating the box as pinned.
-        Box::into_raw(unsafe { Pin::into_inner_unchecked(self) }).cast()
+        Box::into_raw(unsafe { Pin::into_inner_unchecked(self) })
     }
 
-    unsafe fn from_foreign(ptr: *mut crate::ffi::c_void) -> Self {
+    unsafe fn from_foreign(ptr: *mut Self::PointedTo) -> Self {
         // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous
         // call to `Self::into_foreign`.
-        unsafe { Pin::new_unchecked(Box::from_raw(ptr.cast())) }
+        unsafe { Pin::new_unchecked(Box::from_raw(ptr)) }
     }
 
-    unsafe fn borrow<'a>(ptr: *mut crate::ffi::c_void) -> Pin<&'a T> {
+    unsafe fn borrow<'a>(ptr: *mut Self::PointedTo) -> Pin<&'a T> {
         // SAFETY: The safety requirements for this function ensure that the object is still alive,
         // so it is safe to dereference the raw pointer.
         // The safety requirements of `from_foreign` also ensure that the object remains alive for
         // the lifetime of the returned value.
-        let r = unsafe { &*ptr.cast() };
+        let r = unsafe { &*ptr };
 
         // SAFETY: This pointer originates from a `Pin<Box<T>>`.
         unsafe { Pin::new_unchecked(r) }
     }
 
-    unsafe fn borrow_mut<'a>(ptr: *mut crate::ffi::c_void) -> Pin<&'a mut T> {
-        let ptr = ptr.cast();
+    unsafe fn borrow_mut<'a>(ptr: *mut Self::PointedTo) -> Pin<&'a mut T> {
         // SAFETY: The safety requirements for this function ensure that the object is still alive,
         // so it is safe to dereference the raw pointer.
         // The safety requirements of `from_foreign` also ensure that the object remains alive for
diff --git a/rust/kernel/alloc/kvec.rs b/rust/kernel/alloc/kvec.rs
index 87a71fd40c3c..1a0dd852a468 100644
--- a/rust/kernel/alloc/kvec.rs
+++ b/rust/kernel/alloc/kvec.rs
@@ -2,9 +2,6 @@
 
 //! Implementation of [`Vec`].
 
-// May not be needed in Rust 1.87.0 (pending beta backport).
-#![allow(clippy::ptr_eq)]
-
 use super::{
     allocator::{KVmalloc, Kmalloc, Vmalloc},
     layout::ArrayLayout,
@@ -24,6 +21,9 @@ use core::{
     slice::SliceIndex,
 };
 
+mod errors;
+pub use self::errors::{InsertError, PushError, RemoveError};
+
 /// Create a [`KVec`] containing the arguments.
 ///
 /// New memory is allocated with `GFP_KERNEL`.
@@ -93,6 +93,8 @@ macro_rules! kvec {
 ///   without re-allocation. For ZSTs `self.layout`'s capacity is zero. However, it is legal for the
 ///   backing buffer to be larger than `layout`.
 ///
+/// - `self.len()` is always less than or equal to `self.capacity()`.
+///
 /// - The `Allocator` type `A` of the vector is the exact same `Allocator` type the backing buffer
 ///   was allocated with (and must be freed with).
 pub struct Vec<T, A: Allocator> {
@@ -186,17 +188,38 @@ where
         self.len
     }
 
-    /// Forcefully sets `self.len` to `new_len`.
+    /// Increments `self.len` by `additional`.
     ///
     /// # Safety
     ///
-    /// - `new_len` must be less than or equal to [`Self::capacity`].
-    /// - If `new_len` is greater than `self.len`, all elements within the interval
-    ///   [`self.len`,`new_len`) must be initialized.
+    /// - `additional` must be less than or equal to `self.capacity - self.len`.
+    /// - All elements within the interval [`self.len`,`self.len + additional`) must be initialized.
     #[inline]
-    pub unsafe fn set_len(&mut self, new_len: usize) {
-        debug_assert!(new_len <= self.capacity());
-        self.len = new_len;
+    pub unsafe fn inc_len(&mut self, additional: usize) {
+        // Guaranteed by the type invariant to never underflow.
+        debug_assert!(additional <= self.capacity() - self.len());
+        // INVARIANT: By the safety requirements of this method this represents the exact number of
+        // elements stored within `self`.
+        self.len += additional;
+    }
+
+    /// Decreases `self.len` by `count`.
+    ///
+    /// Returns a mutable slice to the elements forgotten by the vector. It is the caller's
+    /// responsibility to drop these elements if necessary.
+    ///
+    /// # Safety
+    ///
+    /// - `count` must be less than or equal to `self.len`.
+    unsafe fn dec_len(&mut self, count: usize) -> &mut [T] {
+        debug_assert!(count <= self.len());
+        // INVARIANT: We relinquish ownership of the elements within the range `[self.len - count,
+        // self.len)`, hence the updated value of `set.len` represents the exact number of elements
+        // stored within `self`.
+        self.len -= count;
+        // SAFETY: The memory after `self.len()` is guaranteed to contain `count` initialized
+        // elements of type `T`.
+        unsafe { slice::from_raw_parts_mut(self.as_mut_ptr().add(self.len), count) }
     }
 
     /// Returns a slice of the entire vector.
@@ -262,8 +285,8 @@ where
     /// Returns a slice of `MaybeUninit<T>` for the remaining spare capacity of the vector.
     pub fn spare_capacity_mut(&mut self) -> &mut [MaybeUninit<T>] {
         // SAFETY:
-        // - `self.len` is smaller than `self.capacity` and hence, the resulting pointer is
-        //   guaranteed to be part of the same allocated object.
+        // - `self.len` is smaller than `self.capacity` by the type invariant and hence, the
+        //   resulting pointer is guaranteed to be part of the same allocated object.
         // - `self.len` can not overflow `isize`.
         let ptr = unsafe { self.as_mut_ptr().add(self.len) } as *mut MaybeUninit<T>;
 
@@ -287,24 +310,170 @@ where
     /// ```
     pub fn push(&mut self, v: T, flags: Flags) -> Result<(), AllocError> {
         self.reserve(1, flags)?;
+        // SAFETY: The call to `reserve` was successful, so the capacity is at least one greater
+        // than the length.
+        unsafe { self.push_within_capacity_unchecked(v) };
+        Ok(())
+    }
 
-        // SAFETY:
-        // - `self.len` is smaller than `self.capacity` and hence, the resulting pointer is
-        //   guaranteed to be part of the same allocated object.
-        // - `self.len` can not overflow `isize`.
-        let ptr = unsafe { self.as_mut_ptr().add(self.len) };
+    /// Appends an element to the back of the [`Vec`] instance without reallocating.
+    ///
+    /// Fails if the vector does not have capacity for the new element.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = KVec::with_capacity(10, GFP_KERNEL)?;
+    /// for i in 0..10 {
+    ///     v.push_within_capacity(i)?;
+    /// }
+    ///
+    /// assert!(v.push_within_capacity(10).is_err());
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn push_within_capacity(&mut self, v: T) -> Result<(), PushError<T>> {
+        if self.len() < self.capacity() {
+            // SAFETY: The length is less than the capacity.
+            unsafe { self.push_within_capacity_unchecked(v) };
+            Ok(())
+        } else {
+            Err(PushError(v))
+        }
+    }
 
-        // SAFETY:
-        // - `ptr` is properly aligned and valid for writes.
-        unsafe { core::ptr::write(ptr, v) };
+    /// Appends an element to the back of the [`Vec`] instance without reallocating.
+    ///
+    /// # Safety
+    ///
+    /// The length must be less than the capacity.
+    unsafe fn push_within_capacity_unchecked(&mut self, v: T) {
+        let spare = self.spare_capacity_mut();
+
+        // SAFETY: By the safety requirements, `spare` is non-empty.
+        unsafe { spare.get_unchecked_mut(0) }.write(v);
 
         // SAFETY: We just initialised the first spare entry, so it is safe to increase the length
-        // by 1. We also know that the new length is <= capacity because of the previous call to
-        // `reserve` above.
-        unsafe { self.set_len(self.len() + 1) };
+        // by 1. We also know that the new length is <= capacity because the caller guarantees that
+        // the length is less than the capacity at the beginning of this function.
+        unsafe { self.inc_len(1) };
+    }
+
+    /// Inserts an element at the given index in the [`Vec`] instance.
+    ///
+    /// Fails if the vector does not have capacity for the new element. Panics if the index is out
+    /// of bounds.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use kernel::alloc::kvec::InsertError;
+    ///
+    /// let mut v = KVec::with_capacity(5, GFP_KERNEL)?;
+    /// for i in 0..5 {
+    ///     v.insert_within_capacity(0, i)?;
+    /// }
+    ///
+    /// assert!(matches!(v.insert_within_capacity(0, 5), Err(InsertError::OutOfCapacity(_))));
+    /// assert!(matches!(v.insert_within_capacity(1000, 5), Err(InsertError::IndexOutOfBounds(_))));
+    /// assert_eq!(v, [4, 3, 2, 1, 0]);
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn insert_within_capacity(
+        &mut self,
+        index: usize,
+        element: T,
+    ) -> Result<(), InsertError<T>> {
+        let len = self.len();
+        if index > len {
+            return Err(InsertError::IndexOutOfBounds(element));
+        }
+
+        if len >= self.capacity() {
+            return Err(InsertError::OutOfCapacity(element));
+        }
+
+        // SAFETY: This is in bounds since `index <= len < capacity`.
+        let p = unsafe { self.as_mut_ptr().add(index) };
+        // INVARIANT: This breaks the Vec invariants by making `index` contain an invalid element,
+        // but we restore the invariants below.
+        // SAFETY: Both the src and dst ranges end no later than one element after the length.
+        // Since the length is less than the capacity, both ranges are in bounds of the allocation.
+        unsafe { ptr::copy(p, p.add(1), len - index) };
+        // INVARIANT: This restores the Vec invariants.
+        // SAFETY: The pointer is in-bounds of the allocation.
+        unsafe { ptr::write(p, element) };
+        // SAFETY: Index `len` contains a valid element due to the above copy and write.
+        unsafe { self.inc_len(1) };
         Ok(())
     }
 
+    /// Removes the last element from a vector and returns it, or `None` if it is empty.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = KVec::new();
+    /// v.push(1, GFP_KERNEL)?;
+    /// v.push(2, GFP_KERNEL)?;
+    /// assert_eq!(&v, &[1, 2]);
+    ///
+    /// assert_eq!(v.pop(), Some(2));
+    /// assert_eq!(v.pop(), Some(1));
+    /// assert_eq!(v.pop(), None);
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn pop(&mut self) -> Option<T> {
+        if self.is_empty() {
+            return None;
+        }
+
+        let removed: *mut T = {
+            // SAFETY: We just checked that the length is at least one.
+            let slice = unsafe { self.dec_len(1) };
+            // SAFETY: The argument to `dec_len` was 1 so this returns a slice of length 1.
+            unsafe { slice.get_unchecked_mut(0) }
+        };
+
+        // SAFETY: The guarantees of `dec_len` allow us to take ownership of this value.
+        Some(unsafe { removed.read() })
+    }
+
+    /// Removes the element at the given index.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = kernel::kvec![1, 2, 3]?;
+    /// assert_eq!(v.remove(1)?, 2);
+    /// assert_eq!(v, [1, 3]);
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn remove(&mut self, i: usize) -> Result<T, RemoveError> {
+        let value = {
+            let value_ref = self.get(i).ok_or(RemoveError)?;
+            // INVARIANT: This breaks the invariants by invalidating the value at index `i`, but we
+            // restore the invariants below.
+            // SAFETY: The value at index `i` is valid, because otherwise we would have already
+            // failed with `RemoveError`.
+            unsafe { ptr::read(value_ref) }
+        };
+
+        // SAFETY: We checked that `i` is in-bounds.
+        let p = unsafe { self.as_mut_ptr().add(i) };
+
+        // INVARIANT: After this call, the invalid value is at the last slot, so the Vec invariants
+        // are restored after the below call to `dec_len(1)`.
+        // SAFETY: `p.add(1).add(self.len - i - 1)` is `i+1+len-i-1 == len` elements after the
+        // beginning of the vector, so this is in-bounds of the vector's allocation.
+        unsafe { ptr::copy(p.add(1), p, self.len - i - 1) };
+
+        // SAFETY: Since the check at the beginning of this call did not fail with `RemoveError`,
+        // the length is at least one.
+        unsafe { self.dec_len(1) };
+
+        Ok(value)
+    }
+
     /// Creates a new [`Vec`] instance with at least the given capacity.
     ///
     /// # Examples
@@ -398,6 +567,26 @@ where
         (ptr, len, capacity)
     }
 
+    /// Clears the vector, removing all values.
+    ///
+    /// Note that this method has no effect on the allocated capacity
+    /// of the vector.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = kernel::kvec![1, 2, 3]?;
+    ///
+    /// v.clear();
+    ///
+    /// assert!(v.is_empty());
+    /// # Ok::<(), Error>(())
+    /// ```
+    #[inline]
+    pub fn clear(&mut self) {
+        self.truncate(0);
+    }
+
     /// Ensures that the capacity exceeds the length by at least `additional` elements.
     ///
     /// # Examples
@@ -455,6 +644,80 @@ where
 
         Ok(())
     }
+
+    /// Shortens the vector, setting the length to `len` and drops the removed values.
+    /// If `len` is greater than or equal to the current length, this does nothing.
+    ///
+    /// This has no effect on the capacity and will not allocate.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = kernel::kvec![1, 2, 3]?;
+    /// v.truncate(1);
+    /// assert_eq!(v.len(), 1);
+    /// assert_eq!(&v, &[1]);
+    ///
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn truncate(&mut self, len: usize) {
+        if let Some(count) = self.len().checked_sub(len) {
+            // SAFETY: `count` is `self.len() - len` so it is guaranteed to be less than or
+            // equal to `self.len()`.
+            let ptr: *mut [T] = unsafe { self.dec_len(count) };
+
+            // SAFETY: the contract of `dec_len` guarantees that the elements in `ptr` are
+            // valid elements whose ownership has been transferred to the caller.
+            unsafe { ptr::drop_in_place(ptr) };
+        }
+    }
+
+    /// Takes ownership of all items in this vector without consuming the allocation.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = kernel::kvec![0, 1, 2, 3]?;
+    ///
+    /// for (i, j) in v.drain_all().enumerate() {
+    ///     assert_eq!(i, j);
+    /// }
+    ///
+    /// assert!(v.capacity() >= 4);
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn drain_all(&mut self) -> DrainAll<'_, T> {
+        // SAFETY: This does not underflow the length.
+        let elems = unsafe { self.dec_len(self.len()) };
+        // INVARIANT: The first `len` elements of the spare capacity are valid values, and as we
+        // just set the length to zero, we may transfer ownership to the `DrainAll` object.
+        DrainAll {
+            elements: elems.iter_mut(),
+        }
+    }
+
+    /// Removes all elements that don't match the provided closure.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = kernel::kvec![1, 2, 3, 4]?;
+    /// v.retain(|i| *i % 2 == 0);
+    /// assert_eq!(v, [2, 4]);
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn retain(&mut self, mut f: impl FnMut(&mut T) -> bool) {
+        let mut num_kept = 0;
+        let mut next_to_check = 0;
+        while let Some(to_check) = self.get_mut(next_to_check) {
+            if f(to_check) {
+                self.swap(num_kept, next_to_check);
+                num_kept += 1;
+            }
+            next_to_check += 1;
+        }
+        self.truncate(num_kept);
+    }
 }
 
 impl<T: Clone, A: Allocator> Vec<T, A> {
@@ -478,7 +741,7 @@ impl<T: Clone, A: Allocator> Vec<T, A> {
         // SAFETY:
         // - `self.len() + n < self.capacity()` due to the call to reserve above,
         // - the loop and the line above initialized the next `n` elements.
-        unsafe { self.set_len(self.len() + n) };
+        unsafe { self.inc_len(n) };
 
         Ok(())
     }
@@ -509,7 +772,7 @@ impl<T: Clone, A: Allocator> Vec<T, A> {
         //   the length by the same number.
         // - `self.len() + other.len() <= self.capacity()` is guaranteed by the preceding `reserve`
         //   call.
-        unsafe { self.set_len(self.len() + other.len()) };
+        unsafe { self.inc_len(other.len()) };
         Ok(())
     }
 
@@ -521,6 +784,33 @@ impl<T: Clone, A: Allocator> Vec<T, A> {
 
         Ok(v)
     }
+
+    /// Resizes the [`Vec`] so that `len` is equal to `new_len`.
+    ///
+    /// If `new_len` is smaller than `len`, the `Vec` is [`Vec::truncate`]d.
+    /// If `new_len` is larger, each new slot is filled with clones of `value`.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = kernel::kvec![1, 2, 3]?;
+    /// v.resize(1, 42, GFP_KERNEL)?;
+    /// assert_eq!(&v, &[1]);
+    ///
+    /// v.resize(3, 42, GFP_KERNEL)?;
+    /// assert_eq!(&v, &[1, 42, 42]);
+    ///
+    /// # Ok::<(), Error>(())
+    /// ```
+    pub fn resize(&mut self, new_len: usize, value: T, flags: Flags) -> Result<(), AllocError> {
+        match new_len.checked_sub(self.len()) {
+            Some(n) => self.extend_with(n, value, flags),
+            None => {
+                self.truncate(new_len);
+                Ok(())
+            }
+        }
+    }
 }
 
 impl<T, A> Drop for Vec<T, A>
@@ -760,12 +1050,13 @@ where
             unsafe { ptr::copy(ptr, buf.as_ptr(), len) };
             ptr = buf.as_ptr();
 
-            // SAFETY: `len` is guaranteed to be smaller than `self.layout.len()`.
+            // SAFETY: `len` is guaranteed to be smaller than `self.layout.len()` by the type
+            // invariant.
             let layout = unsafe { ArrayLayout::<T>::new_unchecked(len) };
 
-            // SAFETY: `buf` points to the start of the backing buffer and `len` is guaranteed to be
-            // smaller than `cap`. Depending on `alloc` this operation may shrink the buffer or leaves
-            // it as it is.
+            // SAFETY: `buf` points to the start of the backing buffer and `len` is guaranteed by
+            // the type invariant to be smaller than `cap`. Depending on `realloc` this operation
+            // may shrink the buffer or leave it as it is.
             ptr = match unsafe {
                 A::realloc(Some(buf.cast()), layout.into(), old_layout.into(), flags)
             } {
@@ -914,3 +1205,87 @@ where
         }
     }
 }
+
+/// An iterator that owns all items in a vector, but does not own its allocation.
+///
+/// # Invariants
+///
+/// Every `&mut T` returned by the iterator references a `T` that the iterator may take ownership
+/// of.
+pub struct DrainAll<'vec, T> {
+    elements: slice::IterMut<'vec, T>,
+}
+
+impl<'vec, T> Iterator for DrainAll<'vec, T> {
+    type Item = T;
+
+    fn next(&mut self) -> Option<T> {
+        let elem: *mut T = self.elements.next()?;
+        // SAFETY: By the type invariants, we may take ownership of this value.
+        Some(unsafe { elem.read() })
+    }
+
+    fn size_hint(&self) -> (usize, Option<usize>) {
+        self.elements.size_hint()
+    }
+}
+
+impl<'vec, T> Drop for DrainAll<'vec, T> {
+    fn drop(&mut self) {
+        if core::mem::needs_drop::<T>() {
+            let iter = core::mem::take(&mut self.elements);
+            let ptr: *mut [T] = iter.into_slice();
+            // SAFETY: By the type invariants, we own these values so we may destroy them.
+            unsafe { ptr::drop_in_place(ptr) };
+        }
+    }
+}
+
+#[macros::kunit_tests(rust_kvec_kunit)]
+mod tests {
+    use super::*;
+    use crate::prelude::*;
+
+    #[test]
+    fn test_kvec_retain() {
+        /// Verify correctness for one specific function.
+        #[expect(clippy::needless_range_loop)]
+        fn verify(c: &[bool]) {
+            let mut vec1: KVec<usize> = KVec::with_capacity(c.len(), GFP_KERNEL).unwrap();
+            let mut vec2: KVec<usize> = KVec::with_capacity(c.len(), GFP_KERNEL).unwrap();
+
+            for i in 0..c.len() {
+                vec1.push_within_capacity(i).unwrap();
+                if c[i] {
+                    vec2.push_within_capacity(i).unwrap();
+                }
+            }
+
+            vec1.retain(|i| c[*i]);
+
+            assert_eq!(vec1, vec2);
+        }
+
+        /// Add one to a binary integer represented as a boolean array.
+        fn add(value: &mut [bool]) {
+            let mut carry = true;
+            for v in value {
+                let new_v = carry != *v;
+                carry = carry && *v;
+                *v = new_v;
+            }
+        }
+
+        // This boolean array represents a function from index to boolean. We check that `retain`
+        // behaves correctly for all possible boolean arrays of every possible length less than
+        // ten.
+        let mut func = KVec::with_capacity(10, GFP_KERNEL).unwrap();
+        for len in 0..10 {
+            for _ in 0u32..1u32 << len {
+                verify(&func);
+                add(&mut func);
+            }
+            func.push_within_capacity(false).unwrap();
+        }
+    }
+}
diff --git a/rust/kernel/alloc/kvec/errors.rs b/rust/kernel/alloc/kvec/errors.rs
new file mode 100644
index 000000000000..348b8d27e102
--- /dev/null
+++ b/rust/kernel/alloc/kvec/errors.rs
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Errors for the [`Vec`] type.
+
+use core::fmt::{self, Debug, Formatter};
+use kernel::prelude::*;
+
+/// Error type for [`Vec::push_within_capacity`].
+pub struct PushError<T>(pub T);
+
+impl<T> Debug for PushError<T> {
+    fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
+        write!(f, "Not enough capacity")
+    }
+}
+
+impl<T> From<PushError<T>> for Error {
+    fn from(_: PushError<T>) -> Error {
+        // Returning ENOMEM isn't appropriate because the system is not out of memory. The vector
+        // is just full and we are refusing to resize it.
+        EINVAL
+    }
+}
+
+/// Error type for [`Vec::remove`].
+pub struct RemoveError;
+
+impl Debug for RemoveError {
+    fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
+        write!(f, "Index out of bounds")
+    }
+}
+
+impl From<RemoveError> for Error {
+    fn from(_: RemoveError) -> Error {
+        EINVAL
+    }
+}
+
+/// Error type for [`Vec::insert_within_capacity`].
+pub enum InsertError<T> {
+    /// The value could not be inserted because the index is out of bounds.
+    IndexOutOfBounds(T),
+    /// The value could not be inserted because the vector is out of capacity.
+    OutOfCapacity(T),
+}
+
+impl<T> Debug for InsertError<T> {
+    fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
+        match self {
+            InsertError::IndexOutOfBounds(_) => write!(f, "Index out of bounds"),
+            InsertError::OutOfCapacity(_) => write!(f, "Not enough capacity"),
+        }
+    }
+}
+
+impl<T> From<InsertError<T>> for Error {
+    fn from(_: InsertError<T>) -> Error {
+        EINVAL
+    }
+}
diff --git a/rust/kernel/auxiliary.rs b/rust/kernel/auxiliary.rs
index 5c072960dee0..d2cfe1eeefb6 100644
--- a/rust/kernel/auxiliary.rs
+++ b/rust/kernel/auxiliary.rs
@@ -73,7 +73,9 @@ impl<T: Driver + 'static> Adapter<T> {
                 // Let the `struct auxiliary_device` own a reference of the driver's private data.
                 // SAFETY: By the type invariant `adev.as_raw` returns a valid pointer to a
                 // `struct auxiliary_device`.
-                unsafe { bindings::auxiliary_set_drvdata(adev.as_raw(), data.into_foreign()) };
+                unsafe {
+                    bindings::auxiliary_set_drvdata(adev.as_raw(), data.into_foreign().cast())
+                };
             }
             Err(err) => return Error::to_errno(err),
         }
@@ -89,7 +91,7 @@ impl<T: Driver + 'static> Adapter<T> {
         // SAFETY: `remove_callback` is only ever called after a successful call to
         // `probe_callback`, hence it's guaranteed that `ptr` points to a valid and initialized
         // `KBox<T>` pointer created through `KBox::into_foreign`.
-        drop(unsafe { KBox::<T>::from_foreign(ptr) });
+        drop(unsafe { KBox::<T>::from_foreign(ptr.cast()) });
     }
 }
 
@@ -234,7 +236,7 @@ impl Device {
     extern "C" fn release(dev: *mut bindings::device) {
         // SAFETY: By the type invariant `self.0.as_raw` is a pointer to the `struct device`
         // embedded in `struct auxiliary_device`.
-        let adev = unsafe { container_of!(dev, bindings::auxiliary_device, dev) }.cast_mut();
+        let adev = unsafe { container_of!(dev, bindings::auxiliary_device, dev) };
 
         // SAFETY: `adev` points to the memory that has been allocated in `Registration::new`, via
         // `KBox::new(Opaque::<bindings::auxiliary_device>::zeroed(), GFP_KERNEL)`.
diff --git a/rust/kernel/block/mq/gen_disk.rs b/rust/kernel/block/mq/gen_disk.rs
index 14806e1997fd..cd54cd64ea88 100644
--- a/rust/kernel/block/mq/gen_disk.rs
+++ b/rust/kernel/block/mq/gen_disk.rs
@@ -129,7 +129,7 @@ impl GenDiskBuilder {
             get_unique_id: None,
             // TODO: Set to THIS_MODULE. Waiting for const_refs_to_static feature to
             // be merged (unstable in rustc 1.78 which is staged for linux 6.10)
-            // https://github.com/rust-lang/rust/issues/119618
+            // <https://github.com/rust-lang/rust/issues/119618>
             owner: core::ptr::null_mut(),
             pr_ops: core::ptr::null_mut(),
             free_disk: None,
diff --git a/rust/kernel/configfs.rs b/rust/kernel/configfs.rs
index b93ac7b0bebc..34d0bea4f9a5 100644
--- a/rust/kernel/configfs.rs
+++ b/rust/kernel/configfs.rs
@@ -554,7 +554,7 @@ where
         let c_group: *mut bindings::config_group =
             // SAFETY: By function safety requirements, `item` is embedded in a
             // `config_group`.
-            unsafe { container_of!(item, bindings::config_group, cg_item) }.cast_mut();
+            unsafe { container_of!(item, bindings::config_group, cg_item) };
 
         // SAFETY: The function safety requirements for this function satisfy
         // the conditions for this call.
@@ -588,7 +588,7 @@ where
         let c_group: *mut bindings::config_group =
         // SAFETY: By function safety requirements, `item` is embedded in a
         // `config_group`.
-            unsafe { container_of!(item, bindings::config_group, cg_item) }.cast_mut();
+            unsafe { container_of!(item, bindings::config_group, cg_item) };
 
         // SAFETY: The function safety requirements for this function satisfy
         // the conditions for this call.
diff --git a/rust/kernel/cpufreq.rs b/rust/kernel/cpufreq.rs
index 09b856bb297b..b0a9c6182aec 100644
--- a/rust/kernel/cpufreq.rs
+++ b/rust/kernel/cpufreq.rs
@@ -635,7 +635,7 @@ impl Policy {
             None
         } else {
             // SAFETY: The data is earlier set from [`set_data`].
-            Some(unsafe { T::borrow(self.as_ref().driver_data) })
+            Some(unsafe { T::borrow(self.as_ref().driver_data.cast()) })
         }
     }
 
@@ -662,7 +662,7 @@ impl Policy {
             let data = Some(
                 // SAFETY: The data is earlier set by us from [`set_data`]. It is safe to take
                 // back the ownership of the data from the foreign interface.
-                unsafe { <T as ForeignOwnable>::from_foreign(self.as_ref().driver_data) },
+                unsafe { <T as ForeignOwnable>::from_foreign(self.as_ref().driver_data.cast()) },
             );
             self.as_mut_ref().driver_data = ptr::null_mut();
             data
diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs
index f08583fa39c9..dea06b79ecb5 100644
--- a/rust/kernel/device.rs
+++ b/rust/kernel/device.rs
@@ -345,7 +345,7 @@ macro_rules! impl_device_context_into_aref {
 macro_rules! dev_printk {
     ($method:ident, $dev:expr, $($f:tt)*) => {
         {
-            ($dev).$method(core::format_args!($($f)*));
+            ($dev).$method(::core::format_args!($($f)*));
         }
     }
 }
@@ -357,9 +357,10 @@ macro_rules! dev_printk {
 /// Equivalent to the kernel's `dev_emerg` macro.
 ///
 /// Mimics the interface of [`std::print!`]. More information about the syntax is available from
-/// [`core::fmt`] and `alloc::format!`.
+/// [`core::fmt`] and [`std::format!`].
 ///
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -382,9 +383,10 @@ macro_rules! dev_emerg {
 /// Equivalent to the kernel's `dev_alert` macro.
 ///
 /// Mimics the interface of [`std::print!`]. More information about the syntax is available from
-/// [`core::fmt`] and `alloc::format!`.
+/// [`core::fmt`] and [`std::format!`].
 ///
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -407,9 +409,10 @@ macro_rules! dev_alert {
 /// Equivalent to the kernel's `dev_crit` macro.
 ///
 /// Mimics the interface of [`std::print!`]. More information about the syntax is available from
-/// [`core::fmt`] and `alloc::format!`.
+/// [`core::fmt`] and [`std::format!`].
 ///
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -432,9 +435,10 @@ macro_rules! dev_crit {
 /// Equivalent to the kernel's `dev_err` macro.
 ///
 /// Mimics the interface of [`std::print!`]. More information about the syntax is available from
-/// [`core::fmt`] and `alloc::format!`.
+/// [`core::fmt`] and [`std::format!`].
 ///
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -457,9 +461,10 @@ macro_rules! dev_err {
 /// Equivalent to the kernel's `dev_warn` macro.
 ///
 /// Mimics the interface of [`std::print!`]. More information about the syntax is available from
-/// [`core::fmt`] and `alloc::format!`.
+/// [`core::fmt`] and [`std::format!`].
 ///
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -482,9 +487,10 @@ macro_rules! dev_warn {
 /// Equivalent to the kernel's `dev_notice` macro.
 ///
 /// Mimics the interface of [`std::print!`]. More information about the syntax is available from
-/// [`core::fmt`] and `alloc::format!`.
+/// [`core::fmt`] and [`std::format!`].
 ///
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -507,9 +513,10 @@ macro_rules! dev_notice {
 /// Equivalent to the kernel's `dev_info` macro.
 ///
 /// Mimics the interface of [`std::print!`]. More information about the syntax is available from
-/// [`core::fmt`] and `alloc::format!`.
+/// [`core::fmt`] and [`std::format!`].
 ///
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -532,9 +539,10 @@ macro_rules! dev_info {
 /// Equivalent to the kernel's `dev_dbg` macro, except that it doesn't support dynamic debug yet.
 ///
 /// Mimics the interface of [`std::print!`]. More information about the syntax is available from
-/// [`core::fmt`] and `alloc::format!`.
+/// [`core::fmt`] and [`std::format!`].
 ///
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
diff --git a/rust/kernel/device_id.rs b/rust/kernel/device_id.rs
index e5859217a579..0a4eb56d98f2 100644
--- a/rust/kernel/device_id.rs
+++ b/rust/kernel/device_id.rs
@@ -159,7 +159,7 @@ macro_rules! module_device_table {
                     "_", line!(),
                     "_", stringify!($table_name))
         ]
-        static $module_table_name: [core::mem::MaybeUninit<u8>; $table_name.raw_ids().size()] =
-            unsafe { core::mem::transmute_copy($table_name.raw_ids()) };
+        static $module_table_name: [::core::mem::MaybeUninit<u8>; $table_name.raw_ids().size()] =
+            unsafe { ::core::mem::transmute_copy($table_name.raw_ids()) };
     };
 }
diff --git a/rust/kernel/dma.rs b/rust/kernel/dma.rs
index 605e01e35715..a33261c62e0c 100644
--- a/rust/kernel/dma.rs
+++ b/rust/kernel/dma.rs
@@ -94,7 +94,7 @@ pub mod attrs {
     pub const DMA_ATTR_ALLOC_SINGLE_PAGES: Attrs = Attrs(bindings::DMA_ATTR_ALLOC_SINGLE_PAGES);
 
     /// This tells the DMA-mapping subsystem to suppress allocation failure reports (similarly to
-    /// __GFP_NOWARN).
+    /// `__GFP_NOWARN`).
     pub const DMA_ATTR_NO_WARN: Attrs = Attrs(bindings::DMA_ATTR_NO_WARN);
 
     /// Used to indicate that the buffer is fully accessible at an elevated privilege level (and
diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs
index 74c9a3dd719e..624d7a4c83ea 100644
--- a/rust/kernel/drm/device.rs
+++ b/rust/kernel/drm/device.rs
@@ -135,6 +135,8 @@ impl<T: drm::Driver> Device<T> {
     ///
     /// `ptr` must be a valid pointer to a `struct device` embedded in `Self`.
     unsafe fn from_drm_device(ptr: *const bindings::drm_device) -> *mut Self {
+        let ptr: *const Opaque<bindings::drm_device> = ptr.cast();
+
         // SAFETY: By the safety requirements of this function `ptr` is a valid pointer to a
         // `struct drm_device` embedded in `Self`.
         unsafe { crate::container_of!(ptr, Self, dev) }.cast_mut()
diff --git a/rust/kernel/drm/gem/mod.rs b/rust/kernel/drm/gem/mod.rs
index d8765e61c6c2..4cd69fa84318 100644
--- a/rust/kernel/drm/gem/mod.rs
+++ b/rust/kernel/drm/gem/mod.rs
@@ -125,6 +125,8 @@ impl<T: DriverObject> IntoGEMObject for Object<T> {
     }
 
     unsafe fn as_ref<'a>(self_ptr: *mut bindings::drm_gem_object) -> &'a Self {
+        let self_ptr: *mut Opaque<bindings::drm_gem_object> = self_ptr.cast();
+
         // SAFETY: `obj` is guaranteed to be in an `Object<T>` via the safety contract of this
         // function
         unsafe { &*crate::container_of!(self_ptr, Object<T>, obj) }
@@ -269,8 +271,10 @@ impl<T: DriverObject> Object<T> {
     }
 
     extern "C" fn free_callback(obj: *mut bindings::drm_gem_object) {
+        let ptr: *mut Opaque<bindings::drm_gem_object> = obj.cast();
+
         // SAFETY: All of our objects are of type `Object<T>`.
-        let this = unsafe { crate::container_of!(obj, Self, obj) }.cast_mut();
+        let this = unsafe { crate::container_of!(ptr, Self, obj) };
 
         // SAFETY: The C code only ever calls this callback with a valid pointer to a `struct
         // drm_gem_object`.
diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs
index 1604fb6a5b1b..4b8cdcb21e77 100644
--- a/rust/kernel/kunit.rs
+++ b/rust/kernel/kunit.rs
@@ -6,6 +6,7 @@
 //!
 //! Reference: <https://docs.kernel.org/dev-tools/kunit/index.html>
 
+use crate::prelude::*;
 use core::{ffi::c_void, fmt};
 
 /// Prints a KUnit error-level message.
@@ -40,8 +41,6 @@ pub fn info(args: fmt::Arguments<'_>) {
     }
 }
 
-use macros::kunit_tests;
-
 /// Asserts that a boolean expression is `true` at runtime.
 ///
 /// Public but hidden since it should only be used from generated tests.
@@ -59,7 +58,7 @@ macro_rules! kunit_assert {
             }
 
             static FILE: &'static $crate::str::CStr = $crate::c_str!($file);
-            static LINE: i32 = core::line!() as i32 - $diff;
+            static LINE: i32 = ::core::line!() as i32 - $diff;
             static CONDITION: &'static $crate::str::CStr = $crate::c_str!(stringify!($condition));
 
             // SAFETY: FFI call without safety requirements.
@@ -130,11 +129,11 @@ macro_rules! kunit_assert {
             unsafe {
                 $crate::bindings::__kunit_do_failed_assertion(
                     kunit_test,
-                    core::ptr::addr_of!(LOCATION.0),
+                    ::core::ptr::addr_of!(LOCATION.0),
                     $crate::bindings::kunit_assert_type_KUNIT_ASSERTION,
-                    core::ptr::addr_of!(ASSERTION.0.assert),
+                    ::core::ptr::addr_of!(ASSERTION.0.assert),
                     Some($crate::bindings::kunit_unary_assert_format),
-                    core::ptr::null(),
+                    ::core::ptr::null(),
                 );
             }
 
@@ -164,6 +163,31 @@ macro_rules! kunit_assert_eq {
     }};
 }
 
+trait TestResult {
+    fn is_test_result_ok(&self) -> bool;
+}
+
+impl TestResult for () {
+    fn is_test_result_ok(&self) -> bool {
+        true
+    }
+}
+
+impl<T, E> TestResult for Result<T, E> {
+    fn is_test_result_ok(&self) -> bool {
+        self.is_ok()
+    }
+}
+
+/// Returns whether a test result is to be considered OK.
+///
+/// This will be `assert!`ed from the generated tests.
+#[doc(hidden)]
+#[expect(private_bounds)]
+pub fn is_test_result_ok(t: impl TestResult) -> bool {
+    t.is_test_result_ok()
+}
+
 /// Represents an individual test case.
 ///
 /// The [`kunit_unsafe_test_suite!`] macro expects a NULL-terminated list of valid test cases.
@@ -323,7 +347,6 @@ mod tests {
 
     #[test]
     fn rust_test_kunit_example_test() {
-        #![expect(clippy::eq_op)]
         assert_eq!(1 + 1, 2);
     }
 
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 911c72a0fc21..6b4774b2b1c3 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -12,20 +12,34 @@
 //! do so first instead of bypassing this crate.
 
 #![no_std]
-#![feature(arbitrary_self_types)]
-#![cfg_attr(CONFIG_RUSTC_HAS_COERCE_POINTEE, feature(derive_coerce_pointee))]
-#![cfg_attr(not(CONFIG_RUSTC_HAS_COERCE_POINTEE), feature(coerce_unsized))]
-#![cfg_attr(not(CONFIG_RUSTC_HAS_COERCE_POINTEE), feature(dispatch_from_dyn))]
-#![cfg_attr(not(CONFIG_RUSTC_HAS_COERCE_POINTEE), feature(unsize))]
+//
+// Please see https://github.com/Rust-for-Linux/linux/issues/2 for details on
+// the unstable features in use.
+//
+// Stable since Rust 1.79.0.
 #![feature(inline_const)]
+//
+// Stable since Rust 1.81.0.
 #![feature(lint_reasons)]
-// Stable in Rust 1.82
+//
+// Stable since Rust 1.82.0.
 #![feature(raw_ref_op)]
-// Stable in Rust 1.83
+//
+// Stable since Rust 1.83.0.
 #![feature(const_maybe_uninit_as_mut_ptr)]
 #![feature(const_mut_refs)]
 #![feature(const_ptr_write)]
 #![feature(const_refs_to_cell)]
+//
+// Expected to become stable.
+#![feature(arbitrary_self_types)]
+//
+// `feature(derive_coerce_pointee)` is expected to become stable. Before Rust
+// 1.84.0, it did not exist, so enable the predecessor features.
+#![cfg_attr(CONFIG_RUSTC_HAS_COERCE_POINTEE, feature(derive_coerce_pointee))]
+#![cfg_attr(not(CONFIG_RUSTC_HAS_COERCE_POINTEE), feature(coerce_unsized))]
+#![cfg_attr(not(CONFIG_RUSTC_HAS_COERCE_POINTEE), feature(dispatch_from_dyn))]
+#![cfg_attr(not(CONFIG_RUSTC_HAS_COERCE_POINTEE), feature(unsize))]
 
 // Ensure conditional compilation based on the kernel configuration works;
 // otherwise we may silently break things like initcall handling.
@@ -102,6 +116,7 @@ pub mod transmute;
 pub mod types;
 pub mod uaccess;
 pub mod workqueue;
+pub mod xarray;
 
 #[doc(hidden)]
 pub use bindings;
@@ -204,7 +219,7 @@ fn panic(info: &core::panic::PanicInfo<'_>) -> ! {
 /// }
 ///
 /// let test = Test { a: 10, b: 20 };
-/// let b_ptr = &test.b;
+/// let b_ptr: *const _ = &test.b;
 /// // SAFETY: The pointer points at the `b` field of a `Test`, so the resulting pointer will be
 /// // in-bounds of the same allocation as `b_ptr`.
 /// let test_alias = unsafe { container_of!(b_ptr, Test, b) };
@@ -212,13 +227,19 @@ fn panic(info: &core::panic::PanicInfo<'_>) -> ! {
 /// ```
 #[macro_export]
 macro_rules! container_of {
-    ($ptr:expr, $type:ty, $($f:tt)*) => {{
-        let ptr = $ptr as *const _ as *const u8;
-        let offset: usize = ::core::mem::offset_of!($type, $($f)*);
-        ptr.sub(offset) as *const $type
+    ($field_ptr:expr, $Container:ty, $($fields:tt)*) => {{
+        let offset: usize = ::core::mem::offset_of!($Container, $($fields)*);
+        let field_ptr = $field_ptr;
+        let container_ptr = field_ptr.byte_sub(offset).cast::<$Container>();
+        $crate::assert_same_type(field_ptr, (&raw const (*container_ptr).$($fields)*).cast_mut());
+        container_ptr
     }}
 }
 
+/// Helper for [`container_of!`].
+#[doc(hidden)]
+pub fn assert_same_type<T>(_: T, _: T) {}
+
 /// Helper for `.rs.S` files.
 #[doc(hidden)]
 #[macro_export]
diff --git a/rust/kernel/list.rs b/rust/kernel/list.rs
index 2054682c5724..c391c30b80f8 100644
--- a/rust/kernel/list.rs
+++ b/rust/kernel/list.rs
@@ -4,9 +4,6 @@
 
 //! A linked list implementation.
 
-// May not be needed in Rust 1.87.0 (pending beta backport).
-#![allow(clippy::ptr_eq)]
-
 use crate::sync::ArcBorrow;
 use crate::types::Opaque;
 use core::iter::{DoubleEndedIterator, FusedIterator};
@@ -38,6 +35,114 @@ pub use self::arc_field::{define_list_arc_field_getter, ListArcField};
 /// * All prev/next pointers in `ListLinks` fields of items in the list are valid and form a cycle.
 /// * For every item in the list, the list owns the associated [`ListArc`] reference and has
 ///   exclusive access to the `ListLinks` field.
+///
+/// # Examples
+///
+/// ```
+/// use kernel::list::*;
+///
+/// #[pin_data]
+/// struct BasicItem {
+///     value: i32,
+///     #[pin]
+///     links: ListLinks,
+/// }
+///
+/// impl BasicItem {
+///     fn new(value: i32) -> Result<ListArc<Self>> {
+///         ListArc::pin_init(try_pin_init!(Self {
+///             value,
+///             links <- ListLinks::new(),
+///         }), GFP_KERNEL)
+///     }
+/// }
+///
+/// impl_has_list_links! {
+///     impl HasListLinks<0> for BasicItem { self.links }
+/// }
+/// impl_list_arc_safe! {
+///     impl ListArcSafe<0> for BasicItem { untracked; }
+/// }
+/// impl_list_item! {
+///     impl ListItem<0> for BasicItem { using ListLinks; }
+/// }
+///
+/// // Create a new empty list.
+/// let mut list = List::new();
+/// {
+///     assert!(list.is_empty());
+/// }
+///
+/// // Insert 3 elements using `push_back()`.
+/// list.push_back(BasicItem::new(15)?);
+/// list.push_back(BasicItem::new(10)?);
+/// list.push_back(BasicItem::new(30)?);
+///
+/// // Iterate over the list to verify the nodes were inserted correctly.
+/// // [15, 10, 30]
+/// {
+///     let mut iter = list.iter();
+///     assert_eq!(iter.next().unwrap().value, 15);
+///     assert_eq!(iter.next().unwrap().value, 10);
+///     assert_eq!(iter.next().unwrap().value, 30);
+///     assert!(iter.next().is_none());
+///
+///     // Verify the length of the list.
+///     assert_eq!(list.iter().count(), 3);
+/// }
+///
+/// // Pop the items from the list using `pop_back()` and verify the content.
+/// {
+///     assert_eq!(list.pop_back().unwrap().value, 30);
+///     assert_eq!(list.pop_back().unwrap().value, 10);
+///     assert_eq!(list.pop_back().unwrap().value, 15);
+/// }
+///
+/// // Insert 3 elements using `push_front()`.
+/// list.push_front(BasicItem::new(15)?);
+/// list.push_front(BasicItem::new(10)?);
+/// list.push_front(BasicItem::new(30)?);
+///
+/// // Iterate over the list to verify the nodes were inserted correctly.
+/// // [30, 10, 15]
+/// {
+///     let mut iter = list.iter();
+///     assert_eq!(iter.next().unwrap().value, 30);
+///     assert_eq!(iter.next().unwrap().value, 10);
+///     assert_eq!(iter.next().unwrap().value, 15);
+///     assert!(iter.next().is_none());
+///
+///     // Verify the length of the list.
+///     assert_eq!(list.iter().count(), 3);
+/// }
+///
+/// // Pop the items from the list using `pop_front()` and verify the content.
+/// {
+///     assert_eq!(list.pop_front().unwrap().value, 30);
+///     assert_eq!(list.pop_front().unwrap().value, 10);
+/// }
+///
+/// // Push `list2` to `list` through `push_all_back()`.
+/// // list: [15]
+/// // list2: [25, 35]
+/// {
+///     let mut list2 = List::new();
+///     list2.push_back(BasicItem::new(25)?);
+///     list2.push_back(BasicItem::new(35)?);
+///
+///     list.push_all_back(&mut list2);
+///
+///     // list: [15, 25, 35]
+///     // list2: []
+///     let mut iter = list.iter();
+///     assert_eq!(iter.next().unwrap().value, 15);
+///     assert_eq!(iter.next().unwrap().value, 25);
+///     assert_eq!(iter.next().unwrap().value, 35);
+///     assert!(iter.next().is_none());
+///     assert!(list2.is_empty());
+/// }
+/// # Result::<(), Error>::Ok(())
+/// ```
 pub struct List<T: ?Sized + ListItem<ID>, const ID: u64 = 0> {
     first: *mut ListLinksFields,
     _ty: PhantomData<ListArc<T, ID>>,
@@ -322,7 +427,7 @@ impl<T: ?Sized + ListItem<ID>, const ID: u64> List<T, ID> {
 
     /// Removes the last item from this list.
     pub fn pop_back(&mut self) -> Option<ListArc<T, ID>> {
-        if self.first.is_null() {
+        if self.is_empty() {
             return None;
         }
 
@@ -334,7 +439,7 @@ impl<T: ?Sized + ListItem<ID>, const ID: u64> List<T, ID> {
 
     /// Removes the first item from this list.
     pub fn pop_front(&mut self) -> Option<ListArc<T, ID>> {
-        if self.first.is_null() {
+        if self.is_empty() {
             return None;
         }
 
diff --git a/rust/kernel/list/arc.rs b/rust/kernel/list/arc.rs
index 13c50df37b89..d92bcf665c89 100644
--- a/rust/kernel/list/arc.rs
+++ b/rust/kernel/list/arc.rs
@@ -74,7 +74,7 @@ pub unsafe trait TryNewListArc<const ID: u64 = 0>: ListArcSafe<ID> {
 ///
 /// * The `untracked` strategy does not actually keep track of whether a [`ListArc`] exists. When
 ///   using this strategy, the only way to create a [`ListArc`] is using a [`UniqueArc`].
-/// * The `tracked_by` strategy defers the tracking to a field of the struct. The user much specify
+/// * The `tracked_by` strategy defers the tracking to a field of the struct. The user must specify
 ///   which field to defer the tracking to. The field must implement [`ListArcSafe`]. If the field
 ///   implements [`TryNewListArc`], then the type will also implement [`TryNewListArc`].
 ///
@@ -96,7 +96,7 @@ macro_rules! impl_list_arc_safe {
     } $($rest:tt)*) => {
         impl$(<$($generics)*>)? $crate::list::ListArcSafe<$num> for $t {
             unsafe fn on_create_list_arc_from_unique(self: ::core::pin::Pin<&mut Self>) {
-                $crate::assert_pinned!($t, $field, $fty, inline);
+                ::pin_init::assert_pinned!($t, $field, $fty, inline);
 
                 // SAFETY: This field is structurally pinned as per the above assertion.
                 let field = unsafe {
@@ -464,7 +464,7 @@ where
 
 /// A utility for tracking whether a [`ListArc`] exists using an atomic.
 ///
-/// # Invariant
+/// # Invariants
 ///
 /// If the boolean is `false`, then there is no [`ListArc`] for this value.
 #[repr(transparent)]
diff --git a/rust/kernel/miscdevice.rs b/rust/kernel/miscdevice.rs
index 9d9771247c38..f33c13c3ff97 100644
--- a/rust/kernel/miscdevice.rs
+++ b/rust/kernel/miscdevice.rs
@@ -217,7 +217,7 @@ impl<T: MiscDevice> MiscdeviceVTable<T> {
         // type.
         //
         // SAFETY: The open call of a file can access the private data.
-        unsafe { (*raw_file).private_data = ptr.into_foreign() };
+        unsafe { (*raw_file).private_data = ptr.into_foreign().cast() };
 
         0
     }
@@ -228,7 +228,7 @@ impl<T: MiscDevice> MiscdeviceVTable<T> {
     /// must be associated with a `MiscDeviceRegistration<T>`.
     unsafe extern "C" fn release(_inode: *mut bindings::inode, file: *mut bindings::file) -> c_int {
         // SAFETY: The release call of a file owns the private data.
-        let private = unsafe { (*file).private_data };
+        let private = unsafe { (*file).private_data }.cast();
         // SAFETY: The release call of a file owns the private data.
         let ptr = unsafe { <T::Ptr as ForeignOwnable>::from_foreign(private) };
 
@@ -253,7 +253,7 @@ impl<T: MiscDevice> MiscdeviceVTable<T> {
         // SAFETY: This is a Rust Miscdevice, so we call `into_foreign` in `open` and
         // `from_foreign` in `release`, and `fops_mmap` is guaranteed to be called between those
         // two operations.
-        let device = unsafe { <T::Ptr as ForeignOwnable>::borrow(private) };
+        let device = unsafe { <T::Ptr as ForeignOwnable>::borrow(private.cast()) };
         // SAFETY: The caller provides a vma that is undergoing initial VMA setup.
         let area = unsafe { VmaNew::from_raw(vma) };
         // SAFETY:
@@ -272,7 +272,7 @@ impl<T: MiscDevice> MiscdeviceVTable<T> {
     /// `file` must be a valid file that is associated with a `MiscDeviceRegistration<T>`.
     unsafe extern "C" fn ioctl(file: *mut bindings::file, cmd: c_uint, arg: c_ulong) -> c_long {
         // SAFETY: The ioctl call of a file can access the private data.
-        let private = unsafe { (*file).private_data };
+        let private = unsafe { (*file).private_data }.cast();
         // SAFETY: Ioctl calls can borrow the private data of the file.
         let device = unsafe { <T::Ptr as ForeignOwnable>::borrow(private) };
 
@@ -297,7 +297,7 @@ impl<T: MiscDevice> MiscdeviceVTable<T> {
         arg: c_ulong,
     ) -> c_long {
         // SAFETY: The compat ioctl call of a file can access the private data.
-        let private = unsafe { (*file).private_data };
+        let private = unsafe { (*file).private_data }.cast();
         // SAFETY: Ioctl calls can borrow the private data of the file.
         let device = unsafe { <T::Ptr as ForeignOwnable>::borrow(private) };
 
@@ -318,7 +318,7 @@ impl<T: MiscDevice> MiscdeviceVTable<T> {
     /// - `seq_file` must be a valid `struct seq_file` that we can write to.
     unsafe extern "C" fn show_fdinfo(seq_file: *mut bindings::seq_file, file: *mut bindings::file) {
         // SAFETY: The release call of a file owns the private data.
-        let private = unsafe { (*file).private_data };
+        let private = unsafe { (*file).private_data }.cast();
         // SAFETY: Ioctl calls can borrow the private data of the file.
         let device = unsafe { <T::Ptr as ForeignOwnable>::borrow(private) };
         // SAFETY:
diff --git a/rust/kernel/mm.rs b/rust/kernel/mm.rs
index 615907a0f3b4..43f525c0d16c 100644
--- a/rust/kernel/mm.rs
+++ b/rust/kernel/mm.rs
@@ -10,7 +10,6 @@
 //! control what happens when userspace reads or writes to that region of memory.
 //!
 //! C header: [`include/linux/mm.h`](srctree/include/linux/mm.h)
-#![cfg(CONFIG_MMU)]
 
 use crate::{
     bindings,
@@ -21,6 +20,10 @@ use core::{ops::Deref, ptr::NonNull};
 pub mod virt;
 use virt::VmaRef;
 
+#[cfg(CONFIG_MMU)]
+pub use mmput_async::MmWithUserAsync;
+mod mmput_async;
+
 /// A wrapper for the kernel's `struct mm_struct`.
 ///
 /// This represents the address space of a userspace process, so each process has one `Mm`
@@ -111,50 +114,6 @@ impl Deref for MmWithUser {
     }
 }
 
-/// A wrapper for the kernel's `struct mm_struct`.
-///
-/// This type is identical to `MmWithUser` except that it uses `mmput_async` when dropping a
-/// refcount. This means that the destructor of `ARef<MmWithUserAsync>` is safe to call in atomic
-/// context.
-///
-/// # Invariants
-///
-/// Values of this type are always refcounted using `mmget`. The value of `mm_users` is non-zero.
-#[repr(transparent)]
-pub struct MmWithUserAsync {
-    mm: MmWithUser,
-}
-
-// SAFETY: It is safe to call `mmput_async` on another thread than where `mmget` was called.
-unsafe impl Send for MmWithUserAsync {}
-// SAFETY: All methods on `MmWithUserAsync` can be called in parallel from several threads.
-unsafe impl Sync for MmWithUserAsync {}
-
-// SAFETY: By the type invariants, this type is always refcounted.
-unsafe impl AlwaysRefCounted for MmWithUserAsync {
-    #[inline]
-    fn inc_ref(&self) {
-        // SAFETY: The pointer is valid since self is a reference.
-        unsafe { bindings::mmget(self.as_raw()) };
-    }
-
-    #[inline]
-    unsafe fn dec_ref(obj: NonNull<Self>) {
-        // SAFETY: The caller is giving up their refcount.
-        unsafe { bindings::mmput_async(obj.cast().as_ptr()) };
-    }
-}
-
-// Make all `MmWithUser` methods available on `MmWithUserAsync`.
-impl Deref for MmWithUserAsync {
-    type Target = MmWithUser;
-
-    #[inline]
-    fn deref(&self) -> &MmWithUser {
-        &self.mm
-    }
-}
-
 // These methods are safe to call even if `mm_users` is zero.
 impl Mm {
     /// Returns a raw pointer to the inner `mm_struct`.
@@ -206,13 +165,6 @@ impl MmWithUser {
         unsafe { &*ptr.cast() }
     }
 
-    /// Use `mmput_async` when dropping this refcount.
-    #[inline]
-    pub fn into_mmput_async(me: ARef<MmWithUser>) -> ARef<MmWithUserAsync> {
-        // SAFETY: The layouts and invariants are compatible.
-        unsafe { ARef::from_raw(ARef::into_raw(me).cast()) }
-    }
-
     /// Attempt to access a vma using the vma read lock.
     ///
     /// This is an optimistic trylock operation, so it may fail if there is contention. In that
diff --git a/rust/kernel/mm/mmput_async.rs b/rust/kernel/mm/mmput_async.rs
new file mode 100644
index 000000000000..9289e05f7a67
--- /dev/null
+++ b/rust/kernel/mm/mmput_async.rs
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2024 Google LLC.
+
+//! Version of `MmWithUser` using `mmput_async`.
+//!
+//! This is a separate file from `mm.rs` due to the dependency on `CONFIG_MMU=y`.
+#![cfg(CONFIG_MMU)]
+
+use crate::{
+    bindings,
+    mm::MmWithUser,
+    types::{ARef, AlwaysRefCounted},
+};
+use core::{ops::Deref, ptr::NonNull};
+
+/// A wrapper for the kernel's `struct mm_struct`.
+///
+/// This type is identical to `MmWithUser` except that it uses `mmput_async` when dropping a
+/// refcount. This means that the destructor of `ARef<MmWithUserAsync>` is safe to call in atomic
+/// context.
+///
+/// # Invariants
+///
+/// Values of this type are always refcounted using `mmget`. The value of `mm_users` is non-zero.
+#[repr(transparent)]
+pub struct MmWithUserAsync {
+    mm: MmWithUser,
+}
+
+// SAFETY: It is safe to call `mmput_async` on another thread than where `mmget` was called.
+unsafe impl Send for MmWithUserAsync {}
+// SAFETY: All methods on `MmWithUserAsync` can be called in parallel from several threads.
+unsafe impl Sync for MmWithUserAsync {}
+
+// SAFETY: By the type invariants, this type is always refcounted.
+unsafe impl AlwaysRefCounted for MmWithUserAsync {
+    #[inline]
+    fn inc_ref(&self) {
+        // SAFETY: The pointer is valid since self is a reference.
+        unsafe { bindings::mmget(self.as_raw()) };
+    }
+
+    #[inline]
+    unsafe fn dec_ref(obj: NonNull<Self>) {
+        // SAFETY: The caller is giving up their refcount.
+        unsafe { bindings::mmput_async(obj.cast().as_ptr()) };
+    }
+}
+
+// Make all `MmWithUser` methods available on `MmWithUserAsync`.
+impl Deref for MmWithUserAsync {
+    type Target = MmWithUser;
+
+    #[inline]
+    fn deref(&self) -> &MmWithUser {
+        &self.mm
+    }
+}
+
+impl MmWithUser {
+    /// Use `mmput_async` when dropping this refcount.
+    #[inline]
+    pub fn into_mmput_async(me: ARef<MmWithUser>) -> ARef<MmWithUserAsync> {
+        // SAFETY: The layouts and invariants are compatible.
+        unsafe { ARef::from_raw(ARef::into_raw(me).cast()) }
+    }
+}
diff --git a/rust/kernel/page.rs b/rust/kernel/page.rs
index f6126aca33a6..7c1b17246ed5 100644
--- a/rust/kernel/page.rs
+++ b/rust/kernel/page.rs
@@ -69,6 +69,7 @@ impl Page {
     /// let page = Page::alloc_page(GFP_KERNEL | __GFP_ZERO)?;
     /// # Ok::<(), kernel::alloc::AllocError>(())
     /// ```
+    #[inline]
     pub fn alloc_page(flags: Flags) -> Result<Self, AllocError> {
         // SAFETY: Depending on the value of `gfp_flags`, this call may sleep. Other than that, it
         // is always safe to call this method.
@@ -251,6 +252,7 @@ impl Page {
 }
 
 impl Drop for Page {
+    #[inline]
     fn drop(&mut self) {
         // SAFETY: By the type invariants, we have ownership of the page and can free it.
         unsafe { bindings::__free_pages(self.page.as_ptr(), 0) };
diff --git a/rust/kernel/pci.rs b/rust/kernel/pci.rs
index 38fc8d5ffbf9..8435f8132e38 100644
--- a/rust/kernel/pci.rs
+++ b/rust/kernel/pci.rs
@@ -89,7 +89,7 @@ impl<T: Driver + 'static> Adapter<T> {
     extern "C" fn remove_callback(pdev: *mut bindings::pci_dev) {
         // SAFETY: The PCI bus only ever calls the remove callback with a valid pointer to a
         // `struct pci_dev`.
-        let ptr = unsafe { bindings::pci_get_drvdata(pdev) };
+        let ptr = unsafe { bindings::pci_get_drvdata(pdev) }.cast();
 
         // SAFETY: `remove_callback` is only ever called after a successful call to
         // `probe_callback`, hence it's guaranteed that `ptr` points to a valid and initialized
@@ -118,7 +118,9 @@ macro_rules! module_pci_driver {
 };
 }
 
-/// Abstraction for bindings::pci_device_id.
+/// Abstraction for the PCI device ID structure ([`struct pci_device_id`]).
+///
+/// [`struct pci_device_id`]: https://docs.kernel.org/PCI/pci.html#c.pci_device_id
 #[repr(transparent)]
 #[derive(Clone, Copy)]
 pub struct DeviceId(bindings::pci_device_id);
@@ -173,7 +175,7 @@ unsafe impl RawDeviceId for DeviceId {
     }
 }
 
-/// IdTable type for PCI
+/// `IdTable` type for PCI.
 pub type IdTable<T> = &'static dyn kernel::device_id::IdTable<DeviceId, T>;
 
 /// Create a PCI `IdTable` with its alias for modpost.
@@ -224,10 +226,11 @@ macro_rules! pci_device_table {
 /// `Adapter` documentation for an example.
 pub trait Driver: Send {
     /// The type holding information about each device id supported by the driver.
-    ///
-    /// TODO: Use associated_type_defaults once stabilized:
-    ///
-    /// type IdInfo: 'static = ();
+    // TODO: Use `associated_type_defaults` once stabilized:
+    //
+    // ```
+    // type IdInfo: 'static = ();
+    // ```
     type IdInfo: 'static;
 
     /// The table of device ids supported by the driver.
diff --git a/rust/kernel/platform.rs b/rust/kernel/platform.rs
index 08849d92c074..5b21fa517e55 100644
--- a/rust/kernel/platform.rs
+++ b/rust/kernel/platform.rs
@@ -79,7 +79,7 @@ impl<T: Driver + 'static> Adapter<T> {
 
     extern "C" fn remove_callback(pdev: *mut bindings::platform_device) {
         // SAFETY: `pdev` is a valid pointer to a `struct platform_device`.
-        let ptr = unsafe { bindings::platform_get_drvdata(pdev) };
+        let ptr = unsafe { bindings::platform_get_drvdata(pdev) }.cast();
 
         // SAFETY: `remove_callback` is only ever called after a successful call to
         // `probe_callback`, hence it's guaranteed that `ptr` points to a valid and initialized
@@ -150,10 +150,11 @@ macro_rules! module_platform_driver {
 ///```
 pub trait Driver: Send {
     /// The type holding driver private data about each device id supported by the driver.
-    ///
-    /// TODO: Use associated_type_defaults once stabilized:
-    ///
-    /// type IdInfo: 'static = ();
+    // TODO: Use associated_type_defaults once stabilized:
+    //
+    // ```
+    // type IdInfo: 'static = ();
+    // ```
     type IdInfo: 'static;
 
     /// The table of OF device ids supported by the driver.
diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs
index baa774a351ce..2f30a398dddd 100644
--- a/rust/kernel/prelude.rs
+++ b/rust/kernel/prelude.rs
@@ -14,10 +14,15 @@
 #[doc(no_inline)]
 pub use core::pin::Pin;
 
+pub use ::ffi::{
+    c_char, c_int, c_long, c_longlong, c_schar, c_short, c_uchar, c_uint, c_ulong, c_ulonglong,
+    c_ushort, c_void,
+};
+
 pub use crate::alloc::{flags::*, Box, KBox, KVBox, KVVec, KVec, VBox, VVec, Vec};
 
 #[doc(no_inline)]
-pub use macros::{export, module, vtable};
+pub use macros::{export, kunit_tests, module, vtable};
 
 pub use pin_init::{init, pin_data, pin_init, pinned_drop, InPlaceWrite, Init, PinInit, Zeroable};
 
diff --git a/rust/kernel/print.rs b/rust/kernel/print.rs
index cf4714242e14..9783d960a97a 100644
--- a/rust/kernel/print.rs
+++ b/rust/kernel/print.rs
@@ -198,10 +198,11 @@ macro_rules! print_macro (
 /// Equivalent to the kernel's [`pr_emerg`] macro.
 ///
 /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and
-/// `alloc::format!` for information about the formatting syntax.
+/// [`std::format!`] for information about the formatting syntax.
 ///
 /// [`pr_emerg`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_emerg
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -222,10 +223,11 @@ macro_rules! pr_emerg (
 /// Equivalent to the kernel's [`pr_alert`] macro.
 ///
 /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and
-/// `alloc::format!` for information about the formatting syntax.
+/// [`std::format!`] for information about the formatting syntax.
 ///
 /// [`pr_alert`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_alert
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -246,10 +248,11 @@ macro_rules! pr_alert (
 /// Equivalent to the kernel's [`pr_crit`] macro.
 ///
 /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and
-/// `alloc::format!` for information about the formatting syntax.
+/// [`std::format!`] for information about the formatting syntax.
 ///
 /// [`pr_crit`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_crit
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -270,10 +273,11 @@ macro_rules! pr_crit (
 /// Equivalent to the kernel's [`pr_err`] macro.
 ///
 /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and
-/// `alloc::format!` for information about the formatting syntax.
+/// [`std::format!`] for information about the formatting syntax.
 ///
 /// [`pr_err`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_err
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -294,10 +298,11 @@ macro_rules! pr_err (
 /// Equivalent to the kernel's [`pr_warn`] macro.
 ///
 /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and
-/// `alloc::format!` for information about the formatting syntax.
+/// [`std::format!`] for information about the formatting syntax.
 ///
 /// [`pr_warn`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_warn
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -318,10 +323,11 @@ macro_rules! pr_warn (
 /// Equivalent to the kernel's [`pr_notice`] macro.
 ///
 /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and
-/// `alloc::format!` for information about the formatting syntax.
+/// [`std::format!`] for information about the formatting syntax.
 ///
 /// [`pr_notice`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_notice
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -342,10 +348,11 @@ macro_rules! pr_notice (
 /// Equivalent to the kernel's [`pr_info`] macro.
 ///
 /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and
-/// `alloc::format!` for information about the formatting syntax.
+/// [`std::format!`] for information about the formatting syntax.
 ///
 /// [`pr_info`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_info
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -368,10 +375,11 @@ macro_rules! pr_info (
 /// yet.
 ///
 /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and
-/// `alloc::format!` for information about the formatting syntax.
+/// [`std::format!`] for information about the formatting syntax.
 ///
 /// [`pr_debug`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_debug
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
@@ -395,11 +403,12 @@ macro_rules! pr_debug (
 /// Equivalent to the kernel's [`pr_cont`] macro.
 ///
 /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and
-/// `alloc::format!` for information about the formatting syntax.
+/// [`std::format!`] for information about the formatting syntax.
 ///
 /// [`pr_info!`]: crate::pr_info!
 /// [`pr_cont`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_cont
 /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+/// [`std::format!`]: https://doc.rust-lang.org/std/macro.format.html
 ///
 /// # Examples
 ///
diff --git a/rust/kernel/rbtree.rs b/rust/kernel/rbtree.rs
index 5246b2c8a4ff..8d978c896747 100644
--- a/rust/kernel/rbtree.rs
+++ b/rust/kernel/rbtree.rs
@@ -424,7 +424,7 @@ where
         while !node.is_null() {
             // SAFETY: By the type invariant of `Self`, all non-null `rb_node` pointers stored in `self`
             // point to the links field of `Node<K, V>` objects.
-            let this = unsafe { container_of!(node, Node<K, V>, links) }.cast_mut();
+            let this = unsafe { container_of!(node, Node<K, V>, links) };
             // SAFETY: `this` is a non-null node so it is valid by the type invariants.
             let this_key = unsafe { &(*this).key };
             // SAFETY: `node` is a non-null node so it is valid by the type invariants.
@@ -496,7 +496,7 @@ impl<K, V> Drop for RBTree<K, V> {
             // but it is not observable. The loop invariant is still maintained.
 
             // SAFETY: `this` is valid per the loop invariant.
-            unsafe { drop(KBox::from_raw(this.cast_mut())) };
+            unsafe { drop(KBox::from_raw(this)) };
         }
     }
 }
@@ -761,7 +761,7 @@ impl<'a, K, V> Cursor<'a, K, V> {
         let next = self.get_neighbor_raw(Direction::Next);
         // SAFETY: By the type invariant of `Self`, all non-null `rb_node` pointers stored in `self`
         // point to the links field of `Node<K, V>` objects.
-        let this = unsafe { container_of!(self.current.as_ptr(), Node<K, V>, links) }.cast_mut();
+        let this = unsafe { container_of!(self.current.as_ptr(), Node<K, V>, links) };
         // SAFETY: `this` is valid by the type invariants as described above.
         let node = unsafe { KBox::from_raw(this) };
         let node = RBTreeNode { node };
@@ -806,7 +806,7 @@ impl<'a, K, V> Cursor<'a, K, V> {
             unsafe { bindings::rb_erase(neighbor, addr_of_mut!(self.tree.root)) };
             // SAFETY: By the type invariant of `Self`, all non-null `rb_node` pointers stored in `self`
             // point to the links field of `Node<K, V>` objects.
-            let this = unsafe { container_of!(neighbor, Node<K, V>, links) }.cast_mut();
+            let this = unsafe { container_of!(neighbor, Node<K, V>, links) };
             // SAFETY: `this` is valid by the type invariants as described above.
             let node = unsafe { KBox::from_raw(this) };
             return Some(RBTreeNode { node });
@@ -912,7 +912,7 @@ impl<'a, K, V> Cursor<'a, K, V> {
     unsafe fn to_key_value_raw<'b>(node: NonNull<bindings::rb_node>) -> (&'b K, *mut V) {
         // SAFETY: By the type invariant of `Self`, all non-null `rb_node` pointers stored in `self`
         // point to the links field of `Node<K, V>` objects.
-        let this = unsafe { container_of!(node.as_ptr(), Node<K, V>, links) }.cast_mut();
+        let this = unsafe { container_of!(node.as_ptr(), Node<K, V>, links) };
         // SAFETY: The passed `node` is the current node or a non-null neighbor,
         // thus `this` is valid by the type invariants.
         let k = unsafe { &(*this).key };
@@ -1021,7 +1021,7 @@ impl<K, V> Iterator for IterRaw<K, V> {
 
         // SAFETY: By the type invariant of `IterRaw`, `self.next` is a valid node in an `RBTree`,
         // and by the type invariant of `RBTree`, all nodes point to the links field of `Node<K, V>` objects.
-        let cur = unsafe { container_of!(self.next, Node<K, V>, links) }.cast_mut();
+        let cur = unsafe { container_of!(self.next, Node<K, V>, links) };
 
         // SAFETY: `self.next` is a valid tree node by the type invariants.
         self.next = unsafe { bindings::rb_next(self.next) };
@@ -1216,7 +1216,7 @@ impl<'a, K, V> OccupiedEntry<'a, K, V> {
         // SAFETY:
         // - `self.node_links` is a valid pointer to a node in the tree.
         // - We have exclusive access to the underlying tree, and can thus give out a mutable reference.
-        unsafe { &mut (*(container_of!(self.node_links, Node<K, V>, links).cast_mut())).value }
+        unsafe { &mut (*(container_of!(self.node_links, Node<K, V>, links))).value }
     }
 
     /// Converts the entry into a mutable reference to its value.
@@ -1226,7 +1226,7 @@ impl<'a, K, V> OccupiedEntry<'a, K, V> {
         // SAFETY:
         // - `self.node_links` is a valid pointer to a node in the tree.
         // - This consumes the `&'a mut RBTree<K, V>`, therefore it can give out a mutable reference that lives for `'a`.
-        unsafe { &mut (*(container_of!(self.node_links, Node<K, V>, links).cast_mut())).value }
+        unsafe { &mut (*(container_of!(self.node_links, Node<K, V>, links))).value }
     }
 
     /// Remove this entry from the [`RBTree`].
@@ -1239,9 +1239,7 @@ impl<'a, K, V> OccupiedEntry<'a, K, V> {
         RBTreeNode {
             // SAFETY: The node was a node in the tree, but we removed it, so we can convert it
             // back into a box.
-            node: unsafe {
-                KBox::from_raw(container_of!(self.node_links, Node<K, V>, links).cast_mut())
-            },
+            node: unsafe { KBox::from_raw(container_of!(self.node_links, Node<K, V>, links)) },
         }
     }
 
@@ -1272,8 +1270,7 @@ impl<'a, K, V> OccupiedEntry<'a, K, V> {
         // SAFETY:
         // - `self.node_ptr` produces a valid pointer to a node in the tree.
         // - Now that we removed this entry from the tree, we can convert the node to a box.
-        let old_node =
-            unsafe { KBox::from_raw(container_of!(self.node_links, Node<K, V>, links).cast_mut()) };
+        let old_node = unsafe { KBox::from_raw(container_of!(self.node_links, Node<K, V>, links)) };
 
         RBTreeNode { node: old_node }
     }
diff --git a/rust/kernel/static_assert.rs b/rust/kernel/static_assert.rs
index 3115ee0ba8e9..a57ba14315a0 100644
--- a/rust/kernel/static_assert.rs
+++ b/rust/kernel/static_assert.rs
@@ -6,6 +6,10 @@
 ///
 /// Similar to C11 [`_Static_assert`] and C++11 [`static_assert`].
 ///
+/// An optional panic message can be supplied after the expression.
+/// Currently only a string literal without formatting is supported
+/// due to constness limitations of the [`assert!`] macro.
+///
 /// The feature may be added to Rust in the future: see [RFC 2790].
 ///
 /// [`_Static_assert`]: https://en.cppreference.com/w/c/language/_Static_assert
@@ -25,10 +29,11 @@
 ///     x + 2
 /// }
 /// static_assert!(f(40) == 42);
+/// static_assert!(f(40) == 42, "f(x) must add 2 to the given input.");
 /// ```
 #[macro_export]
 macro_rules! static_assert {
-    ($condition:expr) => {
-        const _: () = core::assert!($condition);
+    ($condition:expr $(,$arg:literal)?) => {
+        const _: () = ::core::assert!($condition $(,$arg)?);
     };
 }
diff --git a/rust/kernel/std_vendor.rs b/rust/kernel/std_vendor.rs
index 279bd353687a..abbab5050cc5 100644
--- a/rust/kernel/std_vendor.rs
+++ b/rust/kernel/std_vendor.rs
@@ -148,7 +148,7 @@ macro_rules! dbg {
     };
     ($val:expr $(,)?) => {
         // Use of `match` here is intentional because it affects the lifetimes
-        // of temporaries - https://stackoverflow.com/a/48732525/1063961
+        // of temporaries - <https://stackoverflow.com/a/48732525/1063961>
         match $val {
             tmp => {
                 $crate::pr_info!("[{}:{}:{}] {} = {:#?}\n",
diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index fb61ce81ea28..a927db8e079c 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -6,7 +6,7 @@ use crate::alloc::{flags::*, AllocError, KVec};
 use core::fmt::{self, Write};
 use core::ops::{self, Deref, DerefMut, Index};
 
-use crate::error::{code::*, Error};
+use crate::prelude::*;
 
 /// Byte string without UTF-8 validity guarantee.
 #[repr(transparent)]
@@ -572,30 +572,13 @@ macro_rules! c_str {
     }};
 }
 
-#[cfg(test)]
-#[expect(clippy::items_after_test_module)]
+#[kunit_tests(rust_kernel_str)]
 mod tests {
     use super::*;
 
-    struct String(CString);
-
-    impl String {
-        fn from_fmt(args: fmt::Arguments<'_>) -> Self {
-            String(CString::try_from_fmt(args).unwrap())
-        }
-    }
-
-    impl Deref for String {
-        type Target = str;
-
-        fn deref(&self) -> &str {
-            self.0.to_str().unwrap()
-        }
-    }
-
     macro_rules! format {
         ($($f:tt)*) => ({
-            &*String::from_fmt(kernel::fmt!($($f)*))
+            CString::try_from_fmt(::kernel::fmt!($($f)*))?.to_str()?
         })
     }
 
@@ -614,67 +597,72 @@ mod tests {
         \\xf0\\xf1\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd\\xfe\\xff";
 
     #[test]
-    fn test_cstr_to_str() {
+    fn test_cstr_to_str() -> Result {
         let good_bytes = b"\xf0\x9f\xa6\x80\0";
-        let checked_cstr = CStr::from_bytes_with_nul(good_bytes).unwrap();
-        let checked_str = checked_cstr.to_str().unwrap();
+        let checked_cstr = CStr::from_bytes_with_nul(good_bytes)?;
+        let checked_str = checked_cstr.to_str()?;
         assert_eq!(checked_str, "🦀");
+        Ok(())
     }
 
     #[test]
-    #[should_panic]
-    fn test_cstr_to_str_panic() {
+    fn test_cstr_to_str_invalid_utf8() -> Result {
         let bad_bytes = b"\xc3\x28\0";
-        let checked_cstr = CStr::from_bytes_with_nul(bad_bytes).unwrap();
-        checked_cstr.to_str().unwrap();
+        let checked_cstr = CStr::from_bytes_with_nul(bad_bytes)?;
+        assert!(checked_cstr.to_str().is_err());
+        Ok(())
     }
 
     #[test]
-    fn test_cstr_as_str_unchecked() {
+    fn test_cstr_as_str_unchecked() -> Result {
         let good_bytes = b"\xf0\x9f\x90\xA7\0";
-        let checked_cstr = CStr::from_bytes_with_nul(good_bytes).unwrap();
+        let checked_cstr = CStr::from_bytes_with_nul(good_bytes)?;
         // SAFETY: The contents come from a string literal which contains valid UTF-8.
         let unchecked_str = unsafe { checked_cstr.as_str_unchecked() };
         assert_eq!(unchecked_str, "🐧");
+        Ok(())
     }
 
     #[test]
-    fn test_cstr_display() {
-        let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap();
+    fn test_cstr_display() -> Result {
+        let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0")?;
         assert_eq!(format!("{hello_world}"), "hello, world!");
-        let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap();
+        let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0")?;
         assert_eq!(format!("{non_printables}"), "\\x01\\x09\\x0a");
-        let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap();
+        let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0")?;
         assert_eq!(format!("{non_ascii}"), "d\\xe9j\\xe0 vu");
-        let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap();
+        let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0")?;
         assert_eq!(format!("{good_bytes}"), "\\xf0\\x9f\\xa6\\x80");
+        Ok(())
     }
 
     #[test]
-    fn test_cstr_display_all_bytes() {
+    fn test_cstr_display_all_bytes() -> Result {
         let mut bytes: [u8; 256] = [0; 256];
         // fill `bytes` with [1..=255] + [0]
         for i in u8::MIN..=u8::MAX {
             bytes[i as usize] = i.wrapping_add(1);
         }
-        let cstr = CStr::from_bytes_with_nul(&bytes).unwrap();
+        let cstr = CStr::from_bytes_with_nul(&bytes)?;
         assert_eq!(format!("{cstr}"), ALL_ASCII_CHARS);
+        Ok(())
     }
 
     #[test]
-    fn test_cstr_debug() {
-        let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap();
+    fn test_cstr_debug() -> Result {
+        let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0")?;
         assert_eq!(format!("{hello_world:?}"), "\"hello, world!\"");
-        let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap();
+        let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0")?;
         assert_eq!(format!("{non_printables:?}"), "\"\\x01\\x09\\x0a\"");
-        let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap();
+        let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0")?;
         assert_eq!(format!("{non_ascii:?}"), "\"d\\xe9j\\xe0 vu\"");
-        let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap();
+        let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0")?;
         assert_eq!(format!("{good_bytes:?}"), "\"\\xf0\\x9f\\xa6\\x80\"");
+        Ok(())
     }
 
     #[test]
-    fn test_bstr_display() {
+    fn test_bstr_display() -> Result {
         let hello_world = BStr::from_bytes(b"hello, world!");
         assert_eq!(format!("{hello_world}"), "hello, world!");
         let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_");
@@ -685,10 +673,11 @@ mod tests {
         assert_eq!(format!("{non_ascii}"), "d\\xe9j\\xe0 vu");
         let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80");
         assert_eq!(format!("{good_bytes}"), "\\xf0\\x9f\\xa6\\x80");
+        Ok(())
     }
 
     #[test]
-    fn test_bstr_debug() {
+    fn test_bstr_debug() -> Result {
         let hello_world = BStr::from_bytes(b"hello, world!");
         assert_eq!(format!("{hello_world:?}"), "\"hello, world!\"");
         let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_");
@@ -699,6 +688,7 @@ mod tests {
         assert_eq!(format!("{non_ascii:?}"), "\"d\\xe9j\\xe0 vu\"");
         let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80");
         assert_eq!(format!("{good_bytes:?}"), "\"\\xf0\\x9f\\xa6\\x80\"");
+        Ok(())
     }
 }
 
@@ -752,7 +742,7 @@ impl RawFormatter {
     /// for the lifetime of the returned [`RawFormatter`].
     pub(crate) unsafe fn from_buffer(buf: *mut u8, len: usize) -> Self {
         let pos = buf as usize;
-        // INVARIANT: We ensure that `end` is never less then `buf`, and the safety requirements
+        // INVARIANT: We ensure that `end` is never less than `buf`, and the safety requirements
         // guarantees that the memory region is valid for writes.
         Self {
             pos,
@@ -886,7 +876,7 @@ impl CString {
 
         // SAFETY: The number of bytes that can be written to `f` is bounded by `size`, which is
         // `buf`'s capacity. The contents of the buffer have been initialised by writes to `f`.
-        unsafe { buf.set_len(f.bytes_written()) };
+        unsafe { buf.inc_len(f.bytes_written()) };
 
         // Check that there are no `NUL` bytes before the end.
         // SAFETY: The buffer is valid for read because `f.bytes_written()` is bounded by `size`
@@ -944,5 +934,5 @@ impl fmt::Debug for CString {
 /// A convenience alias for [`core::format_args`].
 #[macro_export]
 macro_rules! fmt {
-    ($($f:tt)*) => ( core::format_args!($($f)*) )
+    ($($f:tt)*) => ( ::core::format_args!($($f)*) )
 }
diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs
index 8484c814609a..c7af0aa48a0a 100644
--- a/rust/kernel/sync/arc.rs
+++ b/rust/kernel/sync/arc.rs
@@ -135,14 +135,15 @@ pub struct Arc<T: ?Sized> {
     // meaningful with respect to dropck - but this may change in the future so this is left here
     // out of an abundance of caution.
     //
-    // See https://doc.rust-lang.org/nomicon/phantom-data.html#generic-parameters-and-drop-checking
+    // See <https://doc.rust-lang.org/nomicon/phantom-data.html#generic-parameters-and-drop-checking>
     // for more detail on the semantics of dropck in the presence of `PhantomData`.
     _p: PhantomData<ArcInner<T>>,
 }
 
+#[doc(hidden)]
 #[pin_data]
 #[repr(C)]
-struct ArcInner<T: ?Sized> {
+pub struct ArcInner<T: ?Sized> {
     refcount: Opaque<bindings::refcount_t>,
     data: T,
 }
@@ -371,18 +372,20 @@ impl<T: ?Sized> Arc<T> {
     }
 }
 
-impl<T: 'static> ForeignOwnable for Arc<T> {
+// SAFETY: The `into_foreign` function returns a pointer that is well-aligned.
+unsafe impl<T: 'static> ForeignOwnable for Arc<T> {
+    type PointedTo = ArcInner<T>;
     type Borrowed<'a> = ArcBorrow<'a, T>;
     type BorrowedMut<'a> = Self::Borrowed<'a>;
 
-    fn into_foreign(self) -> *mut crate::ffi::c_void {
-        ManuallyDrop::new(self).ptr.as_ptr().cast()
+    fn into_foreign(self) -> *mut Self::PointedTo {
+        ManuallyDrop::new(self).ptr.as_ptr()
     }
 
-    unsafe fn from_foreign(ptr: *mut crate::ffi::c_void) -> Self {
+    unsafe fn from_foreign(ptr: *mut Self::PointedTo) -> Self {
         // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous
         // call to `Self::into_foreign`.
-        let inner = unsafe { NonNull::new_unchecked(ptr.cast::<ArcInner<T>>()) };
+        let inner = unsafe { NonNull::new_unchecked(ptr) };
 
         // SAFETY: By the safety requirement of this function, we know that `ptr` came from
         // a previous call to `Arc::into_foreign`, which guarantees that `ptr` is valid and
@@ -390,17 +393,17 @@ impl<T: 'static> ForeignOwnable for Arc<T> {
         unsafe { Self::from_inner(inner) }
     }
 
-    unsafe fn borrow<'a>(ptr: *mut crate::ffi::c_void) -> ArcBorrow<'a, T> {
+    unsafe fn borrow<'a>(ptr: *mut Self::PointedTo) -> ArcBorrow<'a, T> {
         // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous
         // call to `Self::into_foreign`.
-        let inner = unsafe { NonNull::new_unchecked(ptr.cast::<ArcInner<T>>()) };
+        let inner = unsafe { NonNull::new_unchecked(ptr) };
 
         // SAFETY: The safety requirements of `from_foreign` ensure that the object remains alive
         // for the lifetime of the returned value.
         unsafe { ArcBorrow::new(inner) }
     }
 
-    unsafe fn borrow_mut<'a>(ptr: *mut crate::ffi::c_void) -> ArcBorrow<'a, T> {
+    unsafe fn borrow_mut<'a>(ptr: *mut Self::PointedTo) -> ArcBorrow<'a, T> {
         // SAFETY: The safety requirements for `borrow_mut` are a superset of the safety
         // requirements for `borrow`.
         unsafe { Self::borrow(ptr) }
@@ -489,7 +492,7 @@ impl<T: ?Sized> From<Pin<UniqueArc<T>>> for Arc<T> {
 /// There are no mutable references to the underlying [`Arc`], and it remains valid for the
 /// lifetime of the [`ArcBorrow`] instance.
 ///
-/// # Example
+/// # Examples
 ///
 /// ```
 /// use kernel::sync::{Arc, ArcBorrow};
diff --git a/rust/kernel/time.rs b/rust/kernel/time.rs
index f509cb0eb71e..a8089a98da9e 100644
--- a/rust/kernel/time.rs
+++ b/rust/kernel/time.rs
@@ -5,14 +5,36 @@
 //! This module contains the kernel APIs related to time and timers that
 //! have been ported or wrapped for usage by Rust code in the kernel.
 //!
+//! There are two types in this module:
+//!
+//! - The [`Instant`] type represents a specific point in time.
+//! - The [`Delta`] type represents a span of time.
+//!
+//! Note that the C side uses `ktime_t` type to represent both. However, timestamp
+//! and timedelta are different. To avoid confusion, we use two different types.
+//!
+//! A [`Instant`] object can be created by calling the [`Instant::now()`] function.
+//! It represents a point in time at which the object was created.
+//! By calling the [`Instant::elapsed()`] method, a [`Delta`] object representing
+//! the elapsed time can be created. The [`Delta`] object can also be created
+//! by subtracting two [`Instant`] objects.
+//!
+//! A [`Delta`] type supports methods to retrieve the duration in various units.
+//!
 //! C header: [`include/linux/jiffies.h`](srctree/include/linux/jiffies.h).
 //! C header: [`include/linux/ktime.h`](srctree/include/linux/ktime.h).
 
 pub mod hrtimer;
 
+/// The number of nanoseconds per microsecond.
+pub const NSEC_PER_USEC: i64 = bindings::NSEC_PER_USEC as i64;
+
 /// The number of nanoseconds per millisecond.
 pub const NSEC_PER_MSEC: i64 = bindings::NSEC_PER_MSEC as i64;
 
+/// The number of nanoseconds per second.
+pub const NSEC_PER_SEC: i64 = bindings::NSEC_PER_SEC as i64;
+
 /// The time unit of Linux kernel. One jiffy equals (1/HZ) second.
 pub type Jiffies = crate::ffi::c_ulong;
 
@@ -27,59 +49,44 @@ pub fn msecs_to_jiffies(msecs: Msecs) -> Jiffies {
     unsafe { bindings::__msecs_to_jiffies(msecs) }
 }
 
-/// A Rust wrapper around a `ktime_t`.
+/// A specific point in time.
+///
+/// # Invariants
+///
+/// The `inner` value is in the range from 0 to `KTIME_MAX`.
 #[repr(transparent)]
-#[derive(Copy, Clone)]
-pub struct Ktime {
+#[derive(Copy, Clone, PartialEq, PartialOrd, Eq, Ord)]
+pub struct Instant {
     inner: bindings::ktime_t,
 }
 
-impl Ktime {
-    /// Create a `Ktime` from a raw `ktime_t`.
-    #[inline]
-    pub fn from_raw(inner: bindings::ktime_t) -> Self {
-        Self { inner }
-    }
-
+impl Instant {
     /// Get the current time using `CLOCK_MONOTONIC`.
     #[inline]
-    pub fn ktime_get() -> Self {
-        // SAFETY: It is always safe to call `ktime_get` outside of NMI context.
-        Self::from_raw(unsafe { bindings::ktime_get() })
-    }
-
-    /// Divide the number of nanoseconds by a compile-time constant.
-    #[inline]
-    fn divns_constant<const DIV: i64>(self) -> i64 {
-        self.to_ns() / DIV
-    }
-
-    /// Returns the number of nanoseconds.
-    #[inline]
-    pub fn to_ns(self) -> i64 {
-        self.inner
+    pub fn now() -> Self {
+        // INVARIANT: The `ktime_get()` function returns a value in the range
+        // from 0 to `KTIME_MAX`.
+        Self {
+            // SAFETY: It is always safe to call `ktime_get()` outside of NMI context.
+            inner: unsafe { bindings::ktime_get() },
+        }
     }
 
-    /// Returns the number of milliseconds.
+    /// Return the amount of time elapsed since the [`Instant`].
     #[inline]
-    pub fn to_ms(self) -> i64 {
-        self.divns_constant::<NSEC_PER_MSEC>()
+    pub fn elapsed(&self) -> Delta {
+        Self::now() - *self
     }
 }
 
-/// Returns the number of milliseconds between two ktimes.
-#[inline]
-pub fn ktime_ms_delta(later: Ktime, earlier: Ktime) -> i64 {
-    (later - earlier).to_ms()
-}
-
-impl core::ops::Sub for Ktime {
-    type Output = Ktime;
+impl core::ops::Sub for Instant {
+    type Output = Delta;
 
+    // By the type invariant, it never overflows.
     #[inline]
-    fn sub(self, other: Ktime) -> Ktime {
-        Self {
-            inner: self.inner - other.inner,
+    fn sub(self, other: Instant) -> Delta {
+        Delta {
+            nanos: self.inner - other.inner,
         }
     }
 }
@@ -149,3 +156,85 @@ impl ClockId {
         self as bindings::clockid_t
     }
 }
+
+/// A span of time.
+///
+/// This struct represents a span of time, with its value stored as nanoseconds.
+/// The value can represent any valid i64 value, including negative, zero, and
+/// positive numbers.
+#[derive(Copy, Clone, PartialEq, PartialOrd, Eq, Ord, Debug)]
+pub struct Delta {
+    nanos: i64,
+}
+
+impl Delta {
+    /// A span of time equal to zero.
+    pub const ZERO: Self = Self { nanos: 0 };
+
+    /// Create a new [`Delta`] from a number of microseconds.
+    ///
+    /// The `micros` can range from -9_223_372_036_854_775 to 9_223_372_036_854_775.
+    /// If `micros` is outside this range, `i64::MIN` is used for negative values,
+    /// and `i64::MAX` is used for positive values due to saturation.
+    #[inline]
+    pub const fn from_micros(micros: i64) -> Self {
+        Self {
+            nanos: micros.saturating_mul(NSEC_PER_USEC),
+        }
+    }
+
+    /// Create a new [`Delta`] from a number of milliseconds.
+    ///
+    /// The `millis` can range from -9_223_372_036_854 to 9_223_372_036_854.
+    /// If `millis` is outside this range, `i64::MIN` is used for negative values,
+    /// and `i64::MAX` is used for positive values due to saturation.
+    #[inline]
+    pub const fn from_millis(millis: i64) -> Self {
+        Self {
+            nanos: millis.saturating_mul(NSEC_PER_MSEC),
+        }
+    }
+
+    /// Create a new [`Delta`] from a number of seconds.
+    ///
+    /// The `secs` can range from -9_223_372_036 to 9_223_372_036.
+    /// If `secs` is outside this range, `i64::MIN` is used for negative values,
+    /// and `i64::MAX` is used for positive values due to saturation.
+    #[inline]
+    pub const fn from_secs(secs: i64) -> Self {
+        Self {
+            nanos: secs.saturating_mul(NSEC_PER_SEC),
+        }
+    }
+
+    /// Return `true` if the [`Delta`] spans no time.
+    #[inline]
+    pub fn is_zero(self) -> bool {
+        self.as_nanos() == 0
+    }
+
+    /// Return `true` if the [`Delta`] spans a negative amount of time.
+    #[inline]
+    pub fn is_negative(self) -> bool {
+        self.as_nanos() < 0
+    }
+
+    /// Return the number of nanoseconds in the [`Delta`].
+    #[inline]
+    pub const fn as_nanos(self) -> i64 {
+        self.nanos
+    }
+
+    /// Return the smallest number of microseconds greater than or equal
+    /// to the value in the [`Delta`].
+    #[inline]
+    pub const fn as_micros_ceil(self) -> i64 {
+        self.as_nanos().saturating_add(NSEC_PER_USEC - 1) / NSEC_PER_USEC
+    }
+
+    /// Return the number of milliseconds in the [`Delta`].
+    #[inline]
+    pub const fn as_millis(self) -> i64 {
+        self.as_nanos() / NSEC_PER_MSEC
+    }
+}
diff --git a/rust/kernel/time/hrtimer.rs b/rust/kernel/time/hrtimer.rs
index ce53f8579d18..9df3dcd2fa39 100644
--- a/rust/kernel/time/hrtimer.rs
+++ b/rust/kernel/time/hrtimer.rs
@@ -68,10 +68,26 @@
 //! `start` operation.
 
 use super::ClockId;
-use crate::{prelude::*, time::Ktime, types::Opaque};
+use crate::{prelude::*, types::Opaque};
 use core::marker::PhantomData;
 use pin_init::PinInit;
 
+/// A Rust wrapper around a `ktime_t`.
+// NOTE: Ktime is going to be removed when hrtimer is converted to Instant/Delta.
+#[repr(transparent)]
+#[derive(Copy, Clone, PartialEq, PartialOrd, Eq, Ord)]
+pub struct Ktime {
+    inner: bindings::ktime_t,
+}
+
+impl Ktime {
+    /// Returns the number of nanoseconds.
+    #[inline]
+    pub fn to_ns(self) -> i64 {
+        self.inner
+    }
+}
+
 /// A timer backed by a C `struct hrtimer`.
 ///
 /// # Invariants
@@ -384,11 +400,9 @@ pub unsafe trait HasHrTimer<T> {
 #[repr(u32)]
 pub enum HrTimerRestart {
     /// Timer should not be restarted.
-    #[allow(clippy::unnecessary_cast)]
-    NoRestart = bindings::hrtimer_restart_HRTIMER_NORESTART as u32,
+    NoRestart = bindings::hrtimer_restart_HRTIMER_NORESTART,
     /// Timer should be restarted.
-    #[allow(clippy::unnecessary_cast)]
-    Restart = bindings::hrtimer_restart_HRTIMER_RESTART as u32,
+    Restart = bindings::hrtimer_restart_HRTIMER_RESTART,
 }
 
 impl HrTimerRestart {
diff --git a/rust/kernel/time/hrtimer/arc.rs b/rust/kernel/time/hrtimer/arc.rs
index 4a984d85b4a1..ccf1e66e5b2d 100644
--- a/rust/kernel/time/hrtimer/arc.rs
+++ b/rust/kernel/time/hrtimer/arc.rs
@@ -5,10 +5,10 @@ use super::HrTimer;
 use super::HrTimerCallback;
 use super::HrTimerHandle;
 use super::HrTimerPointer;
+use super::Ktime;
 use super::RawHrTimerCallback;
 use crate::sync::Arc;
 use crate::sync::ArcBorrow;
-use crate::time::Ktime;
 
 /// A handle for an `Arc<HasHrTimer<T>>` returned by a call to
 /// [`HrTimerPointer::start`].
diff --git a/rust/kernel/time/hrtimer/pin.rs b/rust/kernel/time/hrtimer/pin.rs
index f760db265c7b..293ca9cf058c 100644
--- a/rust/kernel/time/hrtimer/pin.rs
+++ b/rust/kernel/time/hrtimer/pin.rs
@@ -4,9 +4,9 @@ use super::HasHrTimer;
 use super::HrTimer;
 use super::HrTimerCallback;
 use super::HrTimerHandle;
+use super::Ktime;
 use super::RawHrTimerCallback;
 use super::UnsafeHrTimerPointer;
-use crate::time::Ktime;
 use core::pin::Pin;
 
 /// A handle for a `Pin<&HasHrTimer>`. When the handle exists, the timer might be
diff --git a/rust/kernel/time/hrtimer/pin_mut.rs b/rust/kernel/time/hrtimer/pin_mut.rs
index 90c0351d62e4..6033572d35ad 100644
--- a/rust/kernel/time/hrtimer/pin_mut.rs
+++ b/rust/kernel/time/hrtimer/pin_mut.rs
@@ -1,9 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 
 use super::{
-    HasHrTimer, HrTimer, HrTimerCallback, HrTimerHandle, RawHrTimerCallback, UnsafeHrTimerPointer,
+    HasHrTimer, HrTimer, HrTimerCallback, HrTimerHandle, Ktime, RawHrTimerCallback,
+    UnsafeHrTimerPointer,
 };
-use crate::time::Ktime;
 use core::{marker::PhantomData, pin::Pin, ptr::NonNull};
 
 /// A handle for a `Pin<&mut HasHrTimer>`. When the handle exists, the timer might
diff --git a/rust/kernel/time/hrtimer/tbox.rs b/rust/kernel/time/hrtimer/tbox.rs
index 2071cae07234..29526a5da203 100644
--- a/rust/kernel/time/hrtimer/tbox.rs
+++ b/rust/kernel/time/hrtimer/tbox.rs
@@ -5,9 +5,9 @@ use super::HrTimer;
 use super::HrTimerCallback;
 use super::HrTimerHandle;
 use super::HrTimerPointer;
+use super::Ktime;
 use super::RawHrTimerCallback;
 use crate::prelude::*;
-use crate::time::Ktime;
 use core::ptr::NonNull;
 
 /// A handle for a [`Box<HasHrTimer<T>>`] returned by a call to
diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index eee387727d1a..22985b6f6982 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -18,7 +18,19 @@ use pin_init::{PinInit, Zeroable};
 ///
 /// This trait is meant to be used in cases when Rust objects are stored in C objects and
 /// eventually "freed" back to Rust.
-pub trait ForeignOwnable: Sized {
+///
+/// # Safety
+///
+/// Implementers must ensure that [`into_foreign`] returns a pointer which meets the alignment
+/// requirements of [`PointedTo`].
+///
+/// [`into_foreign`]: Self::into_foreign
+/// [`PointedTo`]: Self::PointedTo
+pub unsafe trait ForeignOwnable: Sized {
+    /// Type used when the value is foreign-owned. In practical terms only defines the alignment of
+    /// the pointer.
+    type PointedTo;
+
     /// Type used to immutably borrow a value that is currently foreign-owned.
     type Borrowed<'a>;
 
@@ -27,16 +39,18 @@ pub trait ForeignOwnable: Sized {
 
     /// Converts a Rust-owned object to a foreign-owned one.
     ///
-    /// The foreign representation is a pointer to void. There are no guarantees for this pointer.
-    /// For example, it might be invalid, dangling or pointing to uninitialized memory. Using it in
-    /// any way except for [`from_foreign`], [`try_from_foreign`], [`borrow`], or [`borrow_mut`] can
-    /// result in undefined behavior.
+    /// # Guarantees
+    ///
+    /// The return value is guaranteed to be well-aligned, but there are no other guarantees for
+    /// this pointer. For example, it might be null, dangling, or point to uninitialized memory.
+    /// Using it in any way except for [`ForeignOwnable::from_foreign`], [`ForeignOwnable::borrow`],
+    /// [`ForeignOwnable::try_from_foreign`] can result in undefined behavior.
     ///
     /// [`from_foreign`]: Self::from_foreign
     /// [`try_from_foreign`]: Self::try_from_foreign
     /// [`borrow`]: Self::borrow
     /// [`borrow_mut`]: Self::borrow_mut
-    fn into_foreign(self) -> *mut crate::ffi::c_void;
+    fn into_foreign(self) -> *mut Self::PointedTo;
 
     /// Converts a foreign-owned object back to a Rust-owned one.
     ///
@@ -46,7 +60,7 @@ pub trait ForeignOwnable: Sized {
     /// must not be passed to `from_foreign` more than once.
     ///
     /// [`into_foreign`]: Self::into_foreign
-    unsafe fn from_foreign(ptr: *mut crate::ffi::c_void) -> Self;
+    unsafe fn from_foreign(ptr: *mut Self::PointedTo) -> Self;
 
     /// Tries to convert a foreign-owned object back to a Rust-owned one.
     ///
@@ -58,7 +72,7 @@ pub trait ForeignOwnable: Sized {
     /// `ptr` must either be null or satisfy the safety requirements for [`from_foreign`].
     ///
     /// [`from_foreign`]: Self::from_foreign
-    unsafe fn try_from_foreign(ptr: *mut crate::ffi::c_void) -> Option<Self> {
+    unsafe fn try_from_foreign(ptr: *mut Self::PointedTo) -> Option<Self> {
         if ptr.is_null() {
             None
         } else {
@@ -81,7 +95,7 @@ pub trait ForeignOwnable: Sized {
     ///
     /// [`into_foreign`]: Self::into_foreign
     /// [`from_foreign`]: Self::from_foreign
-    unsafe fn borrow<'a>(ptr: *mut crate::ffi::c_void) -> Self::Borrowed<'a>;
+    unsafe fn borrow<'a>(ptr: *mut Self::PointedTo) -> Self::Borrowed<'a>;
 
     /// Borrows a foreign-owned object mutably.
     ///
@@ -109,21 +123,23 @@ pub trait ForeignOwnable: Sized {
     /// [`from_foreign`]: Self::from_foreign
     /// [`borrow`]: Self::borrow
     /// [`Arc`]: crate::sync::Arc
-    unsafe fn borrow_mut<'a>(ptr: *mut crate::ffi::c_void) -> Self::BorrowedMut<'a>;
+    unsafe fn borrow_mut<'a>(ptr: *mut Self::PointedTo) -> Self::BorrowedMut<'a>;
 }
 
-impl ForeignOwnable for () {
+// SAFETY: The `into_foreign` function returns a pointer that is dangling, but well-aligned.
+unsafe impl ForeignOwnable for () {
+    type PointedTo = ();
     type Borrowed<'a> = ();
     type BorrowedMut<'a> = ();
 
-    fn into_foreign(self) -> *mut crate::ffi::c_void {
+    fn into_foreign(self) -> *mut Self::PointedTo {
         core::ptr::NonNull::dangling().as_ptr()
     }
 
-    unsafe fn from_foreign(_: *mut crate::ffi::c_void) -> Self {}
+    unsafe fn from_foreign(_: *mut Self::PointedTo) -> Self {}
 
-    unsafe fn borrow<'a>(_: *mut crate::ffi::c_void) -> Self::Borrowed<'a> {}
-    unsafe fn borrow_mut<'a>(_: *mut crate::ffi::c_void) -> Self::BorrowedMut<'a> {}
+    unsafe fn borrow<'a>(_: *mut Self::PointedTo) -> Self::Borrowed<'a> {}
+    unsafe fn borrow_mut<'a>(_: *mut Self::PointedTo) -> Self::BorrowedMut<'a> {}
 }
 
 /// Runs a cleanup function/closure when dropped.
diff --git a/rust/kernel/uaccess.rs b/rust/kernel/uaccess.rs
index 80a9782b1c6e..6d70edd8086a 100644
--- a/rust/kernel/uaccess.rs
+++ b/rust/kernel/uaccess.rs
@@ -46,10 +46,9 @@ pub type UserPtr = usize;
 ///
 /// ```no_run
 /// use kernel::ffi::c_void;
-/// use kernel::error::Result;
 /// use kernel::uaccess::{UserPtr, UserSlice};
 ///
-/// fn bytes_add_one(uptr: UserPtr, len: usize) -> Result<()> {
+/// fn bytes_add_one(uptr: UserPtr, len: usize) -> Result {
 ///     let (read, mut write) = UserSlice::new(uptr, len).reader_writer();
 ///
 ///     let mut buf = KVec::new();
@@ -68,7 +67,6 @@ pub type UserPtr = usize;
 ///
 /// ```no_run
 /// use kernel::ffi::c_void;
-/// use kernel::error::{code::EINVAL, Result};
 /// use kernel::uaccess::{UserPtr, UserSlice};
 ///
 /// /// Returns whether the data in this region is valid.
@@ -290,7 +288,7 @@ impl UserSliceReader {
 
         // SAFETY: Since the call to `read_raw` was successful, so the next `len` bytes of the
         // vector have been initialized.
-        unsafe { buf.set_len(buf.len() + len) };
+        unsafe { buf.inc_len(len) };
         Ok(())
     }
 }
diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs
index f98bd02b838f..d092112d843f 100644
--- a/rust/kernel/workqueue.rs
+++ b/rust/kernel/workqueue.rs
@@ -429,51 +429,28 @@ impl<T: ?Sized, const ID: u64> Work<T, ID> {
 ///
 /// # Safety
 ///
-/// The [`OFFSET`] constant must be the offset of a field in `Self` of type [`Work<T, ID>`]. The
-/// methods on this trait must have exactly the behavior that the definitions given below have.
+/// The methods [`raw_get_work`] and [`work_container_of`] must return valid pointers and must be
+/// true inverses of each other; that is, they must satisfy the following invariants:
+/// - `work_container_of(raw_get_work(ptr)) == ptr` for any `ptr: *mut Self`.
+/// - `raw_get_work(work_container_of(ptr)) == ptr` for any `ptr: *mut Work<T, ID>`.
 ///
 /// [`impl_has_work!`]: crate::impl_has_work
-/// [`OFFSET`]: HasWork::OFFSET
+/// [`raw_get_work`]: HasWork::raw_get_work
+/// [`work_container_of`]: HasWork::work_container_of
 pub unsafe trait HasWork<T, const ID: u64 = 0> {
-    /// The offset of the [`Work<T, ID>`] field.
-    const OFFSET: usize;
-
-    /// Returns the offset of the [`Work<T, ID>`] field.
-    ///
-    /// This method exists because the [`OFFSET`] constant cannot be accessed if the type is not
-    /// [`Sized`].
-    ///
-    /// [`OFFSET`]: HasWork::OFFSET
-    #[inline]
-    fn get_work_offset(&self) -> usize {
-        Self::OFFSET
-    }
-
     /// Returns a pointer to the [`Work<T, ID>`] field.
     ///
     /// # Safety
     ///
     /// The provided pointer must point at a valid struct of type `Self`.
-    #[inline]
-    unsafe fn raw_get_work(ptr: *mut Self) -> *mut Work<T, ID> {
-        // SAFETY: The caller promises that the pointer is valid.
-        unsafe { (ptr as *mut u8).add(Self::OFFSET) as *mut Work<T, ID> }
-    }
+    unsafe fn raw_get_work(ptr: *mut Self) -> *mut Work<T, ID>;
 
     /// Returns a pointer to the struct containing the [`Work<T, ID>`] field.
     ///
     /// # Safety
     ///
     /// The pointer must point at a [`Work<T, ID>`] field in a struct of type `Self`.
-    #[inline]
-    unsafe fn work_container_of(ptr: *mut Work<T, ID>) -> *mut Self
-    where
-        Self: Sized,
-    {
-        // SAFETY: The caller promises that the pointer points at a field of the right type in the
-        // right kind of struct.
-        unsafe { (ptr as *mut u8).sub(Self::OFFSET) as *mut Self }
-    }
+    unsafe fn work_container_of(ptr: *mut Work<T, ID>) -> *mut Self;
 }
 
 /// Used to safely implement the [`HasWork<T, ID>`] trait.
@@ -504,8 +481,6 @@ macro_rules! impl_has_work {
         // SAFETY: The implementation of `raw_get_work` only compiles if the field has the right
         // type.
         unsafe impl$(<$($generics)+>)? $crate::workqueue::HasWork<$work_type $(, $id)?> for $self {
-            const OFFSET: usize = ::core::mem::offset_of!(Self, $field) as usize;
-
             #[inline]
             unsafe fn raw_get_work(ptr: *mut Self) -> *mut $crate::workqueue::Work<$work_type $(, $id)?> {
                 // SAFETY: The caller promises that the pointer is not dangling.
@@ -513,6 +488,15 @@ macro_rules! impl_has_work {
                     ::core::ptr::addr_of_mut!((*ptr).$field)
                 }
             }
+
+            #[inline]
+            unsafe fn work_container_of(
+                ptr: *mut $crate::workqueue::Work<$work_type $(, $id)?>,
+            ) -> *mut Self {
+                // SAFETY: The caller promises that the pointer points at a field of the right type
+                // in the right kind of struct.
+                unsafe { $crate::container_of!(ptr, Self, $field) }
+            }
         }
     )*};
 }
diff --git a/rust/kernel/xarray.rs b/rust/kernel/xarray.rs
new file mode 100644
index 000000000000..75719e7bb491
--- /dev/null
+++ b/rust/kernel/xarray.rs
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! XArray abstraction.
+//!
+//! C header: [`include/linux/xarray.h`](srctree/include/linux/xarray.h)
+
+use crate::{
+    alloc, bindings, build_assert,
+    error::{Error, Result},
+    types::{ForeignOwnable, NotThreadSafe, Opaque},
+};
+use core::{iter, marker::PhantomData, mem, pin::Pin, ptr::NonNull};
+use pin_init::{pin_data, pin_init, pinned_drop, PinInit};
+
+/// An array which efficiently maps sparse integer indices to owned objects.
+///
+/// This is similar to a [`crate::alloc::kvec::Vec<Option<T>>`], but more efficient when there are
+/// holes in the index space, and can be efficiently grown.
+///
+/// # Invariants
+///
+/// `self.xa` is always an initialized and valid [`bindings::xarray`] whose entries are either
+/// `XA_ZERO_ENTRY` or came from `T::into_foreign`.
+///
+/// # Examples
+///
+/// ```rust
+/// use kernel::alloc::KBox;
+/// use kernel::xarray::{AllocKind, XArray};
+///
+/// let xa = KBox::pin_init(XArray::new(AllocKind::Alloc1), GFP_KERNEL)?;
+///
+/// let dead = KBox::new(0xdead, GFP_KERNEL)?;
+/// let beef = KBox::new(0xbeef, GFP_KERNEL)?;
+///
+/// let mut guard = xa.lock();
+///
+/// assert_eq!(guard.get(0), None);
+///
+/// assert_eq!(guard.store(0, dead, GFP_KERNEL)?.as_deref(), None);
+/// assert_eq!(guard.get(0).copied(), Some(0xdead));
+///
+/// *guard.get_mut(0).unwrap() = 0xffff;
+/// assert_eq!(guard.get(0).copied(), Some(0xffff));
+///
+/// assert_eq!(guard.store(0, beef, GFP_KERNEL)?.as_deref().copied(), Some(0xffff));
+/// assert_eq!(guard.get(0).copied(), Some(0xbeef));
+///
+/// guard.remove(0);
+/// assert_eq!(guard.get(0), None);
+///
+/// # Ok::<(), Error>(())
+/// ```
+#[pin_data(PinnedDrop)]
+pub struct XArray<T: ForeignOwnable> {
+    #[pin]
+    xa: Opaque<bindings::xarray>,
+    _p: PhantomData<T>,
+}
+
+#[pinned_drop]
+impl<T: ForeignOwnable> PinnedDrop for XArray<T> {
+    fn drop(self: Pin<&mut Self>) {
+        self.iter().for_each(|ptr| {
+            let ptr = ptr.as_ptr();
+            // SAFETY: `ptr` came from `T::into_foreign`.
+            //
+            // INVARIANT: we own the only reference to the array which is being dropped so the
+            // broken invariant is not observable on function exit.
+            drop(unsafe { T::from_foreign(ptr) })
+        });
+
+        // SAFETY: `self.xa` is always valid by the type invariant.
+        unsafe { bindings::xa_destroy(self.xa.get()) };
+    }
+}
+
+/// Flags passed to [`XArray::new`] to configure the array's allocation tracking behavior.
+pub enum AllocKind {
+    /// Consider the first element to be at index 0.
+    Alloc,
+    /// Consider the first element to be at index 1.
+    Alloc1,
+}
+
+impl<T: ForeignOwnable> XArray<T> {
+    /// Creates a new initializer for this type.
+    pub fn new(kind: AllocKind) -> impl PinInit<Self> {
+        let flags = match kind {
+            AllocKind::Alloc => bindings::XA_FLAGS_ALLOC,
+            AllocKind::Alloc1 => bindings::XA_FLAGS_ALLOC1,
+        };
+        pin_init!(Self {
+            // SAFETY: `xa` is valid while the closure is called.
+            //
+            // INVARIANT: `xa` is initialized here to an empty, valid [`bindings::xarray`].
+            xa <- Opaque::ffi_init(|xa| unsafe {
+                bindings::xa_init_flags(xa, flags)
+            }),
+            _p: PhantomData,
+        })
+    }
+
+    fn iter(&self) -> impl Iterator<Item = NonNull<T::PointedTo>> + '_ {
+        let mut index = 0;
+
+        // SAFETY: `self.xa` is always valid by the type invariant.
+        iter::once(unsafe {
+            bindings::xa_find(self.xa.get(), &mut index, usize::MAX, bindings::XA_PRESENT)
+        })
+        .chain(iter::from_fn(move || {
+            // SAFETY: `self.xa` is always valid by the type invariant.
+            Some(unsafe {
+                bindings::xa_find_after(self.xa.get(), &mut index, usize::MAX, bindings::XA_PRESENT)
+            })
+        }))
+        .map_while(|ptr| NonNull::new(ptr.cast()))
+    }
+
+    /// Attempts to lock the [`XArray`] for exclusive access.
+    pub fn try_lock(&self) -> Option<Guard<'_, T>> {
+        // SAFETY: `self.xa` is always valid by the type invariant.
+        if (unsafe { bindings::xa_trylock(self.xa.get()) } != 0) {
+            Some(Guard {
+                xa: self,
+                _not_send: NotThreadSafe,
+            })
+        } else {
+            None
+        }
+    }
+
+    /// Locks the [`XArray`] for exclusive access.
+    pub fn lock(&self) -> Guard<'_, T> {
+        // SAFETY: `self.xa` is always valid by the type invariant.
+        unsafe { bindings::xa_lock(self.xa.get()) };
+
+        Guard {
+            xa: self,
+            _not_send: NotThreadSafe,
+        }
+    }
+}
+
+/// A lock guard.
+///
+/// The lock is unlocked when the guard goes out of scope.
+#[must_use = "the lock unlocks immediately when the guard is unused"]
+pub struct Guard<'a, T: ForeignOwnable> {
+    xa: &'a XArray<T>,
+    _not_send: NotThreadSafe,
+}
+
+impl<T: ForeignOwnable> Drop for Guard<'_, T> {
+    fn drop(&mut self) {
+        // SAFETY:
+        // - `self.xa.xa` is always valid by the type invariant.
+        // - The caller holds the lock, so it is safe to unlock it.
+        unsafe { bindings::xa_unlock(self.xa.xa.get()) };
+    }
+}
+
+/// The error returned by [`store`](Guard::store).
+///
+/// Contains the underlying error and the value that was not stored.
+pub struct StoreError<T> {
+    /// The error that occurred.
+    pub error: Error,
+    /// The value that was not stored.
+    pub value: T,
+}
+
+impl<T> From<StoreError<T>> for Error {
+    fn from(value: StoreError<T>) -> Self {
+        value.error
+    }
+}
+
+impl<'a, T: ForeignOwnable> Guard<'a, T> {
+    fn load<F, U>(&self, index: usize, f: F) -> Option<U>
+    where
+        F: FnOnce(NonNull<T::PointedTo>) -> U,
+    {
+        // SAFETY: `self.xa.xa` is always valid by the type invariant.
+        let ptr = unsafe { bindings::xa_load(self.xa.xa.get(), index) };
+        let ptr = NonNull::new(ptr.cast())?;
+        Some(f(ptr))
+    }
+
+    /// Provides a reference to the element at the given index.
+    pub fn get(&self, index: usize) -> Option<T::Borrowed<'_>> {
+        self.load(index, |ptr| {
+            // SAFETY: `ptr` came from `T::into_foreign`.
+            unsafe { T::borrow(ptr.as_ptr()) }
+        })
+    }
+
+    /// Provides a mutable reference to the element at the given index.
+    pub fn get_mut(&mut self, index: usize) -> Option<T::BorrowedMut<'_>> {
+        self.load(index, |ptr| {
+            // SAFETY: `ptr` came from `T::into_foreign`.
+            unsafe { T::borrow_mut(ptr.as_ptr()) }
+        })
+    }
+
+    /// Removes and returns the element at the given index.
+    pub fn remove(&mut self, index: usize) -> Option<T> {
+        // SAFETY:
+        // - `self.xa.xa` is always valid by the type invariant.
+        // - The caller holds the lock.
+        let ptr = unsafe { bindings::__xa_erase(self.xa.xa.get(), index) }.cast();
+        // SAFETY:
+        // - `ptr` is either NULL or came from `T::into_foreign`.
+        // - `&mut self` guarantees that the lifetimes of [`T::Borrowed`] and [`T::BorrowedMut`]
+        // borrowed from `self` have ended.
+        unsafe { T::try_from_foreign(ptr) }
+    }
+
+    /// Stores an element at the given index.
+    ///
+    /// May drop the lock if needed to allocate memory, and then reacquire it afterwards.
+    ///
+    /// On success, returns the element which was previously at the given index.
+    ///
+    /// On failure, returns the element which was attempted to be stored.
+    pub fn store(
+        &mut self,
+        index: usize,
+        value: T,
+        gfp: alloc::Flags,
+    ) -> Result<Option<T>, StoreError<T>> {
+        build_assert!(
+            mem::align_of::<T::PointedTo>() >= 4,
+            "pointers stored in XArray must be 4-byte aligned"
+        );
+        let new = value.into_foreign();
+
+        let old = {
+            let new = new.cast();
+            // SAFETY:
+            // - `self.xa.xa` is always valid by the type invariant.
+            // - The caller holds the lock.
+            //
+            // INVARIANT: `new` came from `T::into_foreign`.
+            unsafe { bindings::__xa_store(self.xa.xa.get(), index, new, gfp.as_raw()) }
+        };
+
+        // SAFETY: `__xa_store` returns the old entry at this index on success or `xa_err` if an
+        // error happened.
+        let errno = unsafe { bindings::xa_err(old) };
+        if errno != 0 {
+            // SAFETY: `new` came from `T::into_foreign` and `__xa_store` does not take
+            // ownership of the value on error.
+            let value = unsafe { T::from_foreign(new) };
+            Err(StoreError {
+                value,
+                error: Error::from_errno(errno),
+            })
+        } else {
+            let old = old.cast();
+            // SAFETY: `ptr` is either NULL or came from `T::into_foreign`.
+            //
+            // NB: `XA_ZERO_ENTRY` is never returned by functions belonging to the Normal XArray
+            // API; such entries present as `NULL`.
+            Ok(unsafe { T::try_from_foreign(old) })
+        }
+    }
+}
+
+// SAFETY: `XArray<T>` has no shared mutable state so it is `Send` iff `T` is `Send`.
+unsafe impl<T: ForeignOwnable + Send> Send for XArray<T> {}
+
+// SAFETY: `XArray<T>` serialises the interior mutability it provides so it is `Sync` iff `T` is
+// `Send`.
+unsafe impl<T: ForeignOwnable + Send> Sync for XArray<T> {}
diff --git a/rust/macros/helpers.rs b/rust/macros/helpers.rs
index a3ee27e29a6f..e2602be402c1 100644
--- a/rust/macros/helpers.rs
+++ b/rust/macros/helpers.rs
@@ -86,3 +86,20 @@ pub(crate) fn function_name(input: TokenStream) -> Option<Ident> {
     }
     None
 }
+
+pub(crate) fn file() -> String {
+    #[cfg(not(CONFIG_RUSTC_HAS_SPAN_FILE))]
+    {
+        proc_macro::Span::call_site()
+            .source_file()
+            .path()
+            .to_string_lossy()
+            .into_owned()
+    }
+
+    #[cfg(CONFIG_RUSTC_HAS_SPAN_FILE)]
+    #[allow(clippy::incompatible_msrv)]
+    {
+        proc_macro::Span::call_site().file()
+    }
+}
diff --git a/rust/macros/kunit.rs b/rust/macros/kunit.rs
index 99ccac82edde..81d18149a0cc 100644
--- a/rust/macros/kunit.rs
+++ b/rust/macros/kunit.rs
@@ -57,8 +57,8 @@ pub(crate) fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream {
         }
     }
 
-    // Add `#[cfg(CONFIG_KUNIT)]` before the module declaration.
-    let config_kunit = "#[cfg(CONFIG_KUNIT)]".to_owned().parse().unwrap();
+    // Add `#[cfg(CONFIG_KUNIT="y")]` before the module declaration.
+    let config_kunit = "#[cfg(CONFIG_KUNIT=\"y\")]".to_owned().parse().unwrap();
     tokens.insert(
         0,
         TokenTree::Group(Group::new(Delimiter::None, config_kunit)),
@@ -85,28 +85,52 @@ pub(crate) fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream {
     // Looks like:
     //
     // ```
-    // unsafe extern "C" fn kunit_rust_wrapper_foo(_test: *mut kernel::bindings::kunit) { foo(); }
-    // unsafe extern "C" fn kunit_rust_wrapper_bar(_test: *mut kernel::bindings::kunit) { bar(); }
+    // unsafe extern "C" fn kunit_rust_wrapper_foo(_test: *mut ::kernel::bindings::kunit) { foo(); }
+    // unsafe extern "C" fn kunit_rust_wrapper_bar(_test: *mut ::kernel::bindings::kunit) { bar(); }
     //
-    // static mut TEST_CASES: [kernel::bindings::kunit_case; 3] = [
-    //     kernel::kunit::kunit_case(kernel::c_str!("foo"), kunit_rust_wrapper_foo),
-    //     kernel::kunit::kunit_case(kernel::c_str!("bar"), kunit_rust_wrapper_bar),
-    //     kernel::kunit::kunit_case_null(),
+    // static mut TEST_CASES: [::kernel::bindings::kunit_case; 3] = [
+    //     ::kernel::kunit::kunit_case(::kernel::c_str!("foo"), kunit_rust_wrapper_foo),
+    //     ::kernel::kunit::kunit_case(::kernel::c_str!("bar"), kunit_rust_wrapper_bar),
+    //     ::kernel::kunit::kunit_case_null(),
     // ];
     //
-    // kernel::kunit_unsafe_test_suite!(kunit_test_suit_name, TEST_CASES);
+    // ::kernel::kunit_unsafe_test_suite!(kunit_test_suit_name, TEST_CASES);
     // ```
     let mut kunit_macros = "".to_owned();
     let mut test_cases = "".to_owned();
+    let mut assert_macros = "".to_owned();
+    let path = crate::helpers::file();
     for test in &tests {
         let kunit_wrapper_fn_name = format!("kunit_rust_wrapper_{test}");
+        // An extra `use` is used here to reduce the length of the message.
         let kunit_wrapper = format!(
-            "unsafe extern \"C\" fn {kunit_wrapper_fn_name}(_test: *mut kernel::bindings::kunit) {{ {test}(); }}"
+            "unsafe extern \"C\" fn {kunit_wrapper_fn_name}(_test: *mut ::kernel::bindings::kunit) {{ use ::kernel::kunit::is_test_result_ok; assert!(is_test_result_ok({test}())); }}",
         );
         writeln!(kunit_macros, "{kunit_wrapper}").unwrap();
         writeln!(
             test_cases,
-            "    kernel::kunit::kunit_case(kernel::c_str!(\"{test}\"), {kunit_wrapper_fn_name}),"
+            "    ::kernel::kunit::kunit_case(::kernel::c_str!(\"{test}\"), {kunit_wrapper_fn_name}),"
+        )
+        .unwrap();
+        writeln!(
+            assert_macros,
+            r#"
+/// Overrides the usual [`assert!`] macro with one that calls KUnit instead.
+#[allow(unused)]
+macro_rules! assert {{
+    ($cond:expr $(,)?) => {{{{
+        kernel::kunit_assert!("{test}", "{path}", 0, $cond);
+    }}}}
+}}
+
+/// Overrides the usual [`assert_eq!`] macro with one that calls KUnit instead.
+#[allow(unused)]
+macro_rules! assert_eq {{
+    ($left:expr, $right:expr $(,)?) => {{{{
+        kernel::kunit_assert_eq!("{test}", "{path}", 0, $left, $right);
+    }}}}
+}}
+        "#
         )
         .unwrap();
     }
@@ -114,14 +138,14 @@ pub(crate) fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream {
     writeln!(kunit_macros).unwrap();
     writeln!(
         kunit_macros,
-        "static mut TEST_CASES: [kernel::bindings::kunit_case; {}] = [\n{test_cases}    kernel::kunit::kunit_case_null(),\n];",
+        "static mut TEST_CASES: [::kernel::bindings::kunit_case; {}] = [\n{test_cases}    ::kernel::kunit::kunit_case_null(),\n];",
         tests.len() + 1
     )
     .unwrap();
 
     writeln!(
         kunit_macros,
-        "kernel::kunit_unsafe_test_suite!({attr}, TEST_CASES);"
+        "::kernel::kunit_unsafe_test_suite!({attr}, TEST_CASES);"
     )
     .unwrap();
 
@@ -147,10 +171,12 @@ pub(crate) fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream {
         }
     }
 
-    let mut new_body = TokenStream::from_iter(new_body);
-    new_body.extend::<TokenStream>(kunit_macros.parse().unwrap());
+    let mut final_body = TokenStream::new();
+    final_body.extend::<TokenStream>(assert_macros.parse().unwrap());
+    final_body.extend(new_body);
+    final_body.extend::<TokenStream>(kunit_macros.parse().unwrap());
 
-    tokens.push(TokenTree::Group(Group::new(Delimiter::Brace, new_body)));
+    tokens.push(TokenTree::Group(Group::new(Delimiter::Brace, final_body)));
 
     tokens.into_iter().collect()
 }
diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index 9acaa68c974e..fa847cf3a9b5 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -6,6 +6,11 @@
 // and thus add a dependency on `include/config/RUSTC_VERSION_TEXT`, which is
 // touched by Kconfig when the version string from the compiler changes.
 
+// Stable since Rust 1.88.0 under a different name, `proc_macro_span_file`,
+// which was added in Rust 1.88.0. This is why `cfg_attr` is used here, i.e.
+// to avoid depending on the full `proc_macro_span` on Rust >= 1.88.0.
+#![cfg_attr(not(CONFIG_RUSTC_HAS_SPAN_FILE), feature(proc_macro_span))]
+
 #[macro_use]
 mod quote;
 mod concat_idents;
@@ -263,7 +268,7 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream {
 /// literals (lifetimes and documentation strings are not supported). There is a difference in
 /// supported modifiers as well.
 ///
-/// # Example
+/// # Examples
 ///
 /// ```
 /// # const binder_driver_return_protocol_BR_OK: u32 = 0;
@@ -283,7 +288,7 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream {
 /// # const binder_driver_return_protocol_BR_FAILED_REPLY: u32 = 14;
 /// macro_rules! pub_no_prefix {
 ///     ($prefix:ident, $($newname:ident),+) => {
-///         kernel::macros::paste! {
+///         ::kernel::macros::paste! {
 ///             $(pub(crate) const $newname: u32 = [<$prefix $newname>];)+
 ///         }
 ///     };
@@ -340,7 +345,7 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream {
 /// # const binder_driver_return_protocol_BR_FAILED_REPLY: u32 = 14;
 /// macro_rules! pub_no_prefix {
 ///     ($prefix:ident, $($newname:ident),+) => {
-///         kernel::macros::paste! {
+///         ::kernel::macros::paste! {
 ///             $(pub(crate) const fn [<$newname:lower:span>]() -> u32 { [<$prefix $newname:span>] })+
 ///         }
 ///     };
@@ -375,7 +380,7 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream {
 /// ```
 /// macro_rules! create_numbered_fn {
 ///     ($name:literal, $val:literal) => {
-///         kernel::macros::paste! {
+///         ::kernel::macros::paste! {
 ///             fn [<some_ $name _fn $val>]() -> u32 { $val }
 ///         }
 ///     };
@@ -402,7 +407,7 @@ pub fn paste(input: TokenStream) -> TokenStream {
 /// # Examples
 ///
 /// ```ignore
-/// # use macros::kunit_tests;
+/// # use kernel::prelude::*;
 /// #[kunit_tests(kunit_test_suit_name)]
 /// mod tests {
 ///     #[test]
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index c4afdd69e490..2ddd2eeb2852 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -217,24 +217,24 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
             // SAFETY: `__this_module` is constructed by the kernel at load time and will not be
             // freed until the module is unloaded.
             #[cfg(MODULE)]
-            static THIS_MODULE: kernel::ThisModule = unsafe {{
+            static THIS_MODULE: ::kernel::ThisModule = unsafe {{
                 extern \"C\" {{
-                    static __this_module: kernel::types::Opaque<kernel::bindings::module>;
+                    static __this_module: ::kernel::types::Opaque<::kernel::bindings::module>;
                 }}
 
-                kernel::ThisModule::from_ptr(__this_module.get())
+                ::kernel::ThisModule::from_ptr(__this_module.get())
             }};
             #[cfg(not(MODULE))]
-            static THIS_MODULE: kernel::ThisModule = unsafe {{
-                kernel::ThisModule::from_ptr(core::ptr::null_mut())
+            static THIS_MODULE: ::kernel::ThisModule = unsafe {{
+                ::kernel::ThisModule::from_ptr(::core::ptr::null_mut())
             }};
 
             /// The `LocalModule` type is the type of the module created by `module!`,
             /// `module_pci_driver!`, `module_platform_driver!`, etc.
             type LocalModule = {type_};
 
-            impl kernel::ModuleMetadata for {type_} {{
-                const NAME: &'static kernel::str::CStr = kernel::c_str!(\"{name}\");
+            impl ::kernel::ModuleMetadata for {type_} {{
+                const NAME: &'static ::kernel::str::CStr = ::kernel::c_str!(\"{name}\");
             }}
 
             // Double nested modules, since then nobody can access the public items inside.
@@ -252,8 +252,8 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
                     #[used]
                     static __IS_RUST_MODULE: () = ();
 
-                    static mut __MOD: core::mem::MaybeUninit<{type_}> =
-                        core::mem::MaybeUninit::uninit();
+                    static mut __MOD: ::core::mem::MaybeUninit<{type_}> =
+                        ::core::mem::MaybeUninit::uninit();
 
                     // Loadable modules need to export the `{{init,cleanup}}_module` identifiers.
                     /// # Safety
@@ -264,7 +264,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
                     #[doc(hidden)]
                     #[no_mangle]
                     #[link_section = \".init.text\"]
-                    pub unsafe extern \"C\" fn init_module() -> kernel::ffi::c_int {{
+                    pub unsafe extern \"C\" fn init_module() -> ::kernel::ffi::c_int {{
                         // SAFETY: This function is inaccessible to the outside due to the double
                         // module wrapping it. It is called exactly once by the C side via its
                         // unique name.
@@ -280,6 +280,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
                     #[cfg(MODULE)]
                     #[doc(hidden)]
                     #[no_mangle]
+                    #[link_section = \".exit.text\"]
                     pub extern \"C\" fn cleanup_module() {{
                         // SAFETY:
                         // - This function is inaccessible to the outside due to the double
@@ -304,11 +305,11 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
                     #[link_section = \"{initcall_section}\"]
                     #[used]
                     pub static __{ident}_initcall: extern \"C\" fn() ->
-                        kernel::ffi::c_int = __{ident}_init;
+                        ::kernel::ffi::c_int = __{ident}_init;
 
                     #[cfg(not(MODULE))]
                     #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)]
-                    core::arch::global_asm!(
+                    ::core::arch::global_asm!(
                         r#\".section \"{initcall_section}\", \"a\"
                         __{ident}_initcall:
                             .long   __{ident}_init - .
@@ -319,7 +320,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
                     #[cfg(not(MODULE))]
                     #[doc(hidden)]
                     #[no_mangle]
-                    pub extern \"C\" fn __{ident}_init() -> kernel::ffi::c_int {{
+                    pub extern \"C\" fn __{ident}_init() -> ::kernel::ffi::c_int {{
                         // SAFETY: This function is inaccessible to the outside due to the double
                         // module wrapping it. It is called exactly once by the C side via its
                         // placement above in the initcall section.
@@ -342,9 +343,9 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
                     /// # Safety
                     ///
                     /// This function must only be called once.
-                    unsafe fn __init() -> kernel::ffi::c_int {{
+                    unsafe fn __init() -> ::kernel::ffi::c_int {{
                         let initer =
-                            <{type_} as kernel::InPlaceModule>::init(&super::super::THIS_MODULE);
+                            <{type_} as ::kernel::InPlaceModule>::init(&super::super::THIS_MODULE);
                         // SAFETY: No data race, since `__MOD` can only be accessed by this module
                         // and there only `__init` and `__exit` access it. These functions are only
                         // called once and `__exit` cannot be called before or during `__init`.
diff --git a/rust/pin-init/README.md b/rust/pin-init/README.md
index 3d04796b212b..2d0cda961d45 100644
--- a/rust/pin-init/README.md
+++ b/rust/pin-init/README.md
@@ -40,6 +40,12 @@ However, using the crate on stable compilers is possible by disabling `alloc`. I
 will require the `std` feature, because stable compilers have neither `Box` nor `Arc` in no-std
 mode.
 
+### Nightly needed for `unsafe-pinned` feature
+
+This feature enables the `Wrapper` implementation on the unstable `core::pin::UnsafePinned` type.
+This requires the [`unsafe_pinned` unstable feature](https://github.com/rust-lang/rust/issues/125735)
+and therefore a nightly compiler. Note that this feature is not enabled by default.
+
 ## Overview
 
 To initialize a `struct` with an in-place constructor you will need two things:
@@ -216,13 +222,15 @@ the `kernel` crate. The [`sync`] module is a good starting point.
 
 [`sync`]: https://rust.docs.kernel.org/kernel/sync/index.html
 [pinning]: https://doc.rust-lang.org/std/pin/index.html
-[structurally pinned fields]: https://doc.rust-lang.org/std/pin/index.html#pinning-is-structural-for-field
+[structurally pinned fields]: https://doc.rust-lang.org/std/pin/index.html#projections-and-structural-pinning
 [stack]: https://docs.rs/pin-init/latest/pin_init/macro.stack_pin_init.html
-[`Arc<T>`]: https://doc.rust-lang.org/stable/alloc/sync/struct.Arc.html
-[`Box<T>`]: https://doc.rust-lang.org/stable/alloc/boxed/struct.Box.html
 [`impl PinInit<Foo>`]: https://docs.rs/pin-init/latest/pin_init/trait.PinInit.html
 [`impl PinInit<T, E>`]: https://docs.rs/pin-init/latest/pin_init/trait.PinInit.html
 [`impl Init<T, E>`]: https://docs.rs/pin-init/latest/pin_init/trait.Init.html
 [Rust-for-Linux]: https://rust-for-linux.com/
 
 <!-- cargo-rdme end -->
+
+<!-- These links are not picked up by cargo-rdme, since they are behind cfgs... -->
+[`Arc<T>`]: https://doc.rust-lang.org/stable/alloc/sync/struct.Arc.html
+[`Box<T>`]: https://doc.rust-lang.org/stable/alloc/boxed/struct.Box.html
diff --git a/rust/pin-init/examples/linked_list.rs b/rust/pin-init/examples/linked_list.rs
index 6d7eb0a0ec0d..0bbc7b8d83a1 100644
--- a/rust/pin-init/examples/linked_list.rs
+++ b/rust/pin-init/examples/linked_list.rs
@@ -2,6 +2,7 @@
 
 #![allow(clippy::undocumented_unsafe_blocks)]
 #![cfg_attr(feature = "alloc", feature(allocator_api))]
+#![cfg_attr(not(RUSTC_LINT_REASONS_IS_STABLE), feature(lint_reasons))]
 
 use core::{
     cell::Cell,
diff --git a/rust/pin-init/examples/mutex.rs b/rust/pin-init/examples/mutex.rs
index 073bb79341d1..3e3630780c96 100644
--- a/rust/pin-init/examples/mutex.rs
+++ b/rust/pin-init/examples/mutex.rs
@@ -2,6 +2,7 @@
 
 #![allow(clippy::undocumented_unsafe_blocks)]
 #![cfg_attr(feature = "alloc", feature(allocator_api))]
+#![cfg_attr(not(RUSTC_LINT_REASONS_IS_STABLE), feature(lint_reasons))]
 #![allow(clippy::missing_safety_doc)]
 
 use core::{
diff --git a/rust/pin-init/examples/pthread_mutex.rs b/rust/pin-init/examples/pthread_mutex.rs
index 5ac22f1880d2..5acc5108b954 100644
--- a/rust/pin-init/examples/pthread_mutex.rs
+++ b/rust/pin-init/examples/pthread_mutex.rs
@@ -3,6 +3,8 @@
 // inspired by <https://github.com/nbdd0121/pin-init/blob/trunk/examples/pthread_mutex.rs>
 #![allow(clippy::undocumented_unsafe_blocks)]
 #![cfg_attr(feature = "alloc", feature(allocator_api))]
+#![cfg_attr(not(RUSTC_LINT_REASONS_IS_STABLE), feature(lint_reasons))]
+
 #[cfg(not(windows))]
 mod pthread_mtx {
     #[cfg(feature = "alloc")]
@@ -40,7 +42,7 @@ mod pthread_mtx {
 
     #[derive(Debug)]
     pub enum Error {
-        #[expect(dead_code)]
+        #[allow(dead_code)]
         IO(std::io::Error),
         Alloc,
     }
diff --git a/rust/pin-init/examples/static_init.rs b/rust/pin-init/examples/static_init.rs
index 3487d761aa26..48531413ab94 100644
--- a/rust/pin-init/examples/static_init.rs
+++ b/rust/pin-init/examples/static_init.rs
@@ -2,6 +2,7 @@
 
 #![allow(clippy::undocumented_unsafe_blocks)]
 #![cfg_attr(feature = "alloc", feature(allocator_api))]
+#![cfg_attr(not(RUSTC_LINT_REASONS_IS_STABLE), feature(lint_reasons))]
 
 use core::{
     cell::{Cell, UnsafeCell},
diff --git a/rust/pin-init/internal/src/lib.rs b/rust/pin-init/internal/src/lib.rs
index babe5e878550..297b0129a5bf 100644
--- a/rust/pin-init/internal/src/lib.rs
+++ b/rust/pin-init/internal/src/lib.rs
@@ -22,6 +22,7 @@ use proc_macro::TokenStream;
 #[cfg(kernel)]
 #[path = "../../../macros/quote.rs"]
 #[macro_use]
+#[cfg_attr(not(kernel), rustfmt::skip)]
 mod quote;
 #[cfg(not(kernel))]
 #[macro_use]
@@ -46,3 +47,8 @@ pub fn pinned_drop(args: TokenStream, input: TokenStream) -> TokenStream {
 pub fn derive_zeroable(input: TokenStream) -> TokenStream {
     zeroable::derive(input.into()).into()
 }
+
+#[proc_macro_derive(MaybeZeroable)]
+pub fn maybe_derive_zeroable(input: TokenStream) -> TokenStream {
+    zeroable::maybe_derive(input.into()).into()
+}
diff --git a/rust/pin-init/internal/src/zeroable.rs b/rust/pin-init/internal/src/zeroable.rs
index acc94008c152..e0ed3998445c 100644
--- a/rust/pin-init/internal/src/zeroable.rs
+++ b/rust/pin-init/internal/src/zeroable.rs
@@ -6,7 +6,14 @@ use proc_macro2 as proc_macro;
 use crate::helpers::{parse_generics, Generics};
 use proc_macro::{TokenStream, TokenTree};
 
-pub(crate) fn derive(input: TokenStream) -> TokenStream {
+pub(crate) fn parse_zeroable_derive_input(
+    input: TokenStream,
+) -> (
+    Vec<TokenTree>,
+    Vec<TokenTree>,
+    Vec<TokenTree>,
+    Option<TokenTree>,
+) {
     let (
         Generics {
             impl_generics,
@@ -64,6 +71,11 @@ pub(crate) fn derive(input: TokenStream) -> TokenStream {
     if in_generic && !inserted {
         new_impl_generics.extend(quote! { : ::pin_init::Zeroable });
     }
+    (rest, new_impl_generics, ty_generics, last)
+}
+
+pub(crate) fn derive(input: TokenStream) -> TokenStream {
+    let (rest, new_impl_generics, ty_generics, last) = parse_zeroable_derive_input(input);
     quote! {
         ::pin_init::__derive_zeroable!(
             parse_input:
@@ -74,3 +86,16 @@ pub(crate) fn derive(input: TokenStream) -> TokenStream {
         );
     }
 }
+
+pub(crate) fn maybe_derive(input: TokenStream) -> TokenStream {
+    let (rest, new_impl_generics, ty_generics, last) = parse_zeroable_derive_input(input);
+    quote! {
+        ::pin_init::__maybe_derive_zeroable!(
+            parse_input:
+                @sig(#(#rest)*),
+                @impl_generics(#(#new_impl_generics)*),
+                @ty_generics(#(#ty_generics)*),
+                @body(#last),
+        );
+    }
+}
diff --git a/rust/pin-init/src/lib.rs b/rust/pin-init/src/lib.rs
index 0806c689f693..9ab34036e6bc 100644
--- a/rust/pin-init/src/lib.rs
+++ b/rust/pin-init/src/lib.rs
@@ -32,6 +32,12 @@
 //! will require the `std` feature, because stable compilers have neither `Box` nor `Arc` in no-std
 //! mode.
 //!
+//! ## Nightly needed for `unsafe-pinned` feature
+//!
+//! This feature enables the `Wrapper` implementation on the unstable `core::pin::UnsafePinned` type.
+//! This requires the [`unsafe_pinned` unstable feature](https://github.com/rust-lang/rust/issues/125735)
+//! and therefore a nightly compiler. Note that this feature is not enabled by default.
+//!
 //! # Overview
 //!
 //! To initialize a `struct` with an in-place constructor you will need two things:
@@ -241,7 +247,7 @@
 //! [`sync`]: https://rust.docs.kernel.org/kernel/sync/index.html
 //! [pinning]: https://doc.rust-lang.org/std/pin/index.html
 //! [structurally pinned fields]:
-//!     https://doc.rust-lang.org/std/pin/index.html#pinning-is-structural-for-field
+//!     https://doc.rust-lang.org/std/pin/index.html#projections-and-structural-pinning
 //! [stack]: crate::stack_pin_init
 #![cfg_attr(
     kernel,
@@ -269,6 +275,10 @@
 #![forbid(missing_docs, unsafe_op_in_unsafe_fn)]
 #![cfg_attr(not(feature = "std"), no_std)]
 #![cfg_attr(feature = "alloc", feature(allocator_api))]
+#![cfg_attr(
+    all(feature = "unsafe-pinned", CONFIG_RUSTC_HAS_UNSAFE_PINNED),
+    feature(unsafe_pinned)
+)]
 
 use core::{
     cell::UnsafeCell,
@@ -385,9 +395,10 @@ pub use ::pin_init_internal::pin_data;
 /// ```
 pub use ::pin_init_internal::pinned_drop;
 
-/// Derives the [`Zeroable`] trait for the given struct.
+/// Derives the [`Zeroable`] trait for the given `struct` or `union`.
 ///
-/// This can only be used for structs where every field implements the [`Zeroable`] trait.
+/// This can only be used for `struct`s/`union`s where every field implements the [`Zeroable`]
+/// trait.
 ///
 /// # Examples
 ///
@@ -396,13 +407,54 @@ pub use ::pin_init_internal::pinned_drop;
 ///
 /// #[derive(Zeroable)]
 /// pub struct DriverData {
-///     id: i64,
+///     pub(crate) id: i64,
 ///     buf_ptr: *mut u8,
 ///     len: usize,
 /// }
 /// ```
+///
+/// ```
+/// use pin_init::Zeroable;
+///
+/// #[derive(Zeroable)]
+/// pub union SignCast {
+///     signed: i64,
+///     unsigned: u64,
+/// }
+/// ```
 pub use ::pin_init_internal::Zeroable;
 
+/// Derives the [`Zeroable`] trait for the given `struct` or `union` if all fields implement
+/// [`Zeroable`].
+///
+/// Contrary to the derive macro named [`macro@Zeroable`], this one silently fails when a field
+/// doesn't implement [`Zeroable`].
+///
+/// # Examples
+///
+/// ```
+/// use pin_init::MaybeZeroable;
+///
+/// // implmements `Zeroable`
+/// #[derive(MaybeZeroable)]
+/// pub struct DriverData {
+///     pub(crate) id: i64,
+///     buf_ptr: *mut u8,
+///     len: usize,
+/// }
+///
+/// // does not implmement `Zeroable`
+/// #[derive(MaybeZeroable)]
+/// pub struct DriverData2 {
+///     pub(crate) id: i64,
+///     buf_ptr: *mut u8,
+///     len: usize,
+///     // this field doesn't implement `Zeroable`
+///     other_data: &'static i32,
+/// }
+/// ```
+pub use ::pin_init_internal::MaybeZeroable;
+
 /// Initialize and pin a type directly on the stack.
 ///
 /// # Examples
@@ -1216,6 +1268,38 @@ pub const unsafe fn init_from_closure<T: ?Sized, E>(
     __internal::InitClosure(f, PhantomData)
 }
 
+/// Changes the to be initialized type.
+///
+/// # Safety
+///
+/// - `*mut U` must be castable to `*mut T` and any value of type `T` written through such a
+///   pointer must result in a valid `U`.
+#[expect(clippy::let_and_return)]
+pub const unsafe fn cast_pin_init<T, U, E>(init: impl PinInit<T, E>) -> impl PinInit<U, E> {
+    // SAFETY: initialization delegated to a valid initializer. Cast is valid by function safety
+    // requirements.
+    let res = unsafe { pin_init_from_closure(|ptr: *mut U| init.__pinned_init(ptr.cast::<T>())) };
+    // FIXME: remove the let statement once the nightly-MSRV allows it (1.78 otherwise encounters a
+    // cycle when computing the type returned by this function)
+    res
+}
+
+/// Changes the to be initialized type.
+///
+/// # Safety
+///
+/// - `*mut U` must be castable to `*mut T` and any value of type `T` written through such a
+///   pointer must result in a valid `U`.
+#[expect(clippy::let_and_return)]
+pub const unsafe fn cast_init<T, U, E>(init: impl Init<T, E>) -> impl Init<U, E> {
+    // SAFETY: initialization delegated to a valid initializer. Cast is valid by function safety
+    // requirements.
+    let res = unsafe { init_from_closure(|ptr: *mut U| init.__init(ptr.cast::<T>())) };
+    // FIXME: remove the let statement once the nightly-MSRV allows it (1.78 otherwise encounters a
+    // cycle when computing the type returned by this function)
+    res
+}
+
 /// An initializer that leaves the memory uninitialized.
 ///
 /// The initializer is a no-op. The `slot` memory is not changed.
@@ -1481,3 +1565,55 @@ macro_rules! impl_tuple_zeroable {
 }
 
 impl_tuple_zeroable!(A, B, C, D, E, F, G, H, I, J);
+
+/// This trait allows creating an instance of `Self` which contains exactly one
+/// [structurally pinned value](https://doc.rust-lang.org/std/pin/index.html#projections-and-structural-pinning).
+///
+/// This is useful when using wrapper `struct`s like [`UnsafeCell`] or with new-type `struct`s.
+///
+/// # Examples
+///
+/// ```
+/// # use core::cell::UnsafeCell;
+/// # use pin_init::{pin_data, pin_init, Wrapper};
+///
+/// #[pin_data]
+/// struct Foo {}
+///
+/// #[pin_data]
+/// struct Bar {
+///     #[pin]
+///     content: UnsafeCell<Foo>
+/// };
+///
+/// let foo_initializer = pin_init!(Foo{});
+/// let initializer = pin_init!(Bar {
+///     content <- UnsafeCell::pin_init(foo_initializer)
+/// });
+/// ```
+pub trait Wrapper<T> {
+    /// Creates an pin-initializer for a [`Self`] containing `T` from the `value_init` initializer.
+    fn pin_init<E>(value_init: impl PinInit<T, E>) -> impl PinInit<Self, E>;
+}
+
+impl<T> Wrapper<T> for UnsafeCell<T> {
+    fn pin_init<E>(value_init: impl PinInit<T, E>) -> impl PinInit<Self, E> {
+        // SAFETY: `UnsafeCell<T>` has a compatible layout to `T`.
+        unsafe { cast_pin_init(value_init) }
+    }
+}
+
+impl<T> Wrapper<T> for MaybeUninit<T> {
+    fn pin_init<E>(value_init: impl PinInit<T, E>) -> impl PinInit<Self, E> {
+        // SAFETY: `MaybeUninit<T>` has a compatible layout to `T`.
+        unsafe { cast_pin_init(value_init) }
+    }
+}
+
+#[cfg(all(feature = "unsafe-pinned", CONFIG_RUSTC_HAS_UNSAFE_PINNED))]
+impl<T> Wrapper<T> for core::pin::UnsafePinned<T> {
+    fn pin_init<E>(init: impl PinInit<T, E>) -> impl PinInit<Self, E> {
+        // SAFETY: `UnsafePinned<T>` has a compatible layout to `T`.
+        unsafe { cast_pin_init(init) }
+    }
+}
diff --git a/rust/pin-init/src/macros.rs b/rust/pin-init/src/macros.rs
index 361623324d5c..935d77745d1d 100644
--- a/rust/pin-init/src/macros.rs
+++ b/rust/pin-init/src/macros.rs
@@ -1393,7 +1393,7 @@ macro_rules! __derive_zeroable {
         @body({
             $(
                 $(#[$($field_attr:tt)*])*
-                $field:ident : $field_ty:ty
+                $field_vis:vis $field:ident : $field_ty:ty
             ),* $(,)?
         }),
     ) => {
@@ -1412,4 +1412,93 @@ macro_rules! __derive_zeroable {
             }
         };
     };
+    (parse_input:
+        @sig(
+            $(#[$($struct_attr:tt)*])*
+            $vis:vis union $name:ident
+            $(where $($whr:tt)*)?
+        ),
+        @impl_generics($($impl_generics:tt)*),
+        @ty_generics($($ty_generics:tt)*),
+        @body({
+            $(
+                $(#[$($field_attr:tt)*])*
+                $field_vis:vis $field:ident : $field_ty:ty
+            ),* $(,)?
+        }),
+    ) => {
+        // SAFETY: Every field type implements `Zeroable` and padding bytes may be zero.
+        #[automatically_derived]
+        unsafe impl<$($impl_generics)*> $crate::Zeroable for $name<$($ty_generics)*>
+        where
+            $($($whr)*)?
+        {}
+        const _: () = {
+            fn assert_zeroable<T: ?::core::marker::Sized + $crate::Zeroable>() {}
+            fn ensure_zeroable<$($impl_generics)*>()
+                where $($($whr)*)?
+            {
+                $(assert_zeroable::<$field_ty>();)*
+            }
+        };
+    };
+}
+
+#[doc(hidden)]
+#[macro_export]
+macro_rules! __maybe_derive_zeroable {
+    (parse_input:
+        @sig(
+            $(#[$($struct_attr:tt)*])*
+            $vis:vis struct $name:ident
+            $(where $($whr:tt)*)?
+        ),
+        @impl_generics($($impl_generics:tt)*),
+        @ty_generics($($ty_generics:tt)*),
+        @body({
+            $(
+                $(#[$($field_attr:tt)*])*
+                $field_vis:vis $field:ident : $field_ty:ty
+            ),* $(,)?
+        }),
+    ) => {
+        // SAFETY: Every field type implements `Zeroable` and padding bytes may be zero.
+        #[automatically_derived]
+        unsafe impl<$($impl_generics)*> $crate::Zeroable for $name<$($ty_generics)*>
+        where
+            $(
+                // the `for<'__dummy>` HRTB makes this not error without the `trivial_bounds`
+                // feature <https://github.com/rust-lang/rust/issues/48214#issuecomment-2557829956>.
+                $field_ty: for<'__dummy> $crate::Zeroable,
+            )*
+            $($($whr)*)?
+        {}
+    };
+    (parse_input:
+        @sig(
+            $(#[$($struct_attr:tt)*])*
+            $vis:vis union $name:ident
+            $(where $($whr:tt)*)?
+        ),
+        @impl_generics($($impl_generics:tt)*),
+        @ty_generics($($ty_generics:tt)*),
+        @body({
+            $(
+                $(#[$($field_attr:tt)*])*
+                $field_vis:vis $field:ident : $field_ty:ty
+            ),* $(,)?
+        }),
+    ) => {
+        // SAFETY: Every field type implements `Zeroable` and padding bytes may be zero.
+        #[automatically_derived]
+        unsafe impl<$($impl_generics)*> $crate::Zeroable for $name<$($ty_generics)*>
+        where
+            $(
+                // the `for<'__dummy>` HRTB makes this not error without the `trivial_bounds`
+                // feature <https://github.com/rust-lang/rust/issues/48214#issuecomment-2557829956>.
+                $field_ty: for<'__dummy> $crate::Zeroable,
+            )*
+            $($($whr)*)?
+        {}
+    };
 }
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 884dc86ce04e..557e725ab932 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -222,6 +222,15 @@ $(obj)/%.lst: $(obj)/%.c FORCE
 # Compile Rust sources (.rs)
 # ---------------------------------------------------------------------------
 
+# The features in this list are the ones allowed for non-`rust/` code.
+#
+#   - Stable since Rust 1.81.0: `feature(lint_reasons)`.
+#   - Stable since Rust 1.82.0: `feature(asm_const)`, `feature(raw_ref_op)`.
+#   - Stable since Rust 1.87.0: `feature(asm_goto)`.
+#   - Expected to become stable: `feature(arbitrary_self_types)`.
+#
+# Please see https://github.com/Rust-for-Linux/linux/issues/2 for details on
+# the unstable features in use.
 rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,raw_ref_op
 
 # `--out-dir` is required to avoid temporaries being created by `rustc` in the
diff --git a/scripts/Makefile.kcov b/scripts/Makefile.kcov
index 01616472f43e..78305a84ba9d 100644
--- a/scripts/Makefile.kcov
+++ b/scripts/Makefile.kcov
@@ -2,4 +2,10 @@
 kcov-flags-y					+= -fsanitize-coverage=trace-pc
 kcov-flags-$(CONFIG_KCOV_ENABLE_COMPARISONS)	+= -fsanitize-coverage=trace-cmp
 
+kcov-rflags-y					+= -Cpasses=sancov-module
+kcov-rflags-y					+= -Cllvm-args=-sanitizer-coverage-level=3
+kcov-rflags-y					+= -Cllvm-args=-sanitizer-coverage-trace-pc
+kcov-rflags-$(CONFIG_KCOV_ENABLE_COMPARISONS)	+= -Cllvm-args=-sanitizer-coverage-trace-compares
+
 export CFLAGS_KCOV := $(kcov-flags-y)
+export RUSTFLAGS_KCOV := $(kcov-rflags-y)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 6fc2a82ee3bb..2b332645e0c2 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -169,6 +169,9 @@ ifeq ($(CONFIG_KCOV),y)
 _c_flags += $(if $(patsubst n%,, \
 	$(KCOV_INSTRUMENT_$(target-stem).o)$(KCOV_INSTRUMENT)$(if $(is-kernel-object),$(CONFIG_KCOV_INSTRUMENT_ALL))), \
 	$(CFLAGS_KCOV))
+_rust_flags += $(if $(patsubst n%,, \
+	$(KCOV_INSTRUMENT_$(target-stem).o)$(KCOV_INSTRUMENT)$(if $(is-kernel-object),$(CONFIG_KCOV_INSTRUMENT_ALL))), \
+	$(RUSTFLAGS_KCOV))
 endif
 
 #
diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py
index fe663dd0c43b..7c3ea2b55041 100755
--- a/scripts/generate_rust_analyzer.py
+++ b/scripts/generate_rust_analyzer.py
@@ -19,7 +19,7 @@ def args_crates_cfgs(cfgs):
 
     return crates_cfgs
 
-def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
+def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs, core_edition):
     # Generate the configuration list.
     cfg = []
     with open(objtree / "include" / "generated" / "rustc_cfg") as fd:
@@ -35,7 +35,7 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
     crates_indexes = {}
     crates_cfgs = args_crates_cfgs(cfgs)
 
-    def append_crate(display_name, root_module, deps, cfg=[], is_workspace_member=True, is_proc_macro=False):
+    def append_crate(display_name, root_module, deps, cfg=[], is_workspace_member=True, is_proc_macro=False, edition="2021"):
         crate = {
             "display_name": display_name,
             "root_module": str(root_module),
@@ -43,7 +43,7 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
             "is_proc_macro": is_proc_macro,
             "deps": [{"crate": crates_indexes[dep], "name": dep} for dep in deps],
             "cfg": cfg,
-            "edition": "2021",
+            "edition": edition,
             "env": {
                 "RUST_MODFILE": "This is only for rust-analyzer"
             }
@@ -61,6 +61,7 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
         display_name,
         deps,
         cfg=[],
+        edition="2021",
     ):
         append_crate(
             display_name,
@@ -68,12 +69,13 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs):
             deps,
             cfg,
             is_workspace_member=False,
+            edition=edition,
         )
 
     # NB: sysroot crates reexport items from one another so setting up our transitive dependencies
     # here is important for ensuring that rust-analyzer can resolve symbols. The sources of truth
     # for this dependency graph are `(sysroot_src / crate / "Cargo.toml" for crate in crates)`.
-    append_sysroot_crate("core", [], cfg=crates_cfgs.get("core", []))
+    append_sysroot_crate("core", [], cfg=crates_cfgs.get("core", []), edition=core_edition)
     append_sysroot_crate("alloc", ["core"])
     append_sysroot_crate("std", ["alloc", "core"])
     append_sysroot_crate("proc_macro", ["core", "std"])
@@ -177,6 +179,7 @@ def main():
     parser = argparse.ArgumentParser()
     parser.add_argument('--verbose', '-v', action='store_true')
     parser.add_argument('--cfgs', action='append', default=[])
+    parser.add_argument("core_edition")
     parser.add_argument("srctree", type=pathlib.Path)
     parser.add_argument("objtree", type=pathlib.Path)
     parser.add_argument("sysroot", type=pathlib.Path)
@@ -193,7 +196,7 @@ def main():
     assert args.sysroot in args.sysroot_src.parents
 
     rust_project = {
-        "crates": generate_crates(args.srctree, args.objtree, args.sysroot_src, args.exttree, args.cfgs),
+        "crates": generate_crates(args.srctree, args.objtree, args.sysroot_src, args.exttree, args.cfgs, args.core_edition),
         "sysroot": str(args.sysroot),
     }
 
diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs
index 8667d0ae3c82..39c82908ff3a 100644
--- a/scripts/generate_rust_target.rs
+++ b/scripts/generate_rust_target.rs
@@ -209,7 +209,7 @@ fn main() {
             // target feature of the same name plus the other two target features in
             // `clang/lib/Driver/ToolChains/Arch/X86.cpp`. These should be eventually enabled via
             // `-Ctarget-feature` when `rustc` starts recognizing them (or via a new dedicated
-            // flag); see https://github.com/rust-lang/rust/issues/116852.
+            // flag); see <https://github.com/rust-lang/rust/issues/116852>.
             features += ",+retpoline-external-thunk";
             features += ",+retpoline-indirect-branches";
             features += ",+retpoline-indirect-calls";
@@ -218,7 +218,7 @@ fn main() {
             // The kernel uses `-mharden-sls=all`, which Clang maps to both these target features in
             // `clang/lib/Driver/ToolChains/Arch/X86.cpp`. These should be eventually enabled via
             // `-Ctarget-feature` when `rustc` starts recognizing them (or via a new dedicated
-            // flag); see https://github.com/rust-lang/rust/issues/116851.
+            // flag); see <https://github.com/rust-lang/rust/issues/116851>.
             features += ",+harden-sls-ijmp";
             features += ",+harden-sls-ret";
         }
diff --git a/scripts/rustdoc_test_builder.rs b/scripts/rustdoc_test_builder.rs
index e5894652f12c..f7540bcf595a 100644
--- a/scripts/rustdoc_test_builder.rs
+++ b/scripts/rustdoc_test_builder.rs
@@ -28,7 +28,7 @@ fn main() {
     //
     // ```
     // fn main() { #[allow(non_snake_case)] fn _doctest_main_rust_kernel_file_rs_28_0() {
-    // fn main() { #[allow(non_snake_case)] fn _doctest_main_rust_kernel_file_rs_37_0() -> Result<(), impl core::fmt::Debug> {
+    // fn main() { #[allow(non_snake_case)] fn _doctest_main_rust_kernel_file_rs_37_0() -> Result<(), impl ::core::fmt::Debug> {
     // ```
     //
     // It should be unlikely that doctest code matches such lines (when code is formatted properly).
@@ -49,8 +49,10 @@ fn main() {
 
     // Qualify `Result` to avoid the collision with our own `Result` coming from the prelude.
     let body = body.replace(
-        &format!("{rustdoc_function_name}() -> Result<(), impl core::fmt::Debug> {{"),
-        &format!("{rustdoc_function_name}() -> core::result::Result<(), impl core::fmt::Debug> {{"),
+        &format!("{rustdoc_function_name}() -> Result<(), impl ::core::fmt::Debug> {{"),
+        &format!(
+            "{rustdoc_function_name}() -> ::core::result::Result<(), impl ::core::fmt::Debug> {{"
+        ),
     );
 
     // For tests that get generated with `Result`, like above, `rustdoc` generates an `unwrap()` on
diff --git a/scripts/rustdoc_test_gen.rs b/scripts/rustdoc_test_gen.rs
index ec8d70ac888b..1ca253594d38 100644
--- a/scripts/rustdoc_test_gen.rs
+++ b/scripts/rustdoc_test_gen.rs
@@ -167,12 +167,14 @@ fn main() {
             rust_tests,
             r#"/// Generated `{name}` KUnit test case from a Rust documentation test.
 #[no_mangle]
-pub extern "C" fn {kunit_name}(__kunit_test: *mut kernel::bindings::kunit) {{
+pub extern "C" fn {kunit_name}(__kunit_test: *mut ::kernel::bindings::kunit) {{
     /// Overrides the usual [`assert!`] macro with one that calls KUnit instead.
     #[allow(unused)]
     macro_rules! assert {{
         ($cond:expr $(,)?) => {{{{
-            kernel::kunit_assert!("{kunit_name}", "{real_path}", __DOCTEST_ANCHOR - {line}, $cond);
+            ::kernel::kunit_assert!(
+                "{kunit_name}", "{real_path}", __DOCTEST_ANCHOR - {line}, $cond
+            );
         }}}}
     }}
 
@@ -180,13 +182,15 @@ pub extern "C" fn {kunit_name}(__kunit_test: *mut kernel::bindings::kunit) {{
     #[allow(unused)]
     macro_rules! assert_eq {{
         ($left:expr, $right:expr $(,)?) => {{{{
-            kernel::kunit_assert_eq!("{kunit_name}", "{real_path}", __DOCTEST_ANCHOR - {line}, $left, $right);
+            ::kernel::kunit_assert_eq!(
+                "{kunit_name}", "{real_path}", __DOCTEST_ANCHOR - {line}, $left, $right
+            );
         }}}}
     }}
 
     // Many tests need the prelude, so provide it by default.
     #[allow(unused)]
-    use kernel::prelude::*;
+    use ::kernel::prelude::*;
 
     // Unconditionally print the location of the original doctest (i.e. rather than the location in
     // the generated file) so that developers can easily map the test back to the source code.
@@ -197,11 +201,11 @@ pub extern "C" fn {kunit_name}(__kunit_test: *mut kernel::bindings::kunit) {{
     // This follows the syntax for declaring test metadata in the proposed KTAP v2 spec, which may
     // be used for the proposed KUnit test attributes API. Thus hopefully this will make migration
     // easier later on.
-    kernel::kunit::info(format_args!("    # {kunit_name}.location: {real_path}:{line}\n"));
+    ::kernel::kunit::info(format_args!("    # {kunit_name}.location: {real_path}:{line}\n"));
 
     /// The anchor where the test code body starts.
     #[allow(unused)]
-    static __DOCTEST_ANCHOR: i32 = core::line!() as i32 + {body_offset} + 1;
+    static __DOCTEST_ANCHOR: i32 = ::core::line!() as i32 + {body_offset} + 1;
     {{
         {body}
         main();
diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index 6a3932d90b43..bdfe388da198 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -192,6 +192,9 @@ static int hda_sdw_probe(struct snd_sof_dev *sdev)
 		res.ext = true;
 		res.ops = &sdw_ace2x_callback;
 
+		/* ACE3+ supports microphone privacy */
+		if (chip->hw_ip_version >= SOF_INTEL_ACE_3_0)
+			res.mic_privacy = true;
 	}
 	res.irq = sdev->ipc_irq;
 	res.handle = hdev->info.handle;
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 488f8e751349..9a5d85cfd1fb 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -129,6 +129,7 @@
 #define FUJITSU_CPU_PART_A64FX		0x001
 
 #define HISI_CPU_PART_TSV110		0xD01
+#define HISI_CPU_PART_HIP12		0xD06
 
 #define APPLE_CPU_PART_M1_ICESTORM	0x022
 #define APPLE_CPU_PART_M1_FIRESTORM	0x023
@@ -202,6 +203,7 @@
 #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
 #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
 #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
+#define MIDR_HISI_HIP12 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP12)
 #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM)
 #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM)
 #define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 98c8931db4a5..e02be2962a01 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -75,7 +75,7 @@
 #define X86_FEATURE_CENTAUR_MCR		( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */
 #define X86_FEATURE_K8			( 3*32+ 4) /* Opteron, Athlon64 */
 #define X86_FEATURE_ZEN5		( 3*32+ 5) /* CPU based on Zen5 microarchitecture */
-/* Free                                 ( 3*32+ 6) */
+#define X86_FEATURE_ZEN6		( 3*32+ 6) /* CPU based on Zen6 microarchitecture */
 /* Free                                 ( 3*32+ 7) */
 #define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */
 #define X86_FEATURE_UP			( 3*32+ 9) /* "up" SMP kernel running on UP */
@@ -482,6 +482,7 @@
 #define X86_FEATURE_AMD_HTR_CORES	(21*32+ 6) /* Heterogeneous Core Topology */
 #define X86_FEATURE_AMD_WORKLOAD_CLASS	(21*32+ 7) /* Workload Classification */
 #define X86_FEATURE_PREFER_YMM		(21*32+ 8) /* Avoid ZMM registers due to downclocking */
+#define X86_FEATURE_INDIRECT_THUNK_ITS	(21*32+ 9) /* Use thunk for indirect branches in lower half of cacheline */
 
 /*
  * BUG word(s)
@@ -534,4 +535,6 @@
 #define X86_BUG_BHI			X86_BUG( 1*32+ 3) /* "bhi" CPU is affected by Branch History Injection */
 #define X86_BUG_IBPB_NO_RET		X86_BUG( 1*32+ 4) /* "ibpb_no_ret" IBPB omits return target predictions */
 #define X86_BUG_SPECTRE_V2_USER		X86_BUG( 1*32+ 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
+#define X86_BUG_ITS			X86_BUG( 1*32+ 6) /* "its" CPU is affected by Indirect Target Selection */
+#define X86_BUG_ITS_NATIVE_ONLY		X86_BUG( 1*32+ 7) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index e6134ef2263d..e7d2f460fcc6 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -211,6 +211,14 @@
 						 * VERW clears CPU Register
 						 * File.
 						 */
+#define ARCH_CAP_ITS_NO			BIT_ULL(62) /*
+						     * Not susceptible to
+						     * Indirect Target Selection.
+						     * This bit is not set by
+						     * HW, but is synthesized by
+						     * VMMs for guests to know
+						     * their affected status.
+						     */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
diff --git a/tools/bootconfig/Makefile b/tools/bootconfig/Makefile
index 566c3e0ee561..90eb47c9d8de 100644
--- a/tools/bootconfig/Makefile
+++ b/tools/bootconfig/Makefile
@@ -10,7 +10,7 @@ srctree := $(patsubst %/,%,$(dir $(srctree)))
 endif
 
 LIBSRC = $(srctree)/lib/bootconfig.c $(srctree)/include/linux/bootconfig.h
-CFLAGS = -Wall -g -I$(CURDIR)/include
+override CFLAGS += -Wall -g -I$(CURDIR)/include
 
 ALL_TARGETS := bootconfig
 ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
@@ -18,7 +18,7 @@ ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
 all: $(ALL_PROGRAMS) test
 
 $(OUTPUT)bootconfig: main.c include/linux/bootconfig.h $(LIBSRC)
-	$(CC) $(filter %.c,$^) $(CFLAGS) -o $@
+	$(CC) $(filter %.c,$^) $(CFLAGS) $(LDFLAGS) -o $@
 
 test: $(ALL_PROGRAMS) test-bootconfig.sh
 	./test-bootconfig.sh $(OUTPUT)
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 1f44ca677ad3..57bd995ce6af 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -87,7 +87,6 @@ FEATURE_TESTS_BASIC :=                  \
         libtracefs                      \
         libcpupower                     \
         libcrypto                       \
-        libunwind                       \
         pthread-attr-setaffinity-np     \
         pthread-barrier     		\
         reallocarray                    \
@@ -148,15 +147,12 @@ endif
 FEATURE_DISPLAY ?=              \
          libdw                  \
          glibc                  \
-         libbfd                 \
-         libbfd-buildid		\
          libelf                 \
          libnuma                \
          numa_num_possible_cpus \
          libperl                \
          libpython              \
          libcrypto              \
-         libunwind              \
          libcapstone            \
          llvm-perf              \
          zlib                   \
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index b9ce3aab15fe..1f64c680be13 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -84,6 +84,7 @@ enum {
 };
 
 static int in_hand_shake;
+static int debug;
 
 static char *os_name = "";
 static char *os_major = "";
@@ -184,6 +185,20 @@ static void kvp_update_file(int pool)
 	kvp_release_lock(pool);
 }
 
+static void kvp_dump_initial_pools(int pool)
+{
+	int i;
+
+	syslog(LOG_DEBUG, "===Start dumping the contents of pool %d ===\n",
+	       pool);
+
+	for (i = 0; i < kvp_file_info[pool].num_records; i++)
+		syslog(LOG_DEBUG, "pool: %d, %d/%d key=%s val=%s\n",
+		       pool, i + 1, kvp_file_info[pool].num_records,
+		       kvp_file_info[pool].records[i].key,
+		       kvp_file_info[pool].records[i].value);
+}
+
 static void kvp_update_mem_state(int pool)
 {
 	FILE *filep;
@@ -271,6 +286,8 @@ static int kvp_file_init(void)
 			return 1;
 		kvp_file_info[i].num_records = 0;
 		kvp_update_mem_state(i);
+		if (debug)
+			kvp_dump_initial_pools(i);
 	}
 
 	return 0;
@@ -298,6 +315,9 @@ static int kvp_key_delete(int pool, const __u8 *key, int key_size)
 		 * Found a match; just move the remaining
 		 * entries up.
 		 */
+		if (debug)
+			syslog(LOG_DEBUG, "%s: deleting the KVP: pool=%d key=%s val=%s",
+			       __func__, pool, record[i].key, record[i].value);
 		if (i == (num_records - 1)) {
 			kvp_file_info[pool].num_records--;
 			kvp_update_file(pool);
@@ -316,20 +336,36 @@ static int kvp_key_delete(int pool, const __u8 *key, int key_size)
 		kvp_update_file(pool);
 		return 0;
 	}
+
+	if (debug)
+		syslog(LOG_DEBUG, "%s: could not delete KVP: pool=%d key=%s. Record not found",
+		       __func__, pool, key);
+
 	return 1;
 }
 
 static int kvp_key_add_or_modify(int pool, const __u8 *key, int key_size,
 				 const __u8 *value, int value_size)
 {
-	int i;
-	int num_records;
 	struct kvp_record *record;
+	int num_records;
 	int num_blocks;
+	int i;
+
+	if (debug)
+		syslog(LOG_DEBUG, "%s: got a KVP: pool=%d key=%s val=%s",
+		       __func__, pool, key, value);
 
 	if ((key_size > HV_KVP_EXCHANGE_MAX_KEY_SIZE) ||
-		(value_size > HV_KVP_EXCHANGE_MAX_VALUE_SIZE))
+		(value_size > HV_KVP_EXCHANGE_MAX_VALUE_SIZE)) {
+		syslog(LOG_ERR, "%s: Too long key or value: key=%s, val=%s",
+		       __func__, key, value);
+
+		if (debug)
+			syslog(LOG_DEBUG, "%s: Too long key or value: pool=%d, key=%s, val=%s",
+			       __func__, pool, key, value);
 		return 1;
+	}
 
 	/*
 	 * First update the in-memory state.
@@ -349,6 +385,9 @@ static int kvp_key_add_or_modify(int pool, const __u8 *key, int key_size,
 		 */
 		memcpy(record[i].value, value, value_size);
 		kvp_update_file(pool);
+		if (debug)
+			syslog(LOG_DEBUG, "%s: updated: pool=%d key=%s val=%s",
+			       __func__, pool, key, value);
 		return 0;
 	}
 
@@ -360,8 +399,10 @@ static int kvp_key_add_or_modify(int pool, const __u8 *key, int key_size,
 		record = realloc(record, sizeof(struct kvp_record) *
 			 ENTRIES_PER_BLOCK * (num_blocks + 1));
 
-		if (record == NULL)
+		if (!record) {
+			syslog(LOG_ERR, "%s: Memory alloc failure", __func__);
 			return 1;
+		}
 		kvp_file_info[pool].num_blocks++;
 
 	}
@@ -369,6 +410,11 @@ static int kvp_key_add_or_modify(int pool, const __u8 *key, int key_size,
 	memcpy(record[i].key, key, key_size);
 	kvp_file_info[pool].records = record;
 	kvp_file_info[pool].num_records++;
+
+	if (debug)
+		syslog(LOG_DEBUG, "%s: added: pool=%d key=%s val=%s",
+		       __func__, pool, key, value);
+
 	kvp_update_file(pool);
 	return 0;
 }
@@ -1722,6 +1768,7 @@ void print_usage(char *argv[])
 	fprintf(stderr, "Usage: %s [options]\n"
 		"Options are:\n"
 		"  -n, --no-daemon        stay in foreground, don't daemonize\n"
+		"  -d, --debug            Enable debug logs(syslog debug by default)\n"
 		"  -h, --help             print this help\n", argv[0]);
 }
 
@@ -1743,10 +1790,11 @@ int main(int argc, char *argv[])
 	static struct option long_options[] = {
 		{"help",	no_argument,	   0,  'h' },
 		{"no-daemon",	no_argument,	   0,  'n' },
+		{"debug",	no_argument,	   0,  'd' },
 		{0,		0,		   0,  0   }
 	};
 
-	while ((opt = getopt_long(argc, argv, "hn", long_options,
+	while ((opt = getopt_long(argc, argv, "hnd", long_options,
 				  &long_index)) != -1) {
 		switch (opt) {
 		case 'n':
@@ -1755,6 +1803,9 @@ int main(int argc, char *argv[])
 		case 'h':
 			print_usage(argv);
 			exit(0);
+		case 'd':
+			debug = 1;
+			break;
 		default:
 			print_usage(argv);
 			exit(EXIT_FAILURE);
@@ -1777,6 +1828,9 @@ int main(int argc, char *argv[])
 	 */
 	kvp_get_domain_name(full_domain_name, sizeof(full_domain_name));
 
+	if (debug)
+		syslog(LOG_INFO, "Logging debug info in syslog(debug)");
+
 	if (kvp_file_init()) {
 		syslog(LOG_ERR, "Failed to initialize the pools");
 		exit(EXIT_FAILURE);
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 8de2914e6510..14fd0ca9a6cd 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -20,9 +20,8 @@
  */
 #if !defined(__ASSEMBLY__)
 #include <linux/build_bug.h>
-#define GENMASK_INPUT_CHECK(h, l) \
-	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
-		__is_constexpr((l) > (h)), (l) > (h), 0)))
+#include <linux/compiler.h>
+#define GENMASK_INPUT_CHECK(h, l) BUILD_BUG_ON_ZERO(const_true((l) > (h)))
 #else
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 9c05a59f0184..d627e66a04a6 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -81,6 +81,28 @@
 #define __is_constexpr(x) \
 	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
 
+/*
+ * Similar to statically_true() but produces a constant expression
+ *
+ * To be used in conjunction with macros, such as BUILD_BUG_ON_ZERO(),
+ * which require their input to be a constant expression and for which
+ * statically_true() would otherwise fail.
+ *
+ * This is a trade-off: const_true() requires all its operands to be
+ * compile time constants. Else, it would always returns false even on
+ * the most trivial cases like:
+ *
+ *   true || non_const_var
+ *
+ * On the opposite, statically_true() is able to fold more complex
+ * tautologies and will return true on expressions such as:
+ *
+ *   !(non_const_var * 8 % 4)
+ *
+ * For the general case, statically_true() is better.
+ */
+#define const_true(x) __builtin_choose_expr(__is_constexpr(x), x, false)
+
 #ifdef __ANDROID__
 /*
  * FIXME: Big hammer to get rid of tons of:
diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h
index 5ee30f882736..682b406e1067 100644
--- a/tools/include/uapi/linux/bits.h
+++ b/tools/include/uapi/linux/bits.h
@@ -4,13 +4,9 @@
 #ifndef _UAPI_LINUX_BITS_H
 #define _UAPI_LINUX_BITS_H
 
-#define __GENMASK(h, l) \
-        (((~_UL(0)) - (_UL(1) << (l)) + 1) & \
-         (~_UL(0) >> (__BITS_PER_LONG - 1 - (h))))
+#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h))))
 
-#define __GENMASK_ULL(h, l) \
-        (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \
-         (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
+#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
 
 #define __GENMASK_U128(h, l) \
 	((_BIT128((h)) << 1) - (_BIT128(l)))
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 85180e4aaa5a..0b4a2f124d11 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2056,6 +2056,7 @@ union bpf_attr {
  * 		for updates resulting in a null checksum the value is set to
  * 		**CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates
  * 		that the modified header field is part of the pseudo-header.
+ * 		Flag **BPF_F_IPV6** should be set for IPv6 packets.
  *
  * 		This helper works in combination with **bpf_csum_diff**\ (),
  * 		which does not update the checksum in-place, but offers more
@@ -6072,6 +6073,7 @@ enum {
 	BPF_F_PSEUDO_HDR		= (1ULL << 4),
 	BPF_F_MARK_MANGLED_0		= (1ULL << 5),
 	BPF_F_MARK_ENFORCE		= (1ULL << 6),
+	BPF_F_IPV6			= (1ULL << 7),
 };
 
 /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
diff --git a/tools/include/vdso/unaligned.h b/tools/include/vdso/unaligned.h
index eee3d2a4dbe4..ff0c06b6513e 100644
--- a/tools/include/vdso/unaligned.h
+++ b/tools/include/vdso/unaligned.h
@@ -2,14 +2,14 @@
 #ifndef __VDSO_UNALIGNED_H
 #define __VDSO_UNALIGNED_H
 
-#define __get_unaligned_t(type, ptr) ({						\
-	const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);	\
-	__pptr->x;								\
+#define __get_unaligned_t(type, ptr) ({							\
+	const struct { type x; } __packed * __get_pptr = (typeof(__get_pptr))(ptr);	\
+	__get_pptr->x;									\
 })
 
-#define __put_unaligned_t(type, val, ptr) do {					\
-	struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);		\
-	__pptr->x = (val);							\
+#define __put_unaligned_t(type, val, ptr) do {						\
+	struct { type x; } __packed * __put_pptr = (typeof(__put_pptr))(ptr);		\
+	__put_pptr->x = (val);								\
 } while (0)
 
 #endif /* __VDSO_UNALIGNED_H */
diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index 59aabdd3cabf..4072bc9b7670 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -210,6 +210,7 @@ SYNOPSIS
   struct perf_record_time_conv;
   struct perf_record_header_feature;
   struct perf_record_compressed;
+  struct perf_record_compressed2;
 --
 
 DESCRIPTION
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 4454a5987570..b20a5280f2b3 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -242,6 +242,16 @@ out:
 	return cpus;
 }
 
+struct perf_cpu_map *perf_cpu_map__new_int(int cpu)
+{
+	struct perf_cpu_map *cpus = perf_cpu_map__alloc(1);
+
+	if (cpus)
+		RC_CHK_ACCESS(cpus)->map[0].cpu = cpu;
+
+	return cpus;
+}
+
 static int __perf_cpu_map__nr(const struct perf_cpu_map *cpus)
 {
 	return RC_CHK_ACCESS(cpus)->nr;
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 8c1ab0f9194e..58cc5c5fa47c 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -37,6 +37,8 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_online_cpus(void);
  *                     perf_cpu_map__new_online_cpus is returned.
  */
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
+/** perf_cpu_map__new_int - create a map with the one given cpu. */
+LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_int(int cpu);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
 LIBPERF_API int perf_cpu_map__merge(struct perf_cpu_map **orig,
 				    struct perf_cpu_map *other);
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index 37bb7771d914..09b7c643ddac 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -457,6 +457,16 @@ struct perf_record_compressed {
 	char			 data[];
 };
 
+/*
+ * `header.size` includes the padding we are going to add while writing the record.
+ * `data_size` only includes the size of `data[]` itself.
+ */
+struct perf_record_compressed2 {
+	struct perf_event_header header;
+	__u64			 data_size;
+	char			 data[];
+};
+
 enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_USER_TYPE_START		= 64,
 	PERF_RECORD_HEADER_ATTR			= 64,
@@ -478,6 +488,7 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_HEADER_FEATURE		= 80,
 	PERF_RECORD_COMPRESSED			= 81,
 	PERF_RECORD_FINISHED_INIT		= 82,
+	PERF_RECORD_COMPRESSED2			= 83,
 	PERF_RECORD_HEADER_MAX
 };
 
@@ -518,6 +529,7 @@ union perf_event {
 	struct perf_record_time_conv		time_conv;
 	struct perf_record_header_feature	feat;
 	struct perf_record_compressed		pack;
+	struct perf_record_compressed2		pack2;
 };
 
 #endif /* __LIBPERF_EVENT_H */
diff --git a/tools/lib/perf/include/perf/threadmap.h b/tools/lib/perf/include/perf/threadmap.h
index 8b40e7777cea..44deb815b817 100644
--- a/tools/lib/perf/include/perf/threadmap.h
+++ b/tools/lib/perf/include/perf/threadmap.h
@@ -14,6 +14,7 @@ LIBPERF_API void perf_thread_map__set_pid(struct perf_thread_map *map, int idx,
 LIBPERF_API char *perf_thread_map__comm(struct perf_thread_map *map, int idx);
 LIBPERF_API int perf_thread_map__nr(struct perf_thread_map *threads);
 LIBPERF_API pid_t perf_thread_map__pid(struct perf_thread_map *map, int idx);
+LIBPERF_API int perf_thread_map__idx(struct perf_thread_map *map, pid_t pid);
 
 LIBPERF_API struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map);
 LIBPERF_API void perf_thread_map__put(struct perf_thread_map *map);
diff --git a/tools/lib/perf/threadmap.c b/tools/lib/perf/threadmap.c
index 07968f3ea093..db431b036f57 100644
--- a/tools/lib/perf/threadmap.c
+++ b/tools/lib/perf/threadmap.c
@@ -97,5 +97,22 @@ int perf_thread_map__nr(struct perf_thread_map *threads)
 
 pid_t perf_thread_map__pid(struct perf_thread_map *map, int idx)
 {
+	if (!map) {
+		assert(idx == 0);
+		return -1;
+	}
+
 	return map->map[idx].pid;
 }
+
+int perf_thread_map__idx(struct perf_thread_map *threads, pid_t pid)
+{
+	if (!threads)
+		return pid == -1 ? 0 : -1;
+
+	for (int i = 0; i < threads->nr; ++i) {
+		if (threads->map[i].pid == pid)
+			return i;
+	}
+	return -1;
+}
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index b21b12ec88d9..f23bdda737aa 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -230,7 +230,8 @@ static bool is_rust_noreturn(const struct symbol *func)
 	       str_ends_with(func->name, "_7___rustc17rust_begin_unwind")				||
 	       strstr(func->name, "_4core9panicking13assert_failed")					||
 	       strstr(func->name, "_4core9panicking11panic_const24panic_const_")			||
-	       (strstr(func->name, "_4core5slice5index24slice_") &&
+	       (strstr(func->name, "_4core5slice5index") &&
+		strstr(func->name, "slice_") &&
 		str_ends_with(func->name, "_fail"));
 }
 
diff --git a/tools/perf/Documentation/perf-amd-ibs.txt b/tools/perf/Documentation/perf-amd-ibs.txt
index 2fd31d9d7b71..55f80beae037 100644
--- a/tools/perf/Documentation/perf-amd-ibs.txt
+++ b/tools/perf/Documentation/perf-amd-ibs.txt
@@ -85,6 +85,15 @@ System-wide profile, uOps event, sampling period: 100000, L3MissOnly (Zen4 onwar
 
 	# perf record -e ibs_op/cnt_ctl=1,l3missonly=1/ -c 100000 -a
 
+System-wide profile, cycles event, sampling period: 100000, LdLat filtering (Zen5
+onward)
+
+	# perf record -e ibs_op/ldlat=128/ -c 100000 -a
+
+	Supported load latency threshold values are 128 to 2048 (both inclusive).
+	Latency value which is a multiple of 128 incurs a little less profiling
+	overhead compared to other values.
+
 Per process(upstream v6.2 onward), uOps event, sampling period: 100000
 
 	# perf record -e ibs_op/cnt_ctl=1/ -c 100000 -p 1234
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 856f0dfb8e5a..f4af2dd6ab31 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -54,8 +54,15 @@ RECORD OPTIONS
 
 -l::
 --ldlat::
-	Configure mem-loads latency. Supported on Intel and Arm64 processors
-	only. Ignored on other archs.
+	Configure mem-loads latency. Supported on Intel, Arm64 and some AMD
+	processors. Ignored on other archs.
+
+	On supported AMD processors:
+	- /sys/bus/event_source/devices/ibs_op/caps/ldlat file contains '1'.
+	- Supported latency values are 128 to 2048 (both inclusive).
+	- Latency value which is a multiple of 128 incurs a little less profiling
+	  overhead compared to other values.
+	- Load latency filtering is disabled by default.
 
 -k::
 --all-kernel::
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 36ebebc875ea..c6f335659667 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -708,6 +708,10 @@ intel-pt.*::
 		the maximum is exceeded there will be a "Never-ending loop"
 		error. The default is 100000.
 
+	intel-pt.all-switch-events::
+		If the user has permission to do so, always record all context
+		switch events on all CPUs.
+
 auxtrace.*::
 
 	auxtrace.dumpdir::
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 8914f12d2b85..ce0735021473 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -289,6 +289,15 @@ Sums up the event counts for all hardware threads in a core, e.g.:
 
   perf stat -e cpu/event=0,umask=0x3,percore=1/
 
+cpu:
+
+Specifies the CPU to open the event upon. The value may be repeated to
+specify opening the event on multiple CPUs:
+
+
+  perf stat -e instructions/cpu=0,cpu=2/,cycles/cpu=1,cpu=2/ -a sleep 1
+  perf stat -e data_read/cpu=0/,data_write/cpu=1/ -a sleep 1
+
 
 EVENT GROUPS
 ------------
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index 859dc11a7372..c17b3e318169 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -216,6 +216,21 @@ CONTENTION OPTIONS
 --cgroup-filter=<value>::
 	Show lock contention only in the given cgroups (comma separated list).
 
+-J::
+--inject-delay=<time@function>::
+	Add delays to the given lock.  It's added to the contention-end part so
+	that the (new) owner of the lock will be delayed.  But by slowing down
+	the owner, the waiters will also be delayed as well.  This is working
+	only with -b/--use-bpf.
+
+	The 'time' is specified in nsec but it can have a unit suffix.  Available
+	units are "ms", "us" and "ns".  Currently it accepts up to 10ms of delays
+	for safety reasons.
+
+	Note that it will busy-wait after it gets the lock. Delaying locks can
+	have significant consequences including potential kernel crashes.  Please
+	use it at your own risk.
+
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 8a1bd9ff0f86..965e73d37772 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -28,6 +28,8 @@ and kernel support is required. See linkperf:perf-arm-spe[1] for a setup guide.
 Due to the statistical nature of SPE sampling, not every memory operation will
 be sampled.
 
+On AMD this use IBS Op PMU to sample load-store operations.
+
 COMMON OPTIONS
 --------------
 -f::
@@ -67,8 +69,15 @@ RECORD OPTIONS
 	Configure all used events to run in user space.
 
 --ldlat <n>::
-	Specify desired latency for loads event. Supported on Intel and Arm64
-	processors only. Ignored on other archs.
+	Specify desired latency for loads event. Supported on Intel, Arm64 and
+	some AMD processors. Ignored on other archs.
+
+	On supported AMD processors:
+	- /sys/bus/event_source/devices/ibs_op/caps/ldlat file contains '1'.
+	- Supported latency values are 128 to 2048 (both inclusive).
+	- Latency value which is a multiple of 128 incurs a little less profiling
+	  overhead compared to other values.
+	- Load latency filtering is disabled by default.
 
 REPORT OPTIONS
 --------------
@@ -128,6 +137,25 @@ REPORT OPTIONS
 In addition, for report all perf report options are valid, and for record
 all perf record options.
 
+OVERHEAD CALCULATION
+--------------------
+Unlike linkperf:perf-report[1], which calculates overhead from the actual
+sample period, perf-mem overhead is calculated using sample weight. E.g.
+there are two samples in perf.data file, both with the same sample period,
+but one sample with weight 180 and the other with weight 20:
+
+  $ perf script -F period,data_src,weight,ip,sym
+  100000    629080842 |OP LOAD|LVL L3 hit|...     20       7e69b93ca524 strcmp
+  100000   1a29081042 |OP LOAD|LVL RAM hit|...   180   ffffffff82429168 memcpy
+
+  $ perf report -F overhead,symbol
+  50%   [.] strcmp
+  50%   [k] memcpy
+
+  $ perf mem report -F overhead,symbol
+  90%   [k] memcpy
+  10%   [.] strcmp
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-arm-spe[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index c7fc1ba265e2..612612fa2d80 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -340,7 +340,7 @@ OPTIONS
 
 -d::
 --data::
-	Record the sample virtual addresses.
+	Record the sample virtual addresses.  Implies --sample-mem-info.
 
 --phys-data::
 	Record the sample physical addresses.
@@ -368,6 +368,11 @@ OPTIONS
 	the sample_type member of the struct perf_event_attr argument to the
 	perf_event_open system call.
 
+--sample-mem-info::
+	Record the sample data source information for memory operations.
+	It requires hardware supports and may work on specific events only.
+	Please consider using 'perf mem record' instead if you're not sure.
+
 -n::
 --no-samples::
 	Don't sample.
@@ -837,6 +842,15 @@ filtered through the mask provided by -C option.
 	only, as of now.  So the applications built without the frame
 	pointer might see bogus addresses.
 
+	off-cpu profiling consists two types of samples: direct samples, which
+	share the same behavior as regular samples, and the accumulated
+	samples, stored in BPF stack trace map, presented after all the regular
+	samples.
+
+--off-cpu-thresh::
+	Once a task's off-cpu time reaches this threshold (in milliseconds), it
+	generates a direct off-cpu sample. The default is 500ms.
+
 --setup-filter=<action>::
 	Prepare BPF filter to be used by regular users.  The action should be
 	either "pin" or "unpin".  The filter can be used after it's pinned.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 3376c4710575..acef3ff4178e 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -94,6 +94,7 @@ OPTIONS
 
 	- comm: command (name) of the task which can be read via /proc/<pid>/comm
 	- pid: command and tid of the task
+	- tgid: command and tgid of the task
 	- dso: name of library or module executed at the time of sample
 	- dso_size: size of library or module executed at the time of sample
 	- symbol: name of function executed at the time of sample
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 2bc063672486..61d091670dee 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -506,6 +506,13 @@ this option is not set. The TPEBS hardware feature starts from Intel Granite
 Rapids microarchitecture. This option only exists in X86_64 and is meaningful on
 Intel platforms with TPEBS feature.
 
+--tpebs-mode=[mean|min|max|last]::
+Set how retirement latency events have their sample times
+combined. The default "mean" gives the average of retirement
+latency. "min" or "max" give the smallest or largest retirment latency
+times respectively. "last" uses the last retirment latency sample's
+time.
+
 --td-level::
 Print the top-down statistics that equal the input level. It allows
 users to print the interested top-down metrics level instead of the
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 887dc37773d0..c1fb6056a0d3 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -152,7 +152,8 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 
 --summary-mode=mode::
 	To be used with -s or -S, to select how to show summary.  By default it'll
-	show the syscall summary by thread.  Possible values are: thread, total.
+	show the syscall summary by thread.  Possible values are: thread, total,
+	cgroup.
 
 --tool_stats::
 	Show tool stats such as number of times fd->pathname was discovered thru
@@ -251,6 +252,12 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 	pretty-printing serves as a fallback to hand-crafted pretty printers, as the latter can
 	better pretty-print integer flags and struct pointers.
 
+--bpf-summary::
+	Collect system call statistics in BPF.  This is only for live mode and
+	works well with -s/--summary option where no argument information is
+	required.
+
+
 PAGEFAULTS
 ----------
 
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index 010a4edcd384..cd95ba09f727 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -370,7 +370,7 @@ struct {
 	u32	mmap_len;
 };
 
-Indicates that trace contains records of PERF_RECORD_COMPRESSED type
+Indicates that trace contains records of PERF_RECORD_COMPRESSED2 type
 that have perf_events records in compressed form.
 
 	HEADER_CPU_PMU_CAPS = 28,
@@ -602,7 +602,14 @@ struct auxtrace_error_event {
 Describes a header feature. These are records used in pipe-mode that
 contain information that otherwise would be in perf.data file's header.
 
-	PERF_RECORD_COMPRESSED 			= 81,
+	PERF_RECORD_COMPRESSED 			= 81, /* deprecated */
+
+The header is followed by compressed data frame that can be decompressed
+into array of perf trace records. The size of the entire compressed event
+record including the header is limited by the max value of header.size.
+
+It is deprecated and new files should use PERF_RECORD_COMPRESSED2 to gurantee
+8-byte alignment.
 
 struct compressed_event {
 	struct perf_event_header	header;
@@ -618,10 +625,17 @@ This is used, for instance, to 'perf inject' events after init and before
 regular events, those emitted by the kernel, to support combining guest and
 host records.
 
+	PERF_RECORD_COMPRESSED2			= 83,
 
-The header is followed by compressed data frame that can be decompressed
-into array of perf trace records. The size of the entire compressed event
-record including the header is limited by the max value of header.size.
+8-byte aligned version of `PERF_RECORD_COMPRESSED`. `header.size` indicates the
+total record size, including padding for 8-byte alignment, and `data_size`
+specifies the actual size of the compressed data.
+
+struct perf_record_compressed2 {
+	struct perf_event_header	header;
+	__u64				data_size;
+	char				data[];
+};
 
 Event types
 
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 364b55b00b48..34af57b8ec2a 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,8 +1,10 @@
 COPYING
 LICENSES/preferred/GPL-2.0
 arch/arm64/tools/gen-sysreg.awk
+arch/arm64/tools/syscall_64.tbl
 arch/arm64/tools/sysreg
 arch/*/include/uapi/asm/bpf_perf_event.h
+include/uapi/asm-generic/Kbuild
 tools/perf
 tools/arch
 tools/scripts
@@ -25,6 +27,10 @@ tools/lib/str_error_r.c
 tools/lib/vsprintf.c
 tools/lib/zalloc.c
 scripts/bpf_doc.py
+scripts/Kbuild.include
+scripts/Makefile.asm-headers
+scripts/syscall.tbl
+scripts/syscallhdr.sh
 tools/bpf/bpftool
 kernel/bpf/disasm.c
 kernel/bpf/disasm.h
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b7769a22fe1a..d1ea7bf44964 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -560,6 +560,8 @@ ifndef NO_LIBELF
     ifeq ($(feature-libdebuginfod), 1)
       CFLAGS += -DHAVE_DEBUGINFOD_SUPPORT
       EXTLIBS += -ldebuginfod
+    else
+      $(warning No elfutils/debuginfod.h found, no debuginfo server support, please install libdebuginfod-dev/elfutils-debuginfod-client-devel or equivalent)
     endif
   endif
 
@@ -625,6 +627,8 @@ endif
 ifndef NO_LIBUNWIND
   have_libunwind :=
 
+  $(call feature_check,libunwind)
+
   $(call feature_check,libunwind-x86)
   ifeq ($(feature-libunwind-x86), 1)
     $(call detected,CONFIG_LIBUNWIND_X86)
@@ -649,7 +653,7 @@ ifndef NO_LIBUNWIND
   endif
 
   ifneq ($(feature-libunwind), 1)
-    $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR)
+    $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR and set LIBUNWIND=1 in the make command line as it is opt-in now)
     NO_LOCAL_LIBUNWIND := 1
   else
     have_libunwind := 1
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 979d4691221a..d4c7031b01a7 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1147,7 +1147,8 @@ install-tests: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_probe'; \
 		$(INSTALL) tests/shell/base_probe/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_probe'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \
-		$(INSTALL) tests/shell/base_probe/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \
+		$(INSTALL) tests/shell/base_report/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \
+		$(INSTALL) tests/shell/base_report/*.txt '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/coresight' ; \
 		$(INSTALL) tests/shell/coresight/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/coresight'
 	$(Q)$(MAKE) -C tests/shell/coresight install-tests
@@ -1175,7 +1176,7 @@ SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h
 SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h
 SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h
 SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h
-SKELETONS += $(SKEL_OUT)/kwork_top.skel.h
+SKELETONS += $(SKEL_OUT)/kwork_top.skel.h $(SKEL_OUT)/syscall_summary.skel.h
 SKELETONS += $(SKEL_OUT)/bench_uprobe.skel.h
 SKELETONS += $(SKEL_OUT)/augmented_raw_syscalls.skel.h
 
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index c0421a26b875..4fd425157d7d 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -14,6 +14,7 @@ int test__intel_pt_hybrid_compat(struct test_suite *test, int subtest);
 int test__bp_modify(struct test_suite *test, int subtest);
 int test__x86_sample_parsing(struct test_suite *test, int subtest);
 int test__amd_ibs_via_core_pmu(struct test_suite *test, int subtest);
+int test__amd_ibs_period(struct test_suite *test, int subtest);
 int test__hybrid(struct test_suite *test, int subtest);
 
 extern struct test_suite *arch_tests[];
diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index 86262c720857..5e00cbfd2d56 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -10,6 +10,7 @@ perf-test-$(CONFIG_AUXTRACE) += insn-x86.o
 endif
 perf-test-$(CONFIG_X86_64) += bp-modify.o
 perf-test-y += amd-ibs-via-core-pmu.o
+perf-test-y += amd-ibs-period.o
 
 ifdef SHELLCHECK
   SHELL_TESTS := gen-insn-x86-dat.sh
diff --git a/tools/perf/arch/x86/tests/amd-ibs-period.c b/tools/perf/arch/x86/tests/amd-ibs-period.c
new file mode 100644
index 000000000000..223e059e04de
--- /dev/null
+++ b/tools/perf/arch/x86/tests/amd-ibs-period.c
@@ -0,0 +1,1032 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sched.h>
+#include <sys/syscall.h>
+#include <sys/mman.h>
+#include <sys/ioctl.h>
+#include <sys/utsname.h>
+#include <string.h>
+
+#include "arch-tests.h"
+#include "linux/perf_event.h"
+#include "linux/zalloc.h"
+#include "tests/tests.h"
+#include "../perf-sys.h"
+#include "pmu.h"
+#include "pmus.h"
+#include "debug.h"
+#include "util.h"
+#include "strbuf.h"
+#include "../util/env.h"
+
+static int page_size;
+
+#define PERF_MMAP_DATA_PAGES    32L
+#define PERF_MMAP_DATA_SIZE     (PERF_MMAP_DATA_PAGES * page_size)
+#define PERF_MMAP_DATA_MASK     (PERF_MMAP_DATA_SIZE - 1)
+#define PERF_MMAP_TOTAL_PAGES   (PERF_MMAP_DATA_PAGES + 1)
+#define PERF_MMAP_TOTAL_SIZE    (PERF_MMAP_TOTAL_PAGES * page_size)
+
+#define rmb()                   asm volatile("lfence":::"memory")
+
+enum {
+	FD_ERROR,
+	FD_SUCCESS,
+};
+
+enum {
+	IBS_FETCH,
+	IBS_OP,
+};
+
+struct perf_pmu *fetch_pmu;
+struct perf_pmu *op_pmu;
+unsigned int perf_event_max_sample_rate;
+
+/* Dummy workload to generate IBS samples. */
+static int dummy_workload_1(unsigned long count)
+{
+	int (*func)(void);
+	int ret = 0;
+	char *p;
+	char insn1[] = {
+		0xb8, 0x01, 0x00, 0x00, 0x00, /* mov 1,%eax */
+		0xc3, /* ret */
+		0xcc, /* int 3 */
+	};
+
+	char insn2[] = {
+		0xb8, 0x02, 0x00, 0x00, 0x00, /* mov 2,%eax */
+		0xc3, /* ret */
+		0xcc, /* int 3 */
+	};
+
+	p = zalloc(2 * page_size);
+	if (!p) {
+		printf("malloc() failed. %m");
+		return 1;
+	}
+
+	func = (void *)((unsigned long)(p + page_size - 1) & ~(page_size - 1));
+
+	ret = mprotect(func, page_size, PROT_READ | PROT_WRITE | PROT_EXEC);
+	if (ret) {
+		printf("mprotect() failed. %m");
+		goto out;
+	}
+
+	if (count < 100000)
+		count = 100000;
+	else if (count > 10000000)
+		count = 10000000;
+	while (count--) {
+		memcpy((void *)func, insn1, sizeof(insn1));
+		if (func() != 1) {
+			pr_debug("ERROR insn1\n");
+			ret = -1;
+			goto out;
+		}
+		memcpy((void *)func, insn2, sizeof(insn2));
+		if (func() != 2) {
+			pr_debug("ERROR insn2\n");
+			ret = -1;
+			goto out;
+		}
+	}
+
+out:
+	free(p);
+	return ret;
+}
+
+/* Another dummy workload to generate IBS samples. */
+static void dummy_workload_2(char *perf)
+{
+	char bench[] = " bench sched messaging -g 10 -l 5000 > /dev/null 2>&1";
+	char taskset[] = "taskset -c 0 ";
+	int ret __maybe_unused;
+	struct strbuf sb;
+	char *cmd;
+
+	strbuf_init(&sb, 0);
+	strbuf_add(&sb, taskset, strlen(taskset));
+	strbuf_add(&sb, perf, strlen(perf));
+	strbuf_add(&sb, bench, strlen(bench));
+	cmd = strbuf_detach(&sb, NULL);
+	ret = system(cmd);
+	free(cmd);
+}
+
+static int sched_affine(int cpu)
+{
+	cpu_set_t set;
+
+	CPU_ZERO(&set);
+	CPU_SET(cpu, &set);
+	if (sched_setaffinity(getpid(), sizeof(set), &set) == -1) {
+		pr_debug("sched_setaffinity() failed. [%m]");
+		return -1;
+	}
+	return 0;
+}
+
+static void
+copy_sample_data(void *src, unsigned long offset, void *dest, size_t size)
+{
+	size_t chunk1_size, chunk2_size;
+
+	if ((offset + size) < (size_t)PERF_MMAP_DATA_SIZE) {
+		memcpy(dest, src + offset, size);
+	} else {
+		chunk1_size = PERF_MMAP_DATA_SIZE - offset;
+		chunk2_size = size - chunk1_size;
+
+		memcpy(dest, src + offset, chunk1_size);
+		memcpy(dest + chunk1_size, src, chunk2_size);
+	}
+}
+
+static int rb_read(struct perf_event_mmap_page *rb, void *dest, size_t size)
+{
+	void *base;
+	unsigned long data_tail, data_head;
+
+	/* Casting to (void *) is needed. */
+	base = (void *)rb + page_size;
+
+	data_head = rb->data_head;
+	rmb();
+	data_tail = rb->data_tail;
+
+	if ((data_head - data_tail) < size)
+		return -1;
+
+	data_tail &= PERF_MMAP_DATA_MASK;
+	copy_sample_data(base, data_tail, dest, size);
+	rb->data_tail += size;
+	return 0;
+}
+
+static void rb_skip(struct perf_event_mmap_page *rb, size_t size)
+{
+	size_t data_head = rb->data_head;
+
+	rmb();
+
+	if ((rb->data_tail + size) > data_head)
+		rb->data_tail = data_head;
+	else
+		rb->data_tail += size;
+}
+
+/* Sample period value taken from perf sample must match with expected value. */
+static int period_equal(unsigned long exp_period, unsigned long act_period)
+{
+	return exp_period == act_period ? 0 : -1;
+}
+
+/*
+ * Sample period value taken from perf sample must be >= minimum sample period
+ * supported by IBS HW.
+ */
+static int period_higher(unsigned long min_period, unsigned long act_period)
+{
+	return min_period <= act_period ? 0 : -1;
+}
+
+static int rb_drain_samples(struct perf_event_mmap_page *rb,
+			    unsigned long exp_period,
+			    int *nr_samples,
+			    int (*callback)(unsigned long, unsigned long))
+{
+	struct perf_event_header hdr;
+	unsigned long period;
+	int ret = 0;
+
+	/*
+	 * PERF_RECORD_SAMPLE:
+	 * struct {
+	 *	struct perf_event_header hdr;
+	 *	{ u64			 period;     } && PERF_SAMPLE_PERIOD
+	 * };
+	 */
+	while (1) {
+		if (rb_read(rb, &hdr, sizeof(hdr)))
+			return ret;
+
+		if (hdr.type == PERF_RECORD_SAMPLE) {
+			(*nr_samples)++;
+			period = 0;
+			if (rb_read(rb, &period, sizeof(period)))
+				pr_debug("rb_read(period) error. [%m]");
+			ret |= callback(exp_period, period);
+		} else {
+			rb_skip(rb, hdr.size - sizeof(hdr));
+		}
+	}
+	return ret;
+}
+
+static long perf_event_open(struct perf_event_attr *attr, pid_t pid,
+			    int cpu, int group_fd, unsigned long flags)
+{
+	return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+}
+
+static void fetch_prepare_attr(struct perf_event_attr *attr,
+			       unsigned long long config, int freq,
+			       unsigned long sample_period)
+{
+	memset(attr, 0, sizeof(struct perf_event_attr));
+
+	attr->type = fetch_pmu->type;
+	attr->size = sizeof(struct perf_event_attr);
+	attr->config = config;
+	attr->disabled = 1;
+	attr->sample_type = PERF_SAMPLE_PERIOD;
+	attr->freq = freq;
+	attr->sample_period = sample_period; /* = ->sample_freq */
+}
+
+static void op_prepare_attr(struct perf_event_attr *attr,
+			    unsigned long config, int freq,
+			    unsigned long sample_period)
+{
+	memset(attr, 0, sizeof(struct perf_event_attr));
+
+	attr->type = op_pmu->type;
+	attr->size = sizeof(struct perf_event_attr);
+	attr->config = config;
+	attr->disabled = 1;
+	attr->sample_type = PERF_SAMPLE_PERIOD;
+	attr->freq = freq;
+	attr->sample_period = sample_period; /* = ->sample_freq */
+}
+
+struct ibs_configs {
+	/* Input */
+	unsigned long config;
+
+	/* Expected output */
+	unsigned long period;
+	int fd;
+};
+
+/*
+ * Somehow first Fetch event with sample period = 0x10 causes 0
+ * samples. So start with large period and decrease it gradually.
+ */
+struct ibs_configs fetch_configs[] = {
+	{ .config =  0xffff, .period = 0xffff0, .fd = FD_SUCCESS },
+	{ .config =  0x1000, .period = 0x10000, .fd = FD_SUCCESS },
+	{ .config =    0xff, .period =   0xff0, .fd = FD_SUCCESS },
+	{ .config =     0x1, .period =    0x10, .fd = FD_SUCCESS },
+	{ .config =     0x0, .period =      -1, .fd = FD_ERROR   },
+	{ .config = 0x10000, .period =      -1, .fd = FD_ERROR   },
+};
+
+struct ibs_configs op_configs[] = {
+	{ .config =        0x0, .period =        -1, .fd = FD_ERROR   },
+	{ .config =        0x1, .period =        -1, .fd = FD_ERROR   },
+	{ .config =        0x8, .period =        -1, .fd = FD_ERROR   },
+	{ .config =        0x9, .period =      0x90, .fd = FD_SUCCESS },
+	{ .config =        0xf, .period =      0xf0, .fd = FD_SUCCESS },
+	{ .config =     0x1000, .period =   0x10000, .fd = FD_SUCCESS },
+	{ .config =     0xffff, .period =   0xffff0, .fd = FD_SUCCESS },
+	{ .config =    0x10000, .period =        -1, .fd = FD_ERROR   },
+	{ .config =   0x100000, .period =  0x100000, .fd = FD_SUCCESS },
+	{ .config =   0xf00000, .period =  0xf00000, .fd = FD_SUCCESS },
+	{ .config =   0xf0ffff, .period =  0xfffff0, .fd = FD_SUCCESS },
+	{ .config =  0x1f0ffff, .period = 0x1fffff0, .fd = FD_SUCCESS },
+	{ .config =  0x7f0ffff, .period = 0x7fffff0, .fd = FD_SUCCESS },
+	{ .config =  0x8f0ffff, .period =        -1, .fd = FD_ERROR   },
+	{ .config = 0x17f0ffff, .period =        -1, .fd = FD_ERROR   },
+};
+
+static int __ibs_config_test(int ibs_type, struct ibs_configs *config, int *nr_samples)
+{
+	struct perf_event_attr attr;
+	int fd, i;
+	void *rb;
+	int ret = 0;
+
+	if (ibs_type == IBS_FETCH)
+		fetch_prepare_attr(&attr, config->config, 0, 0);
+	else
+		op_prepare_attr(&attr, config->config, 0, 0);
+
+	/* CPU0, All processes */
+	fd = perf_event_open(&attr, -1, 0, -1, 0);
+	if (config->fd == FD_ERROR) {
+		if (fd != -1) {
+			close(fd);
+			return -1;
+		}
+		return 0;
+	}
+	if (fd <= -1)
+		return -1;
+
+	rb = mmap(NULL, PERF_MMAP_TOTAL_SIZE, PROT_READ | PROT_WRITE,
+		  MAP_SHARED, fd, 0);
+	if (rb == MAP_FAILED) {
+		pr_debug("mmap() failed. [%m]\n");
+		return -1;
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
+
+	i = 5;
+	while (i--) {
+		dummy_workload_1(1000000);
+
+		ret = rb_drain_samples(rb, config->period, nr_samples,
+				       period_equal);
+		if (ret)
+			break;
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
+	munmap(rb, PERF_MMAP_TOTAL_SIZE);
+	close(fd);
+	return ret;
+}
+
+static int ibs_config_test(void)
+{
+	int nr_samples = 0;
+	unsigned long i;
+	int ret = 0;
+	int r;
+
+	pr_debug("\nIBS config tests:\n");
+	pr_debug("-----------------\n");
+
+	pr_debug("Fetch PMU tests:\n");
+	for (i = 0; i < ARRAY_SIZE(fetch_configs); i++) {
+		nr_samples = 0;
+		r = __ibs_config_test(IBS_FETCH, &(fetch_configs[i]), &nr_samples);
+
+		if (fetch_configs[i].fd == FD_ERROR) {
+			pr_debug("0x%-16lx: %-4s\n", fetch_configs[i].config,
+				 !r ? "Ok" : "Fail");
+		} else {
+			/*
+			 * Although nr_samples == 0 is reported as Fail here,
+			 * the failure status is not cascaded up because, we
+			 * can not decide whether test really failed or not
+			 * without actual samples.
+			 */
+			pr_debug("0x%-16lx: %-4s (nr samples: %d)\n", fetch_configs[i].config,
+				 (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples);
+		}
+
+		ret |= r;
+	}
+
+	pr_debug("Op PMU tests:\n");
+	for (i = 0; i < ARRAY_SIZE(op_configs); i++) {
+		nr_samples = 0;
+		r = __ibs_config_test(IBS_OP, &(op_configs[i]), &nr_samples);
+
+		if (op_configs[i].fd == FD_ERROR) {
+			pr_debug("0x%-16lx: %-4s\n", op_configs[i].config,
+				 !r ? "Ok" : "Fail");
+		} else {
+			/*
+			 * Although nr_samples == 0 is reported as Fail here,
+			 * the failure status is not cascaded up because, we
+			 * can not decide whether test really failed or not
+			 * without actual samples.
+			 */
+			pr_debug("0x%-16lx: %-4s (nr samples: %d)\n", op_configs[i].config,
+				 (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples);
+		}
+
+		ret |= r;
+	}
+
+	return ret;
+}
+
+struct ibs_period {
+	/* Input */
+	int freq;
+	unsigned long sample_freq;
+
+	/* Output */
+	int ret;
+	unsigned long period;
+};
+
+struct ibs_period fetch_period[] = {
+	{ .freq = 0, .sample_freq =         0, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =         1, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =       0xf, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =      0x10, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 0, .sample_freq =      0x11, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 0, .sample_freq =      0x8f, .ret = FD_SUCCESS, .period =      0x80 },
+	{ .freq = 0, .sample_freq =      0x90, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 0, .sample_freq =      0x91, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 0, .sample_freq =     0x4d2, .ret = FD_SUCCESS, .period =     0x4d0 },
+	{ .freq = 0, .sample_freq =    0x1007, .ret = FD_SUCCESS, .period =    0x1000 },
+	{ .freq = 0, .sample_freq =    0xfff0, .ret = FD_SUCCESS, .period =    0xfff0 },
+	{ .freq = 0, .sample_freq =    0xffff, .ret = FD_SUCCESS, .period =    0xfff0 },
+	{ .freq = 0, .sample_freq =   0x10010, .ret = FD_SUCCESS, .period =   0x10010 },
+	{ .freq = 0, .sample_freq =  0x7fffff, .ret = FD_SUCCESS, .period =  0x7ffff0 },
+	{ .freq = 0, .sample_freq = 0xfffffff, .ret = FD_SUCCESS, .period = 0xffffff0 },
+	{ .freq = 1, .sample_freq =         0, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 1, .sample_freq =         1, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =       0xf, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =      0x10, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =      0x11, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =      0x8f, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =      0x90, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =      0x91, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =     0x4d2, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =    0x1007, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =    0xfff0, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =    0xffff, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =   0x10010, .ret = FD_SUCCESS, .period =      0x10 },
+	/* ret=FD_ERROR because freq > default perf_event_max_sample_rate (100000) */
+	{ .freq = 1, .sample_freq =  0x7fffff, .ret = FD_ERROR,   .period =        -1 },
+};
+
+struct ibs_period op_period[] = {
+	{ .freq = 0, .sample_freq =         0, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =         1, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =       0xf, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =      0x10, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =      0x11, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =      0x8f, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =      0x90, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 0, .sample_freq =      0x91, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 0, .sample_freq =     0x4d2, .ret = FD_SUCCESS, .period =     0x4d0 },
+	{ .freq = 0, .sample_freq =    0x1007, .ret = FD_SUCCESS, .period =    0x1000 },
+	{ .freq = 0, .sample_freq =    0xfff0, .ret = FD_SUCCESS, .period =    0xfff0 },
+	{ .freq = 0, .sample_freq =    0xffff, .ret = FD_SUCCESS, .period =    0xfff0 },
+	{ .freq = 0, .sample_freq =   0x10010, .ret = FD_SUCCESS, .period =   0x10010 },
+	{ .freq = 0, .sample_freq =  0x7fffff, .ret = FD_SUCCESS, .period =  0x7ffff0 },
+	{ .freq = 0, .sample_freq = 0xfffffff, .ret = FD_SUCCESS, .period = 0xffffff0 },
+	{ .freq = 1, .sample_freq =         0, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 1, .sample_freq =         1, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =       0xf, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =      0x10, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =      0x11, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =      0x8f, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =      0x90, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =      0x91, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =     0x4d2, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =    0x1007, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =    0xfff0, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =    0xffff, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =   0x10010, .ret = FD_SUCCESS, .period =      0x90 },
+	/* ret=FD_ERROR because freq > default perf_event_max_sample_rate (100000) */
+	{ .freq = 1, .sample_freq =  0x7fffff, .ret = FD_ERROR,   .period =        -1 },
+};
+
+static int __ibs_period_constraint_test(int ibs_type, struct ibs_period *period,
+					int *nr_samples)
+{
+	struct perf_event_attr attr;
+	int ret = 0;
+	void *rb;
+	int fd;
+
+	if (period->freq && period->sample_freq > perf_event_max_sample_rate)
+		period->ret = FD_ERROR;
+
+	if (ibs_type == IBS_FETCH)
+		fetch_prepare_attr(&attr, 0, period->freq, period->sample_freq);
+	else
+		op_prepare_attr(&attr, 0, period->freq, period->sample_freq);
+
+	/* CPU0, All processes */
+	fd = perf_event_open(&attr, -1, 0, -1, 0);
+	if (period->ret == FD_ERROR) {
+		if (fd != -1) {
+			close(fd);
+			return -1;
+		}
+		return 0;
+	}
+	if (fd <= -1)
+		return -1;
+
+	rb = mmap(NULL, PERF_MMAP_TOTAL_SIZE, PROT_READ | PROT_WRITE,
+		  MAP_SHARED, fd, 0);
+	if (rb == MAP_FAILED) {
+		pr_debug("mmap() failed. [%m]\n");
+		close(fd);
+		return -1;
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
+
+	if (period->freq) {
+		dummy_workload_1(100000);
+		ret = rb_drain_samples(rb, period->period, nr_samples,
+				       period_higher);
+	} else {
+		dummy_workload_1(period->sample_freq * 10);
+		ret = rb_drain_samples(rb, period->period, nr_samples,
+				       period_equal);
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
+	munmap(rb, PERF_MMAP_TOTAL_SIZE);
+	close(fd);
+	return ret;
+}
+
+static int ibs_period_constraint_test(void)
+{
+	unsigned long i;
+	int nr_samples;
+	int ret = 0;
+	int r;
+
+	pr_debug("\nIBS sample period constraint tests:\n");
+	pr_debug("-----------------------------------\n");
+
+	pr_debug("Fetch PMU test:\n");
+	for (i = 0; i < ARRAY_SIZE(fetch_period); i++) {
+		nr_samples = 0;
+		r = __ibs_period_constraint_test(IBS_FETCH, &fetch_period[i],
+						 &nr_samples);
+
+		if (fetch_period[i].ret == FD_ERROR) {
+			pr_debug("freq %d, sample_freq %9ld: %-4s\n",
+				 fetch_period[i].freq, fetch_period[i].sample_freq,
+				 !r ? "Ok" : "Fail");
+		} else {
+			/*
+			 * Although nr_samples == 0 is reported as Fail here,
+			 * the failure status is not cascaded up because, we
+			 * can not decide whether test really failed or not
+			 * without actual samples.
+			 */
+			pr_debug("freq %d, sample_freq %9ld: %-4s (nr samples: %d)\n",
+				 fetch_period[i].freq, fetch_period[i].sample_freq,
+				 (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples);
+		}
+		ret |= r;
+	}
+
+	pr_debug("Op PMU test:\n");
+	for (i = 0; i < ARRAY_SIZE(op_period); i++) {
+		nr_samples = 0;
+		r = __ibs_period_constraint_test(IBS_OP, &op_period[i],
+						 &nr_samples);
+
+		if (op_period[i].ret == FD_ERROR) {
+			pr_debug("freq %d, sample_freq %9ld: %-4s\n",
+				 op_period[i].freq, op_period[i].sample_freq,
+				 !r ? "Ok" : "Fail");
+		} else {
+			/*
+			 * Although nr_samples == 0 is reported as Fail here,
+			 * the failure status is not cascaded up because, we
+			 * can not decide whether test really failed or not
+			 * without actual samples.
+			 */
+			pr_debug("freq %d, sample_freq %9ld: %-4s (nr samples: %d)\n",
+				 op_period[i].freq, op_period[i].sample_freq,
+				 (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples);
+		}
+		ret |= r;
+	}
+
+	return ret;
+}
+
+struct ibs_ioctl {
+	/* Input */
+	int freq;
+	unsigned long period;
+
+	/* Expected output */
+	int ret;
+};
+
+struct ibs_ioctl fetch_ioctl[] = {
+	{ .freq = 0, .period =     0x0, .ret = FD_ERROR   },
+	{ .freq = 0, .period =     0x1, .ret = FD_ERROR   },
+	{ .freq = 0, .period =     0xf, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x10, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =    0x11, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x1f, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x20, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =    0x80, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =    0x8f, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x90, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =    0x91, .ret = FD_ERROR   },
+	{ .freq = 0, .period =   0x100, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =  0xfff0, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =  0xffff, .ret = FD_ERROR   },
+	{ .freq = 0, .period = 0x10000, .ret = FD_SUCCESS },
+	{ .freq = 0, .period = 0x1fff0, .ret = FD_SUCCESS },
+	{ .freq = 0, .period = 0x1fff5, .ret = FD_ERROR   },
+	{ .freq = 1, .period =     0x0, .ret = FD_ERROR   },
+	{ .freq = 1, .period =     0x1, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =     0xf, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x10, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x11, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x1f, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x20, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x80, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x8f, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x90, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x91, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =   0x100, .ret = FD_SUCCESS },
+};
+
+struct ibs_ioctl op_ioctl[] = {
+	{ .freq = 0, .period =     0x0, .ret = FD_ERROR   },
+	{ .freq = 0, .period =     0x1, .ret = FD_ERROR   },
+	{ .freq = 0, .period =     0xf, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x10, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x11, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x1f, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x20, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x80, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x8f, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x90, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =    0x91, .ret = FD_ERROR   },
+	{ .freq = 0, .period =   0x100, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =  0xfff0, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =  0xffff, .ret = FD_ERROR   },
+	{ .freq = 0, .period = 0x10000, .ret = FD_SUCCESS },
+	{ .freq = 0, .period = 0x1fff0, .ret = FD_SUCCESS },
+	{ .freq = 0, .period = 0x1fff5, .ret = FD_ERROR   },
+	{ .freq = 1, .period =     0x0, .ret = FD_ERROR   },
+	{ .freq = 1, .period =     0x1, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =     0xf, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x10, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x11, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x1f, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x20, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x80, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x8f, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x90, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x91, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =   0x100, .ret = FD_SUCCESS },
+};
+
+static int __ibs_ioctl_test(int ibs_type, struct ibs_ioctl *ibs_ioctl)
+{
+	struct perf_event_attr attr;
+	int ret = 0;
+	int fd;
+	int r;
+
+	if (ibs_type == IBS_FETCH)
+		fetch_prepare_attr(&attr, 0, ibs_ioctl->freq, 1000);
+	else
+		op_prepare_attr(&attr, 0, ibs_ioctl->freq, 1000);
+
+	/* CPU0, All processes */
+	fd = perf_event_open(&attr, -1, 0, -1, 0);
+	if (fd <= -1) {
+		pr_debug("event_open() Failed\n");
+		return -1;
+	}
+
+	r = ioctl(fd, PERF_EVENT_IOC_PERIOD, &ibs_ioctl->period);
+	if ((ibs_ioctl->ret == FD_SUCCESS && r <= -1) ||
+	    (ibs_ioctl->ret == FD_ERROR && r >= 0)) {
+		ret = -1;
+	}
+
+	close(fd);
+	return ret;
+}
+
+static int ibs_ioctl_test(void)
+{
+	unsigned long i;
+	int ret = 0;
+	int r;
+
+	pr_debug("\nIBS ioctl() tests:\n");
+	pr_debug("------------------\n");
+
+	pr_debug("Fetch PMU tests\n");
+	for (i = 0; i < ARRAY_SIZE(fetch_ioctl); i++) {
+		r = __ibs_ioctl_test(IBS_FETCH, &fetch_ioctl[i]);
+
+		pr_debug("ioctl(%s = 0x%-7lx): %s\n",
+			 fetch_ioctl[i].freq ? "freq  " : "period",
+			 fetch_ioctl[i].period, r ? "Fail" : "Ok");
+		ret |= r;
+	}
+
+	pr_debug("Op PMU tests\n");
+	for (i = 0; i < ARRAY_SIZE(op_ioctl); i++) {
+		r = __ibs_ioctl_test(IBS_OP, &op_ioctl[i]);
+
+		pr_debug("ioctl(%s = 0x%-7lx): %s\n",
+			 op_ioctl[i].freq ? "freq  " : "period",
+			 op_ioctl[i].period, r ? "Fail" : "Ok");
+		ret |= r;
+	}
+
+	return ret;
+}
+
+static int ibs_freq_neg_test(void)
+{
+	struct perf_event_attr attr;
+	int fd;
+
+	pr_debug("\nIBS freq (negative) tests:\n");
+	pr_debug("--------------------------\n");
+
+	/*
+	 * Assuming perf_event_max_sample_rate <= 100000,
+	 * config: 0x300D40 ==> MaxCnt: 200000
+	 */
+	op_prepare_attr(&attr, 0x300D40, 1, 0);
+
+	/* CPU0, All processes */
+	fd = perf_event_open(&attr, -1, 0, -1, 0);
+	if (fd != -1) {
+		pr_debug("freq 1, sample_freq 200000: Fail\n");
+		close(fd);
+		return -1;
+	}
+
+	pr_debug("freq 1, sample_freq 200000: Ok\n");
+
+	return 0;
+}
+
+struct ibs_l3missonly {
+	/* Input */
+	int freq;
+	unsigned long sample_freq;
+
+	/* Expected output */
+	int ret;
+	unsigned long min_period;
+};
+
+struct ibs_l3missonly fetch_l3missonly = {
+	.freq = 1,
+	.sample_freq = 10000,
+	.ret = FD_SUCCESS,
+	.min_period = 0x10,
+};
+
+struct ibs_l3missonly op_l3missonly = {
+	.freq = 1,
+	.sample_freq = 10000,
+	.ret = FD_SUCCESS,
+	.min_period = 0x90,
+};
+
+static int __ibs_l3missonly_test(char *perf, int ibs_type, int *nr_samples,
+				 struct ibs_l3missonly *l3missonly)
+{
+	struct perf_event_attr attr;
+	int ret = 0;
+	void *rb;
+	int fd;
+
+	if (l3missonly->sample_freq > perf_event_max_sample_rate)
+		l3missonly->ret = FD_ERROR;
+
+	if (ibs_type == IBS_FETCH) {
+		fetch_prepare_attr(&attr, 0x800000000000000UL, l3missonly->freq,
+				   l3missonly->sample_freq);
+	} else {
+		op_prepare_attr(&attr, 0x10000, l3missonly->freq,
+				l3missonly->sample_freq);
+	}
+
+	/* CPU0, All processes */
+	fd = perf_event_open(&attr, -1, 0, -1, 0);
+	if (l3missonly->ret == FD_ERROR) {
+		if (fd != -1) {
+			close(fd);
+			return -1;
+		}
+		return 0;
+	}
+	if (fd == -1) {
+		pr_debug("perf_event_open() failed. [%m]\n");
+		return -1;
+	}
+
+	rb = mmap(NULL, PERF_MMAP_TOTAL_SIZE, PROT_READ | PROT_WRITE,
+		  MAP_SHARED, fd, 0);
+	if (rb == MAP_FAILED) {
+		pr_debug("mmap() failed. [%m]\n");
+		close(fd);
+		return -1;
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
+
+	dummy_workload_2(perf);
+
+	ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
+
+	ret = rb_drain_samples(rb, l3missonly->min_period, nr_samples, period_higher);
+
+	munmap(rb, PERF_MMAP_TOTAL_SIZE);
+	close(fd);
+	return ret;
+}
+
+static int ibs_l3missonly_test(char *perf)
+{
+	int nr_samples = 0;
+	int ret = 0;
+	int r = 0;
+
+	pr_debug("\nIBS L3MissOnly test: (takes a while)\n");
+	pr_debug("--------------------\n");
+
+	if (perf_pmu__has_format(fetch_pmu, "l3missonly")) {
+		nr_samples = 0;
+		r = __ibs_l3missonly_test(perf, IBS_FETCH, &nr_samples, &fetch_l3missonly);
+		if (fetch_l3missonly.ret == FD_ERROR) {
+			pr_debug("Fetch L3MissOnly: %-4s\n", !r ? "Ok" : "Fail");
+		} else {
+			/*
+			 * Although nr_samples == 0 is reported as Fail here,
+			 * the failure status is not cascaded up because, we
+			 * can not decide whether test really failed or not
+			 * without actual samples.
+			 */
+			pr_debug("Fetch L3MissOnly: %-4s (nr_samples: %d)\n",
+				 (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples);
+		}
+		ret |= r;
+	}
+
+	if (perf_pmu__has_format(op_pmu, "l3missonly")) {
+		nr_samples = 0;
+		r = __ibs_l3missonly_test(perf, IBS_OP, &nr_samples, &op_l3missonly);
+		if (op_l3missonly.ret == FD_ERROR) {
+			pr_debug("Op L3MissOnly:    %-4s\n", !r ? "Ok" : "Fail");
+		} else {
+			/*
+			 * Although nr_samples == 0 is reported as Fail here,
+			 * the failure status is not cascaded up because, we
+			 * can not decide whether test really failed or not
+			 * without actual samples.
+			 */
+			pr_debug("Op L3MissOnly:    %-4s (nr_samples: %d)\n",
+				 (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples);
+		}
+		ret |= r;
+	}
+
+	return ret;
+}
+
+static unsigned int get_perf_event_max_sample_rate(void)
+{
+	unsigned int max_sample_rate = 100000;
+	FILE *fp;
+	int ret;
+
+	fp = fopen("/proc/sys/kernel/perf_event_max_sample_rate", "r");
+	if (!fp) {
+		pr_debug("Can't open perf_event_max_sample_rate. Assuming %d\n",
+			 max_sample_rate);
+		goto out;
+	}
+
+	ret = fscanf(fp, "%d", &max_sample_rate);
+	if (ret == EOF) {
+		pr_debug("Can't read perf_event_max_sample_rate. Assuming 100000\n");
+		max_sample_rate = 100000;
+	}
+	fclose(fp);
+
+out:
+	return max_sample_rate;
+}
+
+/*
+ * Bunch of IBS sample period fixes that this test exercise went in v6.15.
+ * Skip the test on older kernels to distinguish between test failure due
+ * to a new bug vs known failure due to older kernel.
+ */
+static bool kernel_v6_15_or_newer(void)
+{
+	struct utsname utsname;
+	char *endptr = NULL;
+	long major, minor;
+
+	if (uname(&utsname) < 0) {
+		pr_debug("uname() failed. [%m]");
+		return false;
+	}
+
+	major = strtol(utsname.release, &endptr, 10);
+	endptr++;
+	minor = strtol(endptr, NULL, 10);
+
+	return major >= 6 && minor >= 15;
+}
+
+int test__amd_ibs_period(struct test_suite *test __maybe_unused,
+			 int subtest __maybe_unused)
+{
+	char perf[PATH_MAX] = {'\0'};
+	int ret = TEST_OK;
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	/*
+	 * Reading perf_event_max_sample_rate only once _might_ cause some
+	 * of the test to fail if kernel changes it after reading it here.
+	 */
+	perf_event_max_sample_rate = get_perf_event_max_sample_rate();
+	fetch_pmu = perf_pmus__find("ibs_fetch");
+	op_pmu = perf_pmus__find("ibs_op");
+
+	if (!x86__is_amd_cpu() || !fetch_pmu || !op_pmu)
+		return TEST_SKIP;
+
+	if (!kernel_v6_15_or_newer()) {
+		pr_debug("Need v6.15 or newer kernel. Skipping.\n");
+		return TEST_SKIP;
+	}
+
+	perf_exe(perf, sizeof(perf));
+
+	if (sched_affine(0))
+		return TEST_FAIL;
+
+	/*
+	 * Perf event can be opened in two modes:
+	 * 1 Freq mode
+	 *   perf_event_attr->freq = 1, ->sample_freq = <frequency>
+	 * 2 Sample period mode
+	 *   perf_event_attr->freq = 0, ->sample_period = <period>
+	 *
+	 * Instead of using above interface, IBS event in 'sample period mode'
+	 * can also be opened by passing <period> value directly in a MaxCnt
+	 * bitfields of perf_event_attr->config. Test this IBS specific special
+	 * interface.
+	 */
+	if (ibs_config_test())
+		ret = TEST_FAIL;
+
+	/*
+	 * IBS Fetch and Op PMUs have HW constraints on minimum sample period.
+	 * Also, sample period value must be in multiple of 0x10. Test that IBS
+	 * driver honors HW constraints for various possible values in Freq as
+	 * well as Sample Period mode IBS events.
+	 */
+	if (ibs_period_constraint_test())
+		ret = TEST_FAIL;
+
+	/*
+	 * Test ioctl() with various sample period values for IBS event.
+	 */
+	if (ibs_ioctl_test())
+		ret = TEST_FAIL;
+
+	/*
+	 * Test that opening of freq mode IBS event fails when the freq value
+	 * is passed through ->config, not explicitly in ->sample_freq. Also
+	 * use high freq value (beyond perf_event_max_sample_rate) to test IBS
+	 * driver do not bypass perf_event_max_sample_rate checks.
+	 */
+	if (ibs_freq_neg_test())
+		ret = TEST_FAIL;
+
+	/*
+	 * L3MissOnly is a post-processing filter, i.e. IBS HW checks for L3
+	 * Miss at the completion of the tagged uOp. The sample is discarded
+	 * if the tagged uOp did not cause L3Miss. Also, IBS HW internally
+	 * resets CurCnt to a small pseudo-random value and resumes counting.
+	 * A new uOp is tagged once CurCnt reaches to MaxCnt. But the process
+	 * repeats until the tagged uOp causes an L3 Miss.
+	 *
+	 * With the freq mode event, the next sample period is calculated by
+	 * generic kernel on every sample to achieve desired freq of samples.
+	 *
+	 * Since the number of times HW internally reset CurCnt and the pseudo-
+	 * random value of CurCnt for all those occurrences are not known to SW,
+	 * the sample period adjustment by kernel goes for a toes for freq mode
+	 * IBS events. Kernel will set very small period for the next sample if
+	 * the window between current sample and prev sample is too high due to
+	 * multiple samples being discarded internally by IBS HW.
+	 *
+	 * Test that IBS sample period constraints are honored when L3MissOnly
+	 * is ON.
+	 */
+	if (ibs_l3missonly_test(perf))
+		ret = TEST_FAIL;
+
+	return ret;
+}
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index a216a5d172ed..bfee2432515b 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -25,6 +25,7 @@ DEFINE_SUITE("x86 bp modify", bp_modify);
 #endif
 DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing);
 DEFINE_SUITE("AMD IBS via core pmu", amd_ibs_via_core_pmu);
+DEFINE_SUITE_EXCLUSIVE("AMD IBS sample period", amd_ibs_period);
 static struct test_case hybrid_tests[] = {
 	TEST_CASE_REASON("x86 hybrid event parsing", hybrid, "not hybrid"),
 	{ .name = NULL, }
@@ -50,6 +51,7 @@ struct test_suite *arch_tests[] = {
 #endif
 	&suite__x86_sample_parsing,
 	&suite__amd_ibs_via_core_pmu,
+	&suite__amd_ibs_period,
 	&suite__hybrid,
 	NULL,
 };
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 8f235d8b67b6..add33cb5d1da 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -19,6 +19,7 @@
 #include "../../../util/evlist.h"
 #include "../../../util/evsel.h"
 #include "../../../util/evsel_config.h"
+#include "../../../util/config.h"
 #include "../../../util/cpumap.h"
 #include "../../../util/mmap.h"
 #include <subcmd/parse-options.h>
@@ -52,6 +53,7 @@ struct intel_pt_recording {
 	struct perf_pmu			*intel_pt_pmu;
 	int				have_sched_switch;
 	struct evlist		*evlist;
+	bool				all_switch_events;
 	bool				snapshot_mode;
 	bool				snapshot_init_done;
 	size_t				snapshot_size;
@@ -794,7 +796,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 			bool cpu_wide = !target__none(&opts->target) &&
 					!target__has_task(&opts->target);
 
-			if (!cpu_wide && perf_can_record_cpu_wide()) {
+			if (ptr->all_switch_events && !cpu_wide && perf_can_record_cpu_wide()) {
 				struct evsel *switch_evsel;
 
 				switch_evsel = evlist__add_dummy_on_all_cpus(evlist);
@@ -1178,6 +1180,16 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused)
 	return rdtsc();
 }
 
+static int intel_pt_perf_config(const char *var, const char *value, void *data)
+{
+	struct intel_pt_recording *ptr = data;
+
+	if (!strcmp(var, "intel-pt.all-switch-events"))
+		ptr->all_switch_events = perf_config_bool(var, value);
+
+	return 0;
+}
+
 struct auxtrace_record *intel_pt_recording_init(int *err)
 {
 	struct perf_pmu *intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME);
@@ -1197,6 +1209,8 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 		return NULL;
 	}
 
+	perf_config(intel_pt_perf_config, ptr);
+
 	ptr->intel_pt_pmu = intel_pt_pmu;
 	ptr->itr.recording_options = intel_pt_recording_options;
 	ptr->itr.info_priv_size = intel_pt_info_priv_size;
diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
index 62df03e91c7e..b38f519020ff 100644
--- a/tools/perf/arch/x86/util/mem-events.c
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -26,3 +26,9 @@ struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
 	E(NULL,		NULL,		NULL,	false,	0),
 	E("mem-ldst",	"%s//",		NULL,	false,	0),
 };
+
+struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX] = {
+	E(NULL,		NULL,		NULL,	false,	0),
+	E(NULL,		NULL,		NULL,	false,	0),
+	E("mem-ldst",	"%s/ldlat=%u/",	NULL,	true,	0),
+};
diff --git a/tools/perf/arch/x86/util/mem-events.h b/tools/perf/arch/x86/util/mem-events.h
index f55c8d3b7d59..11e09a256f5b 100644
--- a/tools/perf/arch/x86/util/mem-events.h
+++ b/tools/perf/arch/x86/util/mem-events.h
@@ -6,5 +6,6 @@ extern struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX];
 extern struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX];
 
 extern struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX];
+extern struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX];
 
 #endif /* _X86_MEM_EVENTS_H */
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index e0060dac2a9f..58113482654b 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -8,6 +8,8 @@
 #include <linux/perf_event.h>
 #include <linux/zalloc.h>
 #include <api/fs/fs.h>
+#include <api/io_dir.h>
+#include <internal/cpumap.h>
 #include <errno.h>
 
 #include "../../../util/intel-pt.h"
@@ -16,10 +18,261 @@
 #include "../../../util/fncache.h"
 #include "../../../util/pmus.h"
 #include "mem-events.h"
+#include "util/debug.h"
 #include "util/env.h"
+#include "util/header.h"
 
-void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused)
+static bool x86__is_intel_graniterapids(void)
 {
+	static bool checked_if_graniterapids;
+	static bool is_graniterapids;
+
+	if (!checked_if_graniterapids) {
+		const char *graniterapids_cpuid = "GenuineIntel-6-A[DE]";
+		char *cpuid = get_cpuid_str((struct perf_cpu){0});
+
+		is_graniterapids = cpuid && strcmp_cpuid_str(graniterapids_cpuid, cpuid) == 0;
+		free(cpuid);
+		checked_if_graniterapids = true;
+	}
+	return is_graniterapids;
+}
+
+static struct perf_cpu_map *read_sysfs_cpu_map(const char *sysfs_path)
+{
+	struct perf_cpu_map *cpus;
+	char *buf = NULL;
+	size_t buf_len;
+
+	if (sysfs__read_str(sysfs_path, &buf, &buf_len) < 0)
+		return NULL;
+
+	cpus = perf_cpu_map__new(buf);
+	free(buf);
+	return cpus;
+}
+
+static int snc_nodes_per_l3_cache(void)
+{
+	static bool checked_snc;
+	static int snc_nodes;
+
+	if (!checked_snc) {
+		struct perf_cpu_map *node_cpus =
+			read_sysfs_cpu_map("devices/system/node/node0/cpulist");
+		struct perf_cpu_map *cache_cpus =
+			read_sysfs_cpu_map("devices/system/cpu/cpu0/cache/index3/shared_cpu_list");
+
+		snc_nodes = perf_cpu_map__nr(cache_cpus) / perf_cpu_map__nr(node_cpus);
+		perf_cpu_map__put(cache_cpus);
+		perf_cpu_map__put(node_cpus);
+		checked_snc = true;
+	}
+	return snc_nodes;
+}
+
+static bool starts_with(const char *str, const char *prefix)
+{
+	return !strncmp(prefix, str, strlen(prefix));
+}
+
+static int num_chas(void)
+{
+	static bool checked_chas;
+	static int num_chas;
+
+	if (!checked_chas) {
+		int fd = perf_pmu__event_source_devices_fd();
+		struct io_dir dir;
+		struct io_dirent64 *dent;
+
+		if (fd < 0)
+			return -1;
+
+		io_dir__init(&dir, fd);
+
+		while ((dent = io_dir__readdir(&dir)) != NULL) {
+			/* Note, dent->d_type will be DT_LNK and so isn't a useful filter. */
+			if (starts_with(dent->d_name, "uncore_cha_"))
+				num_chas++;
+		}
+		close(fd);
+		checked_chas = true;
+	}
+	return num_chas;
+}
+
+#define MAX_SNCS 6
+
+static int uncore_cha_snc(struct perf_pmu *pmu)
+{
+	// CHA SNC numbers are ordered correspond to the CHAs number.
+	unsigned int cha_num;
+	int num_cha, chas_per_node, cha_snc;
+	int snc_nodes = snc_nodes_per_l3_cache();
+
+	if (snc_nodes <= 1)
+		return 0;
+
+	num_cha = num_chas();
+	if (num_cha <= 0) {
+		pr_warning("Unexpected: no CHAs found\n");
+		return 0;
+	}
+
+	/* Compute SNC for PMU. */
+	if (sscanf(pmu->name, "uncore_cha_%u", &cha_num) != 1) {
+		pr_warning("Unexpected: unable to compute CHA number '%s'\n", pmu->name);
+		return 0;
+	}
+	chas_per_node = num_cha / snc_nodes;
+	cha_snc = cha_num / chas_per_node;
+
+	/* Range check cha_snc. for unexpected out of bounds. */
+	return cha_snc >= MAX_SNCS ? 0 : cha_snc;
+}
+
+static int uncore_imc_snc(struct perf_pmu *pmu)
+{
+	// Compute the IMC SNC using lookup tables.
+	unsigned int imc_num;
+	int snc_nodes = snc_nodes_per_l3_cache();
+	const u8 snc2_map[] = {1, 1, 0, 0, 1, 1, 0, 0};
+	const u8 snc3_map[] = {1, 1, 0, 0, 2, 2, 1, 1, 0, 0, 2, 2};
+	const u8 *snc_map;
+	size_t snc_map_len;
+
+	switch (snc_nodes) {
+	case 2:
+		snc_map = snc2_map;
+		snc_map_len = ARRAY_SIZE(snc2_map);
+		break;
+	case 3:
+		snc_map = snc3_map;
+		snc_map_len = ARRAY_SIZE(snc3_map);
+		break;
+	default:
+		/* Error or no lookup support for SNC with >3 nodes. */
+		return 0;
+	}
+
+	/* Compute SNC for PMU. */
+	if (sscanf(pmu->name, "uncore_imc_%u", &imc_num) != 1) {
+		pr_warning("Unexpected: unable to compute IMC number '%s'\n", pmu->name);
+		return 0;
+	}
+	if (imc_num >= snc_map_len) {
+		pr_warning("Unexpected IMC %d for SNC%d mapping\n", imc_num, snc_nodes);
+		return 0;
+	}
+	return snc_map[imc_num];
+}
+
+static int uncore_cha_imc_compute_cpu_adjust(int pmu_snc)
+{
+	static bool checked_cpu_adjust[MAX_SNCS];
+	static int cpu_adjust[MAX_SNCS];
+	struct perf_cpu_map *node_cpus;
+	char node_path[] = "devices/system/node/node0/cpulist";
+
+	/* Was adjust already computed? */
+	if (checked_cpu_adjust[pmu_snc])
+		return cpu_adjust[pmu_snc];
+
+	/* SNC0 doesn't need an adjust. */
+	if (pmu_snc == 0) {
+		cpu_adjust[0] = 0;
+		checked_cpu_adjust[0] = true;
+		return 0;
+	}
+
+	/*
+	 * Use NUMA topology to compute first CPU of the NUMA node, we want to
+	 * adjust CPU 0 to be this and similarly for other CPUs if there is >1
+	 * socket.
+	 */
+	assert(pmu_snc >= 0 && pmu_snc <= 9);
+	node_path[24] += pmu_snc; // Shift node0 to be node<pmu_snc>.
+	node_cpus = read_sysfs_cpu_map(node_path);
+	cpu_adjust[pmu_snc] = perf_cpu_map__cpu(node_cpus, 0).cpu;
+	if (cpu_adjust[pmu_snc] < 0) {
+		pr_debug("Failed to read valid CPU list from <sysfs>/%s\n", node_path);
+		cpu_adjust[pmu_snc] = 0;
+	} else {
+		checked_cpu_adjust[pmu_snc] = true;
+	}
+	perf_cpu_map__put(node_cpus);
+	return cpu_adjust[pmu_snc];
+}
+
+static void gnr_uncore_cha_imc_adjust_cpumask_for_snc(struct perf_pmu *pmu, bool cha)
+{
+	// With sub-NUMA clustering (SNC) there is a NUMA node per SNC in the
+	// topology. For example, a two socket graniterapids machine may be set
+	// up with 3-way SNC meaning there are 6 NUMA nodes that should be
+	// displayed with --per-node. The cpumask of the CHA and IMC PMUs
+	// reflects per-socket information meaning, for example, uncore_cha_60
+	// on a two socket graniterapids machine with 120 cores per socket will
+	// have a cpumask of "0,120". This cpumask needs adjusting to "40,160"
+	// to reflect that uncore_cha_60 is used for the 2nd SNC of each
+	// socket. Without the adjustment events on uncore_cha_60 will appear in
+	// node 0 and node 3 (in our example 2 socket 3-way set up), but with
+	// the adjustment they will appear in node 1 and node 4. The number of
+	// CHAs is typically larger than the number of cores. The CHA numbers
+	// are assumed to split evenly and inorder wrt core numbers. There are
+	// fewer memory IMC PMUs than cores and mapping is handled using lookup
+	// tables.
+	static struct perf_cpu_map *cha_adjusted[MAX_SNCS];
+	static struct perf_cpu_map *imc_adjusted[MAX_SNCS];
+	struct perf_cpu_map **adjusted = cha ? cha_adjusted : imc_adjusted;
+	int idx, pmu_snc, cpu_adjust;
+	struct perf_cpu cpu;
+	bool alloc;
+
+	// Cpus from the kernel holds first CPU of each socket. e.g. 0,120.
+	if (perf_cpu_map__cpu(pmu->cpus, 0).cpu != 0) {
+		pr_debug("Ignoring cpumask adjust for %s as unexpected first CPU\n", pmu->name);
+		return;
+	}
+
+	pmu_snc = cha ? uncore_cha_snc(pmu) : uncore_imc_snc(pmu);
+	if (pmu_snc == 0) {
+		// No adjustment necessary for the first SNC.
+		return;
+	}
+
+	alloc = adjusted[pmu_snc] == NULL;
+	if (alloc) {
+		// Hold onto the perf_cpu_map globally to avoid recomputation.
+		cpu_adjust = uncore_cha_imc_compute_cpu_adjust(pmu_snc);
+		adjusted[pmu_snc] = perf_cpu_map__empty_new(perf_cpu_map__nr(pmu->cpus));
+		if (!adjusted[pmu_snc])
+			return;
+	}
+
+	perf_cpu_map__for_each_cpu(cpu, idx, pmu->cpus) {
+		// Compute the new cpu map values or if not allocating, assert
+		// that they match expectations. asserts will be removed to
+		// avoid overhead in NDEBUG builds.
+		if (alloc) {
+			RC_CHK_ACCESS(adjusted[pmu_snc])->map[idx].cpu = cpu.cpu + cpu_adjust;
+		} else if (idx == 0) {
+			cpu_adjust = perf_cpu_map__cpu(adjusted[pmu_snc], idx).cpu - cpu.cpu;
+			assert(uncore_cha_imc_compute_cpu_adjust(pmu_snc) == cpu_adjust);
+		} else {
+			assert(perf_cpu_map__cpu(adjusted[pmu_snc], idx).cpu ==
+			       cpu.cpu + cpu_adjust);
+		}
+	}
+
+	perf_cpu_map__put(pmu->cpus);
+	pmu->cpus = perf_cpu_map__get(adjusted[pmu_snc]);
+}
+
+void perf_pmu__arch_init(struct perf_pmu *pmu)
+{
+	struct perf_pmu_caps *ldlat_cap;
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 	if (!strcmp(pmu->name, INTEL_PT_PMU_NAME)) {
 		pmu->auxtrace = true;
@@ -33,12 +286,31 @@ void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused)
 #endif
 
 	if (x86__is_amd_cpu()) {
-		if (!strcmp(pmu->name, "ibs_op"))
-			pmu->mem_events = perf_mem_events_amd;
-	} else if (pmu->is_core) {
-		if (perf_pmu__have_event(pmu, "mem-loads-aux"))
-			pmu->mem_events = perf_mem_events_intel_aux;
-		else
-			pmu->mem_events = perf_mem_events_intel;
+		if (strcmp(pmu->name, "ibs_op"))
+			return;
+
+		pmu->mem_events = perf_mem_events_amd;
+
+		if (!perf_pmu__caps_parse(pmu))
+			return;
+
+		ldlat_cap = perf_pmu__get_cap(pmu, "ldlat");
+		if (!ldlat_cap || strcmp(ldlat_cap->value, "1"))
+			return;
+
+		perf_mem_events__loads_ldlat = 0;
+		pmu->mem_events = perf_mem_events_amd_ldlat;
+	} else {
+		if (pmu->is_core) {
+			if (perf_pmu__have_event(pmu, "mem-loads-aux"))
+				pmu->mem_events = perf_mem_events_intel_aux;
+			else
+				pmu->mem_events = perf_mem_events_intel;
+		} else if (x86__is_intel_graniterapids()) {
+			if (starts_with(pmu->name, "uncore_cha_"))
+				gnr_uncore_cha_imc_adjust_cpumask_for_snc(pmu, /*cha=*/true);
+			else if (starts_with(pmu->name, "uncore_imc_"))
+				gnr_uncore_cha_imc_adjust_cpumask_for_snc(pmu, /*cha=*/false);
+		}
 	}
 }
diff --git a/tools/perf/bench/evlist-open-close.c b/tools/perf/bench/evlist-open-close.c
index 5a27691469ed..79cedcf94a39 100644
--- a/tools/perf/bench/evlist-open-close.c
+++ b/tools/perf/bench/evlist-open-close.c
@@ -46,25 +46,6 @@ static struct record_opts opts = {
 	.ctl_fd_ack          = -1,
 };
 
-static const struct option options[] = {
-	OPT_STRING('e', "event", &event_string, "event", "event selector. use 'perf list' to list available events"),
-	OPT_INTEGER('n', "nr-events", &nr_events,
-		     "number of dummy events to create (default 1). If used with -e, it clones those events n times (1 = no change)"),
-	OPT_INTEGER('i', "iterations", &iterations, "Number of iterations used to compute average (default=100)"),
-	OPT_BOOLEAN('a', "all-cpus", &opts.target.system_wide, "system-wide collection from all CPUs"),
-	OPT_STRING('C', "cpu", &opts.target.cpu_list, "cpu", "list of cpus where to open events"),
-	OPT_STRING('p', "pid", &opts.target.pid, "pid", "record events on existing process id"),
-	OPT_STRING('t', "tid", &opts.target.tid, "tid", "record events on existing thread id"),
-	OPT_STRING('u', "uid", &opts.target.uid_str, "user", "user to profile"),
-	OPT_BOOLEAN(0, "per-thread", &opts.target.per_thread, "use per-thread mmaps"),
-	OPT_END()
-};
-
-static const char *const bench_usage[] = {
-	"perf bench internals evlist-open-close <options>",
-	NULL
-};
-
 static int evlist__count_evsel_fds(struct evlist *evlist)
 {
 	struct evsel *evsel;
@@ -225,6 +206,29 @@ out_error:
 
 int bench_evlist_open_close(int argc, const char **argv)
 {
+	const struct option options[] = {
+		OPT_STRING('e', "event", &event_string, "event",
+			   "event selector. use 'perf list' to list available events"),
+		OPT_INTEGER('n', "nr-events", &nr_events,
+			    "number of dummy events to create (default 1). If used with -e, it clones those events n times (1 = no change)"),
+		OPT_INTEGER('i', "iterations", &iterations,
+			    "Number of iterations used to compute average (default=100)"),
+		OPT_BOOLEAN('a', "all-cpus", &opts.target.system_wide,
+			    "system-wide collection from all CPUs"),
+		OPT_STRING('C', "cpu", &opts.target.cpu_list, "cpu",
+			   "list of cpus where to open events"),
+		OPT_STRING('p', "pid", &opts.target.pid, "pid",
+			   "record events on existing process id"),
+		OPT_STRING('t', "tid", &opts.target.tid, "tid",
+			   "record events on existing thread id"),
+		OPT_STRING('u', "uid", &opts.target.uid_str, "user", "user to profile"),
+		OPT_BOOLEAN(0, "per-thread", &opts.target.per_thread, "use per-thread mmaps"),
+		OPT_END()
+	};
+	const char *const bench_usage[] = {
+		"perf bench internals evlist-open-close <options>",
+		NULL
+	};
 	char *evstr, errbuf[BUFSIZ];
 	int err;
 
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 5d5bb0f32334..e2e257bcc461 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -1969,10 +1969,11 @@ static struct c2c_fmt *get_format(const char *name)
 static int c2c_hists__init_output(struct perf_hpp_list *hpp_list, char *name)
 {
 	struct c2c_fmt *c2c_fmt = get_format(name);
+	int level = 0;
 
 	if (!c2c_fmt) {
 		reset_dimensions();
-		return output_field_add(hpp_list, name);
+		return output_field_add(hpp_list, name, &level);
 	}
 
 	perf_hpp_list__column_register(hpp_list, &c2c_fmt->fmt);
diff --git a/tools/perf/builtin-check.c b/tools/perf/builtin-check.c
index 61a11a9b4e75..9a509cb3bb9a 100644
--- a/tools/perf/builtin-check.c
+++ b/tools/perf/builtin-check.c
@@ -22,6 +22,17 @@ static const char *check_feature_usage[] = {
 	NULL
 };
 
+#define FEATURE_STATUS(name_, macro_) {    \
+	.name = name_,                     \
+	.macro = #macro_,                  \
+	.is_builtin = IS_BUILTIN(macro_) }
+
+#define FEATURE_STATUS_TIP(name_, macro_, tip_) { \
+	.name = name_,				  \
+	.macro = #macro_,			  \
+	.tip = tip_,				  \
+	.is_builtin = IS_BUILTIN(macro_) }
+
 struct feature_status supported_features[] = {
 	FEATURE_STATUS("aio", HAVE_AIO_SUPPORT),
 	FEATURE_STATUS("bpf", HAVE_LIBBPF_SUPPORT),
@@ -31,7 +42,7 @@ struct feature_status supported_features[] = {
 	FEATURE_STATUS("dwarf_getlocations", HAVE_LIBDW_SUPPORT),
 	FEATURE_STATUS("dwarf-unwind", HAVE_DWARF_UNWIND_SUPPORT),
 	FEATURE_STATUS("auxtrace", HAVE_AUXTRACE_SUPPORT),
-	FEATURE_STATUS("libbfd", HAVE_LIBBFD_SUPPORT),
+	FEATURE_STATUS_TIP("libbfd", HAVE_LIBBFD_SUPPORT, "Deprecated, license incompatibility, use BUILD_NONDISTRO=1 and install binutils-dev[el]"),
 	FEATURE_STATUS("libcapstone", HAVE_LIBCAPSTONE_SUPPORT),
 	FEATURE_STATUS("libcrypto", HAVE_LIBCRYPTO_SUPPORT),
 	FEATURE_STATUS("libdw-dwarf-unwind", HAVE_LIBDW_SUPPORT),
@@ -43,7 +54,7 @@ struct feature_status supported_features[] = {
 	FEATURE_STATUS("libpython", HAVE_LIBPYTHON_SUPPORT),
 	FEATURE_STATUS("libslang", HAVE_SLANG_SUPPORT),
 	FEATURE_STATUS("libtraceevent", HAVE_LIBTRACEEVENT),
-	FEATURE_STATUS("libunwind", HAVE_LIBUNWIND_SUPPORT),
+	FEATURE_STATUS_TIP("libunwind", HAVE_LIBUNWIND_SUPPORT, "Deprecated, use LIBUNWIND=1 and install libunwind-dev[el] to build with it"),
 	FEATURE_STATUS("lzma", HAVE_LZMA_SUPPORT),
 	FEATURE_STATUS("numa_num_possible_cpus", HAVE_LIBNUMA_SUPPORT),
 	FEATURE_STATUS("zlib", HAVE_ZLIB_SUPPORT),
@@ -66,21 +77,20 @@ static void on_off_print(const char *status)
 }
 
 /* Helper function to print status of a feature along with name/macro */
-static void status_print(const char *name, const char *macro,
-			 const char *status)
+void feature_status__printf(const struct feature_status *feature)
 {
+	const char *name = feature->name, *macro = feature->macro,
+		   *status = feature->is_builtin ? "on" : "OFF";
+
 	printf("%22s: ", name);
 	on_off_print(status);
-	printf("  # %s\n", macro);
-}
+	printf("  # %s", macro);
+
+	if (!feature->is_builtin && feature->tip)
+		printf(" ( tip: %s )", feature->tip);
 
-#define STATUS(feature)                                           \
-do {                                                              \
-	if (feature.is_builtin)                                   \
-		status_print(feature.name, feature.macro, "on");  \
-	else                                                      \
-		status_print(feature.name, feature.macro, "OFF"); \
-} while (0)
+	putchar('\n');
+}
 
 /**
  * check whether "feature" is built-in with perf
@@ -95,7 +105,7 @@ static int has_support(const char *feature)
 		if ((strcasecmp(feature, supported_features[i].name) == 0) ||
 		    (strcasecmp(feature, supported_features[i].macro) == 0)) {
 			if (!quiet)
-				STATUS(supported_features[i]);
+				feature_status__printf(&supported_features[i]);
 			return supported_features[i].is_builtin;
 		}
 	}
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 7caa18d5ffc3..bba36ebc2aa7 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -19,6 +19,7 @@
 #include <ctype.h>
 #include <linux/capability.h>
 #include <linux/string.h>
+#include <sys/stat.h>
 
 #include "debug.h"
 #include <subcmd/pager.h>
@@ -45,6 +46,8 @@ static volatile sig_atomic_t done;
 
 static struct stats latency_stats;  /* for tracepoints */
 
+static char tracing_instance[PATH_MAX];	/* Trace instance directory */
+
 static void sig_handler(int sig __maybe_unused)
 {
 	done = true;
@@ -100,6 +103,34 @@ static bool is_ftrace_supported(void)
 	return supported;
 }
 
+/*
+ * Wrapper to test if a file in directory .../tracing/instances/XXX
+ * exists. If so return the .../tracing/instances/XXX file for use.
+ * Otherwise the file exists only in directory .../tracing and
+ * is applicable to all instances, for example file available_filter_functions.
+ * Return that file name in this case.
+ *
+ * This functions works similar to get_tracing_file() and expects its caller
+ * to free the returned file name.
+ *
+ * The global variable tracing_instance is set in init_tracing_instance()
+ * called at the  beginning to a process specific tracing subdirectory.
+ */
+static char *get_tracing_instance_file(const char *name)
+{
+	char *file;
+
+	if (asprintf(&file, "%s/%s", tracing_instance, name) < 0)
+		return NULL;
+
+	if (!access(file, F_OK))
+		return file;
+
+	free(file);
+	file = get_tracing_file(name);
+	return file;
+}
+
 static int __write_tracing_file(const char *name, const char *val, bool append)
 {
 	char *file;
@@ -109,7 +140,7 @@ static int __write_tracing_file(const char *name, const char *val, bool append)
 	char errbuf[512];
 	char *val_copy;
 
-	file = get_tracing_file(name);
+	file = get_tracing_instance_file(name);
 	if (!file) {
 		pr_debug("cannot get tracing file: %s\n", name);
 		return -1;
@@ -167,7 +198,7 @@ static int read_tracing_file_to_stdout(const char *name)
 	int fd;
 	int ret = -1;
 
-	file = get_tracing_file(name);
+	file = get_tracing_instance_file(name);
 	if (!file) {
 		pr_debug("cannot get tracing file: %s\n", name);
 		return -1;
@@ -209,7 +240,7 @@ static int read_tracing_file_by_line(const char *name,
 	char *file;
 	FILE *fp;
 
-	file = get_tracing_file(name);
+	file = get_tracing_instance_file(name);
 	if (!file) {
 		pr_debug("cannot get tracing file: %s\n", name);
 		return -1;
@@ -299,6 +330,39 @@ static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
 	return 0;
 }
 
+/* Remove .../tracing/instances/XXX subdirectory created with
+ * init_tracing_instance().
+ */
+static void exit_tracing_instance(void)
+{
+	if (rmdir(tracing_instance))
+		pr_err("failed to delete tracing/instances directory\n");
+}
+
+/* Create subdirectory within .../tracing/instances/XXX to have session
+ * or process specific setup. To delete this setup, simply remove the
+ * subdirectory.
+ */
+static int init_tracing_instance(void)
+{
+	char dirname[] = "instances/perf-ftrace-XXXXXX";
+	char *path;
+
+	path = get_tracing_file(dirname);
+	if (!path)
+		goto error;
+	strncpy(tracing_instance, path, sizeof(tracing_instance) - 1);
+	put_tracing_file(path);
+	path = mkdtemp(tracing_instance);
+	if (!path)
+		goto error;
+	return 0;
+
+error:
+	pr_err("failed to create tracing/instances directory\n");
+	return -1;
+}
+
 static int set_tracing_pid(struct perf_ftrace *ftrace)
 {
 	int i;
@@ -629,14 +693,17 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace)
 
 	select_tracer(ftrace);
 
+	if (init_tracing_instance() < 0)
+		goto out;
+
 	if (reset_tracing_files(ftrace) < 0) {
 		pr_err("failed to reset ftrace\n");
-		goto out;
+		goto out_reset;
 	}
 
 	/* reset ftrace buffer */
 	if (write_tracing_file("trace", "0") < 0)
-		goto out;
+		goto out_reset;
 
 	if (set_tracing_options(ftrace) < 0)
 		goto out_reset;
@@ -648,7 +715,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace)
 
 	setup_pager();
 
-	trace_file = get_tracing_file("trace_pipe");
+	trace_file = get_tracing_instance_file("trace_pipe");
 	if (!trace_file) {
 		pr_err("failed to open trace_pipe\n");
 		goto out_reset;
@@ -723,7 +790,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace)
 out_close_fd:
 	close(trace_fd);
 out_reset:
-	reset_tracing_files(ftrace);
+	exit_tracing_instance();
 out:
 	return (done && !workload_exec_errno) ? 0 : -1;
 }
@@ -924,6 +991,9 @@ static int prepare_func_latency(struct perf_ftrace *ftrace)
 	if (ftrace->target.use_bpf)
 		return perf_ftrace__latency_prepare_bpf(ftrace);
 
+	if (init_tracing_instance() < 0)
+		return -1;
+
 	if (reset_tracing_files(ftrace) < 0) {
 		pr_err("failed to reset ftrace\n");
 		return -1;
@@ -942,7 +1012,7 @@ static int prepare_func_latency(struct perf_ftrace *ftrace)
 		return -1;
 	}
 
-	trace_file = get_tracing_file("trace_pipe");
+	trace_file = get_tracing_instance_file("trace_pipe");
 	if (!trace_file) {
 		pr_err("failed to open trace_pipe\n");
 		return -1;
@@ -993,7 +1063,7 @@ static int cleanup_func_latency(struct perf_ftrace *ftrace)
 	if (ftrace->target.use_bpf)
 		return perf_ftrace__latency_cleanup_bpf(ftrace);
 
-	reset_tracing_files(ftrace);
+	exit_tracing_instance();
 	return 0;
 }
 
@@ -1304,17 +1374,20 @@ static int __cmd_profile(struct perf_ftrace *ftrace)
 		goto out;
 	}
 
+	if (init_tracing_instance() < 0)
+		goto out;
+
 	if (reset_tracing_files(ftrace) < 0) {
 		pr_err("failed to reset ftrace\n");
-		goto out;
+		goto out_reset;
 	}
 
 	/* reset ftrace buffer */
 	if (write_tracing_file("trace", "0") < 0)
-		goto out;
+		goto out_reset;
 
 	if (set_tracing_options(ftrace) < 0)
-		return -1;
+		goto out_reset;
 
 	if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
 		pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
@@ -1323,7 +1396,7 @@ static int __cmd_profile(struct perf_ftrace *ftrace)
 
 	setup_pager();
 
-	trace_file = get_tracing_file("trace_pipe");
+	trace_file = get_tracing_instance_file("trace_pipe");
 	if (!trace_file) {
 		pr_err("failed to open trace_pipe\n");
 		goto out_reset;
@@ -1385,7 +1458,7 @@ out_free_line:
 out_close_fd:
 	close(trace_fd);
 out_reset:
-	reset_tracing_files(ftrace);
+	exit_tracing_instance();
 out:
 	return (done && !workload_exec_errno) ? 0 : -1;
 }
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index fed482adb039..e9b595d75df2 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -197,7 +197,8 @@ static void default_print_metric(void *ps,
 				const char *long_desc,
 				const char *expr,
 				const char *threshold,
-				const char *unit __maybe_unused)
+				const char *unit __maybe_unused,
+				const char *pmu_name __maybe_unused)
 {
 	struct print_state *print_state = ps;
 	FILE *fp = print_state->fp;
@@ -433,7 +434,8 @@ static void json_print_event(void *ps, const char *topic, const char *pmu_name,
 static void json_print_metric(void *ps __maybe_unused, const char *group,
 			      const char *name, const char *desc,
 			      const char *long_desc, const char *expr,
-			      const char *threshold, const char *unit)
+			      const char *threshold, const char *unit,
+			      const char *pmu_name)
 {
 	struct json_print_state *print_state = ps;
 	bool need_sep = false;
@@ -483,6 +485,12 @@ static void json_print_metric(void *ps __maybe_unused, const char *group,
 				   long_desc);
 		need_sep = true;
 	}
+	if (pmu_name) {
+		fix_escape_fprintf(fp, &buf, "%s\t\"Unit\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   pmu_name);
+		need_sep = true;
+	}
 	fprintf(fp, "%s}", need_sep ? "\n" : "");
 	strbuf_release(&buf);
 }
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 05e7bc30488a..3b3ade7a39ca 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -62,6 +62,8 @@ static const char *output_name = NULL;
 static FILE *lock_output;
 
 static struct lock_filter filters;
+static struct lock_delay *delays;
+static int nr_delays;
 
 static enum lock_aggr_mode aggr_mode = LOCK_AGGR_ADDR;
 
@@ -2001,6 +2003,8 @@ static int __cmd_contention(int argc, const char **argv)
 		.max_stack = max_stack_depth,
 		.stack_skip = stack_skip,
 		.filters = &filters,
+		.delays = delays,
+		.nr_delays = nr_delays,
 		.save_callstack = needs_callstack(),
 		.owner = show_lock_owner,
 		.cgroups = RB_ROOT,
@@ -2504,6 +2508,79 @@ static int parse_cgroup_filter(const struct option *opt __maybe_unused, const ch
 	return ret;
 }
 
+static bool add_lock_delay(char *spec)
+{
+	char *at, *pos;
+	struct lock_delay *tmp;
+	unsigned long duration;
+
+	at = strchr(spec, '@');
+	if (at == NULL) {
+		pr_err("lock delay should have '@' sign: %s\n", spec);
+		return false;
+	}
+	if (at == spec) {
+		pr_err("lock delay should have time before '@': %s\n", spec);
+		return false;
+	}
+
+	*at = '\0';
+	duration = strtoul(spec, &pos, 0);
+	if (!strcmp(pos, "ns"))
+		duration *= 1;
+	else if (!strcmp(pos, "us"))
+		duration *= 1000;
+	else if (!strcmp(pos, "ms"))
+		duration *= 1000 * 1000;
+	else if (*pos) {
+		pr_err("invalid delay time: %s@%s\n", spec, at + 1);
+		return false;
+	}
+
+	if (duration > 10 * 1000 * 1000) {
+		pr_err("lock delay is too long: %s (> 10ms)\n", spec);
+		return false;
+	}
+
+	tmp = realloc(delays, (nr_delays + 1) * sizeof(*delays));
+	if (tmp == NULL) {
+		pr_err("Memory allocation failure\n");
+		return false;
+	}
+	delays = tmp;
+
+	delays[nr_delays].sym = strdup(at + 1);
+	if (delays[nr_delays].sym == NULL) {
+		pr_err("Memory allocation failure\n");
+		return false;
+	}
+	delays[nr_delays].time = duration;
+
+	nr_delays++;
+	return true;
+}
+
+static int parse_lock_delay(const struct option *opt __maybe_unused, const char *str,
+			    int unset __maybe_unused)
+{
+	char *s, *tmp, *tok;
+	int ret = 0;
+
+	s = strdup(str);
+	if (s == NULL)
+		return -1;
+
+	for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		if (!add_lock_delay(tok)) {
+			ret = -1;
+			break;
+		}
+	}
+
+	free(s);
+	return ret;
+}
+
 int cmd_lock(int argc, const char **argv)
 {
 	const struct option lock_options[] = {
@@ -2580,6 +2657,8 @@ int cmd_lock(int argc, const char **argv)
 	OPT_BOOLEAN(0, "lock-cgroup", &show_lock_cgroups, "show lock stats by cgroup"),
 	OPT_CALLBACK('G', "cgroup-filter", NULL, "CGROUPS",
 		     "Filter specific cgroups", parse_cgroup_filter),
+	OPT_CALLBACK('J', "inject-delay", NULL, "TIME@FUNC",
+		     "Inject delays to specific locks", parse_lock_delay),
 	OPT_PARENT(lock_options)
 	};
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ba20bf7c011d..8059bce85a51 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -26,6 +26,7 @@
 #include "util/target.h"
 #include "util/session.h"
 #include "util/tool.h"
+#include "util/stat.h"
 #include "util/symbol.h"
 #include "util/record.h"
 #include "util/cpumap.h"
@@ -51,6 +52,7 @@
 #include "util/clockid.h"
 #include "util/off_cpu.h"
 #include "util/bpf-filter.h"
+#include "util/strbuf.h"
 #include "asm/bug.h"
 #include "perf.h"
 #include "cputopo.h"
@@ -648,14 +650,27 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
 	struct record *rec = to;
 
 	if (record__comp_enabled(rec)) {
+		struct perf_record_compressed2 *event = map->data;
+		size_t padding = 0;
+		u8 pad[8] = {0};
 		ssize_t compressed = zstd_compress(rec->session, map, map->data,
 						   mmap__mmap_len(map), bf, size);
 
 		if (compressed < 0)
 			return (int)compressed;
 
-		size = compressed;
-		bf   = map->data;
+		bf = event;
+		thread->samples++;
+
+		/*
+		 * The record from `zstd_compress` is not 8 bytes aligned, which would cause asan
+		 * error. We make it aligned here.
+		 */
+		event->data_size = compressed - sizeof(struct perf_record_compressed2);
+		event->header.size = PERF_ALIGN(compressed, sizeof(u64));
+		padding = event->header.size - compressed;
+		return record__write(rec, map, bf, compressed) ||
+		       record__write(rec, map, &pad, padding);
 	}
 
 	thread->samples++;
@@ -1534,7 +1549,7 @@ static void record__adjust_affinity(struct record *rec, struct mmap *map)
 
 static size_t process_comp_header(void *record, size_t increment)
 {
-	struct perf_record_compressed *event = record;
+	struct perf_record_compressed2 *event = record;
 	size_t size = sizeof(*event);
 
 	if (increment) {
@@ -1542,7 +1557,7 @@ static size_t process_comp_header(void *record, size_t increment)
 		return increment;
 	}
 
-	event->header.type = PERF_RECORD_COMPRESSED;
+	event->header.type = PERF_RECORD_COMPRESSED2;
 	event->header.size = size;
 
 	return size;
@@ -1552,7 +1567,7 @@ static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size)
 {
 	ssize_t compressed;
-	size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed) - 1;
+	size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed2) - 1;
 	struct zstd_data *zstd_data = &session->zstd_data;
 
 	if (map && map->file)
@@ -2483,7 +2498,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		pr_warning("WARNING: --timestamp-filename option is not available in pipe mode.\n");
 	}
 
-	evlist__uniquify_name(rec->evlist);
+	/*
+	 * Use global stat_config that is zero meaning aggr_mode is AGGR_NONE
+	 * and hybrid_merge is false.
+	 */
+	evlist__uniquify_evsel_names(rec->evlist, &stat_config);
 
 	evlist__config(rec->evlist, opts, &callchain_param);
 
@@ -2569,6 +2588,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		evlist__enable(rec->evlist);
 
 	/*
+	 * offcpu-time does not call execve, so enable_on_exe wouldn't work
+	 * when recording a workload, do it manually
+	 */
+	if (rec->off_cpu)
+		evlist__enable_evsel(rec->evlist, (char *)OFFCPU_EVENT);
+
+	/*
 	 * Let the child rip
 	 */
 	if (forks) {
@@ -2784,13 +2810,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		record__auxtrace_snapshot_exit(rec);
 
 	if (forks && workload_exec_errno) {
-		char msg[STRERR_BUFSIZE], strevsels[2048];
+		char msg[STRERR_BUFSIZE];
 		const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
+		struct strbuf sb = STRBUF_INIT;
 
-		evlist__scnprintf_evsels(rec->evlist, sizeof(strevsels), strevsels);
+		evlist__format_evsels(rec->evlist, &sb, 2048);
 
 		pr_err("Failed to collect '%s' for the '%s' workload: %s\n",
-			strevsels, argv[0], emsg);
+			sb.buf, argv[0], emsg);
+		strbuf_release(&sb);
 		err = -1;
 		goto out_child;
 	}
@@ -3155,6 +3183,28 @@ out_free:
 	return ret;
 }
 
+static int record__parse_off_cpu_thresh(const struct option *opt,
+					const char *str,
+					int unset __maybe_unused)
+{
+	struct record_opts *opts = opt->value;
+	char *endptr;
+	u64 off_cpu_thresh_ms;
+
+	if (!str)
+		return -EINVAL;
+
+	off_cpu_thresh_ms = strtoull(str, &endptr, 10);
+
+	/* the threshold isn't string "0", yet strtoull() returns 0, parsing failed */
+	if (*endptr || (off_cpu_thresh_ms == 0 && strcmp(str, "0")))
+		return -EINVAL;
+	else
+		opts->off_cpu_thresh_ns = off_cpu_thresh_ms * NSEC_PER_MSEC;
+
+	return 0;
+}
+
 void __weak arch__add_leaf_frame_record_opts(struct record_opts *opts __maybe_unused)
 {
 }
@@ -3348,6 +3398,7 @@ static struct record record = {
 		.ctl_fd              = -1,
 		.ctl_fd_ack          = -1,
 		.synth               = PERF_SYNTH_ALL,
+		.off_cpu_thresh_ns   = OFFCPU_THRESH,
 	},
 };
 
@@ -3436,6 +3487,8 @@ static struct option __record_options[] = {
 		    "Record the sampled data address data page size"),
 	OPT_BOOLEAN(0, "code-page-size", &record.opts.sample_code_page_size,
 		    "Record the sampled code address (ip) page size"),
+	OPT_BOOLEAN(0, "sample-mem-info", &record.opts.sample_data_src,
+		    "Record the data source for memory operations"),
 	OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"),
 	OPT_BOOLEAN(0, "sample-identifier", &record.opts.sample_identifier,
 		    "Record the sample identifier"),
@@ -3480,7 +3533,7 @@ static struct option __record_options[] = {
 		    "sample selected machine registers on interrupt,"
 		    " use '-I?' to list register names", parse_intr_regs),
 	OPT_CALLBACK_OPTARG(0, "user-regs", &record.opts.sample_user_regs, NULL, "any register",
-		    "sample selected machine registers on interrupt,"
+		    "sample selected machine registers in user space,"
 		    " use '--user-regs=?' to list register names", parse_user_regs),
 	OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
 		    "Record running/enabled time of read (:S) events"),
@@ -3573,6 +3626,9 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN(0, "off-cpu", &record.off_cpu, "Enable off-cpu analysis"),
 	OPT_STRING(0, "setup-filter", &record.filter_action, "pin|unpin",
 		   "BPF filter action"),
+	OPT_CALLBACK(0, "off-cpu-thresh", &record.opts, "ms",
+		     "Dump off-cpu samples if off-cpu time exceeds this threshold (in milliseconds). (Default: 500ms)",
+		     record__parse_off_cpu_thresh),
 	OPT_END()
 };
 
@@ -4130,6 +4186,10 @@ int cmd_record(int argc, const char **argv)
 		goto out_opts;
 	}
 
+	/* For backward compatibility, -d implies --mem-info */
+	if (rec->opts.sample_address)
+		rec->opts.sample_data_src = true;
+
 	/*
 	 * Allow aliases to facilitate the lookup of symbols for address
 	 * filters. Refer to auxtrace_parse_filters().
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index b030ce72e13e..e662e1c3a7c6 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -413,7 +413,7 @@ static int report__setup_sample_type(struct report *rep)
 		/* Silently ignore if callchain is missing */
 		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 			symbol_conf.cumulate_callchain = false;
-			perf_hpp__cancel_cumulate();
+			perf_hpp__cancel_cumulate(session->evlist);
 		}
 	}
 
@@ -529,7 +529,10 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 
 	if (rep->mem_mode) {
 		ret += fprintf(fp, "\n# Total weight : %" PRIu64, nr_events);
-		ret += fprintf(fp, "\n# Sort order   : %s", sort_order ? : default_mem_sort_order);
+		if (sort_order || !field_order) {
+			ret += fprintf(fp, "\n# Sort order   : %s",
+				       sort_order ? : default_mem_sort_order);
+		}
 	} else
 		ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
 
@@ -1088,7 +1091,7 @@ static int __cmd_report(struct report *rep)
 	/* Don't show Latency column for non-parallel profiles by default. */
 	if (!symbol_conf.prefer_latency && rep->total_samples &&
 		rep->singlethreaded_samples * 100 / rep->total_samples >= 99)
-		perf_hpp__cancel_latency();
+		perf_hpp__cancel_latency(session->evlist);
 
 	evlist__check_mem_load_aux(session->evlist);
 
@@ -1672,14 +1675,10 @@ repeat:
 	}
 
 	if (symbol_conf.report_hierarchy) {
-		/* disable incompatible options */
-		if (field_order) {
-			pr_err("Error: --hierarchy and --fields options cannot be used together\n");
-			parse_options_usage(report_usage, options, "F", 1);
-			parse_options_usage(NULL, options, "hierarchy", 0);
-			goto error;
-		}
-
+		/*
+		 * The hist entries in hierarchy are added during the collpase
+		 * phase.  Let's enable it even if no sort keys require it.
+		 */
 		perf_hpp_list.need_collapse = true;
 	}
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9b16df881af8..6c3bf74dd78c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -680,7 +680,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 
 		evlist__for_each_entry(session->evlist, evsel) {
 			not_pipe = true;
-			if (evsel__has_callchain(evsel)) {
+			if (evsel__has_callchain(evsel) || evsel__is_offcpu_event(evsel)) {
 				use_callchain = true;
 				break;
 			}
@@ -2295,7 +2295,7 @@ static void process_event(struct perf_script *script,
 	else if (PRINT_FIELD(BRSTACKOFF))
 		perf_sample__fprintf_brstackoff(sample, thread, evsel, fp);
 
-	if (evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
+	if (evsel__is_bpf_output(evsel) && !evsel__is_offcpu_event(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		perf_sample__fprintf_bpf_output(sample, fp);
 	perf_sample__fprintf_insn(sample, evsel, attr, thread, machine, fp, al);
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 68ea7589c143..bf0e5e12d992 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -681,8 +681,6 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 	if (child_pid != -1)
 		kill(child_pid, SIGTERM);
 
-	tpebs_delete();
-
 	return COUNTER_FATAL;
 }
 
@@ -1856,7 +1854,7 @@ static int add_default_events(void)
 		 * will use this approach. To determine transaction support
 		 * on an architecture test for such a metric name.
 		 */
-		if (!metricgroup__has_metric(pmu, "transaction")) {
+		if (!metricgroup__has_metric_or_groups(pmu, "transaction")) {
 			pr_err("Missing transaction metrics\n");
 			ret = -1;
 			goto out;
@@ -1890,7 +1888,7 @@ static int add_default_events(void)
 			smi_reset = true;
 		}
 
-		if (!metricgroup__has_metric(pmu, "smi")) {
+		if (!metricgroup__has_metric_or_groups(pmu, "smi")) {
 			pr_err("Missing smi metrics\n");
 			ret = -1;
 			goto out;
@@ -1980,7 +1978,7 @@ static int add_default_events(void)
 		 * Add TopdownL1 metrics if they exist. To minimize
 		 * multiplexing, don't request threshold computation.
 		 */
-		if (metricgroup__has_metric(pmu, "Default")) {
+		if (metricgroup__has_metric_or_groups(pmu, "Default")) {
 			struct evlist *metric_evlist = evlist__new();
 
 			if (!metric_evlist) {
@@ -2329,6 +2327,32 @@ static void setup_system_wide(int forks)
 	}
 }
 
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+static int parse_tpebs_mode(const struct option *opt, const char *str,
+			    int unset __maybe_unused)
+{
+	enum tpebs_mode *mode = opt->value;
+
+	if (!strcasecmp("mean", str)) {
+		*mode = TPEBS_MODE__MEAN;
+		return 0;
+	}
+	if (!strcasecmp("min", str)) {
+		*mode = TPEBS_MODE__MIN;
+		return 0;
+	}
+	if (!strcasecmp("max", str)) {
+		*mode = TPEBS_MODE__MAX;
+		return 0;
+	}
+	if (!strcasecmp("last", str)) {
+		*mode = TPEBS_MODE__LAST;
+		return 0;
+	}
+	return -1;
+}
+#endif // HAVE_ARCH_X86_64_SUPPORT
+
 int cmd_stat(int argc, const char **argv)
 {
 	struct opt_aggr_mode opt_mode = {};
@@ -2433,6 +2457,9 @@ int cmd_stat(int argc, const char **argv)
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 		OPT_BOOLEAN(0, "record-tpebs", &tpebs_recording,
 			"enable recording for tpebs when retire_latency required"),
+		OPT_CALLBACK(0, "tpebs-mode", &tpebs_mode, "tpebs-mode",
+			"Mode of TPEBS recording: mean, min or max",
+			parse_tpebs_mode),
 #endif
 		OPT_UINTEGER(0, "td-level", &stat_config.topdown_level,
 			"Set the metrics level for the top-down statistics (0: max level)"),
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1061f4eebc3f..7b6cde87d2af 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -35,6 +35,7 @@
 #include "util/mmap.h"
 #include "util/session.h"
 #include "util/thread.h"
+#include "util/stat.h"
 #include "util/symbol.h"
 #include "util/synthetic-events.h"
 #include "util/top.h"
@@ -1309,7 +1310,11 @@ static int __cmd_top(struct perf_top *top)
 		}
 	}
 
-	evlist__uniquify_name(top->evlist);
+	/*
+	 * Use global stat_config that is zero meaning aggr_mode is AGGR_NONE
+	 * and hybrid_merge is false.
+	 */
+	evlist__uniquify_evsel_names(top->evlist, &stat_config);
 	ret = perf_top__start_counters(top);
 	if (ret)
 		return ret;
@@ -1790,7 +1795,7 @@ int cmd_top(int argc, const char **argv)
 
 	if (!callchain_param.enabled) {
 		symbol_conf.cumulate_callchain = false;
-		perf_hpp__cancel_cumulate();
+		perf_hpp__cancel_cumulate(top.evlist);
 	}
 
 	if (symbol_conf.cumulate_callchain && !callchain_param.order_set)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6ac51925ea42..2ab1b8e05ad3 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -55,6 +55,7 @@
 #include "util/thread_map.h"
 #include "util/stat.h"
 #include "util/tool.h"
+#include "util/trace.h"
 #include "util/util.h"
 #include "trace/beauty/beauty.h"
 #include "trace-event.h"
@@ -141,12 +142,6 @@ struct syscall_fmt {
 	bool	   hexret;
 };
 
-enum summary_mode {
-	SUMMARY__NONE = 0,
-	SUMMARY__BY_TOTAL,
-	SUMMARY__BY_THREAD,
-};
-
 struct trace {
 	struct perf_tool	tool;
 	struct {
@@ -205,7 +200,7 @@ struct trace {
 	} stats;
 	unsigned int		max_stack;
 	unsigned int		min_stack;
-	enum summary_mode	summary_mode;
+	enum trace_summary_mode	summary_mode;
 	int			raw_augmented_syscalls_args_size;
 	bool			raw_augmented_syscalls;
 	bool			fd_path_disabled;
@@ -234,6 +229,7 @@ struct trace {
 	bool			force;
 	bool			vfs_getname;
 	bool			force_btf;
+	bool			summary_bpf;
 	int			trace_pgfaults;
 	char			*perfconfig_events;
 	struct {
@@ -1352,7 +1348,7 @@ static const struct syscall_fmt syscall_fmts[] = {
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* olddirfd */ },
 		   [2] = { .scnprintf = SCA_FDAT, /* newdirfd */ },
 		   [4] = { .scnprintf = SCA_RENAMEAT2_FLAGS, /* flags */ }, }, },
-	{ .name	    = "rseq",	    .errpid = true,
+	{ .name	    = "rseq",
 	  .arg = { [0] = { .from_user = true /* rseq */, }, }, },
 	{ .name	    = "rt_sigaction",
 	  .arg = { [0] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
@@ -1376,7 +1372,7 @@ static const struct syscall_fmt syscall_fmts[] = {
 	{ .name	    = "sendto",
 	  .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ },
 		   [4] = SCA_SOCKADDR_FROM_USER(addr), }, },
-	{ .name	    = "set_robust_list",	    .errpid = true,
+	{ .name	    = "set_robust_list",
 	  .arg = { [0] = { .from_user = true /* head */, }, }, },
 	{ .name	    = "set_tid_address", .errpid = true, },
 	{ .name	    = "setitimer",
@@ -1657,7 +1653,7 @@ static const size_t trace__entry_str_size = 2048;
 
 static void thread_trace__free_files(struct thread_trace *ttrace)
 {
-	for (int i = 0; i < ttrace->files.max; ++i) {
+	for (int i = 0; i <= ttrace->files.max; ++i) {
 		struct file *file = ttrace->files.table + i;
 		zfree(&file->pathname);
 	}
@@ -1703,6 +1699,7 @@ static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pat
 
 	if (file != NULL) {
 		struct stat st;
+
 		if (stat(pathname, &st) == 0)
 			file->dev_maj = major(st.st_rdev);
 		file->pathname = strdup(pathname);
@@ -2614,6 +2611,9 @@ static void thread__update_stats(struct thread *thread, struct thread_trace *ttr
 	struct syscall_stats *stats = NULL;
 	u64 duration = 0;
 
+	if (trace->summary_bpf)
+		return;
+
 	if (trace->summary_mode == SUMMARY__BY_TOTAL)
 		syscall_stats = trace->syscall_stats;
 
@@ -2842,7 +2842,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct evsel *evsel,
 	e_machine = thread__e_machine(thread, trace->host);
 	sc = trace__syscall_info(trace, evsel, e_machine, id);
 	if (sc == NULL)
-		return -1;
+		goto out_put;
 	ttrace = thread__trace(thread, trace);
 	/*
 	 * We need to get ttrace just to make sure it is there when syscall__scnprintf_args()
@@ -3005,8 +3005,8 @@ errno_print: {
 	else if (sc->fmt->errpid) {
 		struct thread *child = machine__find_thread(trace->host, ret, ret);
 
+		fprintf(trace->output, "%ld", ret);
 		if (child != NULL) {
-			fprintf(trace->output, "%ld", ret);
 			if (thread__comm_set(child))
 				fprintf(trace->output, " (%s)", thread__comm_str(child));
 			thread__put(child);
@@ -4128,10 +4128,13 @@ static int trace__set_filter_loop_pids(struct trace *trace)
 		if (!strcmp(thread__comm_str(parent), "sshd") ||
 		    strstarts(thread__comm_str(parent), "gnome-terminal")) {
 			pids[nr++] = thread__tid(parent);
+			thread__put(parent);
 			break;
 		}
+		thread__put(thread);
 		thread = parent;
 	}
+	thread__put(thread);
 
 	err = evlist__append_tp_filter_pids(trace->evlist, nr, pids);
 	if (!err && trace->filter_pids.map)
@@ -4377,6 +4380,14 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 	trace->live = true;
 
+	if (trace->summary_bpf) {
+		if (trace_prepare_bpf_summary(trace->summary_mode) < 0)
+			goto out_delete_evlist;
+
+		if (trace->summary_only)
+			goto create_maps;
+	}
+
 	if (!trace->raw_augmented_syscalls) {
 		if (trace->trace_syscalls && trace__add_syscall_newtp(trace))
 			goto out_error_raw_syscalls;
@@ -4435,6 +4446,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (trace->cgroup)
 		evlist__set_default_cgroup(trace->evlist, trace->cgroup);
 
+create_maps:
 	err = evlist__create_maps(evlist, &trace->opts.target);
 	if (err < 0) {
 		fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
@@ -4447,7 +4459,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
-	if (trace->summary_mode == SUMMARY__BY_TOTAL) {
+	if (trace->summary_mode == SUMMARY__BY_TOTAL && !trace->summary_bpf) {
 		trace->syscall_stats = alloc_syscall_stats();
 		if (trace->syscall_stats == NULL)
 			goto out_delete_evlist;
@@ -4535,9 +4547,11 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_apply_filters;
 
-	err = evlist__mmap(evlist, trace->opts.mmap_pages);
-	if (err < 0)
-		goto out_error_mmap;
+	if (!trace->summary_only || !trace->summary_bpf) {
+		err = evlist__mmap(evlist, trace->opts.mmap_pages);
+		if (err < 0)
+			goto out_error_mmap;
+	}
 
 	if (!target__none(&trace->opts.target) && !trace->opts.target.initial_delay)
 		evlist__enable(evlist);
@@ -4550,6 +4564,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		evlist__enable(evlist);
 	}
 
+	if (trace->summary_bpf)
+		trace_start_bpf_summary();
+
 	trace->multiple_threads = perf_thread_map__pid(evlist->core.threads, 0) == -1 ||
 		perf_thread_map__nr(evlist->core.threads) > 1 ||
 		evlist__first(evlist)->core.attr.inherit;
@@ -4617,12 +4634,17 @@ out_disable:
 
 	evlist__disable(evlist);
 
+	if (trace->summary_bpf)
+		trace_end_bpf_summary();
+
 	if (trace->sort_events)
 		ordered_events__flush(&trace->oe.data, OE_FLUSH__FINAL);
 
 	if (!err) {
 		if (trace->summary) {
-			if (trace->summary_mode == SUMMARY__BY_TOTAL)
+			if (trace->summary_bpf)
+				trace_print_bpf_summary(trace->output);
+			else if (trace->summary_mode == SUMMARY__BY_TOTAL)
 				trace__fprintf_total_summary(trace, trace->output);
 			else
 				trace__fprintf_thread_summary(trace, trace->output);
@@ -4638,6 +4660,7 @@ out_disable:
 	}
 
 out_delete_evlist:
+	trace_cleanup_bpf_summary();
 	delete_syscall_stats(trace->syscall_stats);
 	trace__symbols__exit(trace);
 	evlist__free_syscall_tp_fields(evlist);
@@ -5279,6 +5302,8 @@ static int trace__parse_summary_mode(const struct option *opt, const char *str,
 		trace->summary_mode = SUMMARY__BY_THREAD;
 	} else if (!strcmp(str, "total")) {
 		trace->summary_mode = SUMMARY__BY_TOTAL;
+	} else if (!strcmp(str, "cgroup")) {
+		trace->summary_mode = SUMMARY__BY_CGROUP;
 	} else {
 		pr_err("Unknown summary mode: %s\n", str);
 		return -1;
@@ -5438,7 +5463,7 @@ int cmd_trace(int argc, const char **argv)
 	OPT_BOOLEAN(0, "errno-summary", &trace.errno_summary,
 		    "Show errno stats per syscall, use with -s or -S"),
 	OPT_CALLBACK(0, "summary-mode", &trace, "mode",
-		     "How to show summary: select thread (default) or total",
+		     "How to show summary: select thread (default), total or cgroup",
 		     trace__parse_summary_mode),
 	OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min",
 		     "Trace pagefaults", parse_pagefaults, "maj"),
@@ -5473,6 +5498,7 @@ int cmd_trace(int argc, const char **argv)
 		     "start"),
 	OPT_BOOLEAN(0, "force-btf", &trace.force_btf, "Prefer btf_dump general pretty printer"
 		       "to customized ones"),
+	OPT_BOOLEAN(0, "bpf-summary", &trace.summary_bpf, "Summary syscall stats in BPF"),
 	OPTS_EVSWITCH(&trace.evswitch),
 	OPT_END()
 	};
@@ -5564,6 +5590,16 @@ int cmd_trace(int argc, const char **argv)
 		goto skip_augmentation;
 	}
 
+	if (trace.summary_bpf) {
+		if (!trace.opts.target.system_wide) {
+			/* TODO: Add filters in the BPF to support other targets. */
+			pr_err("Error: --bpf-summary only works for system-wide mode.\n");
+			goto out;
+		}
+		if (trace.summary_only)
+			goto skip_augmentation;
+	}
+
 	trace.skel = augmented_raw_syscalls_bpf__open();
 	if (!trace.skel) {
 		pr_debug("Failed to open augmented syscalls BPF skeleton");
@@ -5741,6 +5777,12 @@ init_augmented_syscall_tp:
 		symbol_conf.keep_exited_threads = true;
 		if (trace.summary_mode == SUMMARY__NONE)
 			trace.summary_mode = SUMMARY__BY_THREAD;
+
+		if (!trace.summary_bpf && trace.summary_mode == SUMMARY__BY_CGROUP) {
+			pr_err("Error: --summary-mode=cgroup only works with --bpf-summary\n");
+			err = -EINVAL;
+			goto out;
+		}
 	}
 
 	if (output_name != NULL) {
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index e149d96c6dc5..10f25c6705b1 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -26,38 +26,10 @@ static const char * const version_usage[] = {
 	NULL
 };
 
-static void on_off_print(const char *status)
-{
-	printf("[ ");
-
-	if (!strcmp(status, "OFF"))
-		color_fprintf(stdout, PERF_COLOR_RED, "%-3s", status);
-	else
-		color_fprintf(stdout, PERF_COLOR_GREEN, "%-3s", status);
-
-	printf(" ]");
-}
-
-static void status_print(const char *name, const char *macro,
-			 const char *status)
-{
-	printf("%22s: ", name);
-	on_off_print(status);
-	printf("  # %s\n", macro);
-}
-
-#define STATUS(feature)                                   \
-do {                                                      \
-	if (feature.is_builtin)                               \
-		status_print(feature.name, feature.macro, "on");  \
-	else                                                  \
-		status_print(feature.name, feature.macro, "OFF"); \
-} while (0)
-
 static void library_status(void)
 {
 	for (int i = 0; supported_features[i].name; ++i)
-		STATUS(supported_features[i]);
+		feature_status__printf(&supported_features[i]);
 }
 
 int cmd_version(int argc, const char **argv)
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index a07e93c53848..40c4078c295f 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -5,15 +5,14 @@
 struct feature_status {
 	const char *name;
 	const char *macro;
+	const char *tip;
 	int is_builtin;
 };
 
-#define FEATURE_STATUS(name_, macro_) {    \
-	.name = name_,                     \
-	.macro = #macro_,                  \
-	.is_builtin = IS_BUILTIN(macro_) }
-
 extern struct feature_status supported_features[];
+
+void feature_status__printf(const struct feature_status *feature);
+
 struct cmdnames;
 
 void list_common_cmds_help(void);
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json
index 2b3cb55df288..014454d78293 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json
@@ -3,56 +3,48 @@
 	    "ConfigCode": "0x00",
 	    "EventName": "flux_wr",
 	    "BriefDescription": "DDRC total write operations",
-	    "PublicDescription": "DDRC total write operations",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x01",
 	    "EventName": "flux_rd",
 	    "BriefDescription": "DDRC total read operations",
-	    "PublicDescription": "DDRC total read operations",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x02",
 	    "EventName": "flux_wcmd",
 	    "BriefDescription": "DDRC write commands",
-	    "PublicDescription": "DDRC write commands",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x03",
 	    "EventName": "flux_rcmd",
 	    "BriefDescription": "DDRC read commands",
-	    "PublicDescription": "DDRC read commands",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x04",
 	    "EventName": "pre_cmd",
 	    "BriefDescription": "DDRC precharge commands",
-	    "PublicDescription": "DDRC precharge commands",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x05",
 	    "EventName": "act_cmd",
 	    "BriefDescription": "DDRC active commands",
-	    "PublicDescription": "DDRC active commands",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x06",
 	    "EventName": "rnk_chg",
 	    "BriefDescription": "DDRC rank commands",
-	    "PublicDescription": "DDRC rank commands",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x07",
 	    "EventName": "rw_chg",
 	    "BriefDescription": "DDRC read and write changes",
-	    "PublicDescription": "DDRC read and write changes",
 	    "Unit": "hisi_sccl,ddrc"
    }
 ]
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
index 9a7ec7af2060..b2b895fa670e 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
@@ -3,42 +3,41 @@
 	    "ConfigCode": "0x00",
 	    "EventName": "rx_ops_num",
 	    "BriefDescription": "The number of all operations received by the HHA",
-	    "PublicDescription": "The number of all operations received by the HHA",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x01",
 	    "EventName": "rx_outer",
 	    "BriefDescription": "The number of all operations received by the HHA from another socket",
-	    "PublicDescription": "The number of all operations received by the HHA from another socket",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x02",
 	    "EventName": "rx_sccl",
 	    "BriefDescription": "The number of all operations received by the HHA from another SCCL in this socket",
-	    "PublicDescription": "The number of all operations received by the HHA from another SCCL in this socket",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x03",
 	    "EventName": "rx_ccix",
 	    "BriefDescription": "Count of the number of operations that HHA has received from CCIX",
-	    "PublicDescription": "Count of the number of operations that HHA has received from CCIX",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x4",
 	    "EventName": "rx_wbi",
+	    "BriefDescription": "Count of the number of WriteBackI operations that HHA has received",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x5",
 	    "EventName": "rx_wbip",
+	    "BriefDescription": "Count of the number of WriteBackIPtl operations that HHA has received",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x11",
+	    "BriefDescription": "Count of the number of WriteThruIStash operations that HHA has received",
 	    "EventName": "rx_wtistash",
 	    "Unit": "hisi_sccl,hha"
    },
@@ -46,107 +45,114 @@
 	    "ConfigCode": "0x1c",
 	    "EventName": "rd_ddr_64b",
 	    "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 64 bytes",
-	    "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 64bytes",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x1d",
 	    "EventName": "wr_ddr_64b",
 	    "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes",
-	    "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x1e",
 	    "EventName": "rd_ddr_128b",
 	    "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes",
-	    "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x1f",
 	    "EventName": "wr_ddr_128b",
 	    "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes",
-	    "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x20",
 	    "EventName": "spill_num",
 	    "BriefDescription": "Count of the number of spill operations that the HHA has sent",
-	    "PublicDescription": "Count of the number of spill operations that the HHA has sent",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x21",
 	    "EventName": "spill_success",
 	    "BriefDescription": "Count of the number of successful spill operations that the HHA has sent",
-	    "PublicDescription": "Count of the number of successful spill operations that the HHA has sent",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x23",
 	    "EventName": "bi_num",
+	    "BriefDescription": "Count of the number of HHA BackInvalid operations",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x32",
 	    "EventName": "mediated_num",
+	    "BriefDescription": "Count of the number of Mediated operations that the HHA has forwarded",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x33",
 	    "EventName": "tx_snp_num",
+	    "BriefDescription": "Count of the number of Snoop operations that the HHA has sent",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x34",
 	    "EventName": "tx_snp_outer",
+	    "BriefDescription": "Count of the number of Snoop operations that the HHA has sent to another socket",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x35",
 	    "EventName": "tx_snp_ccix",
+	    "BriefDescription": "Count of the number of Snoop operations that the HHA has sent to CCIX",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x38",
 	    "EventName": "rx_snprspdata",
+	    "BriefDescription": "Count of the number of SnprspData flit operations that HHA has received",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x3c",
 	    "EventName": "rx_snprsp_outer",
+	    "BriefDescription": "Count of the number of SnprspData operations that HHA has received from another socket",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x40",
 	    "EventName": "sdir-lookup",
+	    "BriefDescription": "Count of the number of HHA S-Dir lookup operations",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x41",
 	    "EventName": "edir-lookup",
+	    "BriefDescription": "Count of the number of HHA E-Dir lookup operations",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x42",
 	    "EventName": "sdir-hit",
+	    "BriefDescription": "Count of the number of HHA S-Dir hit operations",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x43",
 	    "EventName": "edir-hit",
+	    "BriefDescription": "Count of the number of HHA E-Dir hit operations",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x4c",
 	    "EventName": "sdir-home-migrate",
+	    "BriefDescription": "Count of the number of HHA S-Dir read home migrate operations",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x4d",
 	    "EventName": "edir-home-migrate",
+	    "BriefDescription": "Count of the number of HHA E-Dir read home migrate operations",
 	    "Unit": "hisi_sccl,hha"
    }
 ]
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json
index e3479b65be9a..d83c22eb1d15 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json
@@ -3,91 +3,78 @@
 	    "ConfigCode": "0x00",
 	    "EventName": "rd_cpipe",
 	    "BriefDescription": "Total read accesses",
-	    "PublicDescription": "Total read accesses",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x01",
 	    "EventName": "wr_cpipe",
 	    "BriefDescription": "Total write accesses",
-	    "PublicDescription": "Total write accesses",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x02",
 	    "EventName": "rd_hit_cpipe",
 	    "BriefDescription": "Total read hits",
-	    "PublicDescription": "Total read hits",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x03",
 	    "EventName": "wr_hit_cpipe",
 	    "BriefDescription": "Total write hits",
-	    "PublicDescription": "Total write hits",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x04",
 	    "EventName": "victim_num",
 	    "BriefDescription": "l3c precharge commands",
-	    "PublicDescription": "l3c precharge commands",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x20",
 	    "EventName": "rd_spipe",
 	    "BriefDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe",
-	    "PublicDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x21",
 	    "EventName": "wr_spipe",
 	    "BriefDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe",
-	    "PublicDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x22",
 	    "EventName": "rd_hit_spipe",
 	    "BriefDescription": "Count of the number of read lines that hits in spipe of this L3C",
-	    "PublicDescription": "Count of the number of read lines that hits in spipe of this L3C",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x23",
 	    "EventName": "wr_hit_spipe",
 	    "BriefDescription": "Count of the number of write lines that hits in spipe of this L3C",
-	    "PublicDescription": "Count of the number of write lines that hits in spipe of this L3C",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x29",
 	    "EventName": "back_invalid",
 	    "BriefDescription": "Count of the number of L3C back invalid operations",
-	    "PublicDescription": "Count of the number of L3C back invalid operations",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x40",
 	    "EventName": "retry_cpu",
 	    "BriefDescription": "Count of the number of retry that L3C suppresses the CPU operations",
-	    "PublicDescription": "Count of the number of retry that L3C suppresses the CPU operations",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x41",
 	    "EventName": "retry_ring",
 	    "BriefDescription": "Count of the number of retry that L3C suppresses the ring operations",
-	    "PublicDescription": "Count of the number of retry that L3C suppresses the ring operations",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x42",
 	    "EventName": "prefetch_drop",
 	    "BriefDescription": "Count of the number of prefetch drops from this L3C",
-	    "PublicDescription": "Count of the number of prefetch drops from this L3C",
 	    "Unit": "hisi_sccl,l3c"
    }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
index 147379cae37b..377dfecd96bd 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -103,7 +103,7 @@
         "MetricExpr": "tma_core_bound",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_allocation_restriction",
-        "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -113,7 +113,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
-        "MetricThreshold": "(tma_backend_bound >0.10)",
+        "MetricThreshold": "tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
         "ScaleUnit": "100%",
@@ -125,7 +125,7 @@
         "MetricExpr": "(5 * cpu_atom@CPU_CLK_UNHALTED.CORE@ - (cpu_atom@TOPDOWN_FE_BOUND.ALL@ + cpu_atom@TOPDOWN_BE_BOUND.ALL@ + cpu_atom@TOPDOWN_RETIRING.ALL@)) / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
-        "MetricThreshold": "(tma_bad_speculation >0.15)",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%",
@@ -136,7 +136,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_detect",
-        "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -146,7 +146,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
-        "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -156,7 +156,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_resteer",
-        "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -165,7 +165,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -174,7 +174,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
-        "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -184,7 +184,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_decode",
-        "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -193,7 +193,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
-        "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -203,7 +203,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
-        "MetricThreshold": "(tma_frontend_bound >0.20)",
+        "MetricThreshold": "tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -213,7 +213,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -222,7 +222,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_bandwidth",
-        "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -232,7 +232,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_latency",
-        "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -567,7 +567,7 @@
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
         "MetricName": "tma_info_system_mux",
-        "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9",
         "Unit": "cpu_atom"
     },
     {
@@ -606,7 +606,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -615,7 +615,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
-        "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -625,7 +625,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
-        "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -634,7 +634,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
-        "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -643,7 +643,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
-        "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -652,7 +652,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_other_fb",
-        "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -661,7 +661,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_predecode",
-        "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -670,7 +670,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
-        "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -679,7 +679,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
-        "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -688,7 +688,7 @@
         "MetricExpr": "tma_backend_bound - tma_core_bound",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_resource_bound",
-        "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -699,7 +699,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
-        "MetricThreshold": "(tma_retiring >0.75)",
+        "MetricThreshold": "tma_retiring > 0.75",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -709,7 +709,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
-        "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -721,7 +721,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_0@ + cpu_core@UOPS_DISPATCHED.PORT_1@ + cpu_core@UOPS_DISPATCHED.PORT_5_11@ + cpu_core@UOPS_DISPATCHED.PORT_6@) / (5 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -734,13 +734,13 @@
         "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
         "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
@@ -751,7 +751,7 @@
     {
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -768,13 +768,13 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20",
@@ -791,7 +791,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -800,7 +800,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -809,16 +809,16 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy",
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20",
@@ -826,7 +826,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -835,7 +835,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -844,16 +844,16 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
-        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -866,11 +866,11 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls",
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -879,7 +879,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
-        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -893,26 +893,26 @@
         "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c01_wait",
-        "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c02_wait",
-        "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -921,7 +921,7 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -931,26 +931,26 @@
         "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
         "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
         "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -959,7 +959,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -968,35 +968,36 @@
         "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricExpr": "((28 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + (27 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(25 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_core_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1007,26 +1008,27 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricExpr": "(27 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "24 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1036,7 +1038,7 @@
         "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1046,7 +1048,7 @@
         "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1057,7 +1059,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1066,28 +1068,28 @@
         "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@) / tma_info_core_core_clks",
+        "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1096,8 +1098,8 @@
         "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1118,18 +1120,18 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
-        "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
+        "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1149,7 +1151,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1159,16 +1161,16 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1177,8 +1179,8 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1187,8 +1189,8 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1197,8 +1199,8 @@
         "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1207,41 +1209,41 @@
         "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
+        "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
         "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
-        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1250,8 +1252,8 @@
         "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1264,7 +1266,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
@@ -1272,7 +1274,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
@@ -1280,15 +1282,15 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000",
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -1320,7 +1322,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -1329,7 +1331,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -1338,10 +1340,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
         "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
@@ -1412,12 +1415,12 @@
         "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)",
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp",
         "Unit": "cpu_core"
@@ -1432,22 +1435,22 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency",
         "Unit": "cpu_core"
@@ -1497,14 +1500,14 @@
     },
     {
         "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
-        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed",
         "MetricName": "tma_info_frontend_unknown_branch_cost",
-        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node",
+        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch",
@@ -1524,7 +1527,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW",
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.",
         "Unit": "cpu_core"
     },
     {
@@ -1533,7 +1536,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1542,7 +1545,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1551,7 +1554,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1560,7 +1563,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1623,7 +1626,7 @@
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 13",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp",
         "Unit": "cpu_core"
     },
@@ -1769,7 +1772,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp",
         "Unit": "cpu_core"
@@ -1849,7 +1852,7 @@
     },
     {
         "BriefDescription": "",
-        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute",
         "Unit": "cpu_core"
@@ -1880,20 +1883,20 @@
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "MicroSeq;Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
@@ -1946,23 +1949,22 @@
     },
     {
         "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
-        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000",
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_utilization",
         "MetricThreshold": "tma_info_system_kernel_utilization > 0.05",
@@ -2030,7 +2032,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks",
@@ -2041,7 +2043,6 @@
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
         "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr",
         "Unit": "cpu_core"
     },
     {
@@ -2049,7 +2050,7 @@
         "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage",
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
         "Unit": "cpu_core"
     },
     {
@@ -2061,14 +2062,14 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "cpu_core@TOPDOWN.SLOTS@",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
+        "MetricExpr": "(tma_info_thread_slots / (cpu_core@TOPDOWN.SLOTS@ / 2) if #SMT_on else 1)",
         "MetricGroup": "SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots_utilization",
         "Unit": "cpu_core"
@@ -2086,15 +2087,15 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5",
+        "MetricThreshold": "tma_info_thread_uptb < 9",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2104,7 +2105,7 @@
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_int_operations",
         "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2113,8 +2114,8 @@
         "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_128b",
-        "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2123,8 +2124,8 @@
         "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_256b",
-        "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2133,8 +2134,8 @@
         "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2143,7 +2144,7 @@
         "MetricExpr": "max((cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2153,7 +2154,7 @@
         "MetricExpr": "min(2 * (cpu_core@MEM_INST_RETIRED.ALL_LOADS@ - cpu_core@MEM_LOAD_RETIRED.FB_HIT@ - cpu_core@MEM_LOAD_RETIRED.L1_MISS@) * 20 / 100, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2163,17 +2164,18 @@
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "3 * tma_info_system_core_frequency * cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2183,18 +2185,19 @@
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(12 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2)) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "9 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2203,19 +2206,19 @@
         "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2234,7 +2237,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2243,34 +2246,34 @@
         "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2279,7 +2282,7 @@
         "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2290,7 +2293,7 @@
         "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_lsd",
         "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2301,16 +2304,16 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2320,34 +2323,34 @@
         "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
-        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
-        "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -2370,7 +2373,7 @@
         "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2386,18 +2389,18 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
-        "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
+        "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
         "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
@@ -2406,10 +2409,10 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
-        "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks",
+        "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2420,7 +2423,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2429,7 +2432,7 @@
         "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2445,20 +2448,20 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2468,7 +2471,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_page_faults",
         "MetricThreshold": "tma_page_faults > 0.05",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2478,7 +2481,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2488,7 +2491,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2498,7 +2501,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2507,8 +2510,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2517,8 +2520,8 @@
         "MetricExpr": "(cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + max(cpu_core@RS.EMPTY_RESOURCE@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0)) / tma_info_thread_clks * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2527,7 +2530,7 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2538,8 +2541,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2549,7 +2552,7 @@
         "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2557,7 +2560,7 @@
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2571,7 +2574,7 @@
         "MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks + tma_c02_wait",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2581,8 +2584,8 @@
         "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_shuffles_256b",
-        "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+        "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2592,7 +2595,7 @@
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2603,7 +2606,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2612,8 +2615,8 @@
         "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2622,7 +2625,7 @@
         "MetricExpr": "(cpu_core@XQ.FULL_CYCLES@ + cpu_core@L1D_PEND_MISS.L2_STALLS@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2632,8 +2635,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2642,8 +2645,8 @@
         "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2652,8 +2655,8 @@
         "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2672,7 +2675,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2681,34 +2684,34 @@
         "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2717,7 +2720,7 @@
         "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2727,7 +2730,7 @@
         "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2737,8 +2740,8 @@
         "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     }
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/cache.json b/tools/perf/pmu-events/arch/x86/alderlake/cache.json
index a20e19738046..c2802fbb853b 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/cache.json
@@ -4,6 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.HWPF_MISS",
+        "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -13,7 +14,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.REPLACEMENT",
-        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -23,7 +24,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -35,7 +36,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS",
-        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -46,6 +47,7 @@
         "Deprecated": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALL",
+        "PublicDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -55,7 +57,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALLS",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -65,7 +67,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING",
-        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -76,7 +78,7 @@
         "CounterMask": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
-        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -86,7 +88,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x25",
         "EventName": "L2_LINES_IN.ALL",
-        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1f",
         "Unit": "cpu_core"
@@ -96,7 +98,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.NON_SILENT",
-        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
+        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -106,7 +108,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.SILENT",
-        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -116,7 +118,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.USELESS_HWPF",
-        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
+        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -135,7 +137,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.ALL",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff",
         "Unit": "cpu_core"
@@ -165,7 +167,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f",
         "Unit": "cpu_core"
@@ -175,7 +177,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "PublicDescription": "Counts the total number of L2 code requests.",
+        "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe4",
         "Unit": "cpu_core"
@@ -185,7 +187,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe1",
         "Unit": "cpu_core"
@@ -195,7 +197,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "PublicDescription": "Counts demand requests that miss L2 cache.",
+        "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x27",
         "Unit": "cpu_core"
@@ -205,6 +207,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_HWPF",
+        "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf0",
         "Unit": "cpu_core"
@@ -214,7 +217,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_RFO",
-        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe2",
         "Unit": "cpu_core"
@@ -224,7 +227,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
+        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc4",
         "Unit": "cpu_core"
@@ -234,7 +237,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+        "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x24",
         "Unit": "cpu_core"
@@ -244,7 +247,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc1",
         "Unit": "cpu_core"
@@ -254,7 +257,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
-        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21",
         "Unit": "cpu_core"
@@ -264,6 +267,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.HWPF_MISS",
+        "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x30",
         "Unit": "cpu_core"
@@ -273,7 +277,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f",
         "Unit": "cpu_core"
@@ -283,7 +287,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.REFERENCES",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff",
         "Unit": "cpu_core"
@@ -293,7 +297,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_HIT",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc2",
         "Unit": "cpu_core"
@@ -303,7 +307,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_MISS",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x22",
         "Unit": "cpu_core"
@@ -313,7 +317,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_HIT",
-        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc8",
         "Unit": "cpu_core"
@@ -323,7 +327,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_MISS",
-        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x28",
         "Unit": "cpu_core"
@@ -333,7 +337,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x23",
         "EventName": "L2_TRANS.L2_WB",
-        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+        "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -353,7 +357,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.MISS",
-        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41",
         "Unit": "cpu_core"
@@ -373,7 +377,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4f",
         "Unit": "cpu_core"
@@ -461,7 +465,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
+        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x81",
         "Unit": "cpu_core"
@@ -472,7 +476,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts all retired store instructions.",
+        "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x82",
         "Unit": "cpu_core"
@@ -483,7 +487,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+        "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x83",
         "Unit": "cpu_core"
@@ -494,7 +498,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PublicDescription": "Counts retired load instructions with locked access.",
+        "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x21",
         "Unit": "cpu_core"
@@ -505,7 +509,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41",
         "Unit": "cpu_core"
@@ -516,7 +520,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x42",
         "Unit": "cpu_core"
@@ -527,7 +531,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x11",
         "Unit": "cpu_core"
@@ -538,7 +542,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x12",
         "Unit": "cpu_core"
@@ -548,7 +552,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY",
-        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)",
+        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfd",
         "Unit": "cpu_core"
@@ -559,7 +563,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -570,7 +574,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -581,7 +585,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -592,7 +596,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -603,7 +607,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
+        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -614,7 +618,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -625,7 +629,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
-        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
+        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -636,7 +640,7 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -647,7 +651,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -658,7 +662,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -669,7 +673,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -680,7 +684,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -691,7 +695,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -702,7 +706,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -713,7 +717,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -724,6 +728,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x80",
         "Unit": "cpu_atom"
@@ -734,6 +739,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x20",
         "Unit": "cpu_atom"
@@ -744,6 +750,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -754,6 +761,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8",
         "Unit": "cpu_atom"
@@ -764,6 +772,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_atom"
@@ -774,6 +783,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x10",
         "Unit": "cpu_atom"
@@ -784,6 +794,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4",
         "Unit": "cpu_atom"
@@ -794,6 +805,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.HIT_E_F",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40",
         "Unit": "cpu_atom"
@@ -804,6 +816,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.L3_MISS",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20",
         "Unit": "cpu_atom"
@@ -849,6 +862,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x44",
         "EventName": "MEM_STORE_RETIRED.L2_HIT",
+        "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -859,7 +873,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts the total number of load uops retired.",
+        "PublicDescription": "Counts the total number of load uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x81",
         "Unit": "cpu_atom"
@@ -870,7 +884,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts the total number of store uops retired.",
+        "PublicDescription": "Counts the total number of store uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x82",
         "Unit": "cpu_atom"
@@ -883,7 +897,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -896,7 +910,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -909,7 +923,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -922,7 +936,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -935,7 +949,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -948,7 +962,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -961,7 +975,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -974,7 +988,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -985,6 +999,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
+        "PublicDescription": "Counts the number of load uops retired that performed one or more locks. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21",
         "Unit": "cpu_atom"
@@ -995,6 +1010,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x41",
         "Unit": "cpu_atom"
@@ -1005,6 +1021,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS",
+        "PublicDescription": "Counts the total number of load and store uops retired that missed in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x13",
         "Unit": "cpu_atom"
@@ -1015,6 +1032,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+        "PublicDescription": "Counts the number of load ops retired that miss in the second Level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x11",
         "Unit": "cpu_atom"
@@ -1025,6 +1043,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
+        "PublicDescription": "Counts the number of store ops retired that miss in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x12",
         "Unit": "cpu_atom"
@@ -1035,7 +1054,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
-        "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x6",
         "Unit": "cpu_atom"
@@ -1045,18 +1064,43 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe5",
         "EventName": "MEM_UOP_RETIRED.ANY",
-        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses",
+        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10008",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1068,6 +1112,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1079,6 +1124,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1090,17 +1136,43 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1112,6 +1184,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1123,6 +1196,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1134,6 +1208,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1145,6 +1220,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1156,6 +1232,31 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1167,6 +1268,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1178,6 +1280,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1189,6 +1292,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1200,6 +1304,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1211,6 +1316,19 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.SWPF_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x14000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1222,6 +1340,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1233,6 +1352,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1244,6 +1364,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1255,6 +1376,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1264,6 +1386,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
+        "PublicDescription": "OFFCORE_REQUESTS.ALL_REQUESTS Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -1273,7 +1396,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DATA_RD",
-        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1283,7 +1406,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
-        "PublicDescription": "Counts both cacheable and non-cacheable code read requests.",
+        "PublicDescription": "Counts both cacheable and non-cacheable code read requests. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1293,7 +1416,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1303,7 +1426,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
-        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1315,6 +1438,7 @@
         "Errata": "ADL038",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "PublicDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1326,6 +1450,7 @@
         "Errata": "ADL038",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1336,7 +1461,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1347,6 +1472,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1357,7 +1483,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
-        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1368,6 +1494,7 @@
         "Errata": "ADL038",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1377,7 +1504,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1387,7 +1514,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
+        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1397,7 +1524,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x2c",
         "EventName": "SQ_MISC.BUS_LOCK",
-        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
+        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1407,6 +1534,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.ANY",
+        "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xf",
         "Unit": "cpu_core"
@@ -1416,7 +1544,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.NTA",
-        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1426,7 +1554,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
-        "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1436,7 +1564,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T0",
-        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1446,7 +1574,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T1_T2",
-        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json
index 62fd70f220e5..ce570b96360a 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json
@@ -14,6 +14,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FPDIV_ACTIVE",
+        "PublicDescription": "ARITH.FPDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -32,7 +33,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.FP",
-        "PublicDescription": "Counts all microcode Floating Point assists.",
+        "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -42,6 +43,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.SSE_AVX_MIX",
+        "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -51,6 +53,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -60,6 +63,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -69,6 +73,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_5",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -78,6 +83,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -87,6 +93,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -96,6 +103,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V2",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -105,7 +113,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -115,7 +123,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -125,7 +133,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -135,7 +143,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -145,7 +153,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x18",
         "Unit": "cpu_core"
@@ -155,7 +163,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -165,7 +173,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -175,7 +183,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -185,7 +193,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.VECTOR",
-        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfc",
         "Unit": "cpu_core"
@@ -205,6 +213,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.FPDIV",
+        "PublicDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_atom"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json
index c5b3818ad479..dae3174a74fb 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json
@@ -14,7 +14,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x60",
         "EventName": "BACLEARS.ANY",
-        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -24,7 +24,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.LCP",
-        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -34,6 +34,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.MS_BUSY",
+        "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -43,7 +44,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x61",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
+        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -55,7 +56,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -67,7 +68,7 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -79,7 +80,7 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -91,7 +92,7 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -103,7 +104,7 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -115,7 +116,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600106",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -127,7 +128,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -139,7 +140,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -151,7 +152,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -163,7 +164,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -175,7 +176,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -187,7 +188,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -199,7 +200,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -211,7 +212,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -223,7 +224,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -235,7 +236,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -247,6 +248,7 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -258,7 +260,7 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -270,6 +272,7 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
+        "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -299,7 +302,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALLS",
-        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
+        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -311,6 +314,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALL_PERIODS",
+        "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -320,7 +324,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x83",
         "EventName": "ICACHE_TAG.STALLS",
-        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -331,7 +335,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -342,7 +346,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -352,7 +356,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -363,7 +367,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -374,7 +378,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -384,7 +388,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -395,7 +399,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_CYCLES_ANY",
-        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -407,7 +411,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_SWITCHES",
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -417,7 +421,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).",
+        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -427,7 +431,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -438,7 +442,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -450,7 +454,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -460,7 +464,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -471,7 +475,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -483,7 +487,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/memory.json b/tools/perf/pmu-events/arch/x86/alderlake/memory.json
index fa15f5797bed..07f5786bdbc0 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/memory.json
@@ -5,6 +5,7 @@
         "CounterMask": "6",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
+        "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x6",
         "Unit": "cpu_core"
@@ -78,7 +79,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
+        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -89,6 +90,7 @@
         "CounterMask": "2",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -99,6 +101,7 @@
         "CounterMask": "3",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -109,7 +112,7 @@
         "CounterMask": "5",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS",
-        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_core"
@@ -120,7 +123,7 @@
         "CounterMask": "9",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS",
-        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9",
         "Unit": "cpu_core"
@@ -248,29 +251,67 @@
         "Data_LA": "1",
         "EventCode": "0xcd",
         "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
-        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
+        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -282,6 +323,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -293,6 +335,19 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -304,6 +359,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -315,6 +371,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -326,6 +383,19 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.SWPF_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784004000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -337,6 +407,7 @@
         "EventName": "OCR.SWPF_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84404000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -346,6 +417,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -355,7 +427,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.",
+        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/other.json b/tools/perf/pmu-events/arch/x86/alderlake/other.json
index a8b23e92408c..e4e75b088ccc 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/other.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.HARDWARE",
-        "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.  This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.",
+        "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.  This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -14,6 +14,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.PAGE_FAULT",
+        "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -23,6 +24,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x28",
         "EventName": "CORE_POWER.LICENSE_1",
+        "PublicDescription": "CORE_POWER.LICENSE_1 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -32,6 +34,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x28",
         "EventName": "CORE_POWER.LICENSE_2",
+        "PublicDescription": "CORE_POWER.LICENSE_2 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -41,6 +44,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x28",
         "EventName": "CORE_POWER.LICENSE_3",
+        "PublicDescription": "CORE_POWER.LICENSE_3 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -51,127 +55,19 @@
         "Deprecated": "1",
         "EventCode": "0xe4",
         "EventName": "LBR_INSERTS.ANY",
+        "PublicDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10008",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
         "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x800000010000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -183,6 +79,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x400000010000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -194,6 +91,7 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -205,103 +103,18 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.SWPF_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x14000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.SWPF_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784004000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "CounterMask": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_COUNT",
-        "Invert": "1",
-        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_RESOURCE",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "CounterMask": "1",
-        "Deprecated": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS_EMPTY.COUNT",
-        "Invert": "1",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "Deprecated": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS_EMPTY.CYCLES",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "200003",
-        "UMask": "0x4",
-        "Unit": "cpu_atom"
-    },
-    {
         "BriefDescription": "Cycles the uncore cannot take further requests",
         "Counter": "0,1,2,3",
         "CounterMask": "1",
         "EventCode": "0x2d",
         "EventName": "XQ.FULL_CYCLES",
-        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).",
+        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json
index f5bf0816f190..7e0e33792c45 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json
@@ -6,6 +6,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9",
         "Unit": "cpu_core"
@@ -26,7 +27,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.DIV_ACTIVE",
-        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
+        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9",
         "Unit": "cpu_core"
@@ -56,6 +57,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FP_DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -76,6 +78,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.IDIV_ACTIVE",
+        "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -105,6 +108,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.INT_DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -114,7 +118,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.ANY",
-        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.",
+        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1b",
         "Unit": "cpu_core"
@@ -124,7 +128,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for.",
+        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "Unit": "cpu_atom"
     },
@@ -133,7 +137,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all branch instructions retired.",
+        "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -143,6 +147,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.CALL",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_CALL Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf9",
         "Unit": "cpu_atom"
@@ -152,6 +157,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
+        "PublicDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e",
         "Unit": "cpu_atom"
@@ -161,7 +167,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
-        "PublicDescription": "Counts conditional branch instructions retired.",
+        "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11",
         "Unit": "cpu_core"
@@ -171,7 +177,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts not taken branch instructions retired.",
+        "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -181,6 +187,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
+        "PublicDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe",
         "Unit": "cpu_atom"
@@ -190,7 +197,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional branch instructions retired.",
+        "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -200,6 +207,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "PublicDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xbf",
         "Unit": "cpu_atom"
@@ -209,7 +217,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "PublicDescription": "Counts far branch instructions retired.",
+        "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -219,6 +227,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
+        "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb",
         "Unit": "cpu_atom"
@@ -228,7 +237,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
-        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -238,6 +247,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT_CALL",
+        "PublicDescription": "Counts the number of near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb",
         "Unit": "cpu_atom"
@@ -248,6 +258,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.IND_CALL",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb",
         "Unit": "cpu_atom"
@@ -258,6 +269,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e",
         "Unit": "cpu_atom"
@@ -267,6 +279,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
+        "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf9",
         "Unit": "cpu_atom"
@@ -276,7 +289,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -286,6 +299,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+        "PublicDescription": "Counts the number of near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7",
         "Unit": "cpu_atom"
@@ -295,7 +309,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "Counts return instructions retired.",
+        "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -305,6 +319,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Counts the number of near taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc0",
         "Unit": "cpu_atom"
@@ -314,7 +329,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts taken branch instructions retired.",
+        "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -325,6 +340,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NON_RETURN_IND",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb",
         "Unit": "cpu_atom"
@@ -334,6 +350,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.REL_CALL",
+        "PublicDescription": "Counts the number of near relative CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfd",
         "Unit": "cpu_atom"
@@ -344,6 +361,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.RETURN",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_RETURN Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7",
         "Unit": "cpu_atom"
@@ -354,6 +372,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.TAKEN_JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND_TAKEN Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe",
         "Unit": "cpu_atom"
@@ -363,7 +382,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
+        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "Unit": "cpu_atom"
     },
@@ -372,7 +391,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -381,6 +400,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
+        "PublicDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e",
         "Unit": "cpu_atom"
@@ -390,7 +410,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
-        "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11",
         "Unit": "cpu_core"
@@ -400,7 +420,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
+        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -410,6 +430,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
+        "PublicDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe",
         "Unit": "cpu_atom"
@@ -419,7 +440,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -429,6 +450,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
+        "PublicDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb",
         "Unit": "cpu_atom"
@@ -438,7 +460,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
-        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -448,6 +470,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
+        "PublicDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb",
         "Unit": "cpu_atom"
@@ -457,7 +480,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
-        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
+        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -468,6 +491,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.IND_CALL",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT_CALL Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb",
         "Unit": "cpu_atom"
@@ -478,6 +502,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e",
         "Unit": "cpu_atom"
@@ -487,6 +512,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Counts the number of mispredicted near taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x80",
         "Unit": "cpu_atom"
@@ -496,7 +522,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -507,6 +533,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb",
         "Unit": "cpu_atom"
@@ -516,7 +543,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -526,6 +553,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RETURN",
+        "PublicDescription": "Counts the number of mispredicted near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7",
         "Unit": "cpu_atom"
@@ -536,6 +564,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.TAKEN_JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND_TAKEN Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe",
         "Unit": "cpu_atom"
@@ -545,7 +574,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C01",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -555,7 +584,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C02",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -565,7 +594,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C0_WAIT",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x70",
         "Unit": "cpu_core"
@@ -593,7 +622,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED",
-        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -603,7 +632,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.",
+        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0",
         "SampleAfterValue": "25003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -613,6 +642,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -624,6 +654,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE_INST",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -643,7 +674,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED",
-        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -681,7 +712,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
-        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -718,7 +749,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "Unit": "cpu_core"
     },
@@ -728,6 +759,7 @@
         "CounterMask": "8",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -738,6 +770,7 @@
         "CounterMask": "1",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -748,6 +781,7 @@
         "CounterMask": "16",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -758,6 +792,7 @@
         "CounterMask": "12",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc",
         "Unit": "cpu_core"
@@ -768,6 +803,7 @@
         "CounterMask": "5",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_core"
@@ -778,6 +814,7 @@
         "CounterMask": "4",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "PublicDescription": "Total execution stalls. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -787,7 +824,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -797,6 +834,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0xc",
         "Unit": "cpu_core"
@@ -806,7 +844,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -816,7 +854,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -826,7 +864,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -837,6 +875,7 @@
         "CounterMask": "5",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS",
+        "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x21",
         "Unit": "cpu_core"
@@ -847,7 +886,7 @@
         "CounterMask": "2",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
-        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.",
+        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -857,7 +896,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
-        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.",
+        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -867,7 +906,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x75",
         "EventName": "INST_DECODED.DECODERS",
-        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.",
+        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -876,7 +915,7 @@
         "BriefDescription": "Counts the total number of instructions retired. (Fixed event)",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -885,7 +924,7 @@
         "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -895,7 +934,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "Unit": "cpu_atom"
     },
@@ -913,6 +952,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -922,7 +962,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
-        "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions",
+        "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -931,7 +971,7 @@
         "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.PREC_DIST",
-        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
+        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -941,7 +981,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -953,7 +993,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEARS_COUNT",
-        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears",
+        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -963,7 +1003,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
-        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
+        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -973,7 +1013,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.RECOVERY_CYCLES",
-        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -985,6 +1025,7 @@
         "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x7",
+        "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -994,7 +1035,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.UOP_DROPPING",
-        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons",
+        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1004,6 +1045,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.128BIT",
+        "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x13",
         "Unit": "cpu_core"
@@ -1013,6 +1055,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.256BIT",
+        "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xac",
         "Unit": "cpu_core"
@@ -1022,7 +1065,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_128",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -1032,7 +1075,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_256",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc",
         "Unit": "cpu_core"
@@ -1042,6 +1085,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.MUL_256",
+        "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -1051,6 +1095,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.SHUFFLES",
+        "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -1060,6 +1105,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_128",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1069,6 +1115,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_256",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1079,6 +1126,7 @@
         "Deprecated": "1",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.4K_ALIAS",
+        "PublicDescription": "This event is deprecated. Refer to new event LD_BLOCKS.ADDRESS_ALIAS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_atom"
@@ -1088,6 +1136,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
+        "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_atom"
@@ -1097,7 +1146,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
-        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.",
+        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1107,6 +1156,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.DATA_UNKNOWN",
+        "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1116,7 +1166,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.NO_SR",
-        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x88",
         "Unit": "cpu_core"
@@ -1126,7 +1176,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.STORE_FORWARD",
-        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
+        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x82",
         "Unit": "cpu_core"
@@ -1136,7 +1186,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x4c",
         "EventName": "LOAD_HIT_PREFETCH.SWPF",
-        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1147,7 +1197,7 @@
         "CounterMask": "1",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_ACTIVE",
-        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1158,7 +1208,7 @@
         "CounterMask": "6",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_OK",
-        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1168,7 +1218,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa8",
         "EventName": "LSD.UOPS",
-        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1180,7 +1230,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.COUNT",
-        "PublicDescription": "Counts the number of machine clears (nukes) of any type.",
+        "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1213,8 +1263,9 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.",
+        "BriefDescription": "This event is deprecated.",
         "Counter": "0,1,2,3,4,5",
+        "Deprecated": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SLOW",
         "SampleAfterValue": "20003",
@@ -1235,7 +1286,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SMC",
-        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1245,7 +1296,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe0",
         "EventName": "MISC2_RETIRED.LFENCE",
-        "PublicDescription": "number of LFENCE retired instructions",
+        "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1255,7 +1306,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xe4",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
-        "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY]",
+        "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1265,7 +1316,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcc",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
-        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1275,7 +1326,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SB",
-        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1285,11 +1336,79 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SCOREBOARD",
+        "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_COUNT",
+        "Invert": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_RESOURCE",
+        "PublicDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "Deprecated": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS_EMPTY.COUNT",
+        "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "Deprecated": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS_EMPTY.CYCLES",
+        "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0x75",
@@ -1304,7 +1423,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
-        "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.",
+        "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1314,7 +1433,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BAD_SPEC_SLOTS",
-        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.",
+        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1324,7 +1443,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
-        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.",
+        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1334,6 +1453,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS",
+        "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1352,7 +1472,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.SLOTS_P",
-        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.",
+        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1561,6 +1681,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "TOPDOWN_RETIRING.ALL",
+        "PublicDescription": "Counts the total number of consumed retirement slots. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "Unit": "cpu_atom"
     },
@@ -1569,6 +1690,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x76",
         "EventName": "UOPS_DECODED.DEC0_UOPS",
+        "PublicDescription": "UOPS_DECODED.DEC0_UOPS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1578,7 +1700,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_0",
-        "PublicDescription": "Number of uops dispatch to execution  port 0.",
+        "PublicDescription": "Number of uops dispatch to execution  port 0. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1588,7 +1710,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_1",
-        "PublicDescription": "Number of uops dispatch to execution  port 1.",
+        "PublicDescription": "Number of uops dispatch to execution  port 1. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1598,7 +1720,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_2_3_10",
-        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10",
+        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1608,7 +1730,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_4_9",
-        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9",
+        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1618,7 +1740,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_5_11",
-        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11",
+        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1628,7 +1750,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_6",
-        "PublicDescription": "Number of uops dispatch to execution  port 6.",
+        "PublicDescription": "Number of uops dispatch to execution  port 6. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -1638,7 +1760,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_7_8",
-        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8.",
+        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -1649,7 +1771,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1660,7 +1782,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1671,7 +1793,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1682,7 +1804,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1693,7 +1815,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_1",
-        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1704,7 +1826,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_2",
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1715,7 +1837,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_3",
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1726,7 +1848,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_4",
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1738,7 +1860,7 @@
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.STALLS",
         "Invert": "1",
-        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1751,6 +1873,7 @@
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.STALL_CYCLES",
         "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1760,6 +1883,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.THREAD",
+        "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1769,7 +1893,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.X87",
-        "PublicDescription": "Counts the number of x87 uops executed.",
+        "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1788,7 +1912,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.ANY",
-        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1799,6 +1923,7 @@
         "CounterMask": "1",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.CYCLES",
+        "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1808,6 +1933,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.ALL",
+        "PublicDescription": "Counts the total number of uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "Unit": "cpu_atom"
     },
@@ -1817,7 +1943,7 @@
         "CounterMask": "1",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.CYCLES",
-        "PublicDescription": "Counts cycles where at least one uop has retired.",
+        "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1827,7 +1953,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.HEAVY",
-        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.",
+        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1837,6 +1963,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.IDIV",
+        "PublicDescription": "Counts the number of integer divide uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_atom"
@@ -1846,7 +1973,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.MS",
-        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.",
+        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1858,6 +1985,7 @@
         "EventName": "UOPS_RETIRED.MS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1867,7 +1995,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.SLOTS",
-        "PublicDescription": "Counts the retirement slots used each cycle.",
+        "PublicDescription": "Counts the retirement slots used each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1879,7 +2007,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.STALLS",
         "Invert": "1",
-        "PublicDescription": "This event counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1892,6 +2020,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1901,6 +2030,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.X87",
+        "PublicDescription": "Counts the number of x87 uops retired, includes those in MS flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_atom"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json
index 132ce48af6d9..3d15275eca61 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
-        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
+        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -15,7 +15,7 @@
         "CounterMask": "1",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -35,7 +35,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe",
         "Unit": "cpu_core"
@@ -45,7 +45,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -55,7 +55,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -65,7 +65,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -75,7 +75,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -85,7 +85,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.STLB_HIT",
-        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
+        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -96,7 +96,7 @@
         "CounterMask": "1",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -116,7 +116,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe",
         "Unit": "cpu_core"
@@ -126,7 +126,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -136,7 +136,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -146,7 +146,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -156,7 +156,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -184,7 +184,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.STLB_HIT",
-        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
+        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -195,7 +195,7 @@
         "CounterMask": "1",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -215,7 +215,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe",
         "Unit": "cpu_core"
@@ -225,7 +225,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -235,7 +235,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -245,7 +245,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -266,6 +266,7 @@
         "Deprecated": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
+        "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x13",
         "Unit": "cpu_atom"
@@ -277,6 +278,7 @@
         "Deprecated": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
+        "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_LOADS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x11",
         "Unit": "cpu_atom"
@@ -288,6 +290,7 @@
         "Deprecated": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
+        "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_STORES Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x12",
         "Unit": "cpu_atom"
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
index ad04b1e3881e..ce93648043ef 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
@@ -75,7 +75,7 @@
         "MetricExpr": "tma_core_bound",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_allocation_restriction",
-        "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
@@ -84,7 +84,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
-        "MetricThreshold": "(tma_backend_bound >0.10)",
+        "MetricThreshold": "tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
         "ScaleUnit": "100%"
@@ -95,7 +95,7 @@
         "MetricExpr": "(5 * CPU_CLK_UNHALTED.CORE - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
-        "MetricThreshold": "(tma_bad_speculation >0.15)",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%"
@@ -105,7 +105,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_detect",
-        "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
         "ScaleUnit": "100%"
     },
@@ -114,7 +114,7 @@
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
-        "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -123,7 +123,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_resteer",
-        "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -131,7 +131,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.CISC / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -139,7 +139,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
-        "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -148,7 +148,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_decode",
-        "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -156,7 +156,7 @@
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
-        "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -165,7 +165,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
-        "MetricThreshold": "(tma_frontend_bound >0.20)",
+        "MetricThreshold": "tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%"
     },
@@ -174,7 +174,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -182,7 +182,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_bandwidth",
-        "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -191,7 +191,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_latency",
-        "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -473,7 +473,7 @@
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE",
         "MetricName": "tma_info_system_mux",
-        "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))"
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
     },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
@@ -506,7 +506,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -514,7 +514,7 @@
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
-        "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -523,7 +523,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
-        "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
@@ -531,7 +531,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
-        "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
@@ -539,7 +539,7 @@
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
-        "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -547,7 +547,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_other_fb",
-        "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -555,7 +555,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_predecode",
-        "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -563,7 +563,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
-        "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
@@ -571,7 +571,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
-        "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
@@ -579,7 +579,7 @@
         "MetricExpr": "tma_backend_bound - tma_core_bound",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_resource_bound",
-        "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -589,7 +589,7 @@
         "MetricExpr": "TOPDOWN_RETIRING.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
-        "MetricThreshold": "(tma_retiring >0.75)",
+        "MetricThreshold": "tma_retiring > 0.75",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%"
     },
@@ -598,7 +598,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
-        "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/cache.json b/tools/perf/pmu-events/arch/x86/alderlaken/cache.json
index fd9ed58c2f90..bf691aee1ef4 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/cache.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/cache.json
@@ -118,6 +118,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x80"
     },
@@ -127,6 +128,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x20"
     },
@@ -136,6 +138,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -145,6 +148,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
     },
@@ -154,6 +158,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -163,6 +168,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x10"
     },
@@ -172,6 +178,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -181,6 +188,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.HIT_E_F",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -190,6 +198,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.L3_MISS",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -231,7 +240,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts the total number of load uops retired.",
+        "PublicDescription": "Counts the total number of load uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x81"
     },
@@ -241,7 +250,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts the total number of store uops retired.",
+        "PublicDescription": "Counts the total number of store uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x82"
     },
@@ -253,7 +262,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -265,7 +274,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -277,7 +286,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -289,7 +298,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -301,7 +310,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -313,7 +322,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -325,7 +334,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -337,7 +346,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -347,6 +356,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
+        "PublicDescription": "Counts the number of load uops retired that performed one or more locks. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21"
     },
@@ -356,6 +366,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x41"
     },
@@ -365,6 +376,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS",
+        "PublicDescription": "Counts the total number of load and store uops retired that missed in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x13"
     },
@@ -374,6 +386,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+        "PublicDescription": "Counts the number of load ops retired that miss in the second Level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x11"
     },
@@ -383,6 +396,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
+        "PublicDescription": "Counts the number of store ops retired that miss in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x12"
     },
@@ -392,17 +406,40 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
-        "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x6"
     },
     {
+        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10008",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -413,6 +450,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -423,6 +461,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -433,6 +472,18 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -443,6 +494,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -453,6 +505,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -463,6 +516,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -473,6 +527,18 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -483,6 +549,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -493,6 +560,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -503,6 +571,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -513,6 +582,18 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.SWPF_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x14000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -523,6 +604,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -533,6 +615,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -543,6 +626,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -553,6 +637,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json b/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json
index ed963fcb6485..f44da31ff1f1 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json
@@ -29,6 +29,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.FPDIV",
+        "PublicDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     }
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json
index 3b46b048dfb2..049c5e2630d7 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json
@@ -57,12 +57,35 @@
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -73,6 +96,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -83,6 +107,18 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -93,6 +129,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -103,6 +140,18 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.SWPF_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784004000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -113,6 +162,7 @@
         "EventName": "OCR.SWPF_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84404000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/other.json b/tools/perf/pmu-events/arch/x86/alderlaken/other.json
index f8c21b7f8f40..8c2b5a284f2a 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/other.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/other.json
@@ -5,86 +5,18 @@
         "Deprecated": "1",
         "EventCode": "0xe4",
         "EventName": "LBR_INSERTS.ANY",
+        "PublicDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10008",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x800000010000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -95,6 +27,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x400000010000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -105,35 +38,8 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.SWPF_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x14000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.SWPF_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784004000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "200003",
-        "UMask": "0x4"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json
index 713ebc21cec0..9616bf0e9f1f 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json
@@ -54,7 +54,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for.",
+        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for. Available PDIST counters: 0",
         "SampleAfterValue": "200003"
     },
     {
@@ -63,6 +63,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.CALL",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_CALL Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf9"
     },
@@ -71,6 +72,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
+        "PublicDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -79,6 +81,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
+        "PublicDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -87,6 +90,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "PublicDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xbf"
     },
@@ -95,6 +99,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
+        "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -103,6 +108,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT_CALL",
+        "PublicDescription": "Counts the number of near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -112,6 +118,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.IND_CALL",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -121,6 +128,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -129,6 +137,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
+        "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf9"
     },
@@ -137,6 +146,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+        "PublicDescription": "Counts the number of near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7"
     },
@@ -145,6 +155,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Counts the number of near taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc0"
     },
@@ -154,6 +165,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NON_RETURN_IND",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -162,6 +174,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.REL_CALL",
+        "PublicDescription": "Counts the number of near relative CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfd"
     },
@@ -171,6 +184,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.RETURN",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_RETURN Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7"
     },
@@ -180,6 +194,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.TAKEN_JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND_TAKEN Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -188,7 +203,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
+        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "200003"
     },
     {
@@ -196,6 +211,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
+        "PublicDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -204,6 +220,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
+        "PublicDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -212,6 +229,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
+        "PublicDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -220,6 +238,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
+        "PublicDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -229,6 +248,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.IND_CALL",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT_CALL Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -238,6 +258,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -246,6 +267,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Counts the number of mispredicted near taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x80"
     },
@@ -255,6 +277,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -263,6 +286,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RETURN",
+        "PublicDescription": "Counts the number of mispredicted near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7"
     },
@@ -272,6 +296,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.TAKEN_JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND_TAKEN Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -337,7 +362,7 @@
         "BriefDescription": "Counts the total number of instructions retired. (Fixed event)",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -346,7 +371,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -355,6 +380,7 @@
         "Deprecated": "1",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.4K_ALIAS",
+        "PublicDescription": "This event is deprecated. Refer to new event LD_BLOCKS.ADDRESS_ALIAS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -363,6 +389,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
+        "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -371,6 +398,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.DATA_UNKNOWN",
+        "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -399,8 +427,9 @@
         "UMask": "0x20"
     },
     {
-        "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.",
+        "BriefDescription": "This event is deprecated.",
         "Counter": "0,1,2,3,4,5",
+        "Deprecated": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SLOW",
         "SampleAfterValue": "20003",
@@ -419,11 +448,19 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xe4",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
-        "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY]",
+        "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0x75",
@@ -614,6 +651,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "TOPDOWN_RETIRING.ALL",
+        "PublicDescription": "Counts the total number of consumed retirement slots. Available PDIST counters: 0",
         "SampleAfterValue": "1000003"
     },
     {
@@ -629,6 +667,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.ALL",
+        "PublicDescription": "Counts the total number of uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -636,6 +675,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.IDIV",
+        "PublicDescription": "Counts the number of integer divide uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -644,7 +684,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.MS",
-        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.",
+        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -653,6 +693,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.X87",
+        "PublicDescription": "Counts the number of x87 uops retired, includes those in MS flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     }
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json
index d9c737a17df0..c348046696bf 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json
@@ -57,6 +57,7 @@
         "Deprecated": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
+        "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x13"
     },
@@ -67,6 +68,7 @@
         "Deprecated": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
+        "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_LOADS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x11"
     },
@@ -77,6 +79,7 @@
         "Deprecated": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
+        "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_STORES Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x12"
     }
diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json b/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json
index 7ddb89dd1871..b22a02450e6c 100644
--- a/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json
@@ -75,7 +75,7 @@
         "MetricExpr": "tma_core_bound",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_allocation_restriction",
-        "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -85,7 +85,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
-        "MetricThreshold": "(tma_backend_bound >0.10)",
+        "MetricThreshold": "tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
         "ScaleUnit": "100%",
@@ -97,7 +97,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
-        "MetricThreshold": "(tma_bad_speculation >0.15)",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%",
@@ -108,7 +108,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_detect",
-        "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -118,7 +118,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
-        "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -128,7 +128,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_resteer",
-        "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -137,7 +137,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -146,7 +146,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
-        "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -156,7 +156,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_decode",
-        "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -165,7 +165,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
-        "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -175,7 +175,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
-        "MetricThreshold": "(tma_frontend_bound >0.20)",
+        "MetricThreshold": "tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -185,7 +185,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -194,7 +194,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_bandwidth",
-        "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -204,7 +204,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_latency",
-        "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -590,7 +590,7 @@
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
         "MetricName": "tma_info_system_mux",
-        "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9",
         "Unit": "cpu_atom"
     },
     {
@@ -629,7 +629,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB_MISS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -638,7 +638,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
-        "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -648,7 +648,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
-        "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -657,7 +657,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
-        "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -666,7 +666,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
-        "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -675,7 +675,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_other_fb",
-        "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -684,7 +684,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_predecode",
-        "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -693,7 +693,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
-        "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -702,7 +702,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
-        "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -711,7 +711,7 @@
         "MetricExpr": "tma_backend_bound - tma_core_bound",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_resource_bound",
-        "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -722,7 +722,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
-        "MetricThreshold": "(tma_retiring >0.75)",
+        "MetricThreshold": "tma_retiring > 0.75",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -732,7 +732,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
-        "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -744,7 +744,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "cpu_core@UOPS_DISPATCHED.ALU@ / (6 * tma_info_thread_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -757,13 +757,13 @@
         "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
         "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
@@ -774,7 +774,7 @@
     {
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -786,18 +786,18 @@
     {
         "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-bad\\-spec / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-bad\\-spec@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20",
@@ -814,11 +814,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
-        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full",
+        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full",
         "Unit": "cpu_core"
     },
     {
@@ -826,22 +826,22 @@
         "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
-        "MetricThreshold": "(tma_bottleneck_cache_memory_latency > 20)",
+        "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
         "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy",
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20",
@@ -849,7 +849,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -861,7 +861,7 @@
         "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
-        "MetricThreshold": "(tma_bottleneck_memory_data_tlbs > 20)",
+        "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
         "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store",
         "Unit": "cpu_core"
     },
@@ -870,13 +870,13 @@
         "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
-        "MetricThreshold": "(tma_bottleneck_memory_synchronization > 10)",
+        "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
         "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -888,12 +888,12 @@
         "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)",
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
-        "MetricThreshold": "(tma_bottleneck_other_bottlenecks > 20)",
+        "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
         "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -902,7 +902,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
-        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -916,26 +916,26 @@
         "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c01_wait",
-        "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c02_wait",
-        "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -944,8 +944,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -954,99 +954,100 @@
         "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
-        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@frontend_retired.l1i_miss@R / tma_info_thread_clks - tma_code_l2_miss)",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
+        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@FRONTEND_RETIRED.L1I_MISS@R / tma_info_thread_clks - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@frontend_retired.l2_miss@R / tma_info_thread_clks",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@FRONTEND_RETIRED.L2_MISS@R / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)",
-        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@frontend_retired.itlb_miss@R / tma_info_thread_clks - tma_code_stlb_miss)",
+        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@FRONTEND_RETIRED.ITLB_MISS@R / tma_info_thread_clks - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@frontend_retired.stlb_miss@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@FRONTEND_RETIRED.STLB_MISS@R / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@br_misp_retired.cond_ntaken_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_nt_mispredicts",
-        "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@ * cpu_core@br_misp_retired.cond_taken_bwd_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_tk_bwd_mispredicts",
-        "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@ * cpu_core@br_misp_retired.cond_taken_fwd_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_tk_fwd_mispredicts",
-        "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * cpu_core@mem_load_l3_hit_retired.xsnp_miss@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_miss@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@R, 25 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1057,17 +1058,18 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 25 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1076,7 +1078,7 @@
         "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1086,7 +1088,7 @@
         "MetricExpr": "cpu_core@MEMORY_STALLS.MEM@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1097,7 +1099,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1106,28 +1108,28 @@
         "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * cpu_core@mem_inst_retired.stlb_hit_loads@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_loads@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) / tma_info_thread_clks + tma_load_stlb_miss",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@R, 7) / tma_info_thread_clks + tma_load_stlb_miss",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * cpu_core@mem_inst_retired.stlb_hit_stores@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_stores@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) / tma_info_thread_clks + tma_store_stlb_miss",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@R, 7) / tma_info_thread_clks + tma_store_stlb_miss",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1136,7 +1138,7 @@
         "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "(tma_false_sharing > 0.05) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1147,7 +1149,7 @@
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1158,18 +1160,18 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
-        "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1179,7 +1181,7 @@
         "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0",
         "MetricName": "tma_few_uops_instructions",
         "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1189,7 +1191,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1199,16 +1201,16 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1217,8 +1219,8 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1227,8 +1229,8 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1237,8 +1239,8 @@
         "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1247,15 +1249,15 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
@@ -1265,23 +1267,23 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
-        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1290,26 +1292,26 @@
         "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ind_call_mispredicts",
-        "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions",
-        "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@br_misp_retired.indirect_cost@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R) / tma_info_thread_clks, 0)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions.",
+        "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_COST@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R) / tma_info_thread_clks, 0)",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ind_jump_mispredicts",
-        "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1322,7 +1324,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
@@ -1330,29 +1332,29 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_bwd",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_fwd",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000",
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -1376,7 +1378,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -1385,7 +1387,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -1394,10 +1396,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
         "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
@@ -1463,12 +1466,12 @@
         "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.V0@ + cpu_core@FP_ARITH_DISPATCHED.V1@ + cpu_core@FP_ARITH_DISPATCHED.V2@ + cpu_core@FP_ARITH_DISPATCHED.V3@) / (4 * tma_info_thread_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)",
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp",
         "Unit": "cpu_core"
@@ -1483,15 +1486,15 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@frontend_retired.any_dsb_miss@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@R / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;Fed;FetchLat",
         "MetricName": "tma_info_frontend_dsb_switches_ret",
         "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05",
@@ -1499,7 +1502,7 @@
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc",
         "Unit": "cpu_core"
@@ -1549,7 +1552,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@frontend_retired.ms_flows@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@FRONTEND_RETIRED.MS_FLOWS@R / tma_info_thread_clks",
         "MetricGroup": "Fed;FetchLat;MicroSeq",
         "MetricName": "tma_info_frontend_ms_latency_ret",
         "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05",
@@ -1564,21 +1567,21 @@
     },
     {
         "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
-        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed",
         "MetricName": "tma_info_frontend_unknown_branch_cost",
-        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node",
+        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@frontend_retired.unknown_branch@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@R / tma_info_thread_clks",
         "MetricGroup": "Fed;FetchLat",
         "MetricName": "tma_info_frontend_unknown_branches_ret",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch",
@@ -1598,7 +1601,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW",
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.",
         "Unit": "cpu_core"
     },
     {
@@ -1607,7 +1610,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1616,7 +1619,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1625,7 +1628,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1634,7 +1637,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1697,7 +1700,7 @@
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 8 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 17",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp",
         "Unit": "cpu_core"
     },
@@ -1709,6 +1712,13 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / tma_info_system_time",
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l1d_cache_fill_bw",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Average per-thread data fill bandwidth to the Level 0 within L1D cache [GB / sec]",
         "MetricExpr": "64 * cpu_core@L1D.L0_REPLACEMENT@ / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
@@ -1815,7 +1825,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp",
         "Unit": "cpu_core"
@@ -1873,7 +1883,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads",
-        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@mem_inst_retired.stlb_miss_loads@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@R / tma_info_thread_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret",
         "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05",
@@ -1896,7 +1906,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores",
-        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@mem_inst_retired.stlb_miss_stores@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@R / tma_info_thread_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret",
         "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05",
@@ -1935,20 +1945,20 @@
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "MicroSeq;Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
@@ -1993,23 +2003,22 @@
     },
     {
         "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
-        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000",
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_utilization",
         "MetricThreshold": "tma_info_system_kernel_utilization > 0.05",
@@ -2053,7 +2062,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks",
@@ -2064,7 +2073,6 @@
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
         "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr",
         "Unit": "cpu_core"
     },
     {
@@ -2072,7 +2080,7 @@
         "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage",
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
         "Unit": "cpu_core"
     },
     {
@@ -2084,7 +2092,7 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "cpu_core@TOPDOWN.SLOTS@",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots",
         "Unit": "cpu_core"
@@ -2102,15 +2110,15 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 8 * 1.5",
+        "MetricThreshold": "tma_info_thread_uptb < 12",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2120,7 +2128,7 @@
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_int_operations",
         "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2129,8 +2137,8 @@
         "MetricExpr": "cpu_core@INT_VEC_RETIRED.128BIT@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_128b",
-        "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2139,8 +2147,8 @@
         "MetricExpr": "cpu_core@INT_VEC_RETIRED.256BIT@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_256b",
-        "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2149,8 +2157,8 @@
         "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2159,17 +2167,17 @@
         "MetricExpr": "cpu_core@MEMORY_STALLS.L1@ / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache",
-        "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * cpu_core@mem_load_retired.l1_hit_l1@R, cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) if 0 < cpu_core@mem_load_retired.l1_hit_l1@R else cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) / tma_info_thread_clks",
+        "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache.",
+        "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * min(cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@R, 9) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_capacity",
-        "MetricThreshold": "tma_l1_latency_capacity > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_capacity > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2178,8 +2186,8 @@
         "MetricExpr": "4 * cpu_core@DEPENDENT_LOADS.ANY@ / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: DEPENDENT_LOADS.ANY",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2188,17 +2196,18 @@
         "MetricExpr": "cpu_core@MEMORY_STALLS.L2@ / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
-        "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * cpu_core@mem_load_retired.l2_hit@R, cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) if 0 < cpu_core@mem_load_retired.l2_hit@R else cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@R, 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2208,18 +2217,19 @@
         "MetricExpr": "cpu_core@MEMORY_STALLS.L3@ / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * cpu_core@mem_load_retired.l3_hit@R, cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_retired.l3_hit@R else cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, 9 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2228,19 +2238,19 @@
         "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2250,7 +2260,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_load_op_utilization",
         "MetricThreshold": "tma_load_op_utilization > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.LOAD",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3_10",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2259,7 +2269,7 @@
         "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2268,43 +2278,43 @@
         "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
-        "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@mem_inst_retired.lock_loads@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2315,7 +2325,7 @@
         "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_lsd",
         "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2326,17 +2336,17 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_sq_full",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2345,34 +2355,34 @@
         "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
-        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
-        "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -2395,14 +2405,14 @@
         "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)",
-        "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks",
+        "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / 2 + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
@@ -2411,17 +2421,17 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
         "MetricExpr": "cpu_core@IDQ.MS_CYCLES_ANY@ / tma_info_thread_clks",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
@@ -2434,7 +2444,7 @@
         "MetricExpr": "3 * cpu_core@IDQ.MS_SWITCHES@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2445,7 +2455,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2454,7 +2464,7 @@
         "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2470,20 +2480,20 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2493,7 +2503,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_page_faults",
         "MetricThreshold": "tma_page_faults > 0.05",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2502,8 +2512,8 @@
         "MetricExpr": "((cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2512,8 +2522,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2522,7 +2532,7 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2533,8 +2543,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2544,24 +2554,24 @@
         "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@br_misp_retired.ret_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@BR_MISP_RETIRED.RET_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ret_mispredicts",
-        "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ret_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2575,8 +2585,8 @@
         "MetricExpr": "(cpu_core@BE_STALLS.SCOREBOARD@ + cpu_core@CPU_CLK_UNHALTED.C02@) / tma_info_thread_clks",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: BE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2585,8 +2595,8 @@
         "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_shuffles_256b",
-        "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+        "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2596,28 +2606,28 @@
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * cpu_core@mem_inst_retired.split_loads@R, cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) if 0 < cpu_core@mem_inst_retired.split_loads@R else cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@R, tma_info_memory_load_miss_real_latency) / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * cpu_core@mem_inst_retired.split_stores@R, cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) if 0 < cpu_core@mem_inst_retired.split_stores@R else cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@R, 1) / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2626,8 +2636,8 @@
         "MetricExpr": "(cpu_core@XQ.FULL@ + cpu_core@L1D_MISS.L2_STALLS@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2636,8 +2646,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2646,8 +2656,8 @@
         "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2656,8 +2666,8 @@
         "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2667,7 +2677,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_store_op_utilization",
         "MetricThreshold": "tma_store_op_utilization > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.STD, UOPS_DISPATCHED.STA",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2676,7 +2686,7 @@
         "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2685,34 +2695,34 @@
         "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2721,7 +2731,7 @@
         "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2731,7 +2741,7 @@
         "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2741,8 +2751,8 @@
         "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     }
diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/cache.json b/tools/perf/pmu-events/arch/x86/arrowlake/cache.json
index f63594b2cca8..70175404540d 100644
--- a/tools/perf/pmu-events/arch/x86/arrowlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/cache.json
@@ -9,6 +9,16 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x51",
+        "EventName": "DL1.DIRTY_EVICTION",
+        "PublicDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.  Does not count evictions or dirty writebacks caused by snoops.  Does not count a replacement unless a (dirty) line was written back.",
+        "SampleAfterValue": "200003",
+        "UMask": "0x1",
+        "Unit": "cpu_lowpower"
+    },
+    {
         "BriefDescription": "Counts the number of cache lines replaced in L0 data cache.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x51",
@@ -19,6 +29,16 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Cachelines replaced into the L0 and L1 d-cache. Successful replacements only (not blocked) and exclude WB-miss case",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x51",
+        "EventName": "L1D.REPLACEMENT",
+        "PublicDescription": "Counts cachelines replaced into the L0 and L1 d-cache.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x49",
@@ -80,6 +100,46 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.E",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_lowpower"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.F",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x10",
+        "Unit": "cpu_lowpower"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.M",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_lowpower"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.S",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_lowpower"
+    },
+    {
         "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x26",
@@ -90,6 +150,16 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x26",
+        "EventName": "L2_LINES_OUT.NON_SILENT",
+        "PublicDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill. Increments on the core that brought the line in originally.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_lowpower"
+    },
+    {
         "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x26",
@@ -100,6 +170,16 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x26",
+        "EventName": "L2_LINES_OUT.SILENT",
+        "PublicDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill.  Increments on the core that brought the line in originally.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_lowpower"
+    },
+    {
         "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x26",
@@ -129,6 +209,15 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of L2 Cache Accesses that resulted in a Hit from a front door request only (does not include rejects or recycles), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.HIT",
+        "SampleAfterValue": "200003",
+        "UMask": "0x2",
+        "Unit": "cpu_lowpower"
+    },
+    {
         "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x24",
@@ -139,6 +228,34 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of total L2 Cache Accesses that resulted in a Miss from a front door request only (does not include rejects or recycles), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.MISS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x1",
+        "Unit": "cpu_lowpower"
+    },
+    {
+        "BriefDescription": "Counts the number of L2 Cache Accesses that miss the L2 and get BBL reject  short and long rejects (includes those counted in L2_reject_XQ.any), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.REJECTS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4",
+        "Unit": "cpu_lowpower"
+    },
+    {
+        "BriefDescription": "L2 code requests",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.ALL_CODE_RD",
+        "PublicDescription": "Counts the total number of L2 code requests.",
+        "SampleAfterValue": "200003",
+        "UMask": "0xe4",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Demand Data Read access L2 cache",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x24",
@@ -409,12 +526,21 @@
         "Unit": "cpu_lowpower"
     },
     {
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS_LOAD.SBFULL",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x80",
+        "Unit": "cpu_lowpower"
+    },
+    {
         "BriefDescription": "Counts all retired load instructions.",
         "Counter": "0,1,2,3",
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts Instructions with at least one architecturally visible load retired.",
+        "PublicDescription": "Counts Instructions with at least one architecturally visible load retired. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x81",
         "Unit": "cpu_core"
@@ -425,7 +551,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts all retired store instructions.",
+        "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x82",
         "Unit": "cpu_core"
@@ -435,7 +561,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_SWPF",
-        "PublicDescription": "Counts all retired software prefetch instructions.",
+        "PublicDescription": "Counts all retired software prefetch instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x84",
         "Unit": "cpu_core"
@@ -446,7 +572,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+        "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x87",
         "Unit": "cpu_core"
@@ -457,7 +583,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PublicDescription": "Counts retired load instructions with locked access.",
+        "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x21",
         "Unit": "cpu_core"
@@ -468,7 +594,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41",
         "Unit": "cpu_core"
@@ -479,7 +605,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x42",
         "Unit": "cpu_core"
@@ -490,7 +616,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS",
-        "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x9",
         "Unit": "cpu_core"
@@ -501,7 +627,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES",
-        "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xa",
         "Unit": "cpu_core"
@@ -512,7 +638,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x11",
         "Unit": "cpu_core"
@@ -523,7 +649,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x12",
         "Unit": "cpu_core"
@@ -534,7 +660,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)",
+        "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$) Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -545,7 +671,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -556,7 +682,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -567,7 +693,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -578,7 +704,7 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -589,7 +715,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -600,7 +726,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -610,6 +736,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT_L1",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "Unit": "cpu_core"
     },
@@ -619,7 +746,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -630,7 +757,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -641,7 +768,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -652,7 +779,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -663,7 +790,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1246,12 +1373,25 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x40001E00001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1263,6 +1403,19 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x20001E00001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1274,6 +1427,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x40001E00002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json b/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json
index fc5f4dd50fe6..67cc83de18d3 100644
--- a/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json
@@ -65,7 +65,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)",
+        "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -77,7 +77,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -89,7 +89,7 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -119,7 +119,7 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -140,7 +140,7 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -152,7 +152,7 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -164,7 +164,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -176,7 +176,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -188,7 +188,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -200,7 +200,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -212,7 +212,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -224,7 +224,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -236,7 +236,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -248,7 +248,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -260,7 +260,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -272,7 +272,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -284,7 +284,7 @@
         "EventName": "FRONTEND_RETIRED.MISP_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PublicDescription": "ANT retired branches that got just mispredicted",
+        "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -296,6 +296,7 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "Counts flows delivered by the Microcode Sequencer Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -307,7 +308,7 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -319,7 +320,7 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
-        "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/memory.json b/tools/perf/pmu-events/arch/x86/arrowlake/memory.json
index 08f01fc66fef..fb8d4ac69bda 100644
--- a/tools/perf/pmu-events/arch/x86/arrowlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/memory.json
@@ -163,7 +163,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x400",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "53",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -176,7 +176,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "1009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -189,7 +189,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -202,7 +202,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x800",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "23",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -215,7 +215,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "503",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -228,7 +228,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -241,7 +241,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -254,7 +254,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "101",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -267,7 +267,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "2003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -280,7 +280,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -291,7 +291,7 @@
         "Data_LA": "1",
         "EventCode": "0xcd",
         "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
-        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
+        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -333,12 +333,25 @@
         "Unit": "cpu_lowpower"
     },
     {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1E780000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0xFE7F8000001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -350,6 +363,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0xFE7F8000002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/other.json b/tools/perf/pmu-events/arch/x86/arrowlake/other.json
index 0175b2193201..51bc763a5887 100644
--- a/tools/perf/pmu-events/arch/x86/arrowlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/other.json
@@ -19,71 +19,6 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0xa2",
-        "EventName": "BE_STALLS.SCOREBOARD",
-        "SampleAfterValue": "100003",
-        "UMask": "0x2",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or  2 cycles back. This event supports in-direct dependency through a single uop.",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x02",
-        "EventName": "DEPENDENT_LOADS.ANY",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on secondary integer ports 0,1,2,3.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.2ND",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x80",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on a load port.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.LD",
-        "PublicDescription": "Counts the number of uops executed on a load port.  This event counts for integer uops even if the destination is FP/vector",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on integer port  0,1, 2, 3.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.PRIMARY",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x78",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on a Store address port.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.STA",
-        "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x2",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.STD_JMP",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x4",
-        "Unit": "cpu_atom"
-    },
-    {
         "BriefDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS]",
         "Counter": "0,1,2,3,4,5,6,7",
         "Deprecated": "1",
@@ -94,81 +29,13 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x46",
-        "EventName": "MEMORY_STALLS.L1",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x46",
-        "EventName": "MEMORY_STALLS.L2",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x2",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x46",
-        "EventName": "MEMORY_STALLS.L3",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x4",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x46",
-        "EventName": "MEMORY_STALLS.MEM",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x8",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1E780000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
         "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x800000010000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -180,6 +47,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x400000010000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -191,6 +59,7 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -202,70 +71,12 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "CounterMask": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_COUNT",
-        "Invert": "1",
-        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_RESOURCE",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x4",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "200003",
-        "UMask": "0x4",
-        "Unit": "cpu_lowpower"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots where no uop could issue due to an IQ scoreboard that stalls allocation until a specified older uop retires or (in the case of jump scoreboard) executes. Commonly executed instructions with IQ scoreboards include LFENCE and MFENCE.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.IQ_JEU_SCB",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
         "BriefDescription": "Cycles the uncore cannot take further requests",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "CounterMask": "1",
diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json b/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json
index 6dbde51e7ead..18a22368b99b 100644
--- a/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json
@@ -52,6 +52,15 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0xa2",
+        "EventName": "BE_STALLS.SCOREBOARD",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts the total number of branch instructions retired for all branch types.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
@@ -65,7 +74,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all branch instructions retired.",
+        "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -92,7 +101,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
-        "PublicDescription": "Counts conditional branch instructions retired.",
+        "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x111",
         "Unit": "cpu_core"
@@ -111,7 +120,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts not taken branch instructions retired.",
+        "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -130,7 +139,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional branch instructions retired.",
+        "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x101",
         "Unit": "cpu_core"
@@ -149,7 +158,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN_BWD",
-        "PublicDescription": "Counts taken backward conditional branch instructions retired.",
+        "PublicDescription": "Counts taken backward conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -159,7 +168,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN_FWD",
-        "PublicDescription": "Counts taken forward conditional branch instructions retired.",
+        "PublicDescription": "Counts taken forward conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x102",
         "Unit": "cpu_core"
@@ -178,7 +187,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "PublicDescription": "Counts far branch instructions retired.",
+        "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -206,7 +215,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
-        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -261,7 +270,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -289,7 +298,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "Counts return instructions retired.",
+        "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -308,7 +317,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts taken branch instructions retired.",
+        "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -363,7 +372,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -381,6 +390,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST",
+        "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x44",
         "Unit": "cpu_core"
@@ -399,7 +409,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
-        "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x111",
         "Unit": "cpu_core"
@@ -418,6 +428,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_COST",
+        "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x151",
         "Unit": "cpu_core"
@@ -427,7 +438,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
+        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -437,6 +448,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST",
+        "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x50",
         "Unit": "cpu_core"
@@ -455,7 +467,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x101",
         "Unit": "cpu_core"
@@ -474,7 +486,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD",
-        "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -484,6 +496,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST",
+        "PublicDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x8001",
         "Unit": "cpu_core"
@@ -493,6 +506,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST",
+        "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x141",
         "Unit": "cpu_core"
@@ -502,7 +516,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD",
-        "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -511,6 +525,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST",
+        "PublicDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x8002",
         "Unit": "cpu_core"
@@ -529,7 +544,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
-        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -557,7 +572,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
-        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
+        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -576,6 +591,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST",
+        "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x42",
         "Unit": "cpu_core"
@@ -585,6 +601,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_COST",
+        "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xc0",
         "Unit": "cpu_core"
@@ -603,7 +620,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -622,6 +639,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST",
+        "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x60",
         "Unit": "cpu_core"
@@ -631,7 +649,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -659,6 +677,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET_COST",
+        "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x48",
         "Unit": "cpu_core"
@@ -889,6 +908,15 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or  2 cycles back. This event supports in-direct dependency through a single uop.",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x02",
+        "EventName": "DEPENDENT_LOADS.ANY",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xa6",
@@ -982,6 +1010,7 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired.",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Fixed Counter: Counts the number of instructions retired. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -990,7 +1019,7 @@
         "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -999,6 +1028,7 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Fixed Counter: Counts the number of instructions retired Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_lowpower"
@@ -1016,7 +1046,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "Unit": "cpu_core"
     },
@@ -1033,6 +1063,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.BR_FUSED",
+        "PublicDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon) Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1042,6 +1073,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x30",
         "Unit": "cpu_core"
@@ -1051,7 +1083,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
-        "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions",
+        "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1060,7 +1092,7 @@
         "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.PREC_DIST",
-        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
+        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1070,7 +1102,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1140,6 +1172,53 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of uops executed on secondary integer ports 0,1,2,3.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.2ND",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x80",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on a load port.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.LD",
+        "PublicDescription": "Counts the number of uops executed on a load port.  This event counts for integer uops even if the destination is FP/vector",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on integer port  0,1, 2, 3.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.PRIMARY",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x78",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on a Store address port.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.STA",
+        "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.STD_JMP",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Number of vector integer instructions retired of 128-bit vector-width.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xe7",
@@ -1405,8 +1484,9 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.",
+        "BriefDescription": "This event is deprecated.",
         "Counter": "0,1,2,3,4,5,6,7",
+        "Deprecated": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SLOW",
         "SampleAfterValue": "20003",
@@ -1433,6 +1513,42 @@
         "Unit": "cpu_lowpower"
     },
     {
+        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x46",
+        "EventName": "MEMORY_STALLS.L1",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x46",
+        "EventName": "MEMORY_STALLS.L2",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x46",
+        "EventName": "MEMORY_STALLS.L3",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x46",
+        "EventName": "MEMORY_STALLS.MEM",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "LFENCE instructions retired",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xe0",
@@ -1447,6 +1563,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xe4",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
+        "PublicDescription": "LBR record is inserted Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1461,6 +1578,65 @@
         "Unit": "cpu_lowpower"
     },
     {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_COUNT",
+        "Invert": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_RESOURCE",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4",
+        "Unit": "cpu_lowpower"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots where no uop could issue due to an IQ scoreboard that stalls allocation until a specified older uop retires or (in the case of jump scoreboard) executes. Commonly executed instructions with IQ scoreboards include LFENCE and MFENCE.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.IQ_JEU_SCB",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x75",
diff --git a/tools/perf/pmu-events/arch/x86/bonnell/other.json b/tools/perf/pmu-events/arch/x86/bonnell/other.json
index 3a55c101fbf7..6e6f64b96834 100644
--- a/tools/perf/pmu-events/arch/x86/bonnell/other.json
+++ b/tools/perf/pmu-events/arch/x86/bonnell/other.json
@@ -324,14 +324,6 @@
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "Memory cluster signals to block micro-op dispatch for any reason",
-        "Counter": "0,1",
-        "EventCode": "0x9",
-        "EventName": "DISPATCH_BLOCKED.ANY",
-        "SampleAfterValue": "200000",
-        "UMask": "0x20"
-    },
-    {
         "BriefDescription": "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions",
         "Counter": "0,1",
         "EventCode": "0x3A",
diff --git a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json
index 9ff032ab11e2..48d3d053a369 100644
--- a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json
@@ -212,6 +212,14 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Memory cluster signals to block micro-op dispatch for any reason",
+        "Counter": "0,1",
+        "EventCode": "0x9",
+        "EventName": "DISPATCH_BLOCKED.ANY",
+        "SampleAfterValue": "200000",
+        "UMask": "0x20"
+    },
+    {
         "BriefDescription": "Divide operations retired",
         "Counter": "0,1",
         "EventCode": "0x13",
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
index 40970fa5566c..89750117a7f6 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
@@ -74,12 +74,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
@@ -92,8 +92,8 @@
         "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
     {
@@ -104,7 +104,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
     {
@@ -114,7 +114,7 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
@@ -125,7 +125,7 @@
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_mispredicts_resteers",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
     {
@@ -133,8 +133,8 @@
         "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -143,8 +143,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -152,7 +152,7 @@
         "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -162,8 +162,8 @@
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -174,7 +174,7 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
@@ -183,8 +183,8 @@
         "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -192,8 +192,8 @@
         "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.FPU_DIV_ACTIVE",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -202,8 +202,8 @@
         "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -212,7 +212,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -220,26 +220,26 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -247,18 +247,18 @@
         "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
     {
@@ -287,7 +287,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -295,8 +295,8 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -304,8 +304,8 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -313,8 +313,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -322,8 +322,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -333,33 +333,33 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "tma_microcode_sequencer",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.",
         "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -370,7 +370,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -391,11 +391,11 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -420,7 +420,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -438,7 +438,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -446,7 +446,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -454,7 +454,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -462,7 +462,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -470,7 +470,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -512,7 +512,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -634,20 +634,20 @@
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks",
+        "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_page_walks_utilization",
         "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -688,14 +688,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -743,7 +742,7 @@
         "MetricName": "tma_info_system_turbo_utilization"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -752,15 +751,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -786,14 +784,14 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 6"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
-        "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED",
         "ScaleUnit": "100%"
     },
@@ -802,8 +800,8 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
     {
@@ -811,8 +809,8 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -821,8 +819,8 @@
         "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -831,8 +829,8 @@
         "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -840,18 +838,18 @@
         "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -870,8 +868,8 @@
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -882,15 +880,15 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -899,7 +897,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -911,7 +909,7 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
@@ -928,8 +926,8 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
     {
@@ -938,7 +936,7 @@
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.",
         "ScaleUnit": "100%"
     },
     {
@@ -946,8 +944,8 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
     {
@@ -956,7 +954,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -965,7 +963,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1001,7 +999,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1010,7 +1008,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1028,43 +1026,43 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1084,7 +1082,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1092,8 +1090,8 @@
         "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -1101,7 +1099,7 @@
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1110,8 +1108,8 @@
         "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1119,8 +1117,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -1129,8 +1127,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1146,7 +1144,7 @@
         "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -1155,8 +1153,8 @@
         "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
index b03a5f2bcd82..81175f0f2603 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
@@ -74,7 +74,7 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "(tma_4k_aliasing > 0.2) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
@@ -84,7 +84,7 @@
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
-        "MetricThreshold": "(tma_alu_op_utilization > 0.4)",
+        "MetricThreshold": "tma_alu_op_utilization > 0.4",
         "ScaleUnit": "100%"
     },
     {
@@ -92,7 +92,7 @@
         "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "(tma_assists > 0.1) & ((tma_microcode_sequencer > 0.05) & ((tma_heavy_operations > 0.1)))",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
@@ -102,7 +102,7 @@
         "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)",
         "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
-        "MetricThreshold": "(tma_backend_bound > 0.2)",
+        "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS",
         "ScaleUnit": "100%"
@@ -112,7 +112,7 @@
         "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots",
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
-        "MetricThreshold": "(tma_bad_speculation > 0.15)",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
@@ -123,7 +123,7 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
-        "MetricThreshold": "(tma_branch_mispredicts > 0.1) & ((tma_bad_speculation > 0.15))",
+        "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
@@ -133,7 +133,7 @@
         "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "(tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
@@ -143,7 +143,7 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "(tma_cisc > 0.1) & ((tma_microcode_sequencer > 0.05) & ((tma_heavy_operations > 0.1)))",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
@@ -152,7 +152,7 @@
         "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "(tma_clears_resteers > 0.05) & ((tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))))",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -162,7 +162,7 @@
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "(tma_contested_accesses > 0.05) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -172,7 +172,7 @@
         "MetricExpr": "tma_backend_bound - tma_memory_bound",
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
-        "MetricThreshold": "(tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
@@ -183,7 +183,7 @@
         "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "(tma_data_sharing > 0.05) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -192,7 +192,7 @@
         "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "(tma_divider > 0.2) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE",
         "ScaleUnit": "100%"
     },
@@ -202,7 +202,7 @@
         "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "(tma_dram_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -211,7 +211,7 @@
         "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
-        "MetricThreshold": "(tma_dsb > 0.15) & ((tma_fetch_bandwidth > 0.2))",
+        "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
         "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
@@ -220,7 +220,7 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "(tma_dsb_switches > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -229,7 +229,7 @@
         "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "(tma_dtlb_load > 0.1) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
         "ScaleUnit": "100%"
     },
@@ -238,7 +238,7 @@
         "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "(tma_dtlb_store > 0.05) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
         "ScaleUnit": "100%"
     },
@@ -248,7 +248,7 @@
         "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
-        "MetricThreshold": "(tma_fb_full > 0.3)",
+        "MetricThreshold": "tma_fb_full > 0.3",
         "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
@@ -257,7 +257,7 @@
         "MetricExpr": "tma_frontend_bound - tma_fetch_latency",
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
-        "MetricThreshold": "(tma_fetch_bandwidth > 0.2)",
+        "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
@@ -267,7 +267,7 @@
         "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_thread_slots",
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
-        "MetricThreshold": "(tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))",
+        "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
@@ -277,7 +277,7 @@
         "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
-        "MetricThreshold": "(tma_fp_arith > 0.2) & ((tma_light_operations > 0.6))",
+        "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
         "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
@@ -286,7 +286,7 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "(tma_fp_scalar > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6)))",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -295,7 +295,7 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "(tma_fp_vector > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6)))",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -304,7 +304,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "(tma_fp_vector_128b > 0.1) & ((tma_fp_vector > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6))))",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -313,7 +313,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "(tma_fp_vector_256b > 0.1) & ((tma_fp_vector > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6))))",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -322,7 +322,7 @@
         "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots",
         "MetricGroup": "BvFB;BvIO;PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
-        "MetricThreshold": "(tma_frontend_bound > 0.15)",
+        "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
@@ -332,7 +332,7 @@
         "MetricExpr": "tma_microcode_sequencer",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
-        "MetricThreshold": "(tma_heavy_operations > 0.1)",
+        "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%"
@@ -342,7 +342,7 @@
         "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "(tma_icache_misses > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
@@ -351,14 +351,14 @@
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "(tma_info_bad_spec_ipmisp_indirect < 1000)"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BadSpec;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmispredict",
-        "MetricThreshold": "(tma_info_bad_spec_ipmispredict < 200)"
+        "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200"
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
@@ -396,7 +396,7 @@
         "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_frontend_dsb_coverage",
-        "MetricThreshold": "(tma_info_frontend_dsb_coverage < 0.7) & ((tma_info_thread_ipc / 4) > 0.35)",
+        "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35",
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
@@ -429,7 +429,7 @@
         "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
-        "MetricThreshold": "(tma_info_inst_mix_iparith < 10)",
+        "MetricThreshold": "tma_info_inst_mix_iparith < 10",
         "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
@@ -437,7 +437,7 @@
         "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
-        "MetricThreshold": "(tma_info_inst_mix_iparith_avx128 < 10)",
+        "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
         "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
@@ -445,7 +445,7 @@
         "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
-        "MetricThreshold": "(tma_info_inst_mix_iparith_avx256 < 10)",
+        "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
         "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
@@ -453,7 +453,7 @@
         "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
-        "MetricThreshold": "(tma_info_inst_mix_iparith_scalar_dp < 10)",
+        "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
         "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
@@ -461,7 +461,7 @@
         "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
-        "MetricThreshold": "(tma_info_inst_mix_iparith_scalar_sp < 10)",
+        "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
         "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
@@ -469,42 +469,42 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Branches;Fed;InsType",
         "MetricName": "tma_info_inst_mix_ipbranch",
-        "MetricThreshold": "(tma_info_inst_mix_ipbranch < 8)"
+        "MetricThreshold": "tma_info_inst_mix_ipbranch < 8"
     },
     {
         "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_ipcall",
-        "MetricThreshold": "(tma_info_inst_mix_ipcall < 200)"
+        "MetricThreshold": "tma_info_inst_mix_ipcall < 200"
     },
     {
         "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_ipflop",
-        "MetricThreshold": "(tma_info_inst_mix_ipflop < 10)"
+        "MetricThreshold": "tma_info_inst_mix_ipflop < 10"
     },
     {
         "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
         "MetricGroup": "InsType",
         "MetricName": "tma_info_inst_mix_ipload",
-        "MetricThreshold": "(tma_info_inst_mix_ipload < 3)"
+        "MetricThreshold": "tma_info_inst_mix_ipload < 3"
     },
     {
         "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
         "MetricGroup": "InsType",
         "MetricName": "tma_info_inst_mix_ipstore",
-        "MetricThreshold": "(tma_info_inst_mix_ipstore < 8)"
+        "MetricThreshold": "tma_info_inst_mix_ipstore < 8"
     },
     {
         "BriefDescription": "Instructions per taken branch",
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "(tma_info_inst_mix_iptb < 4 * 2 + 1)",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -629,7 +629,7 @@
         "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_page_walks_utilization",
-        "MetricThreshold": "(tma_info_memory_tlb_page_walks_utilization > 0.5)"
+        "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
         "BriefDescription": "",
@@ -680,7 +680,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "(tma_info_system_ipfarbranch < 1000000)"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
@@ -693,14 +693,14 @@
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_utilization",
-        "MetricThreshold": "(tma_info_system_kernel_utilization > 0.05)"
+        "MetricThreshold": "tma_info_system_kernel_utilization > 0.05"
     },
     {
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "tma_info_system_mux",
-        "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))"
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
     },
     {
         "BriefDescription": "Total package Power in Watts",
@@ -725,7 +725,7 @@
         "MetricExpr": "duration_time",
         "MetricGroup": "Summary",
         "MetricName": "tma_info_system_time",
-        "MetricThreshold": "(tma_info_system_time < 1)"
+        "MetricThreshold": "tma_info_system_time < 1"
     },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
@@ -769,21 +769,21 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
         "MetricGroup": "Pipeline;Ret;Retire",
         "MetricName": "tma_info_thread_uoppi",
-        "MetricThreshold": "(tma_info_thread_uoppi > 1.05)"
+        "MetricThreshold": "tma_info_thread_uoppi > 1.05"
     },
     {
         "BriefDescription": "Uops per taken branch",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "(tma_info_thread_uptb < 4 * 1.5)"
+        "MetricThreshold": "tma_info_thread_uptb < 6"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
         "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "(tma_itlb_misses > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
@@ -792,7 +792,7 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "(tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -801,7 +801,7 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "(tma_l2_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -811,7 +811,7 @@
         "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "(tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
@@ -821,7 +821,7 @@
         "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "(tma_l3_hit_latency > 0.1) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency",
         "ScaleUnit": "100%"
     },
@@ -830,7 +830,7 @@
         "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "(tma_lcp > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
@@ -839,7 +839,7 @@
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
-        "MetricThreshold": "(tma_light_operations > 0.6)",
+        "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
@@ -850,7 +850,7 @@
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_load_op_utilization",
-        "MetricThreshold": "(tma_load_op_utilization > 0.6)",
+        "MetricThreshold": "tma_load_op_utilization > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3_10",
         "ScaleUnit": "100%"
     },
@@ -860,7 +860,7 @@
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "(tma_lock_latency > 0.2) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -870,7 +870,7 @@
         "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts",
         "MetricGroup": "BadSpec;BvMS;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
-        "MetricThreshold": "(tma_machine_clears > 0.1) & ((tma_bad_speculation > 0.15))",
+        "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
@@ -880,7 +880,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "(tma_mem_bandwidth > 0.2) & ((tma_dram_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -889,7 +889,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "(tma_mem_latency > 0.1) & ((tma_dram_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -899,7 +899,7 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
-        "MetricThreshold": "(tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
@@ -909,7 +909,7 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
         "MetricName": "tma_microcode_sequencer",
-        "MetricThreshold": "(tma_microcode_sequencer > 0.05) & ((tma_heavy_operations > 0.1))",
+        "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
         "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -918,7 +918,7 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "(tma_mispredicts_resteers > 0.05) & ((tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))))",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -927,7 +927,7 @@
         "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
-        "MetricThreshold": "(tma_mite > 0.1) & ((tma_fetch_bandwidth > 0.2))",
+        "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
         "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS",
         "ScaleUnit": "100%"
     },
@@ -936,7 +936,7 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "(tma_ms_switches > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
@@ -945,7 +945,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks",
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
-        "MetricThreshold": "(tma_port_0 > 0.6)",
+        "MetricThreshold": "tma_port_0 > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -954,7 +954,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
-        "MetricThreshold": "(tma_port_1 > 0.6)",
+        "MetricThreshold": "tma_port_1 > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -963,7 +963,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group",
         "MetricName": "tma_port_2",
-        "MetricThreshold": "(tma_port_2 > 0.6)",
+        "MetricThreshold": "tma_port_2 > 0.6",
         "ScaleUnit": "100%"
     },
     {
@@ -971,7 +971,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group",
         "MetricName": "tma_port_3",
-        "MetricThreshold": "(tma_port_3 > 0.6)",
+        "MetricThreshold": "tma_port_3 > 0.6",
         "ScaleUnit": "100%"
     },
     {
@@ -979,7 +979,7 @@
         "MetricExpr": "tma_store_op_utilization",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group",
         "MetricName": "tma_port_4",
-        "MetricThreshold": "(tma_port_4 > 0.6)",
+        "MetricThreshold": "tma_port_4 > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Related metrics: tma_split_stores",
         "ScaleUnit": "100%"
     },
@@ -988,7 +988,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
-        "MetricThreshold": "(tma_port_5 > 0.6)",
+        "MetricThreshold": "tma_port_5 > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -997,7 +997,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
-        "MetricThreshold": "(tma_port_6 > 0.6)",
+        "MetricThreshold": "tma_port_6 > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -1006,7 +1006,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group",
         "MetricName": "tma_port_7",
-        "MetricThreshold": "(tma_port_7 > 0.6)",
+        "MetricThreshold": "tma_port_7 > 0.6",
         "ScaleUnit": "100%"
     },
     {
@@ -1015,7 +1015,7 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "(tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
@@ -1024,7 +1024,7 @@
         "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "(tma_ports_utilized_0 > 0.2) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
@@ -1033,7 +1033,7 @@
         "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "(tma_ports_utilized_1 > 0.2) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -1042,7 +1042,7 @@
         "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "(tma_ports_utilized_2 > 0.15) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
@@ -1051,7 +1051,7 @@
         "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "(tma_ports_utilized_3m > 0.4) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%"
     },
@@ -1060,7 +1060,7 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots",
         "MetricGroup": "BvUW;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
-        "MetricThreshold": "((tma_retiring > 0.7)|(tma_heavy_operations > 0.1))",
+        "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS",
         "ScaleUnit": "100%"
@@ -1071,7 +1071,7 @@
         "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
-        "MetricThreshold": "(tma_split_loads > 0.3)",
+        "MetricThreshold": "tma_split_loads > 0.3",
         "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
@@ -1080,7 +1080,7 @@
         "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "(tma_split_stores > 0.2) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
@@ -1089,7 +1089,7 @@
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "(tma_sq_full > 0.3) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1098,7 +1098,7 @@
         "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "(tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
@@ -1107,7 +1107,7 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "(tma_store_fwd_blk > 0.1) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
@@ -1117,7 +1117,7 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "(tma_store_latency > 0.1) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
@@ -1126,7 +1126,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_store_op_utilization",
-        "MetricThreshold": "(tma_store_op_utilization > 0.6)",
+        "MetricThreshold": "tma_store_op_utilization > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8",
         "ScaleUnit": "100%"
     },
@@ -1135,7 +1135,7 @@
         "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "(tma_unknown_branches > 0.05) & ((tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))))",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "ScaleUnit": "100%"
     },
@@ -1144,7 +1144,7 @@
         "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "(tma_x87_use > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6)))",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
index 8016202bad1f..5d06a3f72be2 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
@@ -276,12 +276,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
@@ -294,8 +294,8 @@
         "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
     {
@@ -306,7 +306,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
     {
@@ -316,7 +316,7 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
@@ -327,7 +327,7 @@
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_mispredicts_resteers",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
     {
@@ -335,8 +335,8 @@
         "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -345,8 +345,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -354,7 +354,7 @@
         "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -364,8 +364,8 @@
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -376,7 +376,7 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
@@ -385,8 +385,8 @@
         "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -394,8 +394,8 @@
         "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.FPU_DIV_ACTIVE",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -404,8 +404,8 @@
         "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -414,7 +414,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -422,26 +422,26 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -449,18 +449,18 @@
         "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE, OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
     {
@@ -489,7 +489,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -497,8 +497,8 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -506,8 +506,8 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -515,8 +515,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -524,8 +524,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -535,33 +535,33 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "tma_microcode_sequencer",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.",
         "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -572,7 +572,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -593,11 +593,11 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -622,7 +622,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -640,7 +640,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -648,7 +648,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -656,7 +656,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -664,7 +664,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -672,7 +672,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -714,7 +714,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -842,14 +842,14 @@
         "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -890,14 +890,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -908,14 +907,14 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@",
+        "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
-        "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)",
+        "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
         "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)"
@@ -965,7 +964,7 @@
         "MetricName": "tma_info_system_uncore_frequency"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -974,15 +973,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1008,14 +1006,14 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 6"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
-        "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED",
         "ScaleUnit": "100%"
     },
@@ -1024,8 +1022,8 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
     {
@@ -1033,8 +1031,8 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1043,8 +1041,8 @@
         "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1053,8 +1051,8 @@
         "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1062,18 +1060,18 @@
         "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1091,8 +1089,8 @@
         "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
+        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1101,8 +1099,8 @@
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1118,10 +1116,10 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1130,7 +1128,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -1142,7 +1140,7 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
@@ -1159,8 +1157,8 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
     {
@@ -1169,7 +1167,7 @@
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.",
         "ScaleUnit": "100%"
     },
     {
@@ -1177,8 +1175,8 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
     {
@@ -1187,7 +1185,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1196,7 +1194,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1232,7 +1230,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1241,7 +1239,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1259,43 +1257,43 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1304,8 +1302,8 @@
         "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
@@ -1313,8 +1311,8 @@
         "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM",
+        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1334,7 +1332,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1342,8 +1340,8 @@
         "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -1351,7 +1349,7 @@
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1360,8 +1358,8 @@
         "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1369,8 +1367,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -1379,8 +1377,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1396,7 +1394,7 @@
         "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -1405,8 +1403,8 @@
         "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json b/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json
index 8bad700ff8ea..d113c14aa7c9 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json
@@ -1,5 +1,79 @@
 [
     {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x20"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITI",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITI",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x40"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x8"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xFE",
+        "EventName": "IDI_MISC.WB_DOWNGRADE",
+        "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xFE",
+        "EventName": "IDI_MISC.WB_UPGRADE",
+        "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2"
+    },
+    {
         "BriefDescription": "L1D data line replacements",
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
@@ -2344,6 +2418,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts all demand code reads have any response type.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP OCR.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -2704,6 +2788,116 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F80400004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x80400004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100400004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F80020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x800020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x400020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x200020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x80020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads have any response type.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP OCR.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -3064,6 +3258,116 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F80400001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x80400001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100400001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F80020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x800020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x400020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x200020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x80020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT.ANY_SNOOP OCR.DEMAND_RFO.L3_HIT.ANY_SNOOP",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -3424,6 +3728,106 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F80400002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x80400002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100400002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F80020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x800020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x400020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x200020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x80020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT.ANY_SNOOP OCR.OTHER.L3_HIT.ANY_SNOOP",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index 5729b93a9c68..6485b565acbc 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -313,12 +313,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -330,7 +330,7 @@
         "MetricExpr": "34 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
@@ -341,7 +341,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
     {
@@ -351,12 +351,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -371,7 +371,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -379,7 +379,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -387,22 +387,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -410,7 +410,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -418,7 +418,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
@@ -426,7 +426,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -438,10 +438,10 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -463,8 +463,8 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -472,8 +472,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -481,7 +481,7 @@
         "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -490,7 +490,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -498,33 +498,33 @@
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "((47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + (47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + 44 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -535,25 +535,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
@@ -562,7 +562,7 @@
         "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
@@ -572,7 +572,7 @@
         "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -582,7 +582,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -590,27 +590,27 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+        "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -619,18 +619,18 @@
         "MetricExpr": "(110 * tma_info_system_core_frequency * (OCR.DEMAND_RFO.L3_MISS.REMOTE_HITM + OCR.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_system_core_frequency * (OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OCR.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
     {
@@ -640,7 +640,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -650,7 +650,7 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -670,7 +670,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -679,7 +679,7 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%"
     },
     {
@@ -687,17 +687,17 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@ / UOPS_RETIRED.RETIRE_SLOTS",
+        "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -706,7 +706,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -715,7 +715,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -724,7 +724,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_512b",
-        "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -735,35 +735,35 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
-        "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / tma_info_thread_clks",
+        "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -774,11 +774,11 @@
         "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -803,7 +803,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -812,7 +812,7 @@
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -820,10 +820,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -852,7 +853,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -877,14 +878,14 @@
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@) / (2 * tma_info_core_core_clks)",
+        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -897,20 +898,20 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@ + 2",
+        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency"
     },
@@ -946,7 +947,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -961,11 +962,11 @@
     {
         "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@)",
+        "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -973,7 +974,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -981,7 +982,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -989,7 +990,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx512",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -997,7 +998,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -1005,7 +1006,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -1061,7 +1062,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -1248,8 +1249,8 @@
         "MetricName": "tma_info_memory_tlb_store_stlb_mpki"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -1270,12 +1271,12 @@
         "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -1331,14 +1332,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1356,7 +1356,7 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@",
+        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
@@ -1386,7 +1386,7 @@
         "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks)",
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license0_utilization",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
@@ -1394,7 +1394,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license1_utilization",
         "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)",
@@ -1402,7 +1402,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license2_utilization",
         "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
@@ -1436,7 +1436,7 @@
         "MetricName": "tma_info_system_uncore_frequency"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1445,15 +1445,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1479,15 +1478,15 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 6"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1495,7 +1494,7 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -1504,17 +1503,17 @@
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
+        "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1523,7 +1522,7 @@
         "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1532,17 +1531,17 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(20.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+        "MetricExpr": "17 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1550,18 +1549,18 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1579,7 +1578,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1587,39 +1586,39 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory",
-        "MetricExpr": "(80 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "59.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
         "ScaleUnit": "100%"
     },
@@ -1628,7 +1627,7 @@
         "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1645,10 +1644,10 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1657,7 +1656,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -1669,11 +1668,11 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -1695,7 +1694,7 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -1709,12 +1708,12 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
@@ -1722,7 +1721,7 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
@@ -1732,7 +1731,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%"
     },
     {
@@ -1740,8 +1739,8 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1754,19 +1753,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -1775,7 +1774,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1784,7 +1783,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1820,7 +1819,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1829,7 +1828,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1846,8 +1845,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
@@ -1855,8 +1854,8 @@
         "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
@@ -1864,7 +1863,7 @@
         "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -1873,35 +1872,35 @@
         "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
         "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "((110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory",
-        "MetricExpr": "(147.5 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "127 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1919,7 +1918,7 @@
         "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -1928,8 +1927,8 @@
         "MetricExpr": "40 * ROB_MISC_EVENTS.PAUSE_INST / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: ROB_MISC_EVENTS.PAUSE_INST",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST",
         "ScaleUnit": "100%"
     },
     {
@@ -1939,7 +1938,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1947,8 +1946,8 @@
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -1956,7 +1955,7 @@
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1965,8 +1964,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1974,8 +1973,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -1984,8 +1983,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -2001,7 +2000,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -2009,31 +2008,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -2041,7 +2040,7 @@
         "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -2050,8 +2049,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/other.json b/tools/perf/pmu-events/arch/x86/cascadelakex/other.json
index f25693b17b8b..51833bce994e 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/other.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/other.json
@@ -36,62 +36,6 @@
         "UMask": "0x40"
     },
     {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x20"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x10"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITI",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITI",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x40"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x8"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x4"
-    },
-    {
         "BriefDescription": "Number of hardware interrupts received by the processor.",
         "Counter": "0,1,2,3",
         "EventCode": "0xCB",
@@ -101,24 +45,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xFE",
-        "EventName": "IDI_MISC.WB_DOWNGRADE",
-        "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.",
-        "SampleAfterValue": "100003",
-        "UMask": "0x4"
-    },
-    {
-        "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xFE",
-        "EventName": "IDI_MISC.WB_UPGRADE",
-        "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.",
-        "SampleAfterValue": "100003",
-        "UMask": "0x2"
-    },
-    {
         "BriefDescription": "OCR.ALL_DATA_RD.ANY_RESPONSE have any response type.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -669,336 +595,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts all demand code reads have any response type.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F80400004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x80400004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100400004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F80020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1000020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x800020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x400020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x200020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x80020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads have any response type.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F80400001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x80400001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100400001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F80020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1000020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x800020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x400020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x200020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x80020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F80400002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x80400002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100400002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F80020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1000020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x800020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x400020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x200020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x80020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts any other requests have any response type.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json
index 875361b30f1d..ecb7dc252208 100644
--- a/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json
@@ -22,6 +22,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
+        "PublicDescription": "Counts the number of load ops retired. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x81"
     },
@@ -30,6 +31,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
+        "PublicDescription": "Counts the number of store ops retired. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x82"
     },
@@ -40,6 +42,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x400",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -50,6 +53,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -60,6 +64,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -70,6 +75,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x800",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -80,6 +86,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -90,6 +97,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -100,6 +108,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -110,6 +119,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -120,6 +130,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -130,6 +141,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -138,7 +150,30 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
+        "PublicDescription": "Counts the number of  stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x6"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json
index f5007e56f39b..58e543550279 100644
--- a/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json
@@ -6,6 +6,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x33FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -16,6 +17,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x33FBFC00002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json
deleted file mode 100644
index 80454e497f83..000000000000
--- a/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json
+++ /dev/null
@@ -1,22 +0,0 @@
-[
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    }
-]
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json
index 6a5faa704b85..26bd12fefa3d 100644
--- a/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for.",
+        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003"
     },
     {
@@ -12,7 +12,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
+        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003"
     },
     {
@@ -63,6 +63,7 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired.",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Fixed Counter: Counts the number of instructions retired. Available PDIST counters: 32",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -71,6 +72,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
+        "PublicDescription": "Counts the number of instructions retired. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json b/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json
index 7882dca9d5e1..3410caf8a57a 100644
--- a/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json
@@ -161,6 +161,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x80"
     },
@@ -171,6 +172,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x20"
     },
@@ -181,6 +183,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -191,6 +194,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
     },
@@ -201,6 +205,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -211,6 +216,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x10"
     },
@@ -221,6 +227,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -231,7 +238,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL",
         "PEBS": "1",
-        "PublicDescription": "Counts the number of memory uops retired.  A single uop that performs both a load AND a store will be counted as 1, not 2 (e.g. ADD [mem], CONST)",
+        "PublicDescription": "Counts the number of memory uops retired.  A single uop that performs both a load AND a store will be counted as 1, not 2 (e.g. ADD [mem], CONST) Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x83"
     },
@@ -242,7 +249,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of load uops retired.",
+        "PublicDescription": "Counts the total number of load uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x81"
     },
@@ -253,7 +260,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of store uops retired.",
+        "PublicDescription": "Counts the total number of store uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x82"
     },
@@ -264,6 +271,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that performed one or more locks. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21"
     },
@@ -274,6 +282,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of memory uops retired that were splits. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x43"
     },
@@ -284,6 +293,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x41"
     },
@@ -294,6 +304,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired split store uops. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x42"
     },
@@ -304,6 +315,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -314,6 +326,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -324,6 +337,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -334,6 +348,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -344,6 +359,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -354,6 +370,18 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3000000010000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -364,6 +392,29 @@
         "EventName": "OCR.COREWB_M.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3001F803C0000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.COREWB_M.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8003000000000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -374,6 +425,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -384,6 +436,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -394,6 +447,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -404,6 +458,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -414,6 +469,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -424,6 +480,18 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -434,6 +502,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -444,6 +513,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -454,6 +524,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -464,6 +535,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -474,6 +546,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -484,6 +557,30 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE",
+        "Counter": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -495,6 +592,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -506,6 +604,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HITM Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -517,6 +616,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_NO_FWD Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -528,6 +628,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_WITH_FWD Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -539,6 +640,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_MISS Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -550,6 +652,30 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_NOT_NEEDED Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING",
+        "Counter": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -560,6 +686,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -570,6 +697,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -580,6 +708,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -590,6 +719,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -600,6 +730,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -610,6 +741,18 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_RFO.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -620,6 +763,18 @@
         "EventName": "OCR.FULL_STREAMING_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x801F803C0000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10400",
+        "PublicDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -630,6 +785,18 @@
         "EventName": "OCR.HWPF_L1D_AND_SWPF.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0400",
+        "PublicDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -640,6 +807,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -650,6 +818,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -660,6 +829,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -670,6 +840,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -680,6 +851,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -690,6 +862,29 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_CODE_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -700,6 +895,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -710,6 +906,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -720,6 +917,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -730,6 +928,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -740,6 +939,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -750,6 +950,18 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -760,6 +972,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -770,6 +983,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -780,6 +994,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -790,6 +1005,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -800,6 +1016,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -810,6 +1027,29 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_RFO.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.L1WB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000000010000",
+        "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -820,6 +1060,18 @@
         "EventName": "OCR.L1WB_M.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1001F803C0000",
+        "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.L2WB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000000010000",
+        "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -830,6 +1082,7 @@
         "EventName": "OCR.L2WB_M.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2001F803C0000",
+        "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -840,6 +1093,18 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x401F803C0000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -850,6 +1115,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -860,6 +1126,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -870,6 +1137,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -880,6 +1148,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -890,6 +1159,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -900,6 +1170,18 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.READS_TO_CORE.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -910,6 +1192,7 @@
         "EventName": "OCR.STREAMING_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0800",
+        "PublicDescription": "Counts streaming stores that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -920,6 +1203,7 @@
         "EventName": "OCR.UC_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x101F803C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -930,6 +1214,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1010003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -940,6 +1225,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1004003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -950,6 +1236,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -960,6 +1247,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1002003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -970,6 +1258,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1001003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -980,6 +1269,7 @@
         "EventName": "OCR.UC_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x201F803C0000",
+        "PublicDescription": "Counts uncached memory writes that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/floating-point.json b/tools/perf/pmu-events/arch/x86/elkhartlake/floating-point.json
index 79a4beba4b78..f47d97dfe0d9 100644
--- a/tools/perf/pmu-events/arch/x86/elkhartlake/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/elkhartlake/floating-point.json
@@ -23,6 +23,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.FPDIV",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     }
diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json b/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json
index 34306ec24e9b..417cd78fc048 100644
--- a/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json
@@ -13,6 +13,7 @@
         "EventCode": "0x13",
         "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of misaligned load uops that are 4K page splits. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -22,16 +23,29 @@
         "EventCode": "0x13",
         "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of misaligned store uops that are 4K page splits. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
     {
+        "BriefDescription": "Counts all code reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.ALL_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000044",
+        "PublicDescription": "Counts all code reads that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all code reads that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0XB7",
         "EventName": "OCR.ALL_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000044",
+        "PublicDescription": "Counts all code reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -42,6 +56,18 @@
         "EventName": "OCR.ALL_CODE_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000044",
+        "PublicDescription": "Counts all code reads that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all code reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.ALL_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000044",
+        "PublicDescription": "Counts all code reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -52,6 +78,7 @@
         "EventName": "OCR.COREWB_M.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3002184000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -62,6 +89,18 @@
         "EventName": "OCR.COREWB_M.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3002184000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -72,6 +111,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -82,6 +122,29 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -92,6 +155,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -102,6 +166,30 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM",
+        "Counter": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -113,6 +201,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -124,6 +213,30 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS_LOCAL Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM",
+        "Counter": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -134,6 +247,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -144,6 +258,18 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -154,6 +280,7 @@
         "EventName": "OCR.FULL_STREAMING_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x802184000000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -164,6 +291,18 @@
         "EventName": "OCR.FULL_STREAMING_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x802184000000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -174,6 +313,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -184,6 +324,29 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -194,6 +357,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -204,6 +368,29 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -214,6 +401,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -224,6 +412,18 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -234,6 +434,7 @@
         "EventName": "OCR.L1WB_M.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1002184000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -244,6 +445,7 @@
         "EventName": "OCR.L1WB_M.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1002184000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -254,6 +456,7 @@
         "EventName": "OCR.L2WB_M.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2002184000000",
+        "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -264,6 +467,7 @@
         "EventName": "OCR.L2WB_M.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2002184000000",
+        "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -274,6 +478,7 @@
         "EventName": "OCR.OTHER.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184008000",
+        "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -284,6 +489,7 @@
         "EventName": "OCR.OTHER.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184008000",
+        "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -294,6 +500,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x402184000000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -304,6 +511,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x402184000000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -314,6 +522,18 @@
         "EventName": "OCR.PREFETCHES.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000470",
+        "PublicDescription": "Counts all hardware and software prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.READS_TO_CORE.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -324,6 +544,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -334,6 +555,18 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -344,6 +577,7 @@
         "EventName": "OCR.STREAMING_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000800",
+        "PublicDescription": "Counts streaming stores that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -354,6 +588,18 @@
         "EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000800",
+        "PublicDescription": "Counts streaming stores that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.UC_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100184000000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -364,6 +610,7 @@
         "EventName": "OCR.UC_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x102184000000",
+        "PublicDescription": "Counts uncached memory reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -374,6 +621,18 @@
         "EventName": "OCR.UC_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x102184000000",
+        "PublicDescription": "Counts uncached memory reads that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.UC_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100184000000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -384,6 +643,7 @@
         "EventName": "OCR.UC_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x202184000000",
+        "PublicDescription": "Counts uncached memory writes that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -394,6 +654,7 @@
         "EventName": "OCR.UC_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x202184000000",
+        "PublicDescription": "Counts uncached memory writes that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/other.json b/tools/perf/pmu-events/arch/x86/elkhartlake/other.json
index 57613207f7ad..2cdc6b64f31d 100644
--- a/tools/perf/pmu-events/arch/x86/elkhartlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/elkhartlake/other.json
@@ -113,26 +113,7 @@
         "EventName": "OCR.ALL_CODE_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10044",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all code reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.ALL_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000044",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all code reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.ALL_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000044",
+        "PublicDescription": "Counts all code reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -143,180 +124,7 @@
         "EventName": "OCR.ALL_CODE_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "MSRValue": "0x8000000000000044",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3000000010000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.COREWB_M.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8003000000000000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE",
-        "Counter": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM",
-        "Counter": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM",
-        "Counter": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING",
-        "Counter": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_RFO.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000002",
+        "PublicDescription": "Counts all code reads that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -327,146 +135,7 @@
         "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x800000010000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10040",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000040",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000040",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_CODE_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000040",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_RFO.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.L1WB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1000000010000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.L2WB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x2000000010000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -477,6 +146,7 @@
         "EventName": "OCR.OTHER.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x18000",
+        "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -487,6 +157,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x400000010000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -497,46 +168,7 @@
         "EventName": "OCR.PREFETCHES.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10470",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.READS_TO_CORE.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.READS_TO_CORE.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000477",
+        "PublicDescription": "Counts all hardware and software prefetches that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -547,6 +179,7 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -557,26 +190,7 @@
         "EventName": "OCR.UC_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x100000010000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.UC_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100184000000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.UC_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100184000000",
+        "PublicDescription": "Counts uncached memory reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -587,6 +201,7 @@
         "EventName": "OCR.UC_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "MSRValue": "0x8000100000000000",
+        "PublicDescription": "Counts uncached memory reads that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -597,6 +212,7 @@
         "EventName": "OCR.UC_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x200000010000",
+        "PublicDescription": "Counts uncached memory writes that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json b/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json
index e4e7902c1162..0fc2e821b14a 100644
--- a/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json
@@ -5,7 +5,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for.",
+        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for. Available PDIST counters: 0",
         "SampleAfterValue": "200003"
     },
     {
@@ -14,6 +14,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.CALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf9"
     },
@@ -23,6 +24,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xbf"
     },
@@ -32,6 +34,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.IND_CALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -41,6 +44,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.JCC",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -50,6 +54,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NON_RETURN_IND",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -59,6 +64,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.REL_CALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near relative CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfd"
     },
@@ -68,6 +74,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.RETURN",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7"
     },
@@ -77,6 +84,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.TAKEN_JCC",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -86,7 +94,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
+        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "200003"
     },
     {
@@ -95,6 +103,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.IND_CALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -104,6 +113,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.JCC",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -113,6 +123,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -122,6 +133,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RETURN",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7"
     },
@@ -131,6 +143,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.TAKEN_JCC",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -206,7 +219,7 @@
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -216,7 +229,7 @@
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -225,6 +238,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.4K_ALIAS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -234,6 +248,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked for any of the following reasons:  DTLB miss, address alias, store forward or data unknown (includes memory disambiguation blocks and ESP consuming load blocks). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -243,6 +258,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.DATA_UNKNOWN",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -252,6 +268,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.STORE_FORWARD",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked because its address partially overlapped with an older store. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -464,6 +481,7 @@
         "EventCode": "0xc2",
         "EventName": "TOPDOWN_RETIRING.ALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the total number of consumed retirement slots. Available PDIST counters: 0",
         "SampleAfterValue": "1000003"
     },
     {
@@ -480,6 +498,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.ALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the total number of uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -488,6 +507,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.IDIV",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of integer divide uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -497,7 +517,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.MS",
         "PEBS": "1",
-        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.",
+        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -507,6 +527,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.X87",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of x87 uops retired, includes those in MS flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     }
diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/elkhartlake/virtual-memory.json
index f9a6caed8776..bf56d72bb4a7 100644
--- a/tools/perf/pmu-events/arch/x86/elkhartlake/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/elkhartlake/virtual-memory.json
@@ -242,6 +242,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.DTLB_MISS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked due to a first level TLB miss. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -252,6 +253,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of memory uops retired that missed in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x13"
     },
@@ -262,6 +264,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that miss in the second Level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x11"
     },
@@ -272,6 +275,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of store uops retired that miss in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x12"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json
index 3b0581151d63..10bdb193c16f 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json
@@ -4,6 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.HWPF_MISS",
+        "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -12,7 +13,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.REPLACEMENT",
-        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -21,7 +22,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -32,7 +33,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS",
-        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -42,6 +43,7 @@
         "Deprecated": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALL",
+        "PublicDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -50,7 +52,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALLS",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -59,7 +61,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING",
-        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -69,7 +71,7 @@
         "CounterMask": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
-        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -78,7 +80,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x25",
         "EventName": "L2_LINES_IN.ALL",
-        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1f"
     },
@@ -87,7 +89,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.NON_SILENT",
-        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
+        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -96,7 +98,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.SILENT",
-        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -105,7 +107,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.USELESS_HWPF",
-        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
+        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -114,7 +116,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.ALL",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff"
     },
@@ -123,7 +125,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f"
     },
@@ -132,7 +134,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "PublicDescription": "Counts the total number of L2 code requests.",
+        "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe4"
     },
@@ -141,7 +143,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe1"
     },
@@ -150,7 +152,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "PublicDescription": "Counts demand requests that miss L2 cache.",
+        "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x27"
     },
@@ -159,7 +161,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
-        "PublicDescription": "Counts demand requests to L2 cache.",
+        "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe7"
     },
@@ -168,6 +170,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_HWPF",
+        "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf0"
     },
@@ -176,7 +179,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_RFO",
-        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe2"
     },
@@ -185,7 +188,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
+        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc4"
     },
@@ -194,7 +197,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+        "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x24"
     },
@@ -203,7 +206,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc1"
     },
@@ -212,7 +215,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
-        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21"
     },
@@ -221,6 +224,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.HWPF_MISS",
+        "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x30"
     },
@@ -229,7 +233,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f"
     },
@@ -238,7 +242,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.REFERENCES",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff"
     },
@@ -247,7 +251,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_HIT",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc2"
     },
@@ -256,7 +260,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_MISS",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x22"
     },
@@ -265,7 +269,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_HIT",
-        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc8"
     },
@@ -274,7 +278,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_MISS",
-        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x28"
     },
@@ -283,7 +287,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x23",
         "EventName": "L2_TRANS.L2_WB",
-        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+        "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x40"
     },
@@ -292,7 +296,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.MISS",
-        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41"
     },
@@ -301,7 +305,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4f"
     },
@@ -311,7 +315,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
+        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x81"
     },
@@ -321,7 +325,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts all retired store instructions.",
+        "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x82"
     },
@@ -331,7 +335,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+        "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x83"
     },
@@ -341,7 +345,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PublicDescription": "Counts retired load instructions with locked access.",
+        "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x21"
     },
@@ -351,7 +355,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41"
     },
@@ -361,7 +365,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x42"
     },
@@ -371,7 +375,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x11"
     },
@@ -381,7 +385,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x12"
     },
@@ -390,7 +394,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY",
-        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)",
+        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfd"
     },
@@ -400,7 +404,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x4"
     },
@@ -410,7 +414,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1"
     },
@@ -420,7 +424,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
+        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -430,7 +434,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x2"
     },
@@ -440,7 +444,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
-        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
+        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -450,6 +454,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -459,7 +464,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
-        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.",
+        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -469,6 +474,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
+        "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -478,7 +484,7 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x4"
     },
@@ -488,7 +494,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
     },
@@ -498,7 +504,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -508,7 +514,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
     },
@@ -518,7 +524,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -528,7 +534,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x10"
     },
@@ -538,7 +544,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x4"
     },
@@ -548,7 +554,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x20"
     },
@@ -557,6 +563,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x44",
         "EventName": "MEM_STORE_RETIRED.L2_HIT",
+        "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -565,17 +572,29 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe5",
         "EventName": "MEM_UOP_RETIRED.ANY",
-        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses",
+        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -586,6 +605,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -596,6 +616,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -606,6 +627,18 @@
         "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -616,6 +649,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0001",
+        "PublicDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -626,6 +660,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -636,6 +671,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -646,6 +682,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -656,6 +693,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1030000001",
+        "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -666,6 +704,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x830000001",
+        "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -676,6 +715,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008000001",
+        "PublicDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -686,6 +726,18 @@
         "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808000001",
+        "PublicDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F3FFC0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -696,6 +748,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -706,6 +759,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -716,6 +770,7 @@
         "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -726,6 +781,40 @@
         "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.HWPF_L1D.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10400",
+        "PublicDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.HWPF_L2.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10070",
+        "PublicDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.HWPF_L3.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x12380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -736,6 +825,40 @@
         "EventName": "OCR.HWPF_L3.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x80082380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.HWPF_L3.REMOTE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x90002380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10808",
+        "PublicDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F3FFC4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -746,6 +869,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -756,6 +880,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -766,6 +891,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -776,6 +902,18 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F33004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -786,6 +924,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1830004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -796,6 +935,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1030004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -806,6 +946,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x830004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -816,6 +957,7 @@
         "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -826,6 +968,7 @@
         "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -836,6 +979,7 @@
         "EventName": "OCR.RFO_TO_CORE.L3_HIT_M",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F80040022",
+        "PublicDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -846,6 +990,7 @@
         "EventName": "OCR.STREAMING_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x80080800",
+        "PublicDescription": "Counts streaming stores that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -854,6 +999,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
+        "PublicDescription": "OFFCORE_REQUESTS.ALL_REQUESTS Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -862,7 +1008,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DATA_RD",
-        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -871,7 +1017,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
-        "PublicDescription": "Counts both cacheable and non-cacheable code read requests.",
+        "PublicDescription": "Counts both cacheable and non-cacheable code read requests. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -880,7 +1026,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -889,7 +1035,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
-        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -899,6 +1045,7 @@
         "Deprecated": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "PublicDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -908,6 +1055,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -917,7 +1065,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -927,6 +1075,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -936,6 +1085,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -944,6 +1094,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -952,7 +1103,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -961,7 +1112,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
+        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -970,7 +1121,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x2c",
         "EventName": "SQ_MISC.BUS_LOCK",
-        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
+        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -979,6 +1130,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.ANY",
+        "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xf"
     },
@@ -987,7 +1139,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.NTA",
-        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -996,7 +1148,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
-        "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -1005,7 +1157,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T0",
-        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -1014,7 +1166,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T1_T2",
-        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json
index d3b51fa6ec1c..34e1cbcd722c 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json
@@ -300,7 +300,7 @@
         "ScaleUnit": "1per_instr"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -312,7 +312,7 @@
         "MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks",
         "MetricGroup": "BvCB;Compute;HPC;Server;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_amx_busy",
-        "MetricThreshold": "tma_amx_busy > 0.5 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_amx_busy > 0.5 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -320,12 +320,12 @@
         "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
         "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
@@ -335,7 +335,7 @@
     {
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -351,12 +351,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -371,7 +371,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -379,7 +379,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -387,22 +387,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * tma_amx_busy / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -410,7 +410,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -418,7 +418,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
@@ -426,7 +426,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -438,10 +438,10 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -450,7 +450,7 @@
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -463,24 +463,24 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
         "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c01_wait",
-        "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
         "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c02_wait",
-        "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -488,8 +488,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -497,24 +497,24 @@
         "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
         "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -522,7 +522,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -530,32 +530,33 @@
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricExpr": "((81 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(76.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 74.6 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -566,24 +567,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricExpr": "(79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "74.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
@@ -592,8 +594,8 @@
         "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -601,7 +603,7 @@
         "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -611,7 +613,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -619,34 +621,34 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
-        "MetricExpr": "(170 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks",
+        "MetricExpr": "(170 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_MISS@offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -667,7 +669,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -678,7 +680,7 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -696,7 +698,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -705,15 +707,15 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -721,8 +723,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -730,8 +732,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.VECTOR + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -739,8 +741,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -748,8 +750,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -757,8 +759,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_512b",
-        "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -769,27 +771,27 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%"
     },
     {
@@ -797,8 +799,8 @@
         "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -809,28 +811,28 @@
         "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -858,7 +860,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -866,7 +868,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -874,10 +876,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -938,11 +941,11 @@
         "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -955,20 +958,20 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency"
     },
@@ -1005,13 +1008,13 @@
     },
     {
         "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
-        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed",
         "MetricName": "tma_info_frontend_unknown_branch_cost",
-        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node"
+        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node."
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -1029,7 +1032,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -1037,7 +1040,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -1045,7 +1048,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -1053,7 +1056,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx512",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -1061,7 +1064,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate)",
@@ -1069,7 +1072,7 @@
         "MetricGroup": "Flops;FpScalar;InsType;Server",
         "MetricName": "tma_info_inst_mix_iparith_scalar_hp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_hp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -1077,7 +1080,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -1132,7 +1135,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 13",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -1269,7 +1272,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp"
     },
@@ -1334,21 +1337,21 @@
         "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_soc_r2c_dram_bw",
-        "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW"
+        "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW."
     },
     {
         "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)",
         "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_soc_r2c_l3m_bw",
-        "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW"
+        "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW."
     },
     {
         "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)",
         "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_soc_r2c_offcore_bw",
-        "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches"
+        "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches."
     },
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
@@ -1376,8 +1379,8 @@
         "MetricName": "tma_info_memory_tlb_store_stlb_mpki"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -1398,18 +1401,18 @@
         "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "MicroSeq;Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1"
@@ -1472,14 +1475,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1490,7 +1492,7 @@
     },
     {
         "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]",
-        "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@",
+        "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@",
         "MetricGroup": "MemOffcore;MemoryLat;Server;SoC",
         "MetricName": "tma_info_system_mem_dram_read_latency",
         "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches"
@@ -1500,11 +1502,11 @@
         "MetricExpr": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH / UNC_CHA_CLOCKTICKS",
         "MetricGroup": "LockCont;MemOffcore;Server;SoC",
         "MetricName": "tma_info_system_mem_irq_duplicate_address",
-        "MetricThreshold": "(tma_info_system_mem_irq_duplicate_address > 0.1)"
+        "MetricThreshold": "tma_info_system_mem_irq_duplicate_address > 0.1"
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@",
+        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
@@ -1538,7 +1540,7 @@
     },
     {
         "BriefDescription": "Socket actual clocks when any core is active on that socket",
-        "MetricExpr": "cha_0@event\\=0x0@",
+        "MetricExpr": "uncore_cha_0@event\\=0x1@",
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_socket_clks"
     },
@@ -1568,7 +1570,7 @@
         "MetricName": "tma_info_system_upi_data_transmit_bw"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1577,15 +1579,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1595,13 +1596,13 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "TOPDOWN.SLOTS",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots"
     },
     {
         "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
+        "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)",
         "MetricGroup": "SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots_utilization"
     },
@@ -1617,14 +1618,14 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 9"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1633,7 +1634,7 @@
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_int_operations",
         "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.",
         "ScaleUnit": "100%"
     },
     {
@@ -1641,8 +1642,8 @@
         "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_128b",
-        "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1650,8 +1651,8 @@
         "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_256b",
-        "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1659,8 +1660,8 @@
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1668,7 +1669,7 @@
         "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -1677,7 +1678,7 @@
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
@@ -1686,16 +1687,17 @@
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "4.4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1704,17 +1706,18 @@
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(37 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "32.6 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1722,19 +1725,19 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "DefaultMetricgroupName": "TopdownL2",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1751,7 +1754,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1759,39 +1762,39 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory",
-        "MetricExpr": "(109 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "72 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
         "ScaleUnit": "100%"
     },
@@ -1800,7 +1803,7 @@
         "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1816,19 +1819,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling)",
+        "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).",
         "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group",
         "MetricName": "tma_mba_stalls",
-        "MetricThreshold": "tma_mba_stalls > 0.1 & tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mba_stalls > 0.1 & (tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1837,32 +1840,32 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
-        "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -1883,7 +1886,7 @@
         "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -1897,17 +1900,17 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
-        "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
+        "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
         "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
@@ -1915,11 +1918,11 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
-        "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks",
+        "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
     {
@@ -1928,7 +1931,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%"
     },
     {
@@ -1936,7 +1939,7 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%"
     },
@@ -1950,19 +1953,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -1971,7 +1974,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_page_faults",
         "MetricThreshold": "tma_page_faults > 0.05",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.",
         "ScaleUnit": "100%"
     },
     {
@@ -1980,7 +1983,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1989,7 +1992,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1998,7 +2001,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -2006,8 +2009,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
@@ -2015,8 +2018,8 @@
         "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(RS.EMPTY_RESOURCE - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
@@ -2024,7 +2027,7 @@
         "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -2034,8 +2037,8 @@
         "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
@@ -2044,32 +2047,32 @@
         "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues",
-        "MetricExpr": "((170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory",
-        "MetricExpr": "(190 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "153 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2082,7 +2085,7 @@
         "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks + tma_c02_wait",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -2091,8 +2094,8 @@
         "MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_shuffles_256b",
-        "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+        "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.",
         "ScaleUnit": "100%"
     },
     {
@@ -2101,7 +2104,7 @@
         "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
         "ScaleUnit": "100%"
     },
@@ -2111,7 +2114,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -2119,8 +2122,8 @@
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -2128,7 +2131,7 @@
         "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -2137,8 +2140,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -2146,8 +2149,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -2155,8 +2158,8 @@
         "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -2173,7 +2176,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -2181,31 +2184,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -2213,7 +2216,7 @@
         "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%"
     },
@@ -2222,7 +2225,7 @@
         "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "ScaleUnit": "100%"
     },
@@ -2231,8 +2234,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json
index bc475e163227..8c9207750c82 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json
@@ -5,6 +5,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FPDIV_ACTIVE",
+        "PublicDescription": "ARITH.FPDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -13,7 +14,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.FP",
-        "PublicDescription": "Counts all microcode Floating Point assists.",
+        "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -22,6 +23,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.SSE_AVX_MIX",
+        "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -30,6 +32,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -38,6 +41,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -46,6 +50,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_5",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -54,6 +59,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -62,6 +68,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -70,6 +77,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V2",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -78,7 +86,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -87,7 +95,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -96,7 +104,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -105,7 +113,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -114,7 +122,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x18"
     },
@@ -123,7 +131,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x40"
     },
@@ -132,7 +140,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 16 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 16 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -141,7 +149,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x60"
     },
@@ -150,7 +158,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -159,7 +167,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -168,7 +176,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -177,7 +185,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.VECTOR",
-        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfc"
     },
@@ -186,6 +194,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -194,6 +203,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -202,6 +212,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -210,6 +221,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -218,7 +230,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.SCALAR",
-        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x3"
     },
@@ -227,6 +239,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -235,7 +248,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.VECTOR",
-        "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1c"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json
index bf68493d4509..9fe9d62b867a 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x60",
         "EventName": "BACLEARS.ANY",
-        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -13,7 +13,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.LCP",
-        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -22,6 +22,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.MS_BUSY",
+        "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x2"
     },
@@ -30,7 +31,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x61",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
+        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -41,7 +42,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -52,7 +53,7 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -63,7 +64,7 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -74,7 +75,7 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -85,7 +86,7 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -96,7 +97,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600106",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -107,7 +108,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -118,7 +119,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -129,7 +130,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -140,7 +141,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -151,7 +152,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -162,7 +163,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -173,7 +174,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -184,7 +185,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -195,7 +196,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -206,7 +207,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -217,6 +218,7 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -227,7 +229,7 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -238,6 +240,7 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
+        "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -246,7 +249,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALLS",
-        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
+        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4"
     },
@@ -257,6 +260,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALL_PERIODS",
+        "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4"
     },
@@ -265,7 +269,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x83",
         "EventName": "ICACHE_TAG.STALLS",
-        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -275,7 +279,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -285,7 +289,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -294,7 +298,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -304,7 +308,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -314,7 +318,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -323,7 +327,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -333,7 +337,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_CYCLES_ANY",
-        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -344,7 +348,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_SWITCHES",
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -353,7 +357,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).",
+        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -362,7 +366,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -372,7 +376,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -383,7 +387,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -392,7 +396,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -402,7 +406,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -413,7 +417,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json
index 41d4120d4dae..7c3f9b76d367 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json
@@ -5,6 +5,7 @@
         "CounterMask": "6",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
+        "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x6"
     },
@@ -13,7 +14,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
+        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -23,6 +24,7 @@
         "CounterMask": "2",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -32,6 +34,7 @@
         "CounterMask": "3",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -41,7 +44,7 @@
         "CounterMask": "5",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS",
-        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -51,7 +54,7 @@
         "CounterMask": "9",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS",
-        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9"
     },
@@ -169,17 +172,62 @@
         "Data_LA": "1",
         "EventCode": "0xcd",
         "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
-        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
+        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -190,6 +238,51 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x730000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to another socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -200,6 +293,29 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F3FC00002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -210,6 +326,7 @@
         "EventName": "OCR.HWPF_L3.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x94002380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that missed the local socket's L1, L2, and L3 caches. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -220,6 +337,18 @@
         "EventName": "OCR.HWPF_L3.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x84002380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -230,6 +359,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F3FC04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -240,6 +370,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F04C04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -250,6 +381,62 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL_SOCKET",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x70CC04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that missed the L3 Cache and were supplied by the local socket (DRAM or PMM), whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM or DRAM accesses that are controlled by the close or distant SNC Cluster.  It does not count misses to the L3 which go to Local CXL Type 2 Memory or Local Non DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x70C004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x730004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x733004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -260,6 +447,7 @@
         "EventName": "OCR.STREAMING_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x94000800",
+        "PublicDescription": "Counts streaming stores that missed the local socket's L1, L2, and L3 caches. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -270,6 +458,18 @@
         "EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x84000800",
+        "PublicDescription": "Counts streaming stores that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.WRITE_ESTIMATE.MEMORY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0xFBFF80822",
+        "PublicDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM) Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -278,6 +478,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -286,7 +487,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.",
+        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -295,7 +496,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PublicDescription": "Counts the number of times RTM abort was triggered.",
+        "PublicDescription": "Counts the number of times RTM abort was triggered. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -304,7 +505,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_EVENTS",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -313,7 +514,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_MEM",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -322,7 +523,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x40"
     },
@@ -331,7 +532,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -340,7 +541,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.COMMIT",
-        "PublicDescription": "Counts the number of times RTM commit succeeded.",
+        "PublicDescription": "Counts the number of times RTM commit succeeded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -349,7 +550,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.START",
-        "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.",
+        "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -358,7 +559,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x54",
         "EventName": "TX_MEM.ABORT_CAPACITY_READ",
-        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads",
+        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -367,7 +568,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x54",
         "EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
-        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.",
+        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -376,7 +577,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x54",
         "EventName": "TX_MEM.ABORT_CONFLICT",
-        "PublicDescription": "Counts the number of times a TSX line had a cache conflict.",
+        "PublicDescription": "Counts the number of times a TSX line had a cache conflict. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json
index c424facf1b95..a58d65556609 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json
@@ -4,354 +4,28 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.PAGE_FAULT",
+        "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
     {
-        "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb7",
-        "EventName": "EXE.AMX_BUSY",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x730000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F3FFC0002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.HWPF_L1D.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.HWPF_L2.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10070",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.HWPF_L3.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x12380",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.HWPF_L3.REMOTE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x90002380",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10808",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F3FFC4477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x70C004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F33004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x730004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x733004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.WRITE_ESTIMATE.MEMORY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0xFBFF80822",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7"
-    },
-    {
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "CounterMask": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_COUNT",
-        "Invert": "1",
-        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7"
-    },
-    {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_RESOURCE",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "CounterMask": "1",
-        "Deprecated": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS_EMPTY.COUNT",
-        "Invert": "1",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "Deprecated": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS_EMPTY.CYCLES",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7"
-    },
-    {
         "BriefDescription": "Cycles the uncore cannot take further requests",
         "Counter": "0,1,2,3",
         "CounterMask": "1",
         "EventCode": "0x2d",
         "EventName": "XQ.FULL_CYCLES",
-        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).",
+        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
index 50cacfbbc7cf..00b05a77c289 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
@@ -6,6 +6,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9"
     },
@@ -15,7 +16,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.DIV_ACTIVE",
-        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
+        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9"
     },
@@ -26,6 +27,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FP_DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -35,6 +37,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.IDIV_ACTIVE",
+        "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -45,6 +48,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.INT_DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -53,7 +57,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.ANY",
-        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.",
+        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1b"
     },
@@ -62,7 +66,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all branch instructions retired.",
+        "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009"
     },
     {
@@ -70,7 +74,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
-        "PublicDescription": "Counts conditional branch instructions retired.",
+        "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11"
     },
@@ -79,7 +83,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts not taken branch instructions retired.",
+        "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10"
     },
@@ -88,7 +92,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional branch instructions retired.",
+        "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1"
     },
@@ -97,7 +101,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "PublicDescription": "Counts far branch instructions retired.",
+        "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
     },
@@ -106,7 +110,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
-        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -115,7 +119,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2"
     },
@@ -124,7 +128,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "Counts return instructions retired.",
+        "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -133,7 +137,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts taken branch instructions retired.",
+        "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
     },
@@ -142,7 +146,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "400009"
     },
     {
@@ -150,7 +154,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
-        "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11"
     },
@@ -159,7 +163,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
+        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10"
     },
@@ -168,7 +172,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1"
     },
@@ -177,7 +181,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
-        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -186,7 +190,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
-        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
+        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x2"
     },
@@ -195,7 +199,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
     },
@@ -204,7 +208,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -213,7 +217,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C01",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -222,7 +226,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C02",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -231,7 +235,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C0_WAIT",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x70"
     },
@@ -240,7 +244,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED",
-        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -249,7 +253,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.",
+        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0",
         "SampleAfterValue": "25003",
         "UMask": "0x2"
     },
@@ -258,6 +262,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40"
     },
@@ -268,6 +273,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE_INST",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40"
     },
@@ -276,7 +282,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED",
-        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -293,7 +299,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
-        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -310,7 +316,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -319,6 +325,7 @@
         "CounterMask": "8",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -328,6 +335,7 @@
         "CounterMask": "1",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -337,6 +345,7 @@
         "CounterMask": "16",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -346,6 +355,7 @@
         "CounterMask": "12",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc"
     },
@@ -355,6 +365,7 @@
         "CounterMask": "5",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -364,15 +375,25 @@
         "CounterMask": "4",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "PublicDescription": "Total execution stalls. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
     {
+        "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb7",
+        "EventName": "EXE.AMX_BUSY",
+        "PublicDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation. Available PDIST counters: 0",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
+    },
+    {
         "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -381,6 +402,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0xc"
     },
@@ -389,7 +411,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -398,7 +420,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -407,7 +429,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -417,6 +439,7 @@
         "CounterMask": "5",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS",
+        "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x21"
     },
@@ -426,7 +449,7 @@
         "CounterMask": "2",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
-        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.",
+        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -435,7 +458,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
-        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.",
+        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80"
     },
@@ -444,7 +467,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x75",
         "EventName": "INST_DECODED.DECODERS",
-        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.",
+        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -452,7 +475,7 @@
         "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -469,6 +492,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -477,7 +501,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
-        "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions",
+        "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -485,7 +509,7 @@
         "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.PREC_DIST",
-        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
+        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -494,7 +518,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -505,7 +529,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEARS_COUNT",
-        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears",
+        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -514,7 +538,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
-        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
+        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x80"
     },
@@ -523,6 +547,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.MBA_STALLS",
+        "PublicDescription": "INT_MISC.MBA_STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -531,7 +556,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.RECOVERY_CYCLES",
-        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -542,6 +567,7 @@
         "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x7",
+        "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -550,7 +576,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.UOP_DROPPING",
-        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons",
+        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -559,6 +585,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.128BIT",
+        "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x13"
     },
@@ -567,6 +594,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.256BIT",
+        "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xac"
     },
@@ -575,7 +603,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_128",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -584,7 +612,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_256",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc"
     },
@@ -593,6 +621,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.MUL_256",
+        "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80"
     },
@@ -601,6 +630,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.SHUFFLES",
+        "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -609,6 +639,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_128",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -617,6 +648,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_256",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -625,7 +657,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
-        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.",
+        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -634,7 +666,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.NO_SR",
-        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x88"
     },
@@ -643,7 +675,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.STORE_FORWARD",
-        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
+        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x82"
     },
@@ -652,7 +684,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x4c",
         "EventName": "LOAD_HIT_PREFETCH.SWPF",
-        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -662,7 +694,7 @@
         "CounterMask": "1",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_ACTIVE",
-        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -672,7 +704,7 @@
         "CounterMask": "6",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_OK",
-        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -681,7 +713,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa8",
         "EventName": "LSD.UOPS",
-        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -692,7 +724,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.COUNT",
-        "PublicDescription": "Counts the number of machine clears (nukes) of any type.",
+        "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -701,7 +733,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SMC",
-        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -710,7 +742,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe0",
         "EventName": "MISC2_RETIRED.LFENCE",
-        "PublicDescription": "number of LFENCE retired instructions",
+        "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
     },
@@ -719,7 +751,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcc",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
-        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -728,7 +760,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SB",
-        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -737,15 +769,69 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SCOREBOARD",
+        "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_COUNT",
+        "Invert": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_RESOURCE",
+        "PublicDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "Deprecated": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS_EMPTY.COUNT",
+        "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "Deprecated": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS_EMPTY.CYCLES",
+        "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7"
+    },
+    {
         "BriefDescription": "TMA slots where no uops were being issued due to lack of back-end resources.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
-        "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.",
+        "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x2"
     },
@@ -754,7 +840,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BAD_SPEC_SLOTS",
-        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.",
+        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x4"
     },
@@ -763,7 +849,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
-        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.",
+        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x8"
     },
@@ -772,6 +858,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS",
+        "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x10"
     },
@@ -788,7 +875,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.SLOTS_P",
-        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.",
+        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x1"
     },
@@ -797,6 +884,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x76",
         "EventName": "UOPS_DECODED.DEC0_UOPS",
+        "PublicDescription": "UOPS_DECODED.DEC0_UOPS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -805,7 +893,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_0",
-        "PublicDescription": "Number of uops dispatch to execution  port 0.",
+        "PublicDescription": "Number of uops dispatch to execution  port 0. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -814,7 +902,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_1",
-        "PublicDescription": "Number of uops dispatch to execution  port 1.",
+        "PublicDescription": "Number of uops dispatch to execution  port 1. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -823,7 +911,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_2_3_10",
-        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10",
+        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -832,7 +920,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_4_9",
-        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9",
+        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -841,7 +929,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_5_11",
-        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11",
+        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -850,7 +938,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_6",
-        "PublicDescription": "Number of uops dispatch to execution  port 6.",
+        "PublicDescription": "Number of uops dispatch to execution  port 6. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40"
     },
@@ -859,7 +947,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_7_8",
-        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8.",
+        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x80"
     },
@@ -868,7 +956,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE",
-        "PublicDescription": "Counts the number of uops executed from any thread.",
+        "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -878,7 +966,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -888,7 +976,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -898,7 +986,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -908,7 +996,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -918,7 +1006,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_1",
-        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -928,7 +1016,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_2",
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -938,7 +1026,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_3",
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -948,7 +1036,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_4",
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -959,7 +1047,7 @@
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.STALLS",
         "Invert": "1",
-        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -971,6 +1059,7 @@
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.STALL_CYCLES",
         "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -979,6 +1068,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.THREAD",
+        "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -987,7 +1077,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.X87",
-        "PublicDescription": "Counts the number of x87 uops executed.",
+        "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -996,7 +1086,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.ANY",
-        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1006,6 +1096,7 @@
         "CounterMask": "1",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.CYCLES",
+        "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1015,7 +1106,7 @@
         "CounterMask": "1",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.CYCLES",
-        "PublicDescription": "Counts cycles where at least one uop has retired.",
+        "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -1024,7 +1115,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.HEAVY",
-        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.",
+        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1035,6 +1126,7 @@
         "EventName": "UOPS_RETIRED.MS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -1043,7 +1135,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.SLOTS",
-        "PublicDescription": "Counts the retirement slots used each cycle.",
+        "PublicDescription": "Counts the retirement slots used each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -1054,7 +1146,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.STALLS",
         "Invert": "1",
-        "PublicDescription": "This event counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -1066,6 +1158,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json
index 609a9549cbf3..3d3f88600e26 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
-        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
+        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -14,7 +14,7 @@
         "CounterMask": "1",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -23,7 +23,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
@@ -32,7 +32,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -41,7 +41,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -50,7 +50,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -59,7 +59,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -68,7 +68,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.STLB_HIT",
-        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
+        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -78,7 +78,7 @@
         "CounterMask": "1",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -87,7 +87,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
@@ -96,7 +96,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -105,7 +105,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -114,7 +114,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -123,7 +123,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -132,7 +132,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.STLB_HIT",
-        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
+        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -142,7 +142,7 @@
         "CounterMask": "1",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -151,7 +151,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
@@ -160,7 +160,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -169,7 +169,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -178,7 +178,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     }
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/cache.json b/tools/perf/pmu-events/arch/x86/grandridge/cache.json
index 04802e254e51..877052db1490 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/cache.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/cache.json
@@ -1,5 +1,92 @@
 [
     {
+        "BriefDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x51",
+        "EventName": "DL1.DIRTY_EVICTION",
+        "PublicDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.  Does not count evictions or dirty writebacks caused by snoops.  Does not count a replacement unless a (dirty) line was written back.",
+        "SampleAfterValue": "200003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.E",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.F",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x10"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.M",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.S",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x26",
+        "EventName": "L2_LINES_OUT.NON_SILENT",
+        "PublicDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill. Increments on the core that brought the line in originally.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x26",
+        "EventName": "L2_LINES_OUT.SILENT",
+        "PublicDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill.  Increments on the core that brought the line in originally.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts the number of L2 Cache Accesses that resulted in a Hit from a front door request only (does not include rejects or recycles), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.HIT",
+        "SampleAfterValue": "200003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts the number of total L2 Cache Accesses that resulted in a Miss from a front door request only (does not include rejects or recycles), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.MISS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts the number of L2 Cache Accesses that miss the L2 and get BBL reject  short and long rejects, per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.REJECTS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4"
+    },
+    {
         "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
@@ -35,7 +122,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which hit in the LLC.",
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an ICACHE or ITLB miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x35",
         "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_HIT",
@@ -43,7 +130,7 @@
         "UMask": "0x6"
     },
     {
-        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which missed all the caches.",
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an ICACHE or ITLB miss which missed all the caches. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x35",
         "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_MISS",
@@ -68,7 +155,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC.",
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x34",
         "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT",
@@ -76,7 +163,7 @@
         "UMask": "0x6"
     },
     {
-        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.",
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x34",
         "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS",
@@ -84,6 +171,14 @@
         "UMask": "0x78"
     },
     {
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS_LOAD.SBFULL",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x80"
+    },
+    {
         "BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in DRAM",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xd3",
@@ -336,6 +431,33 @@
         "UMask": "0x42"
     },
     {
+        "BriefDescription": "Counts the number of memory uops retired that missed in the second level TLB.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "Data_LA": "1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.STLB_MISS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x13"
+    },
+    {
+        "BriefDescription": "Counts the number of load uops retired that miss in the second Level TLB.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "Data_LA": "1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x11"
+    },
+    {
+        "BriefDescription": "Counts the number of store uops retired that miss in the second level TLB.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "Data_LA": "1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
+        "SampleAfterValue": "200003",
+        "UMask": "0x12"
+    },
+    {
         "BriefDescription": "Counts the number of  stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES",
         "Counter": "0,1,2,3,4,5,6,7",
         "Data_LA": "1",
@@ -345,12 +467,24 @@
         "UMask": "0x6"
     },
     {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -361,6 +495,18 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -371,6 +517,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/counter.json b/tools/perf/pmu-events/arch/x86/grandridge/counter.json
index 9fd5d8ad6d3b..d9ac3aca5bd5 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/counter.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/counter.json
@@ -37,6 +37,6 @@
     {
         "Unit": "CHACMS",
         "CountersNumFixed": "0",
-        "CountersNumGeneric": 4
+        "CountersNumGeneric": "4"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/frontend.json b/tools/perf/pmu-events/arch/x86/grandridge/frontend.json
index 7cdf611efb23..fef5cba533bb 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/frontend.json
@@ -31,5 +31,13 @@
         "EventName": "ICACHE.MISSES",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the micro-sequencer is busy.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xe7",
+        "EventName": "MS_DECODED.MS_BUSY",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json b/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json
index 2f9959c61718..1c6dba7b2822 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json
@@ -216,15 +216,17 @@
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions",
         "MetricExpr": "tma_core_bound",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_core_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_allocation_restriction",
+        "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls",
         "MetricExpr": "TOPDOWN_BE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
+        "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
+        "MetricThreshold": "tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
         "ScaleUnit": "100%"
@@ -232,92 +234,104 @@
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
+        "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear",
+        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend",
         "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_detect",
-        "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches",
+        "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
+        "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
+        "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
         "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_resteer",
+        "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS)",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).",
         "MetricExpr": "TOPDOWN_FE_BOUND.CISC / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_cisc",
+        "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of cycles due to backend bound stalls that are bounded by core restrictions and not attributed to an outstanding load or stores, or resource limitation",
         "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.",
         "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_decode",
+        "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that does not require the use of microcode, classified as a fast nuke, due to memory ordering, memory disambiguation and memory renaming",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
+        "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls",
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.",
         "MetricExpr": "TOPDOWN_FE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
+        "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
+        "MetricThreshold": "tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.",
         "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_icache_misses",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
         "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_bandwidth",
+        "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations.",
         "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_latency",
+        "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -348,33 +362,28 @@
     {
         "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss",
         "MetricExpr": "100 * (LD_HEAD.DTLB_MISS_AT_RET + LD_HEAD.PGWALK_AT_RET) / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Cycles",
-        "MetricName": "tma_info_bottleneck_dtlb_miss_bound_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_bottleneck_%_dtlb_miss_bound_cycles"
     },
     {
         "BriefDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss",
         "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.ALL / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Cycles;Ifetch",
-        "MetricName": "tma_info_bottleneck_ifetch_miss_bound_cycles",
-        "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound",
-        "ScaleUnit": "100%"
+        "MetricGroup": "Ifetch",
+        "MetricName": "tma_info_bottleneck_%_ifetch_miss_bound_cycles",
+        "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound"
     },
     {
         "BriefDescription": "Percentage of time that retirement is stalled due to an L1 miss",
         "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.ALL / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Cycles;Load_Store_Miss",
-        "MetricName": "tma_info_bottleneck_load_miss_bound_cycles",
-        "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound",
-        "ScaleUnit": "100%"
+        "MetricGroup": "Load_Store_Miss",
+        "MetricName": "tma_info_bottleneck_%_load_miss_bound_cycles",
+        "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound"
     },
     {
         "BriefDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall",
         "MetricExpr": "100 * LD_HEAD.ANY_AT_RET / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Cycles;Mem_Exec",
-        "MetricName": "tma_info_bottleneck_mem_exec_bound_cycles",
-        "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound",
-        "ScaleUnit": "100%"
+        "MetricGroup": "Mem_Exec",
+        "MetricName": "tma_info_bottleneck_%_mem_exec_bound_cycles",
+        "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound"
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -429,26 +438,22 @@
     {
         "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full",
         "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.LD_BUF / CPU_CLK_UNHALTED.CORE",
-        "MetricName": "tma_info_buffer_stalls_load_buffer_stall_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_buffer_stalls_%_load_buffer_stall_cycles"
     },
     {
         "BriefDescription": "Percentage of time that allocation is stalled due to memory reservation stations full",
         "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.RSV / CPU_CLK_UNHALTED.CORE",
-        "MetricName": "tma_info_buffer_stalls_mem_rsv_stall_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_buffer_stalls_%_mem_rsv_stall_cycles"
     },
     {
         "BriefDescription": "Percentage of time that allocation is stalled due to store buffer full",
         "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.ST_BUF / CPU_CLK_UNHALTED.CORE",
-        "MetricName": "tma_info_buffer_stalls_store_buffer_stall_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_buffer_stalls_%_store_buffer_stall_cycles"
     },
     {
         "BriefDescription": "Cycles Per Instruction",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE / INST_RETIRED.ANY",
-        "MetricName": "tma_info_core_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_core_cpi"
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
@@ -469,28 +474,46 @@
     {
         "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2",
         "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.L2_HIT / MEM_BOUND_STALLS_IFETCH.ALL",
-        "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l2hit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit"
+    },
+    {
+        "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss doesn't hit in the L2",
+        "MetricExpr": "100 * (MEM_BOUND_STALLS_IFETCH.LLC_HIT + MEM_BOUND_STALLS_IFETCH.LLC_MISS) / MEM_BOUND_STALLS_IFETCH.ALL",
+        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2miss"
     },
     {
         "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3",
         "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_HIT / MEM_BOUND_STALLS_IFETCH.ALL",
-        "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l3hit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3hit"
+    },
+    {
+        "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss subsequently misses in the L3",
+        "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_MISS / MEM_BOUND_STALLS_IFETCH.ALL",
+        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3miss"
     },
     {
         "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2",
         "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.L2_HIT / MEM_BOUND_STALLS_LOAD.ALL",
         "MetricGroup": "load_store_bound",
-        "MetricName": "tma_info_load_miss_bound_loadmissbound_with_l2hit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit"
+    },
+    {
+        "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses in the L2",
+        "MetricExpr": "100 * (MEM_BOUND_STALLS_LOAD.LLC_HIT + MEM_BOUND_STALLS_LOAD.LLC_MISS) / MEM_BOUND_STALLS_LOAD.ALL",
+        "MetricGroup": "load_store_bound",
+        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2miss"
     },
     {
         "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3",
         "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_HIT / MEM_BOUND_STALLS_LOAD.ALL",
         "MetricGroup": "load_store_bound",
-        "MetricName": "tma_info_load_miss_bound_loadmissbound_with_l3hit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3hit"
+    },
+    {
+        "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses the L3",
+        "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_MISS / MEM_BOUND_STALLS_LOAD.ALL",
+        "MetricGroup": "load_store_bound",
+        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3miss"
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a pipeline block",
@@ -528,44 +551,37 @@
     {
         "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block",
         "MetricExpr": "100 * LD_BLOCKS.ADDRESS_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricName": "tma_info_mem_exec_blocks_loads_with_adressaliasing",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_blocks_%_loads_with_adressaliasing"
     },
     {
         "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block",
         "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricName": "tma_info_mem_exec_blocks_loads_with_storefwdblk",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_blocks_%_loads_with_storefwdblk"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss",
         "MetricExpr": "100 * LD_HEAD.L1_MISS_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_l1miss",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_l1miss"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to other block cases, such as pipeline conflicts, fences, etc",
         "MetricExpr": "100 * LD_HEAD.OTHER_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_otherpipelineblks",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_otherpipelineblks"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a pagewalk",
         "MetricExpr": "100 * LD_HEAD.PGWALK_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_pagewalk",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_pagewalk"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a second level TLB miss",
         "MetricExpr": "100 * LD_HEAD.DTLB_MISS_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_stlbhit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_stlbhit"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a store forward address match",
         "MetricExpr": "100 * LD_HEAD.ST_ADDR_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_storefwding",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_storefwding"
     },
     {
         "BriefDescription": "Instructions per Load",
@@ -595,8 +611,7 @@
     {
         "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction",
         "MetricExpr": "100 * SERIALIZATION.C01_MS_SCB / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricName": "tma_info_serialization_tpause_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_serialization_%_tpause_cycles"
     },
     {
         "BriefDescription": "Average CPU Utilization",
@@ -612,17 +627,20 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.CORE_P:k / CPU_CLK_UNHALTED.CORE",
+        "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE_P@k / CPU_CLK_UNHALTED.CORE",
+        "MetricGroup": "Summary",
         "MetricName": "tma_info_system_kernel_utilization"
     },
     {
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE",
-        "MetricName": "tma_info_system_mux"
+        "MetricName": "tma_info_system_mux",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
     },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
         "MetricName": "tma_info_system_turbo_utilization"
     },
     {
@@ -646,90 +664,102 @@
         "MetricName": "tma_info_uop_mix_x87_uop_ratio"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.",
         "MetricExpr": "TOPDOWN_FE_BOUND.ITLB_MISS / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_itlb_misses",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
+        "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops",
         "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
+        "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops",
         "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
+        "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that requires the use of microcode (slow nuke)",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
+        "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.",
         "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_other_fb",
+        "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.",
         "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_predecode",
+        "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls)",
         "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
+        "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls)",
         "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
+        "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a resource limitation",
         "MetricExpr": "tma_backend_bound - tma_core_bound",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_resource_bound",
+        "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that result in retirement slots",
         "MetricExpr": "TOPDOWN_RETIRING.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
+        "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
+        "MetricThreshold": "tma_retiring > 0.75",
         "MetricgroupNoGroup": "TopdownL1",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS)",
         "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
+        "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/memory.json b/tools/perf/pmu-events/arch/x86/grandridge/memory.json
index 22d23077618e..48b6301e7696 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/memory.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/memory.json
@@ -79,6 +79,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -89,6 +90,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/other.json b/tools/perf/pmu-events/arch/x86/grandridge/other.json
index 28f9a4c3ea84..ea34103a8292 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/other.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/other.json
@@ -9,41 +9,14 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "200003",
-        "UMask": "0x4"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json b/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json
index 40fa4f5ae261..f56d8d816e53 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json
@@ -57,6 +57,14 @@
         "UMask": "0xfb"
     },
     {
+        "BriefDescription": "Counts the number of near indirect JMP branch instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc4",
+        "EventName": "BR_INST_RETIRED.INDIRECT_JMP",
+        "SampleAfterValue": "200003",
+        "UMask": "0xef"
+    },
+    {
         "BriefDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL",
         "Counter": "0,1,2,3,4,5,6,7",
         "Deprecated": "1",
@@ -82,6 +90,30 @@
         "UMask": "0xf7"
     },
     {
+        "BriefDescription": "Counts the number of near taken branch instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc4",
+        "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "SampleAfterValue": "200003",
+        "UMask": "0xc0"
+    },
+    {
+        "BriefDescription": "Counts the number of near relative CALL branch instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc4",
+        "EventName": "BR_INST_RETIRED.REL_CALL",
+        "SampleAfterValue": "200003",
+        "UMask": "0xfd"
+    },
+    {
+        "BriefDescription": "Counts the number of near relative JMP branch instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc4",
+        "EventName": "BR_INST_RETIRED.REL_JMP",
+        "SampleAfterValue": "200003",
+        "UMask": "0xdf"
+    },
+    {
         "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
@@ -122,6 +154,14 @@
         "UMask": "0xfb"
     },
     {
+        "BriefDescription": "Counts the number of mispredicted near indirect JMP branch instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc5",
+        "EventName": "BR_MISP_RETIRED.INDIRECT_JMP",
+        "SampleAfterValue": "200003",
+        "UMask": "0xef"
+    },
+    {
         "BriefDescription": "Counts the number of mispredicted near taken branch instructions retired.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
@@ -185,6 +225,7 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Fixed Counter: Counts the number of instructions retired Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -236,8 +277,9 @@
         "UMask": "0x20"
     },
     {
-        "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.",
+        "BriefDescription": "This event is deprecated.",
         "Counter": "0,1,2,3,4,5,6,7",
+        "Deprecated": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SLOW",
         "SampleAfterValue": "20003",
@@ -260,6 +302,14 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x73",
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json b/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json
index 6a80cf6cbd36..b89ab6e5cfb5 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json
@@ -9,6 +9,16 @@
         "Unit": "CHACMS"
     },
     {
+        "BriefDescription": "Counts the number of cycles FAST trigger is received from the global FAST distress wire.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x34",
+        "EventName": "UNC_CHACMS_RING_SRC_THRTL",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PortMask": "0x000",
+        "Unit": "CHACMS"
+    },
+    {
         "BriefDescription": "Number of CHA clock cycles while the event is enabled",
         "Counter": "0,1,2,3",
         "EventCode": "0x01",
@@ -531,6 +541,26 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "Ingress (from CMS) Allocations : IRQ : Counts number of allocations per cycle into the specified Ingress queue.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x13",
+        "EventName": "UNC_CHA_RxC_INSERTS.IRQ",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Ingress (from CMS) Occupancy : IRQ : Counts number of entries in the specified Ingress queue in each cycle.",
+        "Counter": "0",
+        "EventCode": "0x11",
+        "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "All TOR Inserts",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
@@ -603,7 +633,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Data read opt prefetch from local IA that miss the cache",
+        "BriefDescription": "Data read opt prefetch from local IA",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT_PREF",
@@ -764,7 +794,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Last level cache prefetch read for ownership from local IA that miss the cache",
+        "BriefDescription": "Last level cache prefetch read for ownership from local IA",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFRFO",
@@ -859,7 +889,7 @@
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_LOCAL",
         "PerPkg": "1",
-        "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC",
+        "PublicDescription": "TOR Inserts : Data read opt prefetch from local iA that missed the LLC targeting local memory",
         "UMask": "0xc8a6fe01",
         "Unit": "CHA"
     },
@@ -934,7 +964,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Read for ownership from local IA that miss the cache",
+        "BriefDescription": "Read for ownership from local IA that miss the LLC targeting local memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_LOCAL",
@@ -954,7 +984,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Read for ownership prefetch from local IA that miss the cache",
+        "BriefDescription": "Read for ownership prefetch from local IA that miss the LLC targeting local memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_LOCAL",
@@ -1024,7 +1054,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Read for ownership from local IA that miss the cache",
+        "BriefDescription": "Read for ownership from local IA",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO",
@@ -1034,7 +1064,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Read for ownership prefetch from local IA that miss the cache",
+        "BriefDescription": "Read for ownership prefetch from local IA",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF",
@@ -1406,7 +1436,6 @@
         "Counter": "0",
         "EventCode": "0x36",
         "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT",
-        "Experimental": "1",
         "PerPkg": "1",
         "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores",
         "UMask": "0xc827ff01",
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json b/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json
index e75b3050ccd5..6a11e5505957 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json
@@ -189,6 +189,256 @@
         "Unit": "IMC"
     },
     {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK2",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK3",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x10",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x20",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK2",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x40",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK3",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x80",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode and all pages are closed",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x88",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD_CYCLES",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x89",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x89",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "MR4 temp reading is throttling",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.MR4BLKEN",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "RAPL is throttling",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RAPLBLK",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
         "BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.",
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
@@ -361,6 +611,94 @@
         "Unit": "IMC"
     },
     {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8e",
+        "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8e",
+        "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at High level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8d",
+        "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at High level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8d",
+        "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8b",
+        "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8b",
+        "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8c",
+        "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8c",
+        "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
         "BriefDescription": "Write Pending Queue Allocations",
         "Counter": "0,1,2,3",
         "EventCode": "0x22",
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json
index d155da8610d8..32f99a8a3871 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json
@@ -4,6 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.HWPF_MISS",
+        "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -12,7 +13,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.REPLACEMENT",
-        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -21,7 +22,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -32,7 +33,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS",
-        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -41,7 +42,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALLS",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -50,7 +51,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING",
-        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -60,7 +61,7 @@
         "CounterMask": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
-        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -69,7 +70,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x25",
         "EventName": "L2_LINES_IN.ALL",
-        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1f"
     },
@@ -78,7 +79,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.NON_SILENT",
-        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
+        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -87,7 +88,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.SILENT",
-        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -96,7 +97,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.USELESS_HWPF",
-        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
+        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -105,7 +106,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.ALL",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff"
     },
@@ -114,7 +115,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.HIT",
-        "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]",
+        "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xdf"
     },
@@ -123,7 +124,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f"
     },
@@ -132,7 +133,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "PublicDescription": "Counts the total number of L2 code requests.",
+        "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe4"
     },
@@ -141,7 +142,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe1"
     },
@@ -150,7 +151,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "PublicDescription": "Counts demand requests that miss L2 cache.",
+        "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x27"
     },
@@ -159,7 +160,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
-        "PublicDescription": "Counts demand requests to L2 cache.",
+        "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe7"
     },
@@ -168,6 +169,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_HWPF",
+        "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf0"
     },
@@ -176,7 +178,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_RFO",
-        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe2"
     },
@@ -185,7 +187,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
+        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc4"
     },
@@ -194,7 +196,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+        "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x24"
     },
@@ -203,7 +205,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc1"
     },
@@ -212,7 +214,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
-        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21"
     },
@@ -221,7 +223,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.HIT",
-        "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]",
+        "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xdf"
     },
@@ -230,6 +232,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.HWPF_MISS",
+        "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x30"
     },
@@ -238,7 +241,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f"
     },
@@ -247,7 +250,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.REFERENCES",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff"
     },
@@ -256,7 +259,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_HIT",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc2"
     },
@@ -265,7 +268,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_MISS",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x22"
     },
@@ -274,7 +277,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_HIT",
-        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc8"
     },
@@ -283,7 +286,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_MISS",
-        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x28"
     },
@@ -292,7 +295,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x23",
         "EventName": "L2_TRANS.L2_WB",
-        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+        "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x40"
     },
@@ -301,7 +304,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.MISS",
-        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41"
     },
@@ -310,7 +313,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4f"
     },
@@ -320,7 +323,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
+        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x81"
     },
@@ -330,7 +333,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts all retired store instructions.",
+        "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x82"
     },
@@ -340,7 +343,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+        "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x83"
     },
@@ -350,7 +353,10 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PublicDescription": "Counts retired load instructions with locked access.",
+        "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0",
+        "RetirementLatencyMax": 5156,
+        "RetirementLatencyMean": 63.76,
+        "RetirementLatencyMin": 15,
         "SampleAfterValue": "100007",
         "UMask": "0x21"
     },
@@ -360,7 +366,10 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0",
+        "RetirementLatencyMax": 4704,
+        "RetirementLatencyMean": 3.97,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100003",
         "UMask": "0x41"
     },
@@ -370,7 +379,10 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0",
+        "RetirementLatencyMax": 65535,
+        "RetirementLatencyMean": 19.0,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100003",
         "UMask": "0x42"
     },
@@ -380,7 +392,10 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS",
-        "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0",
+        "RetirementLatencyMax": 3424,
+        "RetirementLatencyMean": 1.57,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100003",
         "UMask": "0x9"
     },
@@ -390,7 +405,10 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES",
-        "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0",
+        "RetirementLatencyMax": 65535,
+        "RetirementLatencyMean": 5.24,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100003",
         "UMask": "0xa"
     },
@@ -400,7 +418,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x11"
     },
@@ -410,7 +428,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x12"
     },
@@ -419,7 +437,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY",
-        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)",
+        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfd"
     },
@@ -429,7 +447,10 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0",
+        "RetirementLatencyMax": 4472,
+        "RetirementLatencyMean": 353.04,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "20011",
         "UMask": "0x4"
     },
@@ -439,7 +460,10 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0",
+        "RetirementLatencyMax": 830,
+        "RetirementLatencyMean": 125.27,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "20011",
         "UMask": "0x1"
     },
@@ -449,7 +473,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
+        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -459,7 +483,10 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
+        "RetirementLatencyMax": 3939,
+        "RetirementLatencyMean": 289.9,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "20011",
         "UMask": "0x2"
     },
@@ -469,7 +496,10 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
-        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
+        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0",
+        "RetirementLatencyMax": 4146,
+        "RetirementLatencyMean": 115.83,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -479,6 +509,10 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM Available PDIST counters: 0",
+        "RetirementLatencyMax": 3572,
+        "RetirementLatencyMean": 430.22,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -488,7 +522,10 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
-        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.",
+        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache. Available PDIST counters: 0",
+        "RetirementLatencyMax": 8552,
+        "RetirementLatencyMean": 125.36,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -498,6 +535,10 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
+        "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM Available PDIST counters: 0",
+        "RetirementLatencyMax": 2580,
+        "RetirementLatencyMean": 135.29,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -507,7 +548,7 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x4"
     },
@@ -517,7 +558,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
     },
@@ -527,7 +568,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -537,7 +578,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
     },
@@ -547,7 +588,10 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0",
+        "RetirementLatencyMax": 7140,
+        "RetirementLatencyMean": 5.71,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -557,7 +601,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x10"
     },
@@ -567,7 +611,10 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0",
+        "RetirementLatencyMax": 5630,
+        "RetirementLatencyMean": 57.64,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100021",
         "UMask": "0x4"
     },
@@ -577,7 +624,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x20"
     },
@@ -586,6 +633,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x44",
         "EventName": "MEM_STORE_RETIRED.L2_HIT",
+        "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -594,17 +642,29 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe5",
         "EventName": "MEM_UOP_RETIRED.ANY",
-        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses",
+        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -615,6 +675,18 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -625,6 +697,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0001",
+        "PublicDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -635,6 +708,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -645,6 +719,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -655,6 +730,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -665,6 +741,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1030000001",
+        "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -675,6 +752,40 @@
         "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x830000001",
+        "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1008000001",
+        "PublicDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x808000001",
+        "PublicDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F3FFC0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -685,6 +796,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -695,6 +807,29 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10808",
+        "PublicDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F3FFC4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -705,6 +840,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -715,6 +851,18 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F33004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -725,6 +873,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1830004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -735,6 +884,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1030004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -745,6 +895,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x830004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -755,6 +906,7 @@
         "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -765,6 +917,7 @@
         "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -775,6 +928,7 @@
         "EventName": "OCR.RFO_TO_CORE.L3_HIT_M",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F80040022",
+        "PublicDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -783,7 +937,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
-        "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..",
+        "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc.. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -792,7 +946,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DATA_RD",
-        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -801,7 +955,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
-        "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.",
+        "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -810,7 +964,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -819,7 +973,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
-        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -829,7 +983,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
-        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -839,7 +993,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -849,6 +1003,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -858,7 +1013,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
-        "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -867,6 +1022,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -875,7 +1031,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -884,7 +1040,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
+        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -893,7 +1049,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
-        "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.",
+        "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -902,7 +1058,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x2c",
         "EventName": "SQ_MISC.BUS_LOCK",
-        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
+        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -911,6 +1067,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.ANY",
+        "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xf"
     },
@@ -919,7 +1076,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.NTA",
-        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -928,7 +1085,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
-        "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -937,7 +1094,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T0",
-        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -946,7 +1103,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T1_T2",
-        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     }
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/counter.json b/tools/perf/pmu-events/arch/x86/graniterapids/counter.json
index 137da7efa8b1..5d3b202eadd3 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/counter.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/counter.json
@@ -73,5 +73,10 @@
         "Unit": "MDF",
         "CountersNumFixed": "0",
         "CountersNumGeneric": "4"
+    },
+    {
+        "Unit": "UBOX",
+        "CountersNumFixed": "0",
+        "CountersNumGeneric": "2"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json b/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json
index 59789eee060c..1832dd952f66 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json
@@ -5,6 +5,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FPDIV_ACTIVE",
+        "PublicDescription": "This event counts the cycles the floating point divider is busy. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -13,7 +14,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.FP",
-        "PublicDescription": "Counts all microcode Floating Point assists.",
+        "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -22,6 +23,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.SSE_AVX_MIX",
+        "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -30,6 +32,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -38,6 +41,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -46,6 +50,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_5",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -54,6 +59,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -62,6 +68,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -70,6 +77,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V2",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -78,7 +86,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -87,7 +95,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -96,7 +104,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -105,7 +113,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -114,7 +122,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x18"
     },
@@ -123,7 +131,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x40"
     },
@@ -132,7 +140,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 16 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 16 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -141,7 +149,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x60"
     },
@@ -150,7 +158,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -159,7 +167,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -168,7 +176,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -177,7 +185,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.VECTOR",
-        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfc"
     },
@@ -186,6 +194,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -194,6 +203,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -202,6 +212,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -210,6 +221,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -218,7 +230,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.SCALAR",
-        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x3"
     },
@@ -227,6 +239,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -235,7 +248,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.VECTOR",
-        "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1c"
     }
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json
index dc81055941b1..b7cd92fbecd5 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x60",
         "EventName": "BACLEARS.ANY",
-        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -13,7 +13,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.LCP",
-        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -22,6 +22,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.MS_BUSY",
+        "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x2"
     },
@@ -30,7 +31,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x61",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
+        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -41,7 +42,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)",
+        "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -52,7 +53,10 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0",
+        "RetirementLatencyMax": 65535,
+        "RetirementLatencyMean": 2.46,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -63,7 +67,7 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -74,7 +78,10 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0",
+        "RetirementLatencyMax": 980,
+        "RetirementLatencyMean": 41.96,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -85,7 +92,10 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0",
+        "RetirementLatencyMax": 1785,
+        "RetirementLatencyMean": 9.83,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -96,7 +106,10 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0",
+        "RetirementLatencyMax": 2854,
+        "RetirementLatencyMean": 137.41,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -107,7 +120,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600106",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -118,7 +131,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -129,7 +142,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -140,7 +153,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -151,7 +164,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -162,7 +175,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -173,7 +186,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -184,7 +197,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -195,7 +208,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -206,7 +219,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -217,7 +230,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -228,7 +241,7 @@
         "EventName": "FRONTEND_RETIRED.LATE_SWPF",
         "MSRIndex": "0x3F7",
         "MSRValue": "0xA",
-        "PublicDescription": "Number of Instruction Cache demand miss in shadow of an on-going i-fetch cache-line triggered by PREFETCHIT0/1 instructions",
+        "PublicDescription": "Number of Instruction Cache demand miss in shadow of an on-going i-fetch cache-line triggered by PREFETCHIT0/1 instructions Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -239,7 +252,7 @@
         "EventName": "FRONTEND_RETIRED.MISP_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PublicDescription": "ANT retired branches that got just mispredicted",
+        "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2"
     },
@@ -250,6 +263,10 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0",
+        "RetirementLatencyMax": 65535,
+        "RetirementLatencyMean": 77.14,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -260,7 +277,10 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0",
+        "RetirementLatencyMax": 754,
+        "RetirementLatencyMean": 206.85,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -271,6 +291,10 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
+        "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0",
+        "RetirementLatencyMax": 532,
+        "RetirementLatencyMean": 3.85,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -279,7 +303,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALLS",
-        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
+        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4"
     },
@@ -290,6 +314,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALL_PERIODS",
+        "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4"
     },
@@ -298,7 +323,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x83",
         "EventName": "ICACHE_TAG.STALLS",
-        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -308,7 +333,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -318,7 +343,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -327,7 +352,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -337,7 +362,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -347,7 +372,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -356,7 +381,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -366,7 +391,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_CYCLES_ANY",
-        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -377,7 +402,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_SWITCHES",
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -386,7 +411,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -395,7 +420,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CORE",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -405,7 +430,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -416,7 +441,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -425,7 +450,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -435,7 +460,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -446,7 +471,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json b/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json
index a345b6874606..af527f7f9d0c 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json
@@ -310,7 +310,7 @@
         "ScaleUnit": "1per_instr"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -322,7 +322,7 @@
         "MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks",
         "MetricGroup": "BvCB;Compute;HPC;Server;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_amx_busy",
-        "MetricThreshold": "tma_amx_busy > 0.5 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_amx_busy > 0.5 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -330,12 +330,12 @@
         "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
         "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
@@ -345,7 +345,7 @@
     {
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -361,12 +361,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -381,7 +381,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -389,7 +389,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -397,22 +397,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * tma_amx_busy / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -420,7 +420,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -428,7 +428,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
@@ -436,7 +436,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -448,10 +448,10 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -460,7 +460,7 @@
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -473,24 +473,24 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
         "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c01_wait",
-        "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
         "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c02_wait",
-        "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -498,8 +498,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -507,24 +507,24 @@
         "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
         "MetricExpr": "max(0, FRONTEND_RETIRED.L1I_MISS * FRONTEND_RETIRED.L1I_MISS:R / tma_info_thread_clks - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
         "MetricExpr": "FRONTEND_RETIRED.L2_MISS * FRONTEND_RETIRED.L2_MISS:R / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -532,7 +532,7 @@
         "MetricExpr": "max(0, FRONTEND_RETIRED.ITLB_MISS * FRONTEND_RETIRED.ITLB_MISS:R / tma_info_thread_clks - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -540,48 +540,49 @@
         "MetricExpr": "FRONTEND_RETIRED.STLB_MISS * FRONTEND_RETIRED.STLB_MISS:R / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches.",
         "MetricExpr": "BR_MISP_RETIRED.COND_NTAKEN_COST * BR_MISP_RETIRED.COND_NTAKEN_COST:R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_nt_mispredicts",
-        "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches.",
         "MetricExpr": "BR_MISP_RETIRED.COND_TAKEN_COST * BR_MISP_RETIRED.COND_TAKEN_COST:R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_tk_mispredicts",
-        "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricExpr": "((min(MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) + (min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (81 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (81 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * min(MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS:R, 74.6 * tma_info_system_core_frequency) + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, 76.6 * tma_info_system_core_frequency) * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -592,24 +593,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricExpr": "((min(MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) + (min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * min(MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD:R, 74.6 * tma_info_system_core_frequency) + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, 74.6 * tma_info_system_core_frequency) * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
@@ -618,7 +620,7 @@
         "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE",
         "ScaleUnit": "100%"
     },
@@ -627,7 +629,7 @@
         "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -637,7 +639,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -645,34 +647,34 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "(min(MEM_INST_RETIRED.STLB_HIT_LOADS * MEM_INST_RETIRED.STLB_HIT_LOADS:R, MEM_INST_RETIRED.STLB_HIT_LOADS * 7) if 0 < MEM_INST_RETIRED.STLB_HIT_LOADS:R else MEM_INST_RETIRED.STLB_HIT_LOADS * 7) / tma_info_thread_clks + tma_load_stlb_miss",
+        "MetricExpr": "MEM_INST_RETIRED.STLB_HIT_LOADS * min(MEM_INST_RETIRED.STLB_HIT_LOADS:R, 7) / tma_info_thread_clks + tma_load_stlb_miss",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(min(MEM_INST_RETIRED.STLB_HIT_STORES * MEM_INST_RETIRED.STLB_HIT_STORES:R, MEM_INST_RETIRED.STLB_HIT_STORES * 7) if 0 < MEM_INST_RETIRED.STLB_HIT_STORES:R else MEM_INST_RETIRED.STLB_HIT_STORES * 7) / tma_info_thread_clks + tma_store_stlb_miss",
+        "MetricExpr": "MEM_INST_RETIRED.STLB_HIT_STORES * min(MEM_INST_RETIRED.STLB_HIT_STORES:R, 7) / tma_info_thread_clks + tma_store_stlb_miss",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
-        "MetricExpr": "(170 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks",
+        "MetricExpr": "(170 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_MISS@offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -693,7 +695,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -704,7 +706,7 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -722,7 +724,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -731,15 +733,15 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -747,8 +749,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -756,8 +758,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.VECTOR + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -765,8 +767,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -774,8 +776,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -783,8 +785,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_512b",
-        "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -795,27 +797,27 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%"
     },
     {
@@ -823,24 +825,24 @@
         "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions.",
         "MetricExpr": "BR_MISP_RETIRED.INDIRECT_CALL_COST * BR_MISP_RETIRED.INDIRECT_CALL_COST:R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ind_call_mispredicts",
-        "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions.",
         "MetricExpr": "max((BR_MISP_RETIRED.INDIRECT_COST * BR_MISP_RETIRED.INDIRECT_COST:R - BR_MISP_RETIRED.INDIRECT_CALL_COST * BR_MISP_RETIRED.INDIRECT_CALL_COST:R) / tma_info_thread_clks, 0)",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ind_jump_mispredicts",
-        "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -851,28 +853,28 @@
         "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -900,7 +902,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -908,7 +910,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -916,10 +918,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -980,11 +983,11 @@
         "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -997,8 +1000,8 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
@@ -1011,7 +1014,7 @@
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
@@ -1061,10 +1064,10 @@
     },
     {
         "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
-        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed",
         "MetricName": "tma_info_frontend_unknown_branch_cost",
-        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node"
+        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node."
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears",
@@ -1073,7 +1076,7 @@
         "MetricName": "tma_info_frontend_unknown_branches_ret"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -1091,7 +1094,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -1099,7 +1102,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -1107,7 +1110,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -1115,7 +1118,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx512",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -1123,7 +1126,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate)",
@@ -1131,7 +1134,7 @@
         "MetricGroup": "Flops;FpScalar;InsType;Server",
         "MetricName": "tma_info_inst_mix_iparith_scalar_hp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_hp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -1139,7 +1142,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -1194,7 +1197,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 13",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -1331,7 +1334,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp"
     },
@@ -1396,21 +1399,21 @@
         "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_soc_r2c_dram_bw",
-        "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW"
+        "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW."
     },
     {
         "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)",
         "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_soc_r2c_l3m_bw",
-        "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW"
+        "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW."
     },
     {
         "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)",
         "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_soc_r2c_offcore_bw",
-        "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches"
+        "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches."
     },
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
@@ -1452,8 +1455,8 @@
         "MetricName": "tma_info_memory_tlb_store_stlb_mpki"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -1474,18 +1477,18 @@
         "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "MicroSeq;Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1"
@@ -1548,14 +1551,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1566,14 +1568,14 @@
     },
     {
         "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]",
-        "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@",
+        "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@",
         "MetricGroup": "MemOffcore;MemoryLat;Server;SoC",
         "MetricName": "tma_info_system_mem_dram_read_latency",
         "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches"
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@",
+        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
@@ -1599,7 +1601,7 @@
     },
     {
         "BriefDescription": "Socket actual clocks when any core is active on that socket",
-        "MetricExpr": "cha_0@event\\=0x0@",
+        "MetricExpr": "uncore_cha_0@event\\=0x1@",
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_socket_clks"
     },
@@ -1629,7 +1631,7 @@
         "MetricName": "tma_info_system_upi_data_transmit_bw"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1638,15 +1640,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1656,13 +1657,13 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "TOPDOWN.SLOTS",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots"
     },
     {
         "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
+        "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)",
         "MetricGroup": "SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots_utilization"
     },
@@ -1678,14 +1679,14 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 9"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1694,7 +1695,7 @@
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_int_operations",
         "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.",
         "ScaleUnit": "100%"
     },
     {
@@ -1702,8 +1703,8 @@
         "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_128b",
-        "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1711,8 +1712,8 @@
         "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_256b",
-        "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1720,8 +1721,8 @@
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1729,7 +1730,7 @@
         "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -1738,7 +1739,7 @@
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
@@ -1747,16 +1748,17 @@
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
-        "MetricExpr": "(min(MEM_LOAD_RETIRED.L2_HIT * MEM_LOAD_RETIRED.L2_HIT:R, MEM_LOAD_RETIRED.L2_HIT * (4.4 * tma_info_system_core_frequency)) if 0 < MEM_LOAD_RETIRED.L2_HIT:R else MEM_LOAD_RETIRED.L2_HIT * (4.4 * tma_info_system_core_frequency)) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * min(MEM_LOAD_RETIRED.L2_HIT:R, 4.4 * tma_info_system_core_frequency) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1765,17 +1767,18 @@
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(min(MEM_LOAD_RETIRED.L3_HIT * MEM_LOAD_RETIRED.L3_HIT:R, MEM_LOAD_RETIRED.L3_HIT * (37 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_RETIRED.L3_HIT:R else MEM_LOAD_RETIRED.L3_HIT * (37 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "MEM_LOAD_RETIRED.L3_HIT * min(MEM_LOAD_RETIRED.L3_HIT:R, 32.6 * tma_info_system_core_frequency) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1783,19 +1786,19 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "DefaultMetricgroupName": "TopdownL2",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1812,7 +1815,7 @@
         "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1820,31 +1823,31 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -1852,7 +1855,7 @@
         "MetricExpr": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM:R * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
         "ScaleUnit": "100%"
     },
@@ -1861,7 +1864,7 @@
         "MetricExpr": "MEM_INST_RETIRED.LOCK_LOADS * MEM_INST_RETIRED.LOCK_LOADS:R / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1877,19 +1880,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling)",
+        "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).",
         "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group",
         "MetricName": "tma_mba_stalls",
-        "MetricThreshold": "tma_mba_stalls > 0.1 & tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mba_stalls > 0.1 & (tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1898,32 +1901,32 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
-        "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -1944,7 +1947,7 @@
         "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -1958,17 +1961,17 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
-        "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
+        "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
         "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
@@ -1976,10 +1979,10 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
-        "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks",
+        "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
@@ -1989,7 +1992,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%"
     },
     {
@@ -1997,7 +2000,7 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%"
     },
@@ -2011,19 +2014,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -2032,7 +2035,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_page_faults",
         "MetricThreshold": "tma_page_faults > 0.05",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.",
         "ScaleUnit": "100%"
     },
     {
@@ -2041,7 +2044,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -2050,7 +2053,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -2059,7 +2062,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -2067,8 +2070,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
@@ -2076,8 +2079,8 @@
         "MetricExpr": "max(EXE_ACTIVITY.EXE_BOUND_0_PORTS - RESOURCE_STALLS.SCOREBOARD, 0) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
@@ -2085,7 +2088,7 @@
         "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -2095,8 +2098,8 @@
         "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
@@ -2105,7 +2108,7 @@
         "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%"
     },
@@ -2114,8 +2117,8 @@
         "MetricExpr": "(MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM:R + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD:R) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
@@ -2123,22 +2126,22 @@
         "MetricExpr": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM:R * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions.",
         "MetricExpr": "BR_MISP_RETIRED.RET_COST * BR_MISP_RETIRED.RET_COST:R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ret_mispredicts",
-        "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ret_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2151,7 +2154,7 @@
         "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks + tma_c02_wait",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -2160,8 +2163,8 @@
         "MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_shuffles_256b",
-        "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+        "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.",
         "ScaleUnit": "100%"
     },
     {
@@ -2170,26 +2173,26 @@
         "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary",
-        "MetricExpr": "(min(MEM_INST_RETIRED.SPLIT_LOADS * MEM_INST_RETIRED.SPLIT_LOADS:R, MEM_INST_RETIRED.SPLIT_LOADS * tma_info_memory_load_miss_real_latency) if 0 < MEM_INST_RETIRED.SPLIT_LOADS:R else MEM_INST_RETIRED.SPLIT_LOADS * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks",
+        "MetricExpr": "MEM_INST_RETIRED.SPLIT_LOADS * min(MEM_INST_RETIRED.SPLIT_LOADS:R, tma_info_memory_load_miss_real_latency) / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricExpr": "(min(MEM_INST_RETIRED.SPLIT_STORES * MEM_INST_RETIRED.SPLIT_STORES:R, MEM_INST_RETIRED.SPLIT_STORES) if 0 < MEM_INST_RETIRED.SPLIT_STORES:R else MEM_INST_RETIRED.SPLIT_STORES) / tma_info_thread_clks",
+        "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES * min(MEM_INST_RETIRED.SPLIT_STORES:R, 1) / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -2197,7 +2200,7 @@
         "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -2206,8 +2209,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -2215,8 +2218,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -2224,8 +2227,8 @@
         "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -2242,7 +2245,7 @@
         "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -2250,31 +2253,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -2282,7 +2285,7 @@
         "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%"
     },
@@ -2291,7 +2294,7 @@
         "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "ScaleUnit": "100%"
     },
@@ -2300,8 +2303,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/memory.json
index 5da5a10275ba..4db39f304c2c 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/memory.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/memory.json
@@ -5,6 +5,7 @@
         "CounterMask": "2",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS",
+        "PublicDescription": "Cycles while L3 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -14,6 +15,7 @@
         "CounterMask": "6",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
+        "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x6"
     },
@@ -22,7 +24,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
+        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -32,6 +34,7 @@
         "CounterMask": "2",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -41,6 +44,7 @@
         "CounterMask": "3",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -50,7 +54,7 @@
         "CounterMask": "5",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS",
-        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -60,7 +64,7 @@
         "CounterMask": "9",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS",
-        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9"
     },
@@ -72,7 +76,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x400",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "53",
         "UMask": "0x1"
     },
@@ -84,7 +88,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "1009",
         "UMask": "0x1"
     },
@@ -96,7 +100,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1"
     },
@@ -108,7 +112,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x800",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "23",
         "UMask": "0x1"
     },
@@ -120,7 +124,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "503",
         "UMask": "0x1"
     },
@@ -132,7 +136,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -144,7 +148,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -156,7 +160,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "101",
         "UMask": "0x1"
     },
@@ -168,7 +172,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "2003",
         "UMask": "0x1"
     },
@@ -180,7 +184,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x1"
     },
@@ -190,17 +194,51 @@
         "Data_LA": "1",
         "EventCode": "0xcd",
         "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
-        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
+        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -211,6 +249,40 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x730000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to another socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -221,6 +293,29 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F3FC00002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -231,6 +326,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F3FC04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -241,6 +337,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F04C04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -251,6 +348,62 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL_SOCKET",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x70CC04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that missed the L3 Cache and were supplied by the local socket (DRAM or PMM), whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM or DRAM accesses that are controlled by the close or distant SNC Cluster.  It does not count misses to the L3 which go to Local CXL Type 2 Memory or Local Non DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x70C004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x730004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x733004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.WRITE_ESTIMATE.MEMORY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0xFBFF80822",
+        "PublicDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM) Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -259,6 +412,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -268,7 +422,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
-        "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
+        "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -277,7 +431,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.",
+        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -286,7 +440,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PublicDescription": "Counts the number of times RTM abort was triggered.",
+        "PublicDescription": "Counts the number of times RTM abort was triggered. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -295,7 +449,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_EVENTS",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -304,7 +458,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_MEM",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -313,7 +467,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x40"
     },
@@ -322,7 +476,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -331,7 +485,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.COMMIT",
-        "PublicDescription": "Counts the number of times RTM commit succeeded.",
+        "PublicDescription": "Counts the number of times RTM commit succeeded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -340,7 +494,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.START",
-        "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.",
+        "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -349,7 +503,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x54",
         "EventName": "TX_MEM.ABORT_CAPACITY_READ",
-        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads",
+        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -358,7 +512,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x54",
         "EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
-        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.",
+        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -367,7 +521,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x54",
         "EventName": "TX_MEM.ABORT_CONFLICT",
-        "PublicDescription": "Counts the number of times a TSX line had a cache conflict.",
+        "PublicDescription": "Counts the number of times a TSX line had a cache conflict. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/other.json b/tools/perf/pmu-events/arch/x86/graniterapids/other.json
index 8df37f303273..8b7aa4caec46 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/other.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/other.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.HARDWARE",
-        "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.  This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.",
+        "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.  This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -13,263 +13,28 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.PAGE_FAULT",
+        "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
     {
-        "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb7",
-        "EventName": "EXE.AMX_BUSY",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x730000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F3FFC0002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10808",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F3FFC4477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x70C004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F33004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x730004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x733004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.WRITE_ESTIMATE.MEMORY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0xFBFF80822",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7"
-    },
-    {
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "CounterMask": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_COUNT",
-        "Invert": "1",
-        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7"
-    },
-    {
-        "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_RESOURCE",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Cycles the uncore cannot take further requests",
         "Counter": "0,1,2,3",
         "CounterMask": "1",
         "EventCode": "0x2d",
         "EventName": "XQ.FULL_CYCLES",
-        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).",
+        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json
index da6478607984..1edfdad1600d 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json
@@ -5,7 +5,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.DIV_ACTIVE",
-        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
+        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9"
     },
@@ -15,6 +15,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.IDIV_ACTIVE",
+        "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -23,7 +24,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.ANY",
-        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.",
+        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1b"
     },
@@ -32,7 +33,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all branch instructions retired.",
+        "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009"
     },
     {
@@ -40,7 +41,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
-        "PublicDescription": "Counts conditional branch instructions retired.",
+        "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11"
     },
@@ -49,7 +50,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts not taken branch instructions retired.",
+        "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10"
     },
@@ -58,7 +59,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional branch instructions retired.",
+        "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1"
     },
@@ -67,7 +68,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "PublicDescription": "Counts far branch instructions retired.",
+        "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
     },
@@ -76,7 +77,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
-        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -85,7 +86,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2"
     },
@@ -94,7 +95,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "Counts return instructions retired.",
+        "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -103,7 +104,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts taken branch instructions retired.",
+        "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
     },
@@ -112,7 +113,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "400009"
     },
     {
@@ -120,6 +121,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST",
+        "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x44"
     },
@@ -128,7 +130,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
-        "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11"
     },
@@ -137,6 +139,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_COST",
+        "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x51"
     },
@@ -145,7 +148,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
+        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10"
     },
@@ -154,6 +157,10 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST",
+        "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
+        "RetirementLatencyMax": 888,
+        "RetirementLatencyMean": 6.11,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "400009",
         "UMask": "0x50"
     },
@@ -162,7 +169,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1"
     },
@@ -171,6 +178,10 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST",
+        "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
+        "RetirementLatencyMax": 2750,
+        "RetirementLatencyMean": 5.09,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "400009",
         "UMask": "0x41"
     },
@@ -179,7 +190,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
-        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -188,7 +199,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
-        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
+        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x2"
     },
@@ -197,6 +208,10 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST",
+        "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
+        "RetirementLatencyMax": 703,
+        "RetirementLatencyMean": 15.56,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "400009",
         "UMask": "0x42"
     },
@@ -205,6 +220,10 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_COST",
+        "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
+        "RetirementLatencyMax": 1562,
+        "RetirementLatencyMean": 11.07,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100003",
         "UMask": "0xc0"
     },
@@ -213,7 +232,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
     },
@@ -222,6 +241,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST",
+        "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x60"
     },
@@ -230,7 +250,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -239,6 +259,10 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET_COST",
+        "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
+        "RetirementLatencyMax": 1082,
+        "RetirementLatencyMean": 32.37,
+        "RetirementLatencyMin": 9,
         "SampleAfterValue": "100007",
         "UMask": "0x48"
     },
@@ -247,7 +271,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C01",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -256,7 +280,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C02",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -265,7 +289,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C0_WAIT",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x70"
     },
@@ -274,7 +298,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED",
-        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -283,7 +307,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.",
+        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0",
         "SampleAfterValue": "25003",
         "UMask": "0x2"
     },
@@ -292,6 +316,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40"
     },
@@ -302,6 +327,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE_INST",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40"
     },
@@ -310,7 +336,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED",
-        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -318,7 +344,7 @@
         "BriefDescription": "Reference cycles when the core is not in halt state.",
         "Counter": "Fixed counter 2",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
-        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x3"
     },
@@ -327,7 +353,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
-        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -335,7 +361,7 @@
         "BriefDescription": "Core cycles when the thread is not in halt state",
         "Counter": "Fixed counter 1",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
-        "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.",
+        "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -344,7 +370,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -353,6 +379,7 @@
         "CounterMask": "8",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -362,6 +389,7 @@
         "CounterMask": "1",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -371,6 +399,7 @@
         "CounterMask": "16",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -380,6 +409,7 @@
         "CounterMask": "12",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc"
     },
@@ -389,6 +419,7 @@
         "CounterMask": "5",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -398,15 +429,25 @@
         "CounterMask": "4",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "PublicDescription": "Total execution stalls. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
     {
+        "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb7",
+        "EventName": "EXE.AMX_BUSY",
+        "PublicDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation. Available PDIST counters: 0",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
+    },
+    {
         "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -415,6 +456,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0xc"
     },
@@ -423,7 +465,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -432,7 +474,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -441,7 +483,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -451,6 +493,7 @@
         "CounterMask": "5",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS",
+        "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x21"
     },
@@ -460,7 +503,7 @@
         "CounterMask": "2",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
-        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.",
+        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -469,7 +512,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
-        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.",
+        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80"
     },
@@ -478,7 +521,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x75",
         "EventName": "INST_DECODED.DECODERS",
-        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.",
+        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -486,7 +529,7 @@
         "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -503,6 +546,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -511,7 +555,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
-        "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions",
+        "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -519,7 +563,7 @@
         "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.PREC_DIST",
-        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
+        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -528,7 +572,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -539,7 +583,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEARS_COUNT",
-        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears",
+        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -548,7 +592,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
-        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
+        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x80"
     },
@@ -557,6 +601,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.MBA_STALLS",
+        "PublicDescription": "INT_MISC.MBA_STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -565,7 +610,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.RECOVERY_CYCLES",
-        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -576,6 +621,7 @@
         "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x7",
+        "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -584,7 +630,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.UOP_DROPPING",
-        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons",
+        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -593,6 +639,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.128BIT",
+        "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x13"
     },
@@ -601,6 +648,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.256BIT",
+        "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xac"
     },
@@ -609,7 +657,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_128",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -618,7 +666,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_256",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc"
     },
@@ -627,6 +675,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.MUL_256",
+        "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80"
     },
@@ -635,6 +684,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.SHUFFLES",
+        "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -643,6 +693,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_128",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -651,6 +702,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_256",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -659,7 +711,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
-        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.",
+        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -668,7 +720,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.NO_SR",
-        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x88"
     },
@@ -677,7 +729,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.STORE_FORWARD",
-        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
+        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x82"
     },
@@ -686,7 +738,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x4c",
         "EventName": "LOAD_HIT_PREFETCH.SWPF",
-        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -696,7 +748,7 @@
         "CounterMask": "1",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_ACTIVE",
-        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -706,7 +758,7 @@
         "CounterMask": "6",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_OK",
-        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -715,7 +767,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa8",
         "EventName": "LSD.UOPS",
-        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -726,7 +778,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.COUNT",
-        "PublicDescription": "Counts the number of machine clears (nukes) of any type.",
+        "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -735,7 +787,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SMC",
-        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -744,7 +796,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe0",
         "EventName": "MISC2_RETIRED.LFENCE",
-        "PublicDescription": "number of LFENCE retired instructions",
+        "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
     },
@@ -753,7 +805,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcc",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
-        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -762,7 +814,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SB",
-        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -771,15 +823,46 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SCOREBOARD",
+        "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_COUNT",
+        "Invert": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_RESOURCE",
+        "PublicDescription": "Cycles when RS was empty and a resource allocation stall is asserted Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x2"
     },
@@ -788,7 +871,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BAD_SPEC_SLOTS",
-        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.",
+        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x4"
     },
@@ -797,7 +880,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
-        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.",
+        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x8"
     },
@@ -806,6 +889,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS",
+        "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x10"
     },
@@ -813,7 +897,7 @@
         "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event",
         "Counter": "Fixed counter 3",
         "EventName": "TOPDOWN.SLOTS",
-        "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).",
+        "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3). Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x4"
     },
@@ -822,7 +906,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.SLOTS_P",
-        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.",
+        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x1"
     },
@@ -831,7 +915,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x76",
         "EventName": "UOPS_DECODED.DEC0_UOPS",
-        "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0.",
+        "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -840,7 +924,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_0",
-        "PublicDescription": "Number of uops dispatch to execution  port 0.",
+        "PublicDescription": "Number of uops dispatch to execution  port 0. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -849,7 +933,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_1",
-        "PublicDescription": "Number of uops dispatch to execution  port 1.",
+        "PublicDescription": "Number of uops dispatch to execution  port 1. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -858,7 +942,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_2_3_10",
-        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10",
+        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -867,7 +951,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_4_9",
-        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9",
+        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -876,7 +960,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_5_11",
-        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11",
+        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -885,7 +969,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_6",
-        "PublicDescription": "Number of uops dispatch to execution  port 6.",
+        "PublicDescription": "Number of uops dispatch to execution  port 6. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40"
     },
@@ -894,7 +978,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_7_8",
-        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8.",
+        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x80"
     },
@@ -903,7 +987,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE",
-        "PublicDescription": "Counts the number of uops executed from any thread.",
+        "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -913,7 +997,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -923,7 +1007,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -933,7 +1017,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -943,7 +1027,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -953,7 +1037,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_1",
-        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -963,7 +1047,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_2",
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -973,7 +1057,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_3",
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -983,7 +1067,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_4",
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -994,7 +1078,7 @@
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.STALLS",
         "Invert": "1",
-        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1003,6 +1087,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.THREAD",
+        "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1011,7 +1096,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.X87",
-        "PublicDescription": "Counts the number of x87 uops executed.",
+        "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -1020,7 +1105,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.ANY",
-        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1030,6 +1115,7 @@
         "CounterMask": "1",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.CYCLES",
+        "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1039,7 +1125,7 @@
         "CounterMask": "1",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.CYCLES",
-        "PublicDescription": "Counts cycles where at least one uop has retired.",
+        "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -1048,7 +1134,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.HEAVY",
-        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.",
+        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1059,6 +1145,7 @@
         "EventName": "UOPS_RETIRED.MS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -1067,7 +1154,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.SLOTS",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -1078,7 +1165,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.STALLS",
         "Invert": "1",
-        "PublicDescription": "This event counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     }
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json
index 53055986534d..b782f6d54fc2 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json
@@ -854,6 +854,16 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "Ingress (from CMS) Allocations : IRQ : Counts number of allocations per cycle into the specified Ingress queue.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x13",
+        "EventName": "UNC_CHA_RxC_INSERTS.IRQ",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "Ingress (from CMS) Occupancy : IRQ : Counts number of entries in the specified Ingress queue in each cycle.",
         "Counter": "0",
         "EventCode": "0x11",
@@ -864,6 +874,38 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the core's cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a core's cache replaces a tracked cacheline with a new cacheline.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x3d",
+        "EventName": "UNC_CHA_SF_EVICTION.E_STATE",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "Snoop Filter Capacity Evictions : E state",
+        "UMask": "0x2",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the core's cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a core's cache replaces a tracked cacheline with a new cacheline.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x3d",
+        "EventName": "UNC_CHA_SF_EVICTION.M_STATE",
+        "PerPkg": "1",
+        "PublicDescription": "Snoop Filter Capacity Evictions : M state",
+        "UMask": "0x1",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the core's cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a core's cache replaces a tracked cacheline with a new cacheline.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x3d",
+        "EventName": "UNC_CHA_SF_EVICTION.S_STATE",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "Snoop Filter Capacity Evictions : S state",
+        "UMask": "0x4",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "All TOR Inserts",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json
index 5c50275c79b0..e5bd11b27bcd 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json
@@ -1076,7 +1076,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Egress bypasses for for AD_BNC",
+        "BriefDescription": "Egress bypasses for AD_BNC",
         "Counter": "0,1,2,3",
         "EventCode": "0x1E",
         "EventName": "UNC_MDF_TxR_BYPASS.AD_BNC",
@@ -1086,7 +1086,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Egress bypasses for for AD_CRD",
+        "BriefDescription": "Egress bypasses for AD_CRD",
         "Counter": "0,1,2,3",
         "EventCode": "0x1E",
         "EventName": "UNC_MDF_TxR_BYPASS.AD_CRD",
@@ -1096,7 +1096,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Egress bypasses for for AK",
+        "BriefDescription": "Egress bypasses for AK",
         "Counter": "0,1,2,3",
         "EventCode": "0x1E",
         "EventName": "UNC_MDF_TxR_BYPASS.AK",
@@ -1106,7 +1106,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Egress bypasses for for BL_BNC",
+        "BriefDescription": "Egress bypasses for BL_BNC",
         "Counter": "0,1,2,3",
         "EventCode": "0x1E",
         "EventName": "UNC_MDF_TxR_BYPASS.BL_BNC",
@@ -1116,7 +1116,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Egress bypasses for for BL_CRD",
+        "BriefDescription": "Egress bypasses for BL_CRD",
         "Counter": "0,1,2,3",
         "EventCode": "0x1E",
         "EventName": "UNC_MDF_TxR_BYPASS.BL_CRD",
@@ -1126,7 +1126,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Egress bypasses for for IV",
+        "BriefDescription": "Egress bypasses for IV",
         "Counter": "0,1,2,3",
         "EventCode": "0x1E",
         "EventName": "UNC_MDF_TxR_BYPASS.IV",
@@ -1136,7 +1136,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of egress inserts for for AD_BNC",
+        "BriefDescription": "Number of egress inserts for AD_BNC",
         "Counter": "0,1,2,3",
         "EventCode": "0x1C",
         "EventName": "UNC_MDF_TxR_INSERTS.AD_BNC",
@@ -1146,7 +1146,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of egress inserts for for AD_CRD",
+        "BriefDescription": "Number of egress inserts for AD_CRD",
         "Counter": "0,1,2,3",
         "EventCode": "0x1C",
         "EventName": "UNC_MDF_TxR_INSERTS.AD_CRD",
@@ -1156,7 +1156,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of egress inserts for for AK",
+        "BriefDescription": "Number of egress inserts for AK",
         "Counter": "0,1,2,3",
         "EventCode": "0x1C",
         "EventName": "UNC_MDF_TxR_INSERTS.AK",
@@ -1166,7 +1166,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of egress inserts for for BL_BNC",
+        "BriefDescription": "Number of egress inserts for BL_BNC",
         "Counter": "0,1,2,3",
         "EventCode": "0x1C",
         "EventName": "UNC_MDF_TxR_INSERTS.BL_BNC",
@@ -1176,7 +1176,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of egress inserts for for BL_CRD",
+        "BriefDescription": "Number of egress inserts for BL_CRD",
         "Counter": "0,1,2,3",
         "EventCode": "0x1C",
         "EventName": "UNC_MDF_TxR_INSERTS.BL_CRD",
@@ -1186,7 +1186,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of egress inserts for for IV",
+        "BriefDescription": "Number of egress inserts for IV",
         "Counter": "0,1,2,3",
         "EventCode": "0x1C",
         "EventName": "UNC_MDF_TxR_INSERTS.IV",
@@ -1196,7 +1196,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Egress occupancy for for AD_BNC",
+        "BriefDescription": "Egress occupancy for AD_BNC",
         "Counter": "0,1,2,3",
         "EventCode": "0x1D",
         "EventName": "UNC_MDF_TxR_OCCUPANCY.AD_BNC",
@@ -1206,7 +1206,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Egress occupancy for for AD_CRD",
+        "BriefDescription": "Egress occupancy for AD_CRD",
         "Counter": "0,1,2,3",
         "EventCode": "0x1D",
         "EventName": "UNC_MDF_TxR_OCCUPANCY.AD_CRD",
@@ -1216,7 +1216,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Egress occupancy for for AK",
+        "BriefDescription": "Egress occupancy for AK",
         "Counter": "0,1,2,3",
         "EventCode": "0x1D",
         "EventName": "UNC_MDF_TxR_OCCUPANCY.AK",
@@ -1226,7 +1226,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Egress occupancy for for BL_BNC",
+        "BriefDescription": "Egress occupancy for BL_BNC",
         "Counter": "0,1,2,3",
         "EventCode": "0x1D",
         "EventName": "UNC_MDF_TxR_OCCUPANCY.BL_BNC",
@@ -1236,7 +1236,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Egress occupancy for for BL_CRD",
+        "BriefDescription": "Egress occupancy for BL_CRD",
         "Counter": "0,1,2,3",
         "EventCode": "0x1D",
         "EventName": "UNC_MDF_TxR_OCCUPANCY.BL_CRD",
@@ -1246,7 +1246,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Egress occupancy for for IV",
+        "BriefDescription": "Egress occupancy for IV",
         "Counter": "0,1,2,3",
         "EventCode": "0x1D",
         "EventName": "UNC_MDF_TxR_OCCUPANCY.IV",
@@ -1932,5 +1932,59 @@
         "Experimental": "1",
         "PerPkg": "1",
         "Unit": "UPI"
+    },
+    {
+        "BriefDescription": "Message Received : Doorbell",
+        "Counter": "0,1",
+        "EventCode": "0x42",
+        "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "UBOX"
+    },
+    {
+        "BriefDescription": "Message Received : Interrupt",
+        "Counter": "0,1",
+        "EventCode": "0x42",
+        "EventName": "UNC_U_EVENT_MSG.INT_PRIO",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "Message Received : Interrupt : Interrupts",
+        "UMask": "0x10",
+        "Unit": "UBOX"
+    },
+    {
+        "BriefDescription": "Message Received : IPI",
+        "Counter": "0,1",
+        "EventCode": "0x42",
+        "EventName": "UNC_U_EVENT_MSG.IPI_RCVD",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "Message Received : IPI : Inter Processor Interrupts",
+        "UMask": "0x4",
+        "Unit": "UBOX"
+    },
+    {
+        "BriefDescription": "Message Received : MSI",
+        "Counter": "0,1",
+        "EventCode": "0x42",
+        "EventName": "UNC_U_EVENT_MSG.MSI_RCVD",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "Message Received : MSI : Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)",
+        "UMask": "0x2",
+        "Unit": "UBOX"
+    },
+    {
+        "BriefDescription": "Message Received : VLW",
+        "Counter": "0,1",
+        "EventCode": "0x42",
+        "EventName": "UNC_U_EVENT_MSG.VLW_RCVD",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "Message Received : VLW : Virtual Logical Wire (legacy) message were received from Uncore.",
+        "UMask": "0x1",
+        "Unit": "UBOX"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json
index 5f4783ff6ce5..b991f6e1afbe 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json
@@ -189,6 +189,94 @@
         "Unit": "IMC"
     },
     {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
         "BriefDescription": "# of cycles a given rank is in Power Down Mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x47",
@@ -287,6 +375,70 @@
         "Unit": "IMC"
     },
     {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x89",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x89",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "MR4 temp reading is throttling",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.MR4BLKEN",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "RAPL is throttling",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RAPLBLK",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
         "BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.",
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
@@ -479,6 +631,94 @@
         "Unit": "IMC"
     },
     {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8e",
+        "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8e",
+        "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at High level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8d",
+        "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at High level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8d",
+        "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8b",
+        "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8b",
+        "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8c",
+        "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8c",
+        "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
         "BriefDescription": "Write Pending Queue Allocations",
         "Counter": "0,1,2,3",
         "EventCode": "0x22",
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json
index 609a9549cbf3..3d3f88600e26 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
-        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
+        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -14,7 +14,7 @@
         "CounterMask": "1",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -23,7 +23,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
@@ -32,7 +32,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -41,7 +41,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -50,7 +50,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -59,7 +59,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -68,7 +68,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.STLB_HIT",
-        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
+        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -78,7 +78,7 @@
         "CounterMask": "1",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -87,7 +87,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
@@ -96,7 +96,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -105,7 +105,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -114,7 +114,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -123,7 +123,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -132,7 +132,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.STLB_HIT",
-        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
+        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -142,7 +142,7 @@
         "CounterMask": "1",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -151,7 +151,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
@@ -160,7 +160,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -169,7 +169,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -178,7 +178,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
index 0c1040b7e38c..b26ea70a3628 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
@@ -74,12 +74,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
@@ -92,8 +92,8 @@
         "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
     {
@@ -104,7 +104,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
     {
@@ -114,7 +114,7 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
@@ -125,7 +125,7 @@
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
     {
@@ -133,8 +133,8 @@
         "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -143,8 +143,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -153,8 +153,8 @@
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -165,7 +165,7 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
@@ -174,8 +174,8 @@
         "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -183,8 +183,8 @@
         "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_core_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -193,8 +193,8 @@
         "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -203,7 +203,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -211,7 +211,7 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -220,8 +220,8 @@
         "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
@@ -229,8 +229,8 @@
         "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -238,18 +238,18 @@
         "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
     {
@@ -279,33 +279,33 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "tma_microcode_sequencer",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.",
         "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -316,7 +316,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -328,7 +328,7 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@))",
+        "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -353,7 +353,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -398,7 +398,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -502,8 +502,8 @@
         "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -537,14 +537,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -592,7 +591,7 @@
         "MetricName": "tma_info_system_turbo_utilization"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -601,8 +600,7 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -628,14 +626,14 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 6"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
         "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED",
         "ScaleUnit": "100%"
     },
@@ -644,8 +642,8 @@
         "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
     {
@@ -653,8 +651,8 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -663,8 +661,8 @@
         "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -673,8 +671,8 @@
         "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -682,18 +680,18 @@
         "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -712,8 +710,8 @@
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -724,15 +722,15 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x6@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -741,19 +739,19 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound",
+        "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
@@ -762,7 +760,7 @@
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
         "MetricName": "tma_microcode_sequencer",
         "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_l1_bound, tma_machine_clears, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
@@ -771,7 +769,7 @@
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.",
         "ScaleUnit": "100%"
     },
     {
@@ -779,8 +777,8 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
     {
@@ -789,7 +787,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -798,7 +796,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -834,7 +832,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -843,7 +841,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -858,46 +856,46 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks",
+        "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / tma_info_core_core_clks",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -917,7 +915,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -925,8 +923,8 @@
         "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -934,7 +932,7 @@
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -943,8 +941,8 @@
         "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -952,8 +950,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -962,8 +960,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
index 1a05b74be575..8245a98ad4b9 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
@@ -276,12 +276,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
@@ -294,8 +294,8 @@
         "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
     {
@@ -306,7 +306,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
     {
@@ -316,7 +316,7 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
@@ -327,7 +327,7 @@
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
     {
@@ -335,8 +335,8 @@
         "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -345,8 +345,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -355,8 +355,8 @@
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -367,7 +367,7 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
@@ -376,8 +376,8 @@
         "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -385,8 +385,8 @@
         "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_core_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -395,8 +395,8 @@
         "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -405,7 +405,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -413,7 +413,7 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -422,8 +422,8 @@
         "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
@@ -431,8 +431,8 @@
         "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -440,18 +440,18 @@
         "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE, OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
     {
@@ -481,33 +481,33 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "tma_microcode_sequencer",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.",
         "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -518,7 +518,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -530,7 +530,7 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@))",
+        "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -555,7 +555,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -600,7 +600,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -704,8 +704,8 @@
         "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -739,14 +739,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -757,14 +756,14 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@",
+        "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
-        "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)",
+        "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
         "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)"
@@ -814,7 +813,7 @@
         "MetricName": "tma_info_system_uncore_frequency"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -823,8 +822,7 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -850,14 +848,14 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 6"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
         "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED",
         "ScaleUnit": "100%"
     },
@@ -866,8 +864,8 @@
         "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
     {
@@ -875,8 +873,8 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -885,8 +883,8 @@
         "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -895,8 +893,8 @@
         "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -904,18 +902,18 @@
         "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -933,8 +931,8 @@
         "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
+        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -943,8 +941,8 @@
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -955,15 +953,15 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x6@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -972,19 +970,19 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound",
+        "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
@@ -993,7 +991,7 @@
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
         "MetricName": "tma_microcode_sequencer",
         "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_l1_bound, tma_machine_clears, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
@@ -1002,7 +1000,7 @@
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.",
         "ScaleUnit": "100%"
     },
     {
@@ -1010,8 +1008,8 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
     {
@@ -1020,7 +1018,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1029,7 +1027,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1065,7 +1063,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1074,7 +1072,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1089,46 +1087,46 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks",
+        "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / tma_info_core_core_clks",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1137,8 +1135,8 @@
         "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
@@ -1146,8 +1144,8 @@
         "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM",
+        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1167,7 +1165,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1175,8 +1173,8 @@
         "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -1184,7 +1182,7 @@
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1193,8 +1191,8 @@
         "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1202,8 +1200,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -1212,8 +1210,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/icelake/cache.json b/tools/perf/pmu-events/arch/x86/icelake/cache.json
index 015f70f157d1..e7bb2ca6f183 100644
--- a/tools/perf/pmu-events/arch/x86/icelake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/cache.json
@@ -446,6 +446,16 @@
         "UMask": "0x20"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop was sent or not.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -506,6 +516,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop was sent or not.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -566,6 +586,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop was sent or not.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -626,6 +656,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10400",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit a cacheline in the L3 where a snoop was sent or not.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -656,6 +696,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10010",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that hit a cacheline in the L3 where a snoop was sent or not.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -716,6 +766,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10020",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent or not.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
index 63e28a03dc60..c5bfdb2f288b 100644
--- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
@@ -89,12 +89,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -106,7 +106,7 @@
         "MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
@@ -129,12 +129,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -149,7 +149,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -157,7 +157,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -165,22 +165,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -188,7 +188,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -196,15 +196,15 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
-        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears"
+        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache"
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -216,17 +216,17 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
         "MetricThreshold": "tma_bottleneck_useful_work > 20"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.",
         "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_branch_instructions",
@@ -248,8 +248,8 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -257,8 +257,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -266,24 +266,24 @@
         "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
         "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -291,7 +291,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -299,33 +299,33 @@
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "((32.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + (27 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(29 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -335,25 +335,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(27 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
@@ -362,7 +362,7 @@
         "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
@@ -372,7 +372,7 @@
         "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -382,7 +382,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -390,26 +390,26 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -417,8 +417,8 @@
         "MetricExpr": "32.5 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -437,7 +437,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -447,7 +447,7 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -465,7 +465,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -474,15 +474,15 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "ARITH.FP_DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -490,7 +490,7 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -499,7 +499,7 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -508,7 +508,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -517,7 +517,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -526,7 +526,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_512b",
-        "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -538,17 +538,17 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
-        "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
@@ -556,8 +556,8 @@
         "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -569,28 +569,28 @@
         "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -619,7 +619,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -628,7 +628,7 @@
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -637,10 +637,11 @@
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -701,11 +702,11 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -718,20 +719,20 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency"
     },
@@ -773,7 +774,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -791,7 +792,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -799,7 +800,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -807,7 +808,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -815,7 +816,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx512",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -823,7 +824,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -831,7 +832,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -886,7 +887,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 5 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 11",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -1005,7 +1006,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp"
     },
@@ -1067,8 +1068,8 @@
         "MetricName": "tma_info_memory_tlb_store_stlb_mpki"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -1095,12 +1096,12 @@
         "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -1141,14 +1142,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1175,7 +1175,7 @@
         "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks",
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license0_utilization",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
@@ -1183,7 +1183,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license1_utilization",
         "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)",
@@ -1191,7 +1191,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license2_utilization",
         "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
@@ -1219,7 +1219,7 @@
         "MetricName": "tma_info_system_turbo_utilization"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1228,15 +1228,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1246,13 +1245,13 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "TOPDOWN.SLOTS",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots"
     },
     {
         "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
+        "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)",
         "MetricGroup": "SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots_utilization"
     },
@@ -1268,14 +1267,14 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 5 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 7.5"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1283,8 +1282,8 @@
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1292,7 +1291,7 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -1301,7 +1300,7 @@
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
@@ -1311,7 +1310,7 @@
         "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1320,7 +1319,7 @@
         "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1330,17 +1329,17 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(12.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+        "MetricExpr": "9 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1348,18 +1347,18 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1376,7 +1375,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1384,31 +1383,31 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -1417,7 +1416,7 @@
         "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1427,7 +1426,7 @@
         "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_lsd",
         "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.",
         "ScaleUnit": "100%"
     },
     {
@@ -1437,15 +1436,15 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1454,7 +1453,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -1465,11 +1464,11 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
@@ -1491,7 +1490,7 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -1506,24 +1505,24 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline",
-        "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / tma_info_thread_clks",
+        "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group",
         "MetricName": "tma_mite_4wide",
-        "MetricThreshold": "tma_mite_4wide > 0.05 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
-        "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=0x1@ / tma_info_core_core_clks / 2",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
+        "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 2",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
         "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
@@ -1534,7 +1533,7 @@
         "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
@@ -1543,7 +1542,7 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%"
     },
@@ -1558,19 +1557,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -1614,8 +1613,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
@@ -1623,8 +1622,8 @@
         "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
@@ -1632,7 +1631,7 @@
         "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -1641,7 +1640,7 @@
         "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
@@ -1650,14 +1649,14 @@
         "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -1670,7 +1669,7 @@
         "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -1679,7 +1678,7 @@
         "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST",
         "ScaleUnit": "100%"
     },
@@ -1689,7 +1688,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1698,8 +1697,8 @@
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -1707,7 +1706,7 @@
         "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1716,8 +1715,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1726,8 +1725,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -1735,8 +1734,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1753,7 +1752,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1761,31 +1760,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -1793,7 +1792,7 @@
         "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%"
     },
@@ -1802,7 +1801,7 @@
         "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -1811,8 +1810,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/icelake/memory.json b/tools/perf/pmu-events/arch/x86/icelake/memory.json
index abaf3f4f9d63..1455aaac37b1 100644
--- a/tools/perf/pmu-events/arch/x86/icelake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/memory.json
@@ -177,6 +177,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -187,6 +197,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -197,6 +227,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand data reads that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -207,6 +257,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000400",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -217,6 +287,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000400",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000010",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -227,6 +317,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000010",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000020",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -237,6 +347,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000020",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.OTHER.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184008000",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -247,6 +377,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.OTHER.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184008000",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts streaming stores that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.STREAMING_WR.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000800",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts streaming stores that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -257,6 +407,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts streaming stores that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.STREAMING_WR.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000800",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data read requests that miss the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xb0",
diff --git a/tools/perf/pmu-events/arch/x86/icelake/other.json b/tools/perf/pmu-events/arch/x86/icelake/other.json
index a96b2a989d3f..141cd30a30af 100644
--- a/tools/perf/pmu-events/arch/x86/icelake/other.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/other.json
@@ -27,186 +27,6 @@
         "UMask": "0x20"
     },
     {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that have any type of response.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -217,26 +37,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.OTHER.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184008000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.OTHER.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184008000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -245,25 +45,5 @@
         "MSRValue": "0x10800",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts streaming stores that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.STREAMING_WR.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000800",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts streaming stores that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.STREAMING_WR.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000800",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/cache.json b/tools/perf/pmu-events/arch/x86/icelakex/cache.json
index e8ab6ef2cd50..e46fd6f91d6b 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/cache.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/cache.json
@@ -1,5 +1,68 @@
 [
     {
+        "BriefDescription": "Hit snoop reply with data, line invalidated.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xef",
+        "EventName": "CORE_SNOOP_RESPONSE.I_FWD_FE",
+        "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's cache, after the data is forwarded back to the requestor and indicating the data was found unmodified in the (FE) Forward or Exclusive State in this cores caches cache.  A single snoop response from the core counts on all hyperthreads of the core.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x20"
+    },
+    {
+        "BriefDescription": "HitM snoop reply with data, line invalidated.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xef",
+        "EventName": "CORE_SNOOP_RESPONSE.I_FWD_M",
+        "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's caches, after the data is forwarded back to the requestor, and indicating the data was found modified(M) in this cores caches cache (aka HitM response).  A single snoop response from the core counts on all hyperthreads of the core.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x10"
+    },
+    {
+        "BriefDescription": "Hit snoop reply without sending the data, line invalidated.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xef",
+        "EventName": "CORE_SNOOP_RESPONSE.I_HIT_FSE",
+        "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated in this core's caches without being forwarded back to the requestor. The line was in Forward, Shared or Exclusive (FSE) state in this cores caches.  A single snoop response from the core counts on all hyperthreads of the core.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Line not found snoop reply",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xef",
+        "EventName": "CORE_SNOOP_RESPONSE.MISS",
+        "PublicDescription": "Counts responses to snoops indicating that the data was not found (IHitI) in this core's caches. A single snoop response from the core counts on all hyperthreads of the Core.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Hit snoop reply with data, line kept in Shared state.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xef",
+        "EventName": "CORE_SNOOP_RESPONSE.S_FWD_FE",
+        "PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (FS) Forward or Shared state.  A single snoop response from the core counts on all hyperthreads of the core.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x40"
+    },
+    {
+        "BriefDescription": "HitM snoop reply with data, line kept in Shared state",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xef",
+        "EventName": "CORE_SNOOP_RESPONSE.S_FWD_M",
+        "PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (M)odified state.  A single snoop response from the core counts on all hyperthreads of the core.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8"
+    },
+    {
+        "BriefDescription": "Hit snoop reply without sending the data, line kept in Shared state.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xef",
+        "EventName": "CORE_SNOOP_RESPONSE.S_HIT_FSE",
+        "PublicDescription": "Counts responses to snoops indicating the line was kept on this core in the (S)hared state, and that the data was found unmodified but not forwarded back to the requestor, initially the data was found in the cache in the (FSE) Forward, Shared state or Exclusive state.  A single snoop response from the core counts on all hyperthreads of the core.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4"
+    },
+    {
         "BriefDescription": "Counts the number of cache lines replaced in L1 data cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
@@ -507,6 +570,16 @@
         "UMask": "0x80"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -547,6 +620,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -587,6 +670,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand data reads that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100400001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by PMM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x703C00001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -607,6 +710,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand data reads that were supplied by PMM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x703000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -627,6 +740,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand data reads that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SNC_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x700800001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F3FFC0002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -647,6 +780,36 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.LOCAL_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100400002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x703C00002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.REMOTE_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x703000002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -667,6 +830,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SNC_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x700800002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -677,6 +850,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts hardware prefetch (which bring data to L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10070",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L3.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x12380",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts hardware prefetches to the L3 only that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -687,6 +880,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L3.REMOTE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x90002380",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts full cacheline writes (ItoM) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.ITOM.REMOTE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x90000002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts hardware and software prefetches to all cache levels that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -697,6 +910,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F3FFC0477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -737,6 +960,36 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100400477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x700C00477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.READS_TO_CORE.REMOTE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F33000477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified).",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -767,6 +1020,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x703000477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -787,6 +1050,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.READS_TO_CORE.SNC_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x700800477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts streaming stores that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
index 7bee03e532e4..a886a0cfee07 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
@@ -335,12 +335,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -352,7 +352,7 @@
         "MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
@@ -375,12 +375,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -395,7 +395,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -403,7 +403,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -411,22 +411,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -434,7 +434,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -442,7 +442,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
@@ -450,7 +450,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -462,17 +462,17 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
         "MetricThreshold": "tma_bottleneck_useful_work > 20"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.",
         "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_branch_instructions",
@@ -494,8 +494,8 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -503,8 +503,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -512,24 +512,24 @@
         "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
         "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -537,7 +537,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -545,33 +545,33 @@
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "((48 * tma_info_system_core_frequency - 4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (47.5 * tma_info_system_core_frequency - 4 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 43.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -581,25 +581,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(47.5 * tma_info_system_core_frequency - 4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "43.5 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
@@ -608,7 +608,7 @@
         "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
@@ -618,7 +618,7 @@
         "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -628,7 +628,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -636,34 +636,34 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
-        "MetricExpr": "(120 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 48 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks",
+        "MetricExpr": "(120 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_MISS@offcore_rsp\\=0x103b800002@ + 48 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -683,7 +683,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -693,7 +693,7 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -711,7 +711,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -720,15 +720,15 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "ARITH.FP_DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -736,7 +736,7 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -745,7 +745,7 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -754,7 +754,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -763,7 +763,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -772,7 +772,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_512b",
-        "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -784,17 +784,17 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
-        "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
@@ -802,8 +802,8 @@
         "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -815,28 +815,28 @@
         "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -865,7 +865,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -874,7 +874,7 @@
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -883,10 +883,11 @@
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -947,11 +948,11 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -964,20 +965,20 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency"
     },
@@ -1013,7 +1014,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -1031,7 +1032,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -1039,7 +1040,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -1047,7 +1048,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -1055,7 +1056,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx512",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -1063,7 +1064,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -1071,7 +1072,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -1126,7 +1127,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 5 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 11",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -1257,7 +1258,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp"
     },
@@ -1319,8 +1320,8 @@
         "MetricName": "tma_info_memory_tlb_store_stlb_mpki"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -1341,12 +1342,12 @@
         "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -1401,14 +1402,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1429,11 +1429,11 @@
         "MetricExpr": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH / UNC_CHA_CLOCKTICKS",
         "MetricGroup": "LockCont;MemOffcore;Server;SoC",
         "MetricName": "tma_info_system_mem_irq_duplicate_address",
-        "MetricThreshold": "(tma_info_system_mem_irq_duplicate_address > 0.1)"
+        "MetricThreshold": "tma_info_system_mem_irq_duplicate_address > 0.1"
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@",
+        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
@@ -1463,7 +1463,7 @@
         "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks",
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license0_utilization",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
@@ -1471,7 +1471,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license1_utilization",
         "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)",
@@ -1479,7 +1479,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license2_utilization",
         "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
@@ -1513,7 +1513,7 @@
         "MetricName": "tma_info_system_uncore_frequency"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1522,15 +1522,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1540,13 +1539,13 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "TOPDOWN.SLOTS",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots"
     },
     {
         "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
+        "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)",
         "MetricGroup": "SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots_utilization"
     },
@@ -1562,14 +1561,14 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 5 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 7.5"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1577,8 +1576,8 @@
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1586,7 +1585,7 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -1595,7 +1594,7 @@
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
@@ -1605,7 +1604,7 @@
         "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1614,7 +1613,7 @@
         "MetricExpr": "4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1624,17 +1623,17 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(23 * tma_info_system_core_frequency - 4 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+        "MetricExpr": "19 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1642,18 +1641,18 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1670,7 +1669,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1678,39 +1677,39 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory",
-        "MetricExpr": "(66.5 * tma_info_system_core_frequency - 23 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "43.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
         "ScaleUnit": "100%"
     },
@@ -1720,7 +1719,7 @@
         "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1736,10 +1735,10 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1748,7 +1747,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -1759,11 +1758,11 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
@@ -1785,7 +1784,7 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -1800,24 +1799,24 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline",
-        "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / tma_info_thread_clks",
+        "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group",
         "MetricName": "tma_mite_4wide",
-        "MetricThreshold": "tma_mite_4wide > 0.05 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
-        "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=0x1@ / tma_info_core_core_clks / 2",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
+        "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 2",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
         "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
@@ -1828,7 +1827,7 @@
         "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
@@ -1837,7 +1836,7 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%"
     },
@@ -1852,19 +1851,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -1908,8 +1907,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
@@ -1917,8 +1916,8 @@
         "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
@@ -1926,7 +1925,7 @@
         "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -1935,7 +1934,7 @@
         "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
@@ -1944,32 +1943,32 @@
         "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues",
-        "MetricExpr": "((120 * tma_info_system_core_frequency - 23 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (120 * tma_info_system_core_frequency - 23 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(97 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 97 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory",
-        "MetricExpr": "(131 * tma_info_system_core_frequency - 23 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "108 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -1982,7 +1981,7 @@
         "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -1991,7 +1990,7 @@
         "MetricExpr": "37 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST",
         "ScaleUnit": "100%"
     },
@@ -2001,7 +2000,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -2010,8 +2009,8 @@
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -2019,7 +2018,7 @@
         "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -2028,8 +2027,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -2038,8 +2037,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -2047,8 +2046,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -2065,7 +2064,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -2073,31 +2072,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -2105,7 +2104,7 @@
         "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%"
     },
@@ -2114,7 +2113,7 @@
         "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -2123,8 +2122,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/memory.json b/tools/perf/pmu-events/arch/x86/icelakex/memory.json
index ec9577cce3ac..ca7f68f67463 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/memory.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/memory.json
@@ -114,6 +114,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -134,6 +144,36 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -154,6 +194,46 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x730000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -174,6 +254,36 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000400",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -194,6 +304,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000400",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts hardware prefetches to the L3 only that missed the local socket's L1, L2, and L3 caches.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -254,6 +374,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.READS_TO_CORE.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -284,6 +414,56 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x70C000477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x730000477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x731800477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.READS_TO_CORE.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts streaming stores that missed the local socket's L1, L2, and L3 caches.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -304,6 +484,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.WRITE_ESTIMATE.MEMORY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0xFBFF80822",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data read requests that miss the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xb0",
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/other.json b/tools/perf/pmu-events/arch/x86/icelakex/other.json
index 05b348d9c838..141cd30a30af 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/other.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/other.json
@@ -27,339 +27,6 @@
         "UMask": "0x20"
     },
     {
-        "BriefDescription": "Hit snoop reply with data, line invalidated.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xef",
-        "EventName": "CORE_SNOOP_RESPONSE.I_FWD_FE",
-        "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's cache, after the data is forwarded back to the requestor and indicating the data was found unmodified in the (FE) Forward or Exclusive State in this cores caches cache.  A single snoop response from the core counts on all hyperthreads of the core.",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x20"
-    },
-    {
-        "BriefDescription": "HitM snoop reply with data, line invalidated.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xef",
-        "EventName": "CORE_SNOOP_RESPONSE.I_FWD_M",
-        "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's caches, after the data is forwarded back to the requestor, and indicating the data was found modified(M) in this cores caches cache (aka HitM response).  A single snoop response from the core counts on all hyperthreads of the core.",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x10"
-    },
-    {
-        "BriefDescription": "Hit snoop reply without sending the data, line invalidated.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xef",
-        "EventName": "CORE_SNOOP_RESPONSE.I_HIT_FSE",
-        "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated in this core's caches without being forwarded back to the requestor. The line was in Forward, Shared or Exclusive (FSE) state in this cores caches.  A single snoop response from the core counts on all hyperthreads of the core.",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "Line not found snoop reply",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xef",
-        "EventName": "CORE_SNOOP_RESPONSE.MISS",
-        "PublicDescription": "Counts responses to snoops indicating that the data was not found (IHitI) in this core's caches. A single snoop response from the core counts on all hyperthreads of the Core.",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Hit snoop reply with data, line kept in Shared state.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xef",
-        "EventName": "CORE_SNOOP_RESPONSE.S_FWD_FE",
-        "PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (FS) Forward or Shared state.  A single snoop response from the core counts on all hyperthreads of the core.",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x40"
-    },
-    {
-        "BriefDescription": "HitM snoop reply with data, line kept in Shared state",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xef",
-        "EventName": "CORE_SNOOP_RESPONSE.S_FWD_M",
-        "PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (M)odified state.  A single snoop response from the core counts on all hyperthreads of the core.",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x8"
-    },
-    {
-        "BriefDescription": "Hit snoop reply without sending the data, line kept in Shared state.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xef",
-        "EventName": "CORE_SNOOP_RESPONSE.S_HIT_FSE",
-        "PublicDescription": "Counts responses to snoops indicating the line was kept on this core in the (S)hared state, and that the data was found unmodified but not forwarded back to the requestor, initially the data was found in the cache in the (FSE) Forward, Shared state or Exclusive state.  A single snoop response from the core counts on all hyperthreads of the core.",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x4"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100400001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by PMM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x703C00001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x730000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by PMM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x703000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SNC_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x700800001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F3FFC0002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.LOCAL_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100400002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x703C00002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.REMOTE_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x703000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SNC_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x700800002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch (which bring data to L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10070",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L3.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x12380",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L3.REMOTE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x90002380",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts full cacheline writes (ItoM) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.ITOM.REMOTE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x90000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that have any type of response.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -370,126 +37,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F3FFC0477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.READS_TO_CORE.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100400477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x70C000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x700C00477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.READS_TO_CORE.REMOTE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F33000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x730000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x731800477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.READS_TO_CORE.REMOTE_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x703000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.READS_TO_CORE.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.READS_TO_CORE.SNC_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x700800477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -498,15 +45,5 @@
         "MSRValue": "0x10800",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.WRITE_ESTIMATE.MEMORY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0xFBFF80822",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
index 77d37db98b70..de651ff9f846 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
@@ -151,7 +151,7 @@
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS)))) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
+        "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
         "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
@@ -184,7 +184,7 @@
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
         "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -236,7 +236,7 @@
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
         "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE / tma_info_thread_clks",
-        "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
+        "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
         "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
@@ -246,7 +246,7 @@
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
+        "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
         "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
@@ -305,7 +305,7 @@
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
         "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -314,7 +314,7 @@
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
         "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -334,7 +334,7 @@
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
@@ -346,7 +346,7 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
@@ -398,6 +398,12 @@
         "MetricName": "tma_info_frontend_ipunknown_branch"
     },
     {
+        "BriefDescription": "Taken Branches retired Per Cycle",
+        "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks",
+        "MetricGroup": "Branches;FetchBW",
+        "MetricName": "tma_info_frontend_tbpc"
+    },
+    {
         "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
@@ -474,7 +480,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
-        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time",
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l1d_cache_fill_bw"
     },
@@ -486,7 +492,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
-        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time",
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l2_cache_fill_bw"
     },
@@ -504,7 +510,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
-        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time",
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l3_cache_fill_bw"
     },
@@ -523,7 +529,7 @@
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricGroup": "LockCont;Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_miss_latency"
     },
     {
@@ -555,7 +561,7 @@
         "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
+        "BriefDescription": "",
         "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
@@ -568,7 +574,7 @@
     },
     {
         "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
-        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time",
         "MetricGroup": "Power;Summary",
         "MetricName": "tma_info_system_core_frequency"
     },
@@ -586,14 +592,14 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3",
+        "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3",
         "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
         "MetricName": "tma_info_system_dram_bw_use",
         "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full"
     },
     {
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time",
+        "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / tma_info_system_time",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_system_gflops",
         "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width"
@@ -619,6 +625,19 @@
         "MetricThreshold": "tma_info_system_kernel_utilization > 0.05"
     },
     {
+        "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_mux",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
+    },
+    {
+        "BriefDescription": "Total package Power in Watts",
+        "MetricExpr": "power@energy\\-pkg@ * 15.6 / (tma_info_system_time * 1e6)",
+        "MetricGroup": "Power;SoC",
+        "MetricName": "tma_info_system_power"
+    },
+    {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
         "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)",
         "MetricGroup": "SMT",
@@ -631,6 +650,13 @@
         "MetricName": "tma_info_system_socket_clks"
     },
     {
+        "BriefDescription": "Run duration time in seconds",
+        "MetricExpr": "duration_time",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_time",
+        "MetricThreshold": "tma_info_system_time < 1"
+    },
+    {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Power",
@@ -691,12 +717,12 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache",
+        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache",
         "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
         "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache.  The L1 data cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
     {
@@ -761,7 +787,7 @@
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
-        "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
+        "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
         "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency",
@@ -781,7 +807,7 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
         "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
@@ -840,7 +866,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -849,7 +875,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -949,7 +975,7 @@
         "MetricExpr": "13 * LD_BLOCKS.NO_SR / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
-        "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_split_loads > 0.3",
         "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
@@ -965,7 +991,7 @@
     {
         "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)",
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
         "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
@@ -993,7 +1019,7 @@
         "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
-        "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
+        "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
         "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/metricgroups.json b/tools/perf/pmu-events/arch/x86/ivybridge/metricgroups.json
index 4193c90c3459..0863375bdead 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/metricgroups.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/metricgroups.json
@@ -9,6 +9,7 @@
     "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -34,6 +35,7 @@
     "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -51,6 +53,7 @@
     "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -78,6 +81,7 @@
     "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
     "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
+    "tma_divider_group": "Metrics contributing to tma_divider category",
     "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
     "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
     "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
@@ -103,6 +107,7 @@
     "tma_issueSpSt": "Metrics related by the issue $issueSpSt",
     "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
     "tma_issueTLB": "Metrics related by the issue $issueTLB",
+    "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
     "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
     "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
index 8fe0512c938f..714d5e6d21e7 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
@@ -151,7 +151,7 @@
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
+        "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
         "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
@@ -184,7 +184,7 @@
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
         "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -236,7 +236,7 @@
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
         "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
+        "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
         "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
@@ -246,7 +246,7 @@
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
+        "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
         "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
@@ -305,7 +305,7 @@
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
         "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -314,7 +314,7 @@
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
         "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -334,7 +334,7 @@
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
@@ -346,7 +346,7 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
@@ -398,6 +398,12 @@
         "MetricName": "tma_info_frontend_ipunknown_branch"
     },
     {
+        "BriefDescription": "Taken Branches retired Per Cycle",
+        "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks",
+        "MetricGroup": "Branches;FetchBW",
+        "MetricName": "tma_info_frontend_tbpc"
+    },
+    {
         "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
@@ -474,7 +480,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
-        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time",
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l1d_cache_fill_bw"
     },
@@ -486,7 +492,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
-        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time",
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l2_cache_fill_bw"
     },
@@ -504,7 +510,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
-        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time",
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l3_cache_fill_bw"
     },
@@ -523,7 +529,7 @@
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricGroup": "LockCont;Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_miss_latency"
     },
     {
@@ -555,7 +561,7 @@
         "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
+        "BriefDescription": "",
         "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
@@ -568,7 +574,7 @@
     },
     {
         "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
-        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time",
         "MetricGroup": "Power;Summary",
         "MetricName": "tma_info_system_core_frequency"
     },
@@ -586,14 +592,14 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time",
+        "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
         "MetricName": "tma_info_system_dram_bw_use",
         "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full"
     },
     {
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time",
+        "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / tma_info_system_time",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_system_gflops",
         "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width"
@@ -627,12 +633,25 @@
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
-        "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)",
+        "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
         "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)"
     },
     {
+        "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_mux",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
+    },
+    {
+        "BriefDescription": "Total package Power in Watts",
+        "MetricExpr": "(power@energy\\-pkg@ + power@energy\\-ram@) * 15.6 / (duration_time * 1e6)",
+        "MetricGroup": "Power;SoC",
+        "MetricName": "tma_info_system_power"
+    },
+    {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
         "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)",
         "MetricGroup": "SMT",
@@ -645,6 +664,13 @@
         "MetricName": "tma_info_system_socket_clks"
     },
     {
+        "BriefDescription": "Run duration time in seconds",
+        "MetricExpr": "duration_time",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_time",
+        "MetricThreshold": "tma_info_system_time < 1"
+    },
+    {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Power",
@@ -652,7 +678,7 @@
     },
     {
         "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]",
-        "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time",
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_uncore_frequency"
     },
@@ -711,12 +737,12 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache",
+        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache",
         "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
         "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache.  The L1 data cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
     {
@@ -790,7 +816,7 @@
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
-        "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
+        "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
         "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency",
@@ -810,7 +836,7 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
         "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
@@ -869,7 +895,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -878,7 +904,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -997,7 +1023,7 @@
         "MetricExpr": "13 * LD_BLOCKS.NO_SR / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
-        "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_split_loads > 0.3",
         "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
@@ -1013,7 +1039,7 @@
     {
         "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)",
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
         "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
@@ -1041,7 +1067,7 @@
         "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
-        "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
+        "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
         "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/metricgroups.json b/tools/perf/pmu-events/arch/x86/ivytown/metricgroups.json
index 4193c90c3459..0863375bdead 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/metricgroups.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/metricgroups.json
@@ -9,6 +9,7 @@
     "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -34,6 +35,7 @@
     "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -51,6 +53,7 @@
     "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -78,6 +81,7 @@
     "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
     "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
+    "tma_divider_group": "Metrics contributing to tma_divider category",
     "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
     "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
     "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
@@ -103,6 +107,7 @@
     "tma_issueSpSt": "Metrics related by the issue $issueSpSt",
     "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
     "tma_issueTLB": "Metrics related by the issue $issueTLB",
+    "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
     "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
     "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/frontend.json b/tools/perf/pmu-events/arch/x86/jaketown/frontend.json
index 3cb468da7011..97e7760aeb26 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/frontend.json
@@ -278,5 +278,13 @@
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Valid instructions written to IQ per cycle.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x17",
+        "EventName": "INSTS_WRITTEN_TO_IQ.INSTS",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
index f8c18741b360..6f636ea0f216 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
@@ -127,7 +127,7 @@
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
         "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -211,7 +211,7 @@
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
         "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -220,7 +220,7 @@
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
         "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -240,7 +240,7 @@
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
@@ -276,6 +276,12 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_lcp"
     },
     {
+        "BriefDescription": "Taken Branches retired Per Cycle",
+        "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks",
+        "MetricGroup": "Branches;FetchBW",
+        "MetricName": "tma_info_frontend_tbpc"
+    },
+    {
         "BriefDescription": "Total number of retired Instructions",
         "MetricExpr": "INST_RETIRED.ANY",
         "MetricGroup": "Summary;TmaL1;tma_L1_group",
@@ -290,7 +296,7 @@
     },
     {
         "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
-        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time",
         "MetricGroup": "Power;Summary",
         "MetricName": "tma_info_system_core_frequency"
     },
@@ -308,14 +314,14 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time",
+        "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
         "MetricName": "tma_info_system_dram_bw_use",
         "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_mem_bandwidth"
     },
     {
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time",
+        "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / tma_info_system_time",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_system_gflops",
         "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width"
@@ -349,12 +355,19 @@
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
-        "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)",
+        "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
         "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)"
     },
     {
+        "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_mux",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
+    },
+    {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
         "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)",
         "MetricGroup": "SMT",
@@ -367,6 +380,13 @@
         "MetricName": "tma_info_system_socket_clks"
     },
     {
+        "BriefDescription": "Run duration time in seconds",
+        "MetricExpr": "duration_time",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_time",
+        "MetricThreshold": "tma_info_system_time < 1"
+    },
+    {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Power",
@@ -374,7 +394,7 @@
     },
     {
         "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]",
-        "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time",
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_uncore_frequency"
     },
@@ -468,7 +488,7 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
         "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_info_system_dram_bw_use",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/metricgroups.json b/tools/perf/pmu-events/arch/x86/jaketown/metricgroups.json
index 7dc7eb0d3dd3..eb8fbd14138a 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/metricgroups.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/metricgroups.json
@@ -9,6 +9,7 @@
     "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -33,6 +34,7 @@
     "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -48,6 +50,7 @@
     "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -75,6 +78,7 @@
     "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
     "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
+    "tma_divider_group": "Metrics contributing to tma_divider category",
     "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
     "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
     "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
@@ -99,6 +103,7 @@
     "tma_issueSmSt": "Metrics related by the issue $issueSmSt",
     "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
     "tma_issueTLB": "Metrics related by the issue $issueTLB",
+    "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
     "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
     "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/other.json b/tools/perf/pmu-events/arch/x86/jaketown/other.json
index 42692fa24b6c..970839a9c786 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/other.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/other.json
@@ -34,14 +34,6 @@
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "Valid instructions written to IQ per cycle.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x17",
-        "EventName": "INSTS_WRITTEN_TO_IQ.INSTS",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock.",
         "Counter": "0,1,2,3",
         "EventCode": "0x63",
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json
index 15fb9921f4fc..b1a6bb867a1e 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json
@@ -418,6 +418,51 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of LLC prefetches that were  throttled due to Dynamic Prefetch Throttling.  The throttle requestor/source could be from the uncore/SOC or the Dead Block Predictor. Counts on a per core basis.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x29",
+        "EventName": "LLC_PREFETCHES_THROTTLED.DPT",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of LLC prefetches throttled due to Demand Throttle Prefetcher.  DTP Global Triggered with no Local Override. Counts on a per core basis.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x29",
+        "EventName": "LLC_PREFETCHES_THROTTLED.DTP",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of LLC prefetches not throttled by DTP due to local override.  These prefetches may still be throttled due to another throttler mechanism. Counts on a per core basis.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x29",
+        "EventName": "LLC_PREFETCHES_THROTTLED.DTP_OVERRIDE",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of LLC prefetches throttled due to LLC hit rate in <insert knob name here>. Counts on a per core basis.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x29",
+        "EventName": "LLC_PREFETCHES_THROTTLED.HIT_RATE",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x10",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of LLC prefetches throttled due to exceeding the XQ threshold set by either XQ_THRESOLD_DTP or LLC_XQ_THRESHOLD. Counts on a per core basis.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x29",
+        "EventName": "LLC_PREFETCHES_THROTTLED.XQ_THRESH",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Cycles when L1D is locked",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x42",
@@ -547,7 +592,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts Instructions with at least one architecturally visible load retired.",
+        "PublicDescription": "Counts Instructions with at least one architecturally visible load retired. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x81",
         "Unit": "cpu_core"
@@ -558,7 +603,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts all retired store instructions.",
+        "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x82",
         "Unit": "cpu_core"
@@ -568,7 +613,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_SWPF",
-        "PublicDescription": "Counts all retired software prefetch instructions.",
+        "PublicDescription": "Counts all retired software prefetch instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x84",
         "Unit": "cpu_core"
@@ -579,7 +624,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+        "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x87",
         "Unit": "cpu_core"
@@ -590,7 +635,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PublicDescription": "Counts retired load instructions with locked access.",
+        "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x21",
         "Unit": "cpu_core"
@@ -601,7 +646,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41",
         "Unit": "cpu_core"
@@ -612,7 +657,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x42",
         "Unit": "cpu_core"
@@ -623,7 +668,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS",
-        "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x9",
         "Unit": "cpu_core"
@@ -634,7 +679,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES",
-        "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xa",
         "Unit": "cpu_core"
@@ -645,7 +690,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x11",
         "Unit": "cpu_core"
@@ -656,7 +701,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x12",
         "Unit": "cpu_core"
@@ -667,7 +712,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)",
+        "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$) Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -678,7 +723,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -689,7 +734,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -700,7 +745,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -711,6 +756,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.MEMSIDE_CACHE",
+        "PublicDescription": "Retired load instructions which data source is memory side cache. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "Unit": "cpu_core"
     },
@@ -720,7 +766,7 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -731,7 +777,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -742,7 +788,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -752,6 +798,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT_L1",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "Unit": "cpu_core"
     },
@@ -761,7 +808,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -772,7 +819,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -783,7 +830,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -794,7 +841,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -805,7 +852,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1184,23 +1231,85 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts writebacks of modified cachelines that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10008",
+        "PublicDescription": "Counts writebacks of modified cachelines that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts writebacks of non-modified cachelines that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.COREWB_NONM.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x11000",
+        "PublicDescription": "Counts writebacks of non-modified cachelines that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by mem side cache.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_CODE_RD.MEMSIDE_CACHE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x11F80000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by mem side cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x40001E00001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1212,6 +1321,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x20001E00001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1223,17 +1333,43 @@
         "EventName": "OCR.DEMAND_DATA_RD.MEMSIDE_CACHE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x11F80000001",
+        "PublicDescription": "Counts demand data reads that were supplied by mem side cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x40001E00002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json
index 07bd38a1904e..e2facc4086e9 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json
@@ -108,7 +108,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)",
+        "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -120,7 +120,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -169,7 +169,7 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -199,7 +199,7 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -211,7 +211,7 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -223,7 +223,7 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -235,7 +235,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -247,7 +247,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -259,7 +259,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -271,7 +271,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -283,7 +283,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -295,7 +295,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -307,7 +307,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -319,7 +319,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -331,7 +331,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -343,7 +343,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -355,7 +355,7 @@
         "EventName": "FRONTEND_RETIRED.MISP_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PublicDescription": "ANT retired branches that got just mispredicted",
+        "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -367,6 +367,7 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "Counts flows delivered by the Microcode Sequencer Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -396,7 +397,7 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -408,7 +409,7 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
-        "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json b/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json
index e748f839c4bd..3c740962e63e 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json
@@ -89,7 +89,7 @@
         "MetricExpr": "tma_core_bound",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_allocation_restriction",
-        "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -99,7 +99,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
-        "MetricThreshold": "(tma_backend_bound >0.10)",
+        "MetricThreshold": "tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
         "ScaleUnit": "100%",
@@ -111,7 +111,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
-        "MetricThreshold": "(tma_bad_speculation >0.15)",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%",
@@ -122,7 +122,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_detect",
-        "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -132,7 +132,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
-        "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -142,7 +142,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_resteer",
-        "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -151,7 +151,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -160,7 +160,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
-        "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -170,7 +170,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_decode",
-        "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -179,7 +179,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
-        "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -189,7 +189,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
-        "MetricThreshold": "(tma_frontend_bound >0.20)",
+        "MetricThreshold": "tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -199,7 +199,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -208,7 +208,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_bandwidth",
-        "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -218,7 +218,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_latency",
-        "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -578,7 +578,7 @@
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
         "MetricName": "tma_info_system_mux",
-        "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9",
         "Unit": "cpu_atom"
     },
     {
@@ -617,7 +617,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB_MISS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -626,7 +626,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
-        "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -636,7 +636,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
-        "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -645,7 +645,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
-        "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -654,7 +654,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
-        "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -663,7 +663,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_other_fb",
-        "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -672,7 +672,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_predecode",
-        "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -681,7 +681,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
-        "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -690,7 +690,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
-        "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -699,7 +699,7 @@
         "MetricExpr": "tma_backend_bound - tma_core_bound",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_resource_bound",
-        "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -710,7 +710,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
-        "MetricThreshold": "(tma_retiring >0.75)",
+        "MetricThreshold": "tma_retiring > 0.75",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -720,12 +720,12 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
-        "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "cpu_core@UOPS_DISPATCHED.ALU@ / (6 * tma_info_thread_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -738,13 +738,13 @@
         "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
         "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
@@ -755,7 +755,7 @@
     {
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -767,18 +767,18 @@
     {
         "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-bad\\-spec / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-bad\\-spec@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20",
@@ -795,16 +795,16 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
-        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full",
+        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -813,16 +813,16 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy",
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20",
@@ -830,7 +830,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -839,7 +839,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -848,16 +848,16 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
-        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -870,11 +870,11 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls",
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -883,7 +883,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
-        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -897,26 +897,26 @@
         "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c01_wait",
-        "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c02_wait",
-        "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -925,8 +925,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -935,99 +935,100 @@
         "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
-        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@frontend_retired.l1i_miss@R / tma_info_thread_clks - tma_code_l2_miss)",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
+        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@FRONTEND_RETIRED.L1I_MISS@R / tma_info_thread_clks - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@frontend_retired.l2_miss@R / tma_info_thread_clks",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@FRONTEND_RETIRED.L2_MISS@R / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)",
-        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@frontend_retired.itlb_miss@R / tma_info_thread_clks - tma_code_stlb_miss)",
+        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@FRONTEND_RETIRED.ITLB_MISS@R / tma_info_thread_clks - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@frontend_retired.stlb_miss@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@FRONTEND_RETIRED.STLB_MISS@R / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@br_misp_retired.cond_ntaken_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_nt_mispredicts",
-        "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@ * cpu_core@br_misp_retired.cond_taken_bwd_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_tk_bwd_mispredicts",
-        "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@ * cpu_core@br_misp_retired.cond_taken_fwd_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_tk_fwd_mispredicts",
-        "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * cpu_core@mem_load_l3_hit_retired.xsnp_miss@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_miss@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@R, 25 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1038,17 +1039,18 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 25 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1057,7 +1059,7 @@
         "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1067,7 +1069,7 @@
         "MetricExpr": "cpu_core@MEMORY_STALLS.MEM@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1078,7 +1080,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1087,28 +1089,28 @@
         "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * cpu_core@mem_inst_retired.stlb_hit_loads@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_loads@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) / tma_info_thread_clks + tma_load_stlb_miss",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@R, 7) / tma_info_thread_clks + tma_load_stlb_miss",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * cpu_core@mem_inst_retired.stlb_hit_stores@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_stores@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) / tma_info_thread_clks + tma_store_stlb_miss",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@R, 7) / tma_info_thread_clks + tma_store_stlb_miss",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1117,8 +1119,8 @@
         "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1128,7 +1130,7 @@
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1145,12 +1147,12 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
-        "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1160,7 +1162,7 @@
         "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0",
         "MetricName": "tma_few_uops_instructions",
         "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1170,7 +1172,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1180,16 +1182,16 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1198,8 +1200,8 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1208,8 +1210,8 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1218,8 +1220,8 @@
         "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1228,41 +1230,41 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
-        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1271,26 +1273,26 @@
         "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ind_call_mispredicts",
-        "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions",
-        "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@br_misp_retired.indirect_cost@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R) / tma_info_thread_clks, 0)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions.",
+        "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_COST@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R) / tma_info_thread_clks, 0)",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ind_jump_mispredicts",
-        "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1303,7 +1305,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
@@ -1311,29 +1313,29 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_bwd",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_fwd",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000",
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -1357,7 +1359,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -1366,7 +1368,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -1375,10 +1377,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
         "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
@@ -1444,12 +1447,12 @@
         "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.V0@ + cpu_core@FP_ARITH_DISPATCHED.V1@ + cpu_core@FP_ARITH_DISPATCHED.V2@ + cpu_core@FP_ARITH_DISPATCHED.V3@) / (4 * tma_info_thread_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)",
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp",
         "Unit": "cpu_core"
@@ -1464,15 +1467,15 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@frontend_retired.any_dsb_miss@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@R / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;Fed;FetchLat",
         "MetricName": "tma_info_frontend_dsb_switches_ret",
         "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05",
@@ -1480,7 +1483,7 @@
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc",
         "Unit": "cpu_core"
@@ -1530,7 +1533,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@frontend_retired.ms_flows@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@FRONTEND_RETIRED.MS_FLOWS@R / tma_info_thread_clks",
         "MetricGroup": "Fed;FetchLat;MicroSeq",
         "MetricName": "tma_info_frontend_ms_latency_ret",
         "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05",
@@ -1545,21 +1548,21 @@
     },
     {
         "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
-        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed",
         "MetricName": "tma_info_frontend_unknown_branch_cost",
-        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node",
+        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@frontend_retired.unknown_branch@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@R / tma_info_thread_clks",
         "MetricGroup": "Fed;FetchLat",
         "MetricName": "tma_info_frontend_unknown_branches_ret",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch",
@@ -1579,7 +1582,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW",
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.",
         "Unit": "cpu_core"
     },
     {
@@ -1588,7 +1591,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1597,7 +1600,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1606,7 +1609,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1615,7 +1618,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1678,7 +1681,7 @@
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 8 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 17",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp",
         "Unit": "cpu_core"
     },
@@ -1803,7 +1806,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp",
         "Unit": "cpu_core"
@@ -1861,7 +1864,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads",
-        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@mem_inst_retired.stlb_miss_loads@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@R / tma_info_thread_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret",
         "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05",
@@ -1884,7 +1887,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores",
-        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@mem_inst_retired.stlb_miss_stores@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@R / tma_info_thread_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret",
         "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05",
@@ -1923,20 +1926,20 @@
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "MicroSeq;Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
@@ -1981,23 +1984,22 @@
     },
     {
         "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
-        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000",
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_utilization",
         "MetricThreshold": "tma_info_system_kernel_utilization > 0.05",
@@ -2034,7 +2036,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks",
@@ -2045,7 +2047,6 @@
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
         "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr",
         "Unit": "cpu_core"
     },
     {
@@ -2053,7 +2054,7 @@
         "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage",
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
         "Unit": "cpu_core"
     },
     {
@@ -2065,7 +2066,7 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "cpu_core@TOPDOWN.SLOTS@",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots",
         "Unit": "cpu_core"
@@ -2083,15 +2084,15 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 8 * 1.5",
+        "MetricThreshold": "tma_info_thread_uptb < 12",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2101,7 +2102,7 @@
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_int_operations",
         "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2110,8 +2111,8 @@
         "MetricExpr": "cpu_core@INT_VEC_RETIRED.128BIT@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_128b",
-        "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2120,8 +2121,8 @@
         "MetricExpr": "cpu_core@INT_VEC_RETIRED.256BIT@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_256b",
-        "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2130,8 +2131,8 @@
         "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2140,17 +2141,17 @@
         "MetricExpr": "cpu_core@MEMORY_STALLS.L1@ / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache",
-        "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * cpu_core@mem_load_retired.l1_hit_l1@R, cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) if 0 < cpu_core@mem_load_retired.l1_hit_l1@R else cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) / tma_info_thread_clks",
+        "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache.",
+        "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * min(cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@R, 9) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_capacity",
-        "MetricThreshold": "tma_l1_latency_capacity > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_capacity > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2159,8 +2160,8 @@
         "MetricExpr": "4 * cpu_core@DEPENDENT_LOADS.ANY@ / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: DEPENDENT_LOADS.ANY",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2169,17 +2170,18 @@
         "MetricExpr": "cpu_core@MEMORY_STALLS.L2@ / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
-        "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * cpu_core@mem_load_retired.l2_hit@R, cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) if 0 < cpu_core@mem_load_retired.l2_hit@R else cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@R, 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2189,18 +2191,19 @@
         "MetricExpr": "cpu_core@MEMORY_STALLS.L3@ / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * cpu_core@mem_load_retired.l3_hit@R, cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_retired.l3_hit@R else cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, 9 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2209,19 +2212,19 @@
         "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2231,7 +2234,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_load_op_utilization",
         "MetricThreshold": "tma_load_op_utilization > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.LOAD",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2240,7 +2243,7 @@
         "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2249,43 +2252,43 @@
         "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
-        "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@mem_inst_retired.lock_loads@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2296,7 +2299,7 @@
         "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_lsd",
         "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2307,17 +2310,17 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_sq_full",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2326,34 +2329,34 @@
         "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
-        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
-        "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -2376,14 +2379,14 @@
         "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)",
-        "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks",
+        "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / 2 + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
@@ -2392,17 +2395,17 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
         "MetricExpr": "cpu_core@IDQ.MS_CYCLES_ANY@ / tma_info_thread_clks",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
@@ -2415,7 +2418,7 @@
         "MetricExpr": "3 * cpu_core@IDQ.MS_SWITCHES@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2426,7 +2429,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2435,7 +2438,7 @@
         "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2451,20 +2454,20 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2474,7 +2477,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_page_faults",
         "MetricThreshold": "tma_page_faults > 0.05",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2483,8 +2486,8 @@
         "MetricExpr": "((cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2493,8 +2496,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2503,7 +2506,7 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2514,8 +2517,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2525,24 +2528,24 @@
         "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@br_misp_retired.ret_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@BR_MISP_RETIRED.RET_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ret_mispredicts",
-        "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ret_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2556,8 +2559,8 @@
         "MetricExpr": "(cpu_core@BE_STALLS.SCOREBOARD@ + cpu_core@CPU_CLK_UNHALTED.C02@) / tma_info_thread_clks",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: BE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2566,8 +2569,8 @@
         "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_shuffles_256b",
-        "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+        "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2577,28 +2580,28 @@
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * cpu_core@mem_inst_retired.split_loads@R, cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) if 0 < cpu_core@mem_inst_retired.split_loads@R else cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@R, tma_info_memory_load_miss_real_latency) / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * cpu_core@mem_inst_retired.split_stores@R, cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) if 0 < cpu_core@mem_inst_retired.split_stores@R else cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@R, 1) / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2607,8 +2610,8 @@
         "MetricExpr": "(cpu_core@XQ.FULL@ + cpu_core@L1D_MISS.L2_STALLS@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2617,8 +2620,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2627,8 +2630,8 @@
         "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2637,8 +2640,8 @@
         "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2648,7 +2651,6 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_store_op_utilization",
         "MetricThreshold": "tma_store_op_utilization > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.STD, UOPS_DISPATCHED.STA",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2657,7 +2659,7 @@
         "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2666,34 +2668,34 @@
         "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2702,7 +2704,7 @@
         "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2712,7 +2714,7 @@
         "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2722,8 +2724,8 @@
         "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     }
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json
index 60daff922a89..8021a1c7dd3b 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json
@@ -163,7 +163,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x400",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "53",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -176,7 +176,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "1009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -189,7 +189,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -202,7 +202,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x800",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "23",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -215,7 +215,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "503",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -228,7 +228,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -241,7 +241,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -254,7 +254,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "101",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -267,7 +267,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "2003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -280,7 +280,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -291,7 +291,7 @@
         "Data_LA": "1",
         "EventCode": "0xcd",
         "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
-        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
+        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -315,23 +315,61 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1FBC000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x13FBFC00004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1FBC000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1E780000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x13FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -343,17 +381,31 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x9E7FA000001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1FBC000002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x13FBFC00002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -365,6 +417,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x9E7FA000002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/other.json b/tools/perf/pmu-events/arch/x86/lunarlake/other.json
index 667707d4fe37..59949f9541d8 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/other.json
@@ -19,15 +19,6 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0xa2",
-        "EventName": "BE_STALLS.SCOREBOARD",
-        "SampleAfterValue": "100003",
-        "UMask": "0x2",
-        "Unit": "cpu_core"
-    },
-    {
         "BriefDescription": "Counts the number of unhalted cycles a Core is blocked due to a lock In Progress issued by another core",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x63",
@@ -66,15 +57,6 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or  2 cycles back. This event supports in-direct dependency through a single uop.",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x02",
-        "EventName": "DEPENDENT_LOADS.ANY",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
         "BriefDescription": "Counts the number of cycles the L2 Prefetchers are at throttle level 0",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x32",
@@ -120,297 +102,13 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of uops executed on all Integer ports.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.ALL",
-        "SampleAfterValue": "1000003",
-        "UMask": "0xff",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on a load port.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.LD",
-        "PublicDescription": "Counts the number of uops executed on a load port.  This event counts for integer uops even if the destination is FP/vector",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on integer port 0.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.P0",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x8",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on integer port 1.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.P1",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x10",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on integer port 2.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.P2",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x20",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on integer port 3.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.P3",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x40",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on integer port  0,1, 2, 3.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.PRIMARY",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x78",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on a Store address port.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.STA",
-        "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x2",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.STD_JMP",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x4",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of LLC prefetches that were  throttled due to Dynamic Prefetch Throttling.  The throttle requestor/source could be from the uncore/SOC or the Dead Block Predictor. Counts on a per core basis.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x29",
-        "EventName": "LLC_PREFETCHES_THROTTLED.DPT",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of LLC prefetches throttled due to Demand Throttle Prefetcher.  DTP Global Triggered with no Local Override. Counts on a per core basis.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x29",
-        "EventName": "LLC_PREFETCHES_THROTTLED.DTP",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x2",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of LLC prefetches not throttled by DTP due to local override.  These prefetches may still be throttled due to another throttler mechanism. Counts on a per core basis.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x29",
-        "EventName": "LLC_PREFETCHES_THROTTLED.DTP_OVERRIDE",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x4",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of LLC prefetches throttled due to LLC hit rate in <insert knob name here>. Counts on a per core basis.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x29",
-        "EventName": "LLC_PREFETCHES_THROTTLED.HIT_RATE",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x10",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of LLC prefetches throttled due to exceeding the XQ threshold set by either XQ_THRESOLD_DTP or LLC_XQ_THRESHOLD. Counts on a per core basis.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x29",
-        "EventName": "LLC_PREFETCHES_THROTTLED.XQ_THRESH",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x8",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x46",
-        "EventName": "MEMORY_STALLS.L1",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x46",
-        "EventName": "MEMORY_STALLS.L2",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x2",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x46",
-        "EventName": "MEMORY_STALLS.L3",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x4",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x46",
-        "EventName": "MEMORY_STALLS.MEM",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x8",
-        "Unit": "cpu_core"
-    },
-    {
         "BriefDescription": "Counts all requests that have any type of response.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.ALL_REQUESTS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0xFF0000001DFFF",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts writebacks of modified cachelines that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10008",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts writebacks of non-modified cachelines that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.COREWB_NONM.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x11000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1FBC000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1FBC000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1E780000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1FBC000002",
+        "PublicDescription": "Counts all requests that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -422,6 +120,7 @@
         "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x800000010000",
+        "PublicDescription": "Counts full streaming stores (64 bytes, WCiLF) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -433,6 +132,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x400000010000",
+        "PublicDescription": "Counts partial streaming stores (less than 64 bytes, WCiL) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -444,6 +144,7 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -455,61 +156,12 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "CounterMask": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_COUNT",
-        "Invert": "1",
-        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_RESOURCE",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x4",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number issue slots not consumed  due to a  color request for an FCW or MXCSR control register when all 4 colors (copies) are already in use",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.COLOR_STALLS",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x8",
-        "Unit": "cpu_atom"
-    },
-    {
         "BriefDescription": "Cycles the uncore cannot take further requests",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "CounterMask": "1",
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
index f4ec7a884937..4875047fb65c 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
@@ -88,6 +88,15 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0xa2",
+        "EventName": "BE_STALLS.SCOREBOARD",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts the total number of branch instructions retired for all branch types.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
@@ -101,7 +110,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all branch instructions retired.",
+        "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -119,7 +128,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
-        "PublicDescription": "Counts conditional branch instructions retired.",
+        "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x111",
         "Unit": "cpu_core"
@@ -138,7 +147,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts not taken branch instructions retired.",
+        "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -157,7 +166,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional branch instructions retired.",
+        "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x101",
         "Unit": "cpu_core"
@@ -167,7 +176,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN_BWD",
-        "PublicDescription": "Counts taken backward conditional branch instructions retired.",
+        "PublicDescription": "Counts taken backward conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -177,7 +186,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN_FWD",
-        "PublicDescription": "Counts taken forward conditional branch instructions retired.",
+        "PublicDescription": "Counts taken forward conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x102",
         "Unit": "cpu_core"
@@ -196,7 +205,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "PublicDescription": "Counts far branch instructions retired.",
+        "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -215,7 +224,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
-        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -252,7 +261,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -271,7 +280,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "Counts return instructions retired.",
+        "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -290,7 +299,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts taken branch instructions retired.",
+        "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -318,7 +327,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -327,6 +336,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST",
+        "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x44",
         "Unit": "cpu_core"
@@ -345,7 +355,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
-        "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x111",
         "Unit": "cpu_core"
@@ -355,6 +365,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_COST",
+        "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x151",
         "Unit": "cpu_core"
@@ -373,7 +384,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
+        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -383,6 +394,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST",
+        "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x50",
         "Unit": "cpu_core"
@@ -401,7 +413,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x101",
         "Unit": "cpu_core"
@@ -411,7 +423,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD",
-        "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -421,6 +433,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST",
+        "PublicDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x8001",
         "Unit": "cpu_core"
@@ -430,6 +443,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST",
+        "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x141",
         "Unit": "cpu_core"
@@ -439,7 +453,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD",
-        "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -448,6 +462,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST",
+        "PublicDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x8002",
         "Unit": "cpu_core"
@@ -466,7 +481,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
-        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -485,7 +500,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
-        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
+        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -495,6 +510,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST",
+        "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x42",
         "Unit": "cpu_core"
@@ -504,6 +520,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_COST",
+        "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xc0",
         "Unit": "cpu_core"
@@ -531,7 +548,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -541,6 +558,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST",
+        "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x60",
         "Unit": "cpu_core"
@@ -550,7 +568,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -569,6 +587,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET_COST",
+        "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x48",
         "Unit": "cpu_core"
@@ -758,6 +777,15 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or  2 cycles back. This event supports in-direct dependency through a single uop.",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x02",
+        "EventName": "DEPENDENT_LOADS.ANY",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xa6",
@@ -851,6 +879,7 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired.",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Fixed Counter: Counts the number of instructions retired. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -859,7 +888,7 @@
         "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -877,7 +906,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "Unit": "cpu_core"
     },
@@ -886,6 +915,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.BR_FUSED",
+        "PublicDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon) Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -895,6 +925,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x30",
         "Unit": "cpu_core"
@@ -904,7 +935,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
-        "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions",
+        "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -913,7 +944,7 @@
         "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.PREC_DIST",
-        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
+        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -923,7 +954,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -993,6 +1024,89 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of uops executed on all Integer ports.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.ALL",
+        "SampleAfterValue": "1000003",
+        "UMask": "0xff",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on a load port.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.LD",
+        "PublicDescription": "Counts the number of uops executed on a load port.  This event counts for integer uops even if the destination is FP/vector",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on integer port 0.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.P0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on integer port 1.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.P1",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x10",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on integer port 2.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.P2",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x20",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on integer port 3.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.P3",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x40",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on integer port  0,1, 2, 3.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.PRIMARY",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x78",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on a Store address port.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.STA",
+        "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.STD_JMP",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Number of vector integer instructions retired of 128-bit vector-width.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xe7",
@@ -1268,6 +1382,42 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x46",
+        "EventName": "MEMORY_STALLS.L1",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x46",
+        "EventName": "MEMORY_STALLS.L2",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x46",
+        "EventName": "MEMORY_STALLS.L3",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x46",
+        "EventName": "MEMORY_STALLS.MEM",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "LFENCE instructions retired",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xe0",
@@ -1291,6 +1441,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xe4",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
+        "PublicDescription": "LBR record is inserted Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1394,6 +1545,56 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_COUNT",
+        "Invert": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_RESOURCE",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number issue slots not consumed  due to a  color request for an FCW or MXCSR control register when all 4 colors (copies) are already in use",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.COLOR_STALLS",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x75",
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 56d5fc419acf..bde2f32423a1 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -1,7 +1,7 @@
 Family-model,Version,Filename,EventType
-GenuineIntel-6-(97|9A|B7|BA|BF),v1.28,alderlake,core
-GenuineIntel-6-BE,v1.28,alderlaken,core
-GenuineIntel-6-C[56],v1.07,arrowlake,core
+GenuineIntel-6-(97|9A|B7|BA|BF),v1.29,alderlake,core
+GenuineIntel-6-BE,v1.29,alderlaken,core
+GenuineIntel-6-C[56],v1.08,arrowlake,core
 GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core
 GenuineIntel-6-(3D|47),v30,broadwell,core
 GenuineIntel-6-56,v12,broadwellde,core
@@ -12,8 +12,8 @@ GenuineIntel-6-9[6C],v1.05,elkhartlake,core
 GenuineIntel-6-CF,v1.11,emeraldrapids,core
 GenuineIntel-6-5[CF],v13,goldmont,core
 GenuineIntel-6-7A,v1.01,goldmontplus,core
-GenuineIntel-6-B6,v1.05,grandridge,core
-GenuineIntel-6-A[DE],v1.06,graniterapids,core
+GenuineIntel-6-B6,v1.07,grandridge,core
+GenuineIntel-6-A[DE],v1.08,graniterapids,core
 GenuineIntel-6-(3C|45|46),v36,haswell,core
 GenuineIntel-6-3F,v29,haswellx,core
 GenuineIntel-6-7[DE],v1.24,icelake,core
@@ -23,13 +23,13 @@ GenuineIntel-6-3E,v24,ivytown,core
 GenuineIntel-6-2D,v24,jaketown,core
 GenuineIntel-6-(57|85),v16,knightslanding,core
 GenuineIntel-6-BD,v1.11,lunarlake,core
-GenuineIntel-6-(AA|AC|B5),v1.12,meteorlake,core
+GenuineIntel-6-(AA|AC|B5),v1.13,meteorlake,core
 GenuineIntel-6-1[AEF],v4,nehalemep,core
 GenuineIntel-6-2E,v4,nehalemex,core
 GenuineIntel-6-A7,v1.04,rocketlake,core
 GenuineIntel-6-2A,v19,sandybridge,core
 GenuineIntel-6-8F,v1.25,sapphirerapids,core
-GenuineIntel-6-AF,v1.08,sierraforest,core
+GenuineIntel-6-AF,v1.09,sierraforest,core
 GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core
 GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v59,skylake,core
 GenuineIntel-6-55-[01234],v1.36,skylakex,core
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
index ce351cd7caaf..c980bbee6146 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
@@ -1,9 +1,20 @@
 [
     {
+        "BriefDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x51",
+        "EventName": "DL1.DIRTY_EVICTION",
+        "PublicDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.  Does not count evictions or dirty writebacks caused by snoops.  Does not count a replacement unless a (dirty) line was written back.",
+        "SampleAfterValue": "200003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "L1D.HWPF_MISS",
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.HWPF_MISS",
+        "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -13,7 +24,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.REPLACEMENT",
-        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -23,7 +34,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -35,7 +46,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS",
-        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -45,7 +56,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALLS",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -55,7 +66,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING",
-        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -66,7 +77,7 @@
         "CounterMask": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
-        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -76,27 +87,87 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x25",
         "EventName": "L2_LINES_IN.ALL",
-        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1f",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.E",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.F",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x10",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.M",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.S",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x26",
+        "EventName": "L2_LINES_OUT.NON_SILENT",
+        "PublicDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill. Increments on the core that brought the line in originally.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.",
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.NON_SILENT",
-        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
+        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x26",
+        "EventName": "L2_LINES_OUT.SILENT",
+        "PublicDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill.  Increments on the core that brought the line in originally.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.SILENT",
-        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -106,7 +177,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.USELESS_HWPF",
-        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
+        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -116,37 +187,64 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.ALL",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of L2 Cache Accesses that resulted in a Hit from a front door request only (does not include rejects or recycles), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.HIT",
+        "SampleAfterValue": "200003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "All requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]",
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.HIT",
-        "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]",
+        "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xdf",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of total L2 Cache Accesses that resulted in a Miss from a front door request only (does not include rejects or recycles), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.MISS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]",
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of L2 Cache Accesses that miss the L2 and get BBL reject  short and long rejects (includes those counted in L2_reject_XQ.any), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.REJECTS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "L2 code requests",
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "PublicDescription": "Counts the total number of L2 code requests.",
+        "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe4",
         "Unit": "cpu_core"
@@ -156,7 +254,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe1",
         "Unit": "cpu_core"
@@ -166,7 +264,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "PublicDescription": "Counts demand requests that miss L2 cache.",
+        "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x27",
         "Unit": "cpu_core"
@@ -176,7 +274,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
-        "PublicDescription": "Counts demand requests to L2 cache.",
+        "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe7",
         "Unit": "cpu_core"
@@ -186,6 +284,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_HWPF",
+        "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf0",
         "Unit": "cpu_core"
@@ -195,7 +294,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_RFO",
-        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe2",
         "Unit": "cpu_core"
@@ -205,7 +304,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
+        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc4",
         "Unit": "cpu_core"
@@ -215,7 +314,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+        "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x24",
         "Unit": "cpu_core"
@@ -225,7 +324,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc1",
         "Unit": "cpu_core"
@@ -235,7 +334,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
-        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21",
         "Unit": "cpu_core"
@@ -245,7 +344,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.HIT",
-        "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]",
+        "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xdf",
         "Unit": "cpu_core"
@@ -255,6 +354,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.HWPF_MISS",
+        "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x30",
         "Unit": "cpu_core"
@@ -264,7 +364,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f",
         "Unit": "cpu_core"
@@ -274,7 +374,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.REFERENCES",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff",
         "Unit": "cpu_core"
@@ -284,7 +384,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_HIT",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc2",
         "Unit": "cpu_core"
@@ -294,7 +394,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_MISS",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x22",
         "Unit": "cpu_core"
@@ -304,7 +404,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_HIT",
-        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc8",
         "Unit": "cpu_core"
@@ -314,7 +414,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_MISS",
-        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x28",
         "Unit": "cpu_core"
@@ -324,7 +424,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x23",
         "EventName": "L2_TRANS.L2_WB",
-        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+        "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -334,7 +434,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x42",
         "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION",
-        "PublicDescription": "This event counts the number of cycles when the L1D is locked. It is a superset of the 0x1 mask (BUS_LOCK_CLOCKS.BUS_LOCK_DURATION).",
+        "PublicDescription": "This event counts the number of cycles when the L1D is locked. It is a superset of the 0x1 mask (BUS_LOCK_CLOCKS.BUS_LOCK_DURATION). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -354,7 +454,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.MISS",
-        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41",
         "Unit": "cpu_core"
@@ -374,7 +474,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4f",
         "Unit": "cpu_core"
@@ -399,6 +499,15 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which missed in the L2 cache.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x35",
+        "EventName": "MEM_BOUND_STALLS_IFETCH.L2_MISS",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7e",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an ICACHE or ITLB miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x35",
@@ -436,6 +545,15 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which missed in the L2 cache.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS_LOAD.L2_MISS",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7e",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x34",
@@ -454,12 +572,21 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS_LOAD.SBFULL",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x80",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Retired load instructions.",
         "Counter": "0,1,2,3",
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
+        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x81",
         "Unit": "cpu_core"
@@ -470,7 +597,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts all retired store instructions.",
+        "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x82",
         "Unit": "cpu_core"
@@ -481,7 +608,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+        "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x83",
         "Unit": "cpu_core"
@@ -492,7 +619,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PublicDescription": "Counts retired load instructions with locked access.",
+        "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x21",
         "Unit": "cpu_core"
@@ -503,7 +630,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41",
         "Unit": "cpu_core"
@@ -514,7 +641,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x42",
         "Unit": "cpu_core"
@@ -525,7 +652,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS",
-        "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x9",
         "Unit": "cpu_core"
@@ -536,7 +663,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES",
-        "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xa",
         "Unit": "cpu_core"
@@ -547,7 +674,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x11",
         "Unit": "cpu_core"
@@ -558,7 +685,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x12",
         "Unit": "cpu_core"
@@ -568,7 +695,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY",
-        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)",
+        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfd",
         "Unit": "cpu_core"
@@ -579,7 +706,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -590,7 +717,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -601,7 +728,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
+        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -612,7 +739,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -623,7 +750,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
-        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
+        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -634,7 +761,7 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -645,7 +772,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -656,7 +783,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -667,7 +794,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -678,7 +805,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -689,7 +816,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -700,7 +827,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -711,7 +838,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -820,6 +947,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x44",
         "EventName": "MEM_STORE_RETIRED.L2_HIT",
+        "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1049,18 +1177,31 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe5",
         "EventName": "MEM_UOP_RETIRED.ANY",
-        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses",
+        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1072,6 +1213,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1083,6 +1225,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1094,17 +1237,43 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1116,6 +1285,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1127,6 +1297,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1138,6 +1309,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1149,6 +1321,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1160,6 +1333,31 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1171,6 +1369,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1182,6 +1381,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1193,6 +1393,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1202,7 +1403,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
-        "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..",
+        "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc.. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -1212,7 +1413,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DATA_RD",
-        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1222,7 +1423,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
-        "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.",
+        "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1232,7 +1433,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1242,7 +1443,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
-        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1253,7 +1454,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
-        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1264,7 +1465,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1275,6 +1476,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1285,7 +1487,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
-        "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1295,6 +1497,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1304,7 +1507,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1314,7 +1517,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
+        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1324,7 +1527,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
-        "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.",
+        "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1334,7 +1537,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x2c",
         "EventName": "SQ_MISC.BUS_LOCK",
-        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
+        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1344,6 +1547,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.ANY",
+        "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xf",
         "Unit": "cpu_core"
@@ -1353,7 +1557,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.NTA",
-        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1363,7 +1567,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
-        "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1373,7 +1577,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T0",
-        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1383,7 +1587,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T1_T2",
-        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json b/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json
index 28dc5e06ee31..ae9778aa755b 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json
@@ -15,6 +15,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FPDIV_ACTIVE",
+        "PublicDescription": "This event counts the cycles the floating point divider is busy. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -24,7 +25,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.FP",
-        "PublicDescription": "Counts all microcode Floating Point assists.",
+        "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -34,6 +35,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.SSE_AVX_MIX",
+        "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -43,6 +45,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -52,6 +55,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -61,6 +65,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_5",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -70,6 +75,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -79,6 +85,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -88,6 +95,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V2",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -97,7 +105,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -107,7 +115,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -117,7 +125,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -127,7 +135,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -137,7 +145,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x18",
         "Unit": "cpu_core"
@@ -147,7 +155,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -157,7 +165,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -167,7 +175,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -177,7 +185,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.VECTOR",
-        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfc",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
index a10614513c8d..509ce68c2ea6 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
@@ -14,7 +14,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x60",
         "EventName": "BACLEARS.ANY",
-        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -24,7 +24,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.LCP",
-        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -34,6 +34,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.MS_BUSY",
+        "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -43,7 +44,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x61",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
+        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -55,7 +56,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)",
+        "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -67,7 +68,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -79,7 +80,7 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -100,7 +101,7 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -112,7 +113,7 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -124,7 +125,7 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -136,7 +137,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600106",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -148,7 +149,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -160,7 +161,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -172,7 +173,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -184,7 +185,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -196,7 +197,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -208,7 +209,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -220,7 +221,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -232,7 +233,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -244,7 +245,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -256,7 +257,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -268,7 +269,7 @@
         "EventName": "FRONTEND_RETIRED.MISP_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PublicDescription": "ANT retired branches that got just mispredicted",
+        "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -280,6 +281,7 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -291,7 +293,7 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -303,6 +305,7 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
+        "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -330,7 +333,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALLS",
-        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
+        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -342,6 +345,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALL_PERIODS",
+        "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -351,7 +355,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x83",
         "EventName": "ICACHE_TAG.STALLS",
-        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -362,7 +366,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -373,7 +377,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -383,7 +387,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -394,7 +398,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -405,7 +409,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -415,7 +419,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -426,7 +430,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_CYCLES_ANY",
-        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -438,7 +442,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_SWITCHES",
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -448,7 +452,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -458,7 +462,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CORE",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -469,7 +473,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -481,7 +485,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -491,7 +495,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -502,7 +506,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -514,7 +518,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json
index e4481fbc1e13..17b94f810d5a 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json
@@ -5,6 +5,7 @@
         "CounterMask": "2",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS",
+        "PublicDescription": "Cycles while L3 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -15,6 +16,7 @@
         "CounterMask": "6",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
+        "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x6",
         "Unit": "cpu_core"
@@ -88,7 +90,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
+        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -99,6 +101,7 @@
         "CounterMask": "2",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -109,6 +112,7 @@
         "CounterMask": "3",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -119,7 +123,7 @@
         "CounterMask": "5",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS",
-        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_core"
@@ -130,7 +134,7 @@
         "CounterMask": "9",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS",
-        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9",
         "Unit": "cpu_core"
@@ -143,7 +147,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x400",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "53",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -156,7 +160,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "1009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -169,7 +173,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -182,7 +186,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x800",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "23",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -195,7 +199,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "503",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -208,7 +212,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -221,7 +225,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -234,7 +238,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "101",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -247,7 +251,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "2003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -260,7 +264,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -271,7 +275,7 @@
         "Data_LA": "1",
         "EventCode": "0xcd",
         "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
-        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
+        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -295,23 +299,61 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -323,17 +365,31 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -345,6 +401,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -354,6 +411,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -364,7 +422,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
-        "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
+        "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -374,7 +432,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.",
+        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json b/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json
index 20c52630127e..0088be169f9b 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json
@@ -75,7 +75,7 @@
         "MetricExpr": "tma_core_bound",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_allocation_restriction",
-        "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -85,7 +85,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL_P@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
-        "MetricThreshold": "(tma_backend_bound >0.10)",
+        "MetricThreshold": "tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
         "ScaleUnit": "100%",
@@ -97,7 +97,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.ALL_P@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
-        "MetricThreshold": "(tma_bad_speculation >0.15)",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%",
@@ -108,7 +108,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_detect",
-        "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -118,7 +118,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
-        "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -128,7 +128,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_resteer",
-        "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -137,7 +137,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -146,7 +146,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
-        "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -156,7 +156,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_decode",
-        "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -165,7 +165,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
-        "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -175,7 +175,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL_P@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
-        "MetricThreshold": "(tma_frontend_bound >0.20)",
+        "MetricThreshold": "tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -185,7 +185,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -194,7 +194,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_bandwidth",
-        "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -204,7 +204,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_latency",
-        "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -564,7 +564,7 @@
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
         "MetricName": "tma_info_system_mux",
-        "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9",
         "Unit": "cpu_atom"
     },
     {
@@ -603,7 +603,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB_MISS@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -612,7 +612,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
-        "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -622,7 +622,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
-        "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -631,7 +631,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
-        "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -640,7 +640,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
-        "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -649,7 +649,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_other_fb",
-        "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -658,7 +658,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_predecode",
-        "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -667,7 +667,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
-        "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -676,7 +676,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
-        "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -685,7 +685,7 @@
         "MetricExpr": "tma_backend_bound - tma_core_bound",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_resource_bound",
-        "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -696,7 +696,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL_P@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
-        "MetricThreshold": "(tma_retiring >0.75)",
+        "MetricThreshold": "tma_retiring > 0.75",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -706,7 +706,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
-        "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -718,7 +718,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_0@ + cpu_core@UOPS_DISPATCHED.PORT_1@ + cpu_core@UOPS_DISPATCHED.PORT_5_11@ + cpu_core@UOPS_DISPATCHED.PORT_6@) / (5 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -731,13 +731,13 @@
         "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
         "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
@@ -748,7 +748,7 @@
     {
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -765,13 +765,13 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20",
@@ -788,16 +788,16 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
-        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full",
+        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -806,16 +806,16 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy",
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20",
@@ -823,7 +823,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -832,7 +832,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -841,16 +841,16 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
-        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -863,11 +863,11 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls",
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -876,7 +876,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
-        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -890,26 +890,26 @@
         "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c01_wait",
-        "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c02_wait",
-        "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -918,7 +918,7 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -928,90 +928,91 @@
         "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
-        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@frontend_retired.l1i_miss@R / tma_info_thread_clks - tma_code_l2_miss)",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
+        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@FRONTEND_RETIRED.L1I_MISS@R / tma_info_thread_clks - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@frontend_retired.l2_miss@R / tma_info_thread_clks",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@FRONTEND_RETIRED.L2_MISS@R / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)",
-        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@frontend_retired.itlb_miss@R / tma_info_thread_clks - tma_code_stlb_miss)",
+        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@FRONTEND_RETIRED.ITLB_MISS@R / tma_info_thread_clks - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@frontend_retired.stlb_miss@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@FRONTEND_RETIRED.STLB_MISS@R / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@br_misp_retired.cond_ntaken_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_nt_mispredicts",
-        "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_COST@ * cpu_core@br_misp_retired.cond_taken_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_tk_mispredicts",
-        "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * cpu_core@mem_load_l3_hit_retired.xsnp_miss@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_miss@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 25 * tma_info_system_core_frequency) * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1022,26 +1023,27 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 24 * tma_info_system_core_frequency) * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1051,7 +1053,7 @@
         "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1061,7 +1063,7 @@
         "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1072,7 +1074,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1081,28 +1083,28 @@
         "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * cpu_core@mem_inst_retired.stlb_hit_loads@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_loads@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) / tma_info_thread_clks + tma_load_stlb_miss",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@R, 7) / tma_info_thread_clks + tma_load_stlb_miss",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * cpu_core@mem_inst_retired.stlb_hit_stores@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_stores@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) / tma_info_thread_clks + tma_store_stlb_miss",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@R, 7) / tma_info_thread_clks + tma_store_stlb_miss",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1111,8 +1113,8 @@
         "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1122,7 +1124,7 @@
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1133,18 +1135,18 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
-        "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
+        "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1164,7 +1166,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1174,16 +1176,16 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1192,8 +1194,8 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1202,8 +1204,8 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1212,8 +1214,8 @@
         "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1222,41 +1224,41 @@
         "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
+        "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
         "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
-        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1265,26 +1267,26 @@
         "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ind_call_mispredicts",
-        "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions",
-        "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@br_misp_retired.indirect_cost@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R) / tma_info_thread_clks, 0)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions.",
+        "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_COST@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R) / tma_info_thread_clks, 0)",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ind_jump_mispredicts",
-        "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1297,7 +1299,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
@@ -1305,7 +1307,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
@@ -1313,15 +1315,15 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000",
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -1353,7 +1355,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -1362,7 +1364,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -1371,10 +1373,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
         "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
@@ -1445,12 +1448,12 @@
         "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)",
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp",
         "Unit": "cpu_core"
@@ -1465,15 +1468,15 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@frontend_retired.any_dsb_miss@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@R / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;Fed;FetchLat",
         "MetricName": "tma_info_frontend_dsb_switches_ret",
         "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05",
@@ -1481,7 +1484,7 @@
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc",
         "Unit": "cpu_core"
@@ -1531,7 +1534,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@frontend_retired.ms_flows@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@FRONTEND_RETIRED.MS_FLOWS@R / tma_info_thread_clks",
         "MetricGroup": "Fed;FetchLat;MicroSeq",
         "MetricName": "tma_info_frontend_ms_latency_ret",
         "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05",
@@ -1546,21 +1549,21 @@
     },
     {
         "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
-        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed",
         "MetricName": "tma_info_frontend_unknown_branch_cost",
-        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node",
+        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@frontend_retired.unknown_branch@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@R / tma_info_thread_clks",
         "MetricGroup": "Fed;FetchLat",
         "MetricName": "tma_info_frontend_unknown_branches_ret",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch",
@@ -1580,7 +1583,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW",
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.",
         "Unit": "cpu_core"
     },
     {
@@ -1589,7 +1592,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1598,7 +1601,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1607,7 +1610,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1616,7 +1619,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1679,7 +1682,7 @@
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 13",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp",
         "Unit": "cpu_core"
     },
@@ -1825,7 +1828,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp",
         "Unit": "cpu_core"
@@ -1883,7 +1886,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads",
-        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@mem_inst_retired.stlb_miss_loads@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@R / tma_info_thread_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret",
         "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05",
@@ -1906,7 +1909,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores",
-        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@mem_inst_retired.stlb_miss_stores@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@R / tma_info_thread_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret",
         "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05",
@@ -1921,7 +1924,7 @@
     },
     {
         "BriefDescription": "",
-        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute",
         "Unit": "cpu_core"
@@ -1952,20 +1955,20 @@
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "MicroSeq;Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
@@ -2018,23 +2021,22 @@
     },
     {
         "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
-        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000",
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_utilization",
         "MetricThreshold": "tma_info_system_kernel_utilization > 0.05",
@@ -2042,7 +2044,7 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@thresh\\=0x1@",
+        "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
@@ -2093,7 +2095,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks",
@@ -2104,7 +2106,6 @@
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
         "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr",
         "Unit": "cpu_core"
     },
     {
@@ -2112,7 +2113,7 @@
         "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage",
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
         "Unit": "cpu_core"
     },
     {
@@ -2124,14 +2125,14 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "cpu_core@TOPDOWN.SLOTS@",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
+        "MetricExpr": "(tma_info_thread_slots / (cpu_core@TOPDOWN.SLOTS@ / 2) if #SMT_on else 1)",
         "MetricGroup": "SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots_utilization",
         "Unit": "cpu_core"
@@ -2149,15 +2150,15 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5",
+        "MetricThreshold": "tma_info_thread_uptb < 9",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2167,7 +2168,7 @@
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_int_operations",
         "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2176,8 +2177,8 @@
         "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_128b",
-        "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2186,8 +2187,8 @@
         "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_256b",
-        "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2196,8 +2197,8 @@
         "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2206,7 +2207,7 @@
         "MetricExpr": "max((cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2216,7 +2217,7 @@
         "MetricExpr": "min(2 * (cpu_core@MEM_INST_RETIRED.ALL_LOADS@ - cpu_core@MEM_LOAD_RETIRED.FB_HIT@ - cpu_core@MEM_LOAD_RETIRED.L1_MISS@) * 20 / 100, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2226,17 +2227,18 @@
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
-        "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * cpu_core@mem_load_retired.l2_hit@R, cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) if 0 < cpu_core@mem_load_retired.l2_hit@R else cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@R, 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2246,18 +2248,19 @@
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * cpu_core@mem_load_retired.l3_hit@R, cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_retired.l3_hit@R else cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, 9 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2266,19 +2269,19 @@
         "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2297,7 +2300,7 @@
         "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2306,43 +2309,43 @@
         "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
-        "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@mem_inst_retired.lock_loads@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2353,7 +2356,7 @@
         "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_lsd",
         "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2364,17 +2367,17 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_sq_full",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2383,34 +2386,34 @@
         "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
-        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
-        "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -2433,7 +2436,7 @@
         "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2449,18 +2452,18 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
-        "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
+        "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
         "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
@@ -2469,10 +2472,10 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
-        "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks",
+        "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2483,7 +2486,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2492,7 +2495,7 @@
         "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2508,20 +2511,20 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2531,7 +2534,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_page_faults",
         "MetricThreshold": "tma_page_faults > 0.05",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2541,7 +2544,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2551,7 +2554,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2561,7 +2564,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2570,8 +2573,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2580,8 +2583,8 @@
         "MetricExpr": "max(cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2590,7 +2593,7 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2601,8 +2604,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2612,24 +2615,24 @@
         "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@br_misp_retired.ret_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@BR_MISP_RETIRED.RET_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ret_mispredicts",
-        "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ret_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2643,7 +2646,7 @@
         "MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks + tma_c02_wait",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2653,8 +2656,8 @@
         "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_shuffles_256b",
-        "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+        "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2664,28 +2667,28 @@
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * cpu_core@mem_inst_retired.split_loads@R, cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) if 0 < cpu_core@mem_inst_retired.split_loads@R else cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@R, tma_info_memory_load_miss_real_latency) / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * cpu_core@mem_inst_retired.split_stores@R, cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) if 0 < cpu_core@mem_inst_retired.split_stores@R else cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@R, 1) / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2694,8 +2697,8 @@
         "MetricExpr": "(cpu_core@XQ.FULL_CYCLES@ + cpu_core@L1D_PEND_MISS.L2_STALLS@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2704,8 +2707,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2714,8 +2717,8 @@
         "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2724,8 +2727,8 @@
         "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2744,7 +2747,7 @@
         "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2753,34 +2756,34 @@
         "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2789,7 +2792,7 @@
         "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2799,7 +2802,7 @@
         "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2809,8 +2812,8 @@
         "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     }
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/other.json b/tools/perf/pmu-events/arch/x86/meteorlake/other.json
index 46a21776a4e9..cb21bb933617 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/other.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.HARDWARE",
-        "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.  This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.",
+        "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.  This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -14,6 +14,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.PAGE_FAULT",
+        "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -29,111 +30,13 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
         "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x800000010000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -145,6 +48,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x400000010000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -156,6 +60,7 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -167,58 +72,18 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "CounterMask": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_COUNT",
-        "Invert": "1",
-        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_RESOURCE",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "200003",
-        "UMask": "0x4",
-        "Unit": "cpu_atom"
-    },
-    {
         "BriefDescription": "Cycles the uncore cannot take further requests",
         "Counter": "0,1,2,3",
         "CounterMask": "1",
         "EventCode": "0x2d",
         "EventName": "XQ.FULL_CYCLES",
-        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).",
+        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
index 265f6c5a0248..a833d6f53d0e 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
@@ -15,7 +15,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.DIV_ACTIVE",
-        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
+        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9",
         "Unit": "cpu_core"
@@ -26,6 +26,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.IDIV_ACTIVE",
+        "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -35,7 +36,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.ANY",
-        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.",
+        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1b",
         "Unit": "cpu_core"
@@ -54,7 +55,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all branch instructions retired.",
+        "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -72,7 +73,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
-        "PublicDescription": "Counts conditional branch instructions retired.",
+        "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11",
         "Unit": "cpu_core"
@@ -82,7 +83,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts not taken branch instructions retired.",
+        "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -101,7 +102,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional branch instructions retired.",
+        "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -120,7 +121,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "PublicDescription": "Counts far branch instructions retired.",
+        "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -139,7 +140,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
-        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -186,7 +187,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -205,7 +206,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "Counts return instructions retired.",
+        "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -224,7 +225,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts taken branch instructions retired.",
+        "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -261,7 +262,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -270,6 +271,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST",
+        "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x44",
         "Unit": "cpu_core"
@@ -288,7 +290,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
-        "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11",
         "Unit": "cpu_core"
@@ -298,6 +300,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_COST",
+        "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x51",
         "Unit": "cpu_core"
@@ -307,7 +310,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
+        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -317,6 +320,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST",
+        "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x50",
         "Unit": "cpu_core"
@@ -335,7 +339,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -345,6 +349,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST",
+        "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x41",
         "Unit": "cpu_core"
@@ -363,7 +368,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
-        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -382,7 +387,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
-        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
+        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -392,6 +397,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST",
+        "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x42",
         "Unit": "cpu_core"
@@ -401,6 +407,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_COST",
+        "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xc0",
         "Unit": "cpu_core"
@@ -428,7 +435,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -438,6 +445,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST",
+        "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x60",
         "Unit": "cpu_core"
@@ -447,7 +455,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -466,6 +474,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET_COST",
+        "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x48",
         "Unit": "cpu_core"
@@ -475,7 +484,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C01",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -485,7 +494,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C02",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -495,7 +504,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C0_WAIT",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x70",
         "Unit": "cpu_core"
@@ -521,7 +530,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED",
-        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -531,7 +540,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.",
+        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0",
         "SampleAfterValue": "25003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -541,6 +550,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -552,6 +562,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE_INST",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -561,7 +572,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED",
-        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -578,7 +589,7 @@
         "BriefDescription": "Reference cycles when the core is not in halt state.",
         "Counter": "Fixed counter 2",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
-        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -598,7 +609,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
-        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -615,7 +626,7 @@
         "BriefDescription": "Core cycles when the thread is not in halt state",
         "Counter": "Fixed counter 1",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
-        "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.",
+        "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -633,7 +644,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "Unit": "cpu_core"
     },
@@ -643,6 +654,7 @@
         "CounterMask": "8",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -653,6 +665,7 @@
         "CounterMask": "1",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -663,6 +676,7 @@
         "CounterMask": "16",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -673,6 +687,7 @@
         "CounterMask": "12",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc",
         "Unit": "cpu_core"
@@ -683,6 +698,7 @@
         "CounterMask": "5",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_core"
@@ -693,6 +709,7 @@
         "CounterMask": "4",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "PublicDescription": "Total execution stalls. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -702,7 +719,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -712,6 +729,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0xc",
         "Unit": "cpu_core"
@@ -721,7 +739,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -731,7 +749,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -741,7 +759,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -752,6 +770,7 @@
         "CounterMask": "5",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS",
+        "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x21",
         "Unit": "cpu_core"
@@ -762,7 +781,7 @@
         "CounterMask": "2",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
-        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.",
+        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -772,7 +791,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
-        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.",
+        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -782,7 +801,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x75",
         "EventName": "INST_DECODED.DECODERS",
-        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.",
+        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -791,6 +810,7 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Fixed Counter: Counts the number of instructions retired Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -799,7 +819,7 @@
         "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -826,6 +846,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -835,7 +856,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
-        "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions",
+        "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -844,7 +865,7 @@
         "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.PREC_DIST",
-        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
+        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -854,7 +875,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -866,7 +887,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEARS_COUNT",
-        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears",
+        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -876,7 +897,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
-        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
+        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -886,7 +907,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.RECOVERY_CYCLES",
-        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -898,6 +919,7 @@
         "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x7",
+        "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -907,7 +929,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.UOP_DROPPING",
-        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons",
+        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -917,6 +939,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.128BIT",
+        "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x13",
         "Unit": "cpu_core"
@@ -926,6 +949,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.256BIT",
+        "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xac",
         "Unit": "cpu_core"
@@ -935,7 +959,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_128",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -945,7 +969,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_256",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc",
         "Unit": "cpu_core"
@@ -955,6 +979,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.MUL_256",
+        "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -964,6 +989,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.SHUFFLES",
+        "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -973,6 +999,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_128",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -982,6 +1009,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_256",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1000,7 +1028,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
-        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.",
+        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1019,7 +1047,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.NO_SR",
-        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x88",
         "Unit": "cpu_core"
@@ -1038,7 +1066,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.STORE_FORWARD",
-        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
+        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x82",
         "Unit": "cpu_core"
@@ -1048,7 +1076,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x4c",
         "EventName": "LOAD_HIT_PREFETCH.SWPF",
-        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1059,7 +1087,7 @@
         "CounterMask": "1",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_ACTIVE",
-        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1070,7 +1098,7 @@
         "CounterMask": "6",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_OK",
-        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1080,7 +1108,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa8",
         "EventName": "LSD.UOPS",
-        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1100,7 +1128,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.COUNT",
-        "PublicDescription": "Counts the number of machine clears (nukes) of any type.",
+        "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1133,8 +1161,9 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.",
+        "BriefDescription": "This event is deprecated.",
         "Counter": "0,1,2,3,4,5,6,7",
+        "Deprecated": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SLOW",
         "SampleAfterValue": "20003",
@@ -1155,7 +1184,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SMC",
-        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1165,7 +1194,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe0",
         "EventName": "MISC2_RETIRED.LFENCE",
-        "PublicDescription": "number of LFENCE retired instructions",
+        "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1184,7 +1213,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcc",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
-        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1194,7 +1223,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SB",
-        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1204,16 +1233,59 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SCOREBOARD",
+        "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_COUNT",
+        "Invert": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_RESOURCE",
+        "PublicDescription": "Cycles when RS was empty and a resource allocation stall is asserted Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1223,7 +1295,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BAD_SPEC_SLOTS",
-        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.",
+        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1233,7 +1305,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
-        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.",
+        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1243,6 +1315,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS",
+        "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1251,7 +1324,7 @@
         "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event",
         "Counter": "Fixed counter 3",
         "EventName": "TOPDOWN.SLOTS",
-        "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).",
+        "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3). Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1261,7 +1334,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.SLOTS_P",
-        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.",
+        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1518,7 +1591,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x76",
         "EventName": "UOPS_DECODED.DEC0_UOPS",
-        "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0.",
+        "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1528,7 +1601,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_0",
-        "PublicDescription": "Number of uops dispatch to execution  port 0.",
+        "PublicDescription": "Number of uops dispatch to execution  port 0. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1538,7 +1611,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_1",
-        "PublicDescription": "Number of uops dispatch to execution  port 1.",
+        "PublicDescription": "Number of uops dispatch to execution  port 1. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1548,7 +1621,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_2_3_10",
-        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10",
+        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1558,7 +1631,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_4_9",
-        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9",
+        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1568,7 +1641,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_5_11",
-        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11",
+        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1578,7 +1651,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_6",
-        "PublicDescription": "Number of uops dispatch to execution  port 6.",
+        "PublicDescription": "Number of uops dispatch to execution  port 6. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -1588,7 +1661,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_7_8",
-        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8.",
+        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -1598,7 +1671,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE",
-        "PublicDescription": "Counts the number of uops executed from any thread.",
+        "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1609,7 +1682,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1620,7 +1693,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1631,7 +1704,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1642,7 +1715,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1653,7 +1726,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_1",
-        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1664,7 +1737,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_2",
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1675,7 +1748,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_3",
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1686,7 +1759,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_4",
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1698,7 +1771,7 @@
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.STALLS",
         "Invert": "1",
-        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1708,6 +1781,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.THREAD",
+        "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1717,7 +1791,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.X87",
-        "PublicDescription": "Counts the number of x87 uops executed.",
+        "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1736,7 +1810,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.ANY",
-        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1747,6 +1821,7 @@
         "CounterMask": "1",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.CYCLES",
+        "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1765,7 +1840,7 @@
         "CounterMask": "1",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.CYCLES",
-        "PublicDescription": "Counts cycles where at least one uop has retired.",
+        "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1775,7 +1850,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.HEAVY",
-        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.",
+        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1805,6 +1880,7 @@
         "EventName": "UOPS_RETIRED.MS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1814,7 +1890,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.SLOTS",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1826,7 +1902,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.STALLS",
         "Invert": "1",
-        "PublicDescription": "This event counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json
index 783a4f7fd05b..ceb8839f0767 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json
@@ -100,6 +100,24 @@
         "Unit": "iMC"
     },
     {
+        "BriefDescription": "Any Rank at Hot state",
+        "Counter": "0,1,2,3,4",
+        "EventCode": "0x19",
+        "EventName": "UNC_M_DRAM_THERMAL_HOT",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Any Rank at Warm state",
+        "Counter": "0,1,2,3,4",
+        "EventCode": "0x1A",
+        "EventName": "UNC_M_DRAM_THERMAL_WARM",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
         "BriefDescription": "PRE command sent to DRAM due to page table idle timer expiration",
         "Counter": "0,1,2,3,4",
         "EventCode": "0x28",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json
index 305b96b26a4e..f300129e9e2d 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json
@@ -13,7 +13,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
-        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
+        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -24,7 +24,7 @@
         "CounterMask": "1",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -43,7 +43,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe",
         "Unit": "cpu_core"
@@ -53,7 +53,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -73,7 +73,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -93,7 +93,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -113,7 +113,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -132,7 +132,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.STLB_HIT",
-        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
+        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -143,7 +143,7 @@
         "CounterMask": "1",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -162,7 +162,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe",
         "Unit": "cpu_core"
@@ -172,7 +172,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -192,7 +192,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -212,7 +212,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -232,7 +232,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -260,7 +260,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.STLB_HIT",
-        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
+        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -271,7 +271,7 @@
         "CounterMask": "1",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -291,7 +291,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe",
         "Unit": "cpu_core"
@@ -311,7 +311,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -331,7 +331,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -351,7 +351,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/nehalemep/cache.json b/tools/perf/pmu-events/arch/x86/nehalemep/cache.json
index b90026df2ce7..c9d154f1d09a 100644
--- a/tools/perf/pmu-events/arch/x86/nehalemep/cache.json
+++ b/tools/perf/pmu-events/arch/x86/nehalemep/cache.json
@@ -240,6 +240,38 @@
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "L1I instruction fetch stall cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.CYCLES_STALLED",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "L1I instruction fetch hits",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.HITS",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "L1I instruction fetch misses",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.MISSES",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "L1I Instruction fetches",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.READS",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x3"
+    },
+    {
         "BriefDescription": "All L2 data requests",
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
diff --git a/tools/perf/pmu-events/arch/x86/nehalemep/other.json b/tools/perf/pmu-events/arch/x86/nehalemep/other.json
index f6887b234b0e..5fe5ca778e9f 100644
--- a/tools/perf/pmu-events/arch/x86/nehalemep/other.json
+++ b/tools/perf/pmu-events/arch/x86/nehalemep/other.json
@@ -16,46 +16,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "L1I instruction fetch stall cycles",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.CYCLES_STALLED",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x4"
-    },
-    {
-        "BriefDescription": "L1I instruction fetch hits",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.HITS",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "L1I instruction fetch misses",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.MISSES",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "L1I Instruction fetches",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.READS",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x3"
-    },
-    {
-        "BriefDescription": "Large ITLB hit",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x82",
-        "EventName": "LARGE_ITLB.HIT",
-        "SampleAfterValue": "200000",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "All loads dispatched",
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
diff --git a/tools/perf/pmu-events/arch/x86/nehalemep/virtual-memory.json b/tools/perf/pmu-events/arch/x86/nehalemep/virtual-memory.json
index e88c0802e679..accd263cfbfd 100644
--- a/tools/perf/pmu-events/arch/x86/nehalemep/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/nehalemep/virtual-memory.json
@@ -89,6 +89,14 @@
         "UMask": "0x20"
     },
     {
+        "BriefDescription": "Large ITLB hit",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x82",
+        "EventName": "LARGE_ITLB.HIT",
+        "SampleAfterValue": "200000",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Retired loads that miss the DTLB (Precise Event)",
         "Counter": "0,1,2,3",
         "EventCode": "0xCB",
diff --git a/tools/perf/pmu-events/arch/x86/nehalemex/cache.json b/tools/perf/pmu-events/arch/x86/nehalemex/cache.json
index 2c0ea6f8c4e0..b6c6b22a3188 100644
--- a/tools/perf/pmu-events/arch/x86/nehalemex/cache.json
+++ b/tools/perf/pmu-events/arch/x86/nehalemex/cache.json
@@ -240,6 +240,38 @@
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "L1I instruction fetch stall cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.CYCLES_STALLED",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "L1I instruction fetch hits",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.HITS",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "L1I instruction fetch misses",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.MISSES",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "L1I Instruction fetches",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.READS",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x3"
+    },
+    {
         "BriefDescription": "All L2 data requests",
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
diff --git a/tools/perf/pmu-events/arch/x86/nehalemex/other.json b/tools/perf/pmu-events/arch/x86/nehalemex/other.json
index f6887b234b0e..5fe5ca778e9f 100644
--- a/tools/perf/pmu-events/arch/x86/nehalemex/other.json
+++ b/tools/perf/pmu-events/arch/x86/nehalemex/other.json
@@ -16,46 +16,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "L1I instruction fetch stall cycles",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.CYCLES_STALLED",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x4"
-    },
-    {
-        "BriefDescription": "L1I instruction fetch hits",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.HITS",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "L1I instruction fetch misses",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.MISSES",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "L1I Instruction fetches",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.READS",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x3"
-    },
-    {
-        "BriefDescription": "Large ITLB hit",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x82",
-        "EventName": "LARGE_ITLB.HIT",
-        "SampleAfterValue": "200000",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "All loads dispatched",
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
diff --git a/tools/perf/pmu-events/arch/x86/nehalemex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/nehalemex/virtual-memory.json
index e88c0802e679..accd263cfbfd 100644
--- a/tools/perf/pmu-events/arch/x86/nehalemex/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/nehalemex/virtual-memory.json
@@ -89,6 +89,14 @@
         "UMask": "0x20"
     },
     {
+        "BriefDescription": "Large ITLB hit",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x82",
+        "EventName": "LARGE_ITLB.HIT",
+        "SampleAfterValue": "200000",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Retired loads that miss the DTLB (Precise Event)",
         "Counter": "0,1,2,3",
         "EventCode": "0xCB",
diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/cache.json b/tools/perf/pmu-events/arch/x86/rocketlake/cache.json
index 791fa526d192..0f543325ec1a 100644
--- a/tools/perf/pmu-events/arch/x86/rocketlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/rocketlake/cache.json
@@ -446,6 +446,16 @@
         "UMask": "0x20"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop was sent or not.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -506,6 +516,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop was sent or not.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -566,6 +586,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop was sent or not.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -626,6 +656,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10400",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit a cacheline in the L3 where a snoop was sent or not.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -656,6 +696,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10010",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that hit a cacheline in the L3 where a snoop was sent or not.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -716,6 +766,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10020",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent or not.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/memory.json b/tools/perf/pmu-events/arch/x86/rocketlake/memory.json
index abaf3f4f9d63..1455aaac37b1 100644
--- a/tools/perf/pmu-events/arch/x86/rocketlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/rocketlake/memory.json
@@ -177,6 +177,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -187,6 +197,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -197,6 +227,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand data reads that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -207,6 +257,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000400",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -217,6 +287,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000400",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000010",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -227,6 +317,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000010",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000020",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -237,6 +347,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000020",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.OTHER.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184008000",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -247,6 +377,26 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.OTHER.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184008000",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts streaming stores that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.STREAMING_WR.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000800",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts streaming stores that was not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -257,6 +407,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts streaming stores that DRAM supplied the request.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.STREAMING_WR.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000800",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data read requests that miss the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xb0",
diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/other.json b/tools/perf/pmu-events/arch/x86/rocketlake/other.json
index a96b2a989d3f..141cd30a30af 100644
--- a/tools/perf/pmu-events/arch/x86/rocketlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/rocketlake/other.json
@@ -27,186 +27,6 @@
         "UMask": "0x20"
     },
     {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2)  that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that have any type of response.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -217,26 +37,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.OTHER.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184008000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.OTHER.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184008000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -245,25 +45,5 @@
         "MSRValue": "0x10800",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts streaming stores that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.STREAMING_WR.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000800",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts streaming stores that DRAM supplied the request.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.STREAMING_WR.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000800",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
index cfda8956353e..71737a1a1997 100644
--- a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json
@@ -89,12 +89,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -106,7 +106,7 @@
         "MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
@@ -129,12 +129,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -149,7 +149,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -157,7 +157,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -165,22 +165,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -188,7 +188,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -196,15 +196,15 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
-        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears"
+        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache"
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -216,17 +216,17 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
         "MetricThreshold": "tma_bottleneck_useful_work > 20"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.",
         "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_branch_instructions",
@@ -248,8 +248,8 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -257,8 +257,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -266,24 +266,24 @@
         "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
         "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -291,7 +291,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -299,33 +299,33 @@
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "((32.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + (27 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(29 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -335,25 +335,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(27 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
@@ -362,7 +362,7 @@
         "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
@@ -372,7 +372,7 @@
         "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -382,7 +382,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -390,26 +390,26 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -417,8 +417,8 @@
         "MetricExpr": "32.5 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -437,7 +437,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -447,7 +447,7 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -465,7 +465,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -474,15 +474,15 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "ARITH.FP_DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -490,7 +490,7 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -499,7 +499,7 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -508,7 +508,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -517,7 +517,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -526,7 +526,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_512b",
-        "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -538,17 +538,17 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
-        "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
@@ -556,8 +556,8 @@
         "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -569,28 +569,28 @@
         "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -619,7 +619,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -628,7 +628,7 @@
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -637,10 +637,11 @@
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -701,11 +702,11 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -718,20 +719,20 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency"
     },
@@ -773,7 +774,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -791,7 +792,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -799,7 +800,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -807,7 +808,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -815,7 +816,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx512",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -823,7 +824,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -831,7 +832,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -886,7 +887,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 5 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 11",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -1011,7 +1012,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp"
     },
@@ -1073,8 +1074,8 @@
         "MetricName": "tma_info_memory_tlb_store_stlb_mpki"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -1101,12 +1102,12 @@
         "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -1147,14 +1148,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1195,7 +1195,7 @@
         "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks",
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license0_utilization",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
@@ -1203,7 +1203,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license1_utilization",
         "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)",
@@ -1211,7 +1211,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license2_utilization",
         "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
@@ -1239,7 +1239,7 @@
         "MetricName": "tma_info_system_turbo_utilization"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1248,15 +1248,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1266,13 +1265,13 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "TOPDOWN.SLOTS",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots"
     },
     {
         "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
+        "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)",
         "MetricGroup": "SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots_utilization"
     },
@@ -1288,14 +1287,14 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 5 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 7.5"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1303,8 +1302,8 @@
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1312,7 +1311,7 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -1321,7 +1320,7 @@
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
@@ -1331,7 +1330,7 @@
         "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1340,7 +1339,7 @@
         "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1350,17 +1349,17 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(12.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+        "MetricExpr": "9 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1368,18 +1367,18 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1396,7 +1395,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1404,31 +1403,31 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -1437,7 +1436,7 @@
         "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1447,7 +1446,7 @@
         "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_lsd",
         "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.",
         "ScaleUnit": "100%"
     },
     {
@@ -1457,15 +1456,15 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1474,7 +1473,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -1485,11 +1484,11 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
@@ -1511,7 +1510,7 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -1526,24 +1525,24 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline",
-        "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / tma_info_thread_clks",
+        "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group",
         "MetricName": "tma_mite_4wide",
-        "MetricThreshold": "tma_mite_4wide > 0.05 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
-        "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=0x1@ / tma_info_core_core_clks / 2",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
+        "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 2",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
         "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
@@ -1554,7 +1553,7 @@
         "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
@@ -1563,7 +1562,7 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%"
     },
@@ -1578,19 +1577,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -1634,8 +1633,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
@@ -1643,8 +1642,8 @@
         "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
@@ -1652,7 +1651,7 @@
         "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -1661,7 +1660,7 @@
         "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
@@ -1670,14 +1669,14 @@
         "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -1690,7 +1689,7 @@
         "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -1699,7 +1698,7 @@
         "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST",
         "ScaleUnit": "100%"
     },
@@ -1709,7 +1708,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1718,8 +1717,8 @@
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -1727,7 +1726,7 @@
         "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1736,8 +1735,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1746,8 +1745,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -1755,8 +1754,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1773,7 +1772,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1781,31 +1780,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -1813,7 +1812,7 @@
         "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%"
     },
@@ -1822,7 +1821,7 @@
         "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -1831,8 +1830,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json
index e95d1005e22f..5c9ab7680762 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json
@@ -278,5 +278,13 @@
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Valid instructions written to IQ per cycle.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x17",
+        "EventName": "INSTS_WRITTEN_TO_IQ.INSTS",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/metricgroups.json b/tools/perf/pmu-events/arch/x86/sandybridge/metricgroups.json
index 7dc7eb0d3dd3..eb8fbd14138a 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/metricgroups.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/metricgroups.json
@@ -9,6 +9,7 @@
     "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -33,6 +34,7 @@
     "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -48,6 +50,7 @@
     "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -75,6 +78,7 @@
     "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
     "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
+    "tma_divider_group": "Metrics contributing to tma_divider category",
     "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
     "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
     "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
@@ -99,6 +103,7 @@
     "tma_issueSmSt": "Metrics related by the issue $issueSmSt",
     "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
     "tma_issueTLB": "Metrics related by the issue $issueTLB",
+    "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
     "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
     "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category",
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/other.json b/tools/perf/pmu-events/arch/x86/sandybridge/other.json
index 42692fa24b6c..970839a9c786 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/other.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/other.json
@@ -34,14 +34,6 @@
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "Valid instructions written to IQ per cycle.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x17",
-        "EventName": "INSTS_WRITTEN_TO_IQ.INSTS",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock.",
         "Counter": "0,1,2,3",
         "EventCode": "0x63",
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
index ff2e515c744a..823d8b7c4224 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
@@ -127,7 +127,7 @@
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
         "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -211,7 +211,7 @@
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
         "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -220,7 +220,7 @@
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
         "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -240,7 +240,7 @@
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
@@ -276,6 +276,12 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_lcp"
     },
     {
+        "BriefDescription": "Taken Branches retired Per Cycle",
+        "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks",
+        "MetricGroup": "Branches;FetchBW",
+        "MetricName": "tma_info_frontend_tbpc"
+    },
+    {
         "BriefDescription": "Total number of retired Instructions",
         "MetricExpr": "INST_RETIRED.ANY",
         "MetricGroup": "Summary;TmaL1;tma_L1_group",
@@ -290,7 +296,7 @@
     },
     {
         "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
-        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time",
         "MetricGroup": "Power;Summary",
         "MetricName": "tma_info_system_core_frequency"
     },
@@ -308,14 +314,14 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3",
+        "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3",
         "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
         "MetricName": "tma_info_system_dram_bw_use",
         "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_mem_bandwidth"
     },
     {
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time",
+        "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / tma_info_system_time",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_system_gflops",
         "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width"
@@ -341,6 +347,13 @@
         "MetricThreshold": "tma_info_system_kernel_utilization > 0.05"
     },
     {
+        "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_mux",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
+    },
+    {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
         "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)",
         "MetricGroup": "SMT",
@@ -353,6 +366,13 @@
         "MetricName": "tma_info_system_socket_clks"
     },
     {
+        "BriefDescription": "Run duration time in seconds",
+        "MetricExpr": "duration_time",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_time",
+        "MetricThreshold": "tma_info_system_time < 1"
+    },
+    {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Power",
@@ -448,7 +468,7 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
         "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_info_system_dram_bw_use",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json
index e35dbb7c2ccd..21db53f9e9d6 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json
@@ -4,6 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.HWPF_MISS",
+        "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -12,7 +13,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.REPLACEMENT",
-        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -21,7 +22,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -32,7 +33,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS",
-        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -42,6 +43,7 @@
         "Deprecated": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALL",
+        "PublicDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -50,7 +52,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALLS",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -59,7 +61,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING",
-        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -69,7 +71,7 @@
         "CounterMask": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
-        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -78,7 +80,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x25",
         "EventName": "L2_LINES_IN.ALL",
-        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1f"
     },
@@ -87,7 +89,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.NON_SILENT",
-        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
+        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -96,7 +98,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.SILENT",
-        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -105,7 +107,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.USELESS_HWPF",
-        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
+        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -114,7 +116,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.ALL",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff"
     },
@@ -123,7 +125,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f"
     },
@@ -132,7 +134,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "PublicDescription": "Counts the total number of L2 code requests.",
+        "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe4"
     },
@@ -141,7 +143,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe1"
     },
@@ -150,7 +152,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "PublicDescription": "Counts demand requests that miss L2 cache.",
+        "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x27"
     },
@@ -159,7 +161,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
-        "PublicDescription": "Counts demand requests to L2 cache.",
+        "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe7"
     },
@@ -168,6 +170,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_HWPF",
+        "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf0"
     },
@@ -176,7 +179,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_RFO",
-        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe2"
     },
@@ -185,7 +188,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
+        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc4"
     },
@@ -194,7 +197,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+        "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x24"
     },
@@ -203,7 +206,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc1"
     },
@@ -212,7 +215,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
-        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21"
     },
@@ -221,6 +224,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.HWPF_MISS",
+        "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x30"
     },
@@ -229,7 +233,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f"
     },
@@ -238,7 +242,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.REFERENCES",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff"
     },
@@ -247,7 +251,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_HIT",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc2"
     },
@@ -256,7 +260,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_MISS",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x22"
     },
@@ -265,7 +269,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_HIT",
-        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc8"
     },
@@ -274,7 +278,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_MISS",
-        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x28"
     },
@@ -283,7 +287,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x23",
         "EventName": "L2_TRANS.L2_WB",
-        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+        "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x40"
     },
@@ -292,7 +296,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.MISS",
-        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41"
     },
@@ -301,7 +305,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4f"
     },
@@ -311,7 +315,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
+        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x81"
     },
@@ -321,7 +325,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts all retired store instructions.",
+        "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x82"
     },
@@ -331,7 +335,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+        "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x83"
     },
@@ -341,7 +345,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PublicDescription": "Counts retired load instructions with locked access.",
+        "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x21"
     },
@@ -351,7 +355,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41"
     },
@@ -361,7 +365,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x42"
     },
@@ -371,7 +375,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x11"
     },
@@ -381,7 +385,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x12"
     },
@@ -390,7 +394,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY",
-        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)",
+        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfd"
     },
@@ -400,7 +404,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x4"
     },
@@ -410,7 +414,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1"
     },
@@ -420,7 +424,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
+        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -430,7 +434,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x2"
     },
@@ -440,7 +444,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
-        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
+        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -450,6 +454,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -459,7 +464,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
-        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.",
+        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -469,6 +474,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
+        "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -477,7 +483,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM",
-        "PublicDescription": "Counts retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3.",
+        "PublicDescription": "Counts retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x10"
     },
@@ -487,7 +493,7 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x4"
     },
@@ -497,7 +503,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
     },
@@ -507,7 +513,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -517,7 +523,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
     },
@@ -527,7 +533,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -537,7 +543,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x10"
     },
@@ -547,7 +553,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x4"
     },
@@ -557,7 +563,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x20"
     },
@@ -567,7 +573,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.LOCAL_PMM",
-        "PublicDescription": "Counts retired load instructions with local Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3.",
+        "PublicDescription": "Counts retired load instructions with local Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80"
     },
@@ -576,6 +582,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x44",
         "EventName": "MEM_STORE_RETIRED.L2_HIT",
+        "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -584,17 +591,29 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe5",
         "EventName": "MEM_UOP_RETIRED.ANY",
-        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses",
+        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -605,6 +624,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -615,6 +635,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -625,6 +646,18 @@
         "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -635,6 +668,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0001",
+        "PublicDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -645,6 +679,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -655,6 +690,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -665,6 +701,29 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_SOCKET_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x700C00001",
+        "PublicDescription": "Counts demand data reads that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by PMM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x703C00001",
+        "PublicDescription": "Counts demand data reads that were supplied by PMM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -675,6 +734,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1030000001",
+        "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -685,6 +745,18 @@
         "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x830000001",
+        "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by PMM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x703000001",
+        "PublicDescription": "Counts demand data reads that were supplied by PMM attached to another socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -695,6 +767,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008000001",
+        "PublicDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -705,6 +778,18 @@
         "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808000001",
+        "PublicDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F3FFC0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -715,6 +800,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -725,6 +811,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -735,6 +822,7 @@
         "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -745,6 +833,40 @@
         "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.HWPF_L1D.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10400",
+        "PublicDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.HWPF_L2.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10070",
+        "PublicDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.HWPF_L3.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x12380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -755,6 +877,40 @@
         "EventName": "OCR.HWPF_L3.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x80082380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.HWPF_L3.REMOTE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x90002380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10808",
+        "PublicDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F3FFC4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -765,6 +921,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -775,6 +932,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -785,6 +943,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -795,6 +954,29 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x700C04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F33004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -805,6 +987,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1830004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -815,6 +998,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1030004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -825,6 +1009,18 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x830004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_PMM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x703004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to another socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -835,6 +1031,7 @@
         "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -845,6 +1042,7 @@
         "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -855,6 +1053,7 @@
         "EventName": "OCR.RFO_TO_CORE.L3_HIT_M",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F80040022",
+        "PublicDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -865,6 +1064,7 @@
         "EventName": "OCR.STREAMING_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x80080800",
+        "PublicDescription": "Counts streaming stores that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -873,6 +1073,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
+        "PublicDescription": "OFFCORE_REQUESTS.ALL_REQUESTS Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -881,7 +1082,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DATA_RD",
-        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -890,7 +1091,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
-        "PublicDescription": "Counts both cacheable and non-cacheable code read requests.",
+        "PublicDescription": "Counts both cacheable and non-cacheable code read requests. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -899,7 +1100,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -908,7 +1109,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
-        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -918,6 +1119,7 @@
         "Deprecated": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "PublicDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -927,6 +1129,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -936,7 +1139,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -946,6 +1149,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -955,6 +1159,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -963,6 +1168,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -971,7 +1177,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -980,7 +1186,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
+        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -989,7 +1195,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x2c",
         "EventName": "SQ_MISC.BUS_LOCK",
-        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
+        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -998,6 +1204,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.ANY",
+        "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xf"
     },
@@ -1006,7 +1213,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.NTA",
-        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -1015,7 +1222,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
-        "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -1024,7 +1231,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T0",
-        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -1033,7 +1240,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T1_T2",
-        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     }
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json
index bc475e163227..8c9207750c82 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json
@@ -5,6 +5,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FPDIV_ACTIVE",
+        "PublicDescription": "ARITH.FPDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -13,7 +14,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.FP",
-        "PublicDescription": "Counts all microcode Floating Point assists.",
+        "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -22,6 +23,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.SSE_AVX_MIX",
+        "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -30,6 +32,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -38,6 +41,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -46,6 +50,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_5",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -54,6 +59,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -62,6 +68,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -70,6 +77,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V2",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -78,7 +86,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -87,7 +95,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -96,7 +104,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -105,7 +113,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -114,7 +122,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x18"
     },
@@ -123,7 +131,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x40"
     },
@@ -132,7 +140,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 16 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 16 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -141,7 +149,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x60"
     },
@@ -150,7 +158,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -159,7 +167,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -168,7 +176,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -177,7 +185,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.VECTOR",
-        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfc"
     },
@@ -186,6 +194,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -194,6 +203,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -202,6 +212,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -210,6 +221,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -218,7 +230,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.SCALAR",
-        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x3"
     },
@@ -227,6 +239,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -235,7 +248,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.VECTOR",
-        "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1c"
     }
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json
index bf68493d4509..9fe9d62b867a 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x60",
         "EventName": "BACLEARS.ANY",
-        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -13,7 +13,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.LCP",
-        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -22,6 +22,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.MS_BUSY",
+        "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x2"
     },
@@ -30,7 +31,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x61",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
+        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -41,7 +42,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -52,7 +53,7 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -63,7 +64,7 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -74,7 +75,7 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -85,7 +86,7 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -96,7 +97,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600106",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -107,7 +108,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -118,7 +119,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -129,7 +130,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -140,7 +141,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -151,7 +152,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -162,7 +163,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -173,7 +174,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -184,7 +185,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -195,7 +196,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -206,7 +207,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -217,6 +218,7 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -227,7 +229,7 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -238,6 +240,7 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
+        "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -246,7 +249,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALLS",
-        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
+        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4"
     },
@@ -257,6 +260,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALL_PERIODS",
+        "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4"
     },
@@ -265,7 +269,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x83",
         "EventName": "ICACHE_TAG.STALLS",
-        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -275,7 +279,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -285,7 +289,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -294,7 +298,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -304,7 +308,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -314,7 +318,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -323,7 +327,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -333,7 +337,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_CYCLES_ANY",
-        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -344,7 +348,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_SWITCHES",
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -353,7 +357,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).",
+        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -362,7 +366,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -372,7 +376,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -383,7 +387,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -392,7 +396,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -402,7 +406,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -413,7 +417,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json
index 41d4120d4dae..7c3f9b76d367 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json
@@ -5,6 +5,7 @@
         "CounterMask": "6",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
+        "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x6"
     },
@@ -13,7 +14,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
+        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -23,6 +24,7 @@
         "CounterMask": "2",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -32,6 +34,7 @@
         "CounterMask": "3",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -41,7 +44,7 @@
         "CounterMask": "5",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS",
-        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -51,7 +54,7 @@
         "CounterMask": "9",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS",
-        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9"
     },
@@ -169,17 +172,62 @@
         "Data_LA": "1",
         "EventCode": "0xcd",
         "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
-        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
+        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -190,6 +238,51 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x730000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to another socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -200,6 +293,29 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F3FC00002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -210,6 +326,7 @@
         "EventName": "OCR.HWPF_L3.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x94002380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that missed the local socket's L1, L2, and L3 caches. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -220,6 +337,18 @@
         "EventName": "OCR.HWPF_L3.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x84002380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -230,6 +359,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F3FC04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -240,6 +370,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F04C04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -250,6 +381,62 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL_SOCKET",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x70CC04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that missed the L3 Cache and were supplied by the local socket (DRAM or PMM), whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM or DRAM accesses that are controlled by the close or distant SNC Cluster.  It does not count misses to the L3 which go to Local CXL Type 2 Memory or Local Non DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x70C004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x730004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x733004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -260,6 +447,7 @@
         "EventName": "OCR.STREAMING_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x94000800",
+        "PublicDescription": "Counts streaming stores that missed the local socket's L1, L2, and L3 caches. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -270,6 +458,18 @@
         "EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x84000800",
+        "PublicDescription": "Counts streaming stores that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.WRITE_ESTIMATE.MEMORY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0xFBFF80822",
+        "PublicDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM) Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -278,6 +478,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -286,7 +487,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.",
+        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -295,7 +496,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PublicDescription": "Counts the number of times RTM abort was triggered.",
+        "PublicDescription": "Counts the number of times RTM abort was triggered. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -304,7 +505,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_EVENTS",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -313,7 +514,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_MEM",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -322,7 +523,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x40"
     },
@@ -331,7 +532,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -340,7 +541,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.COMMIT",
-        "PublicDescription": "Counts the number of times RTM commit succeeded.",
+        "PublicDescription": "Counts the number of times RTM commit succeeded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -349,7 +550,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.START",
-        "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.",
+        "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -358,7 +559,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x54",
         "EventName": "TX_MEM.ABORT_CAPACITY_READ",
-        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads",
+        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -367,7 +568,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x54",
         "EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
-        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.",
+        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -376,7 +577,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x54",
         "EventName": "TX_MEM.ABORT_CONFLICT",
-        "PublicDescription": "Counts the number of times a TSX line had a cache conflict.",
+        "PublicDescription": "Counts the number of times a TSX line had a cache conflict. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json
index 05d8f14956ee..a58d65556609 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json
@@ -4,404 +4,28 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.PAGE_FAULT",
+        "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
     {
-        "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb7",
-        "EventName": "EXE.AMX_BUSY",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_SOCKET_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x700C00001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by PMM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x703C00001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x730000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by PMM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x703000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F3FFC0002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.HWPF_L1D.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.HWPF_L2.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10070",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.HWPF_L3.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x12380",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.HWPF_L3.REMOTE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x90002380",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10808",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F3FFC4477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x70C004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x700C04477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F33004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x730004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x733004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE_PMM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x703004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.WRITE_ESTIMATE.MEMORY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0xFBFF80822",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7"
-    },
-    {
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "CounterMask": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_COUNT",
-        "Invert": "1",
-        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7"
-    },
-    {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_RESOURCE",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "CounterMask": "1",
-        "Deprecated": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS_EMPTY.COUNT",
-        "Invert": "1",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "Deprecated": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS_EMPTY.CYCLES",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7"
-    },
-    {
         "BriefDescription": "Cycles the uncore cannot take further requests",
         "Counter": "0,1,2,3",
         "CounterMask": "1",
         "EventCode": "0x2d",
         "EventName": "XQ.FULL_CYCLES",
-        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).",
+        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
index 50cacfbbc7cf..00b05a77c289 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
@@ -6,6 +6,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9"
     },
@@ -15,7 +16,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.DIV_ACTIVE",
-        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
+        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9"
     },
@@ -26,6 +27,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FP_DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -35,6 +37,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.IDIV_ACTIVE",
+        "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -45,6 +48,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.INT_DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -53,7 +57,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.ANY",
-        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.",
+        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1b"
     },
@@ -62,7 +66,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all branch instructions retired.",
+        "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009"
     },
     {
@@ -70,7 +74,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
-        "PublicDescription": "Counts conditional branch instructions retired.",
+        "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11"
     },
@@ -79,7 +83,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts not taken branch instructions retired.",
+        "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10"
     },
@@ -88,7 +92,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional branch instructions retired.",
+        "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1"
     },
@@ -97,7 +101,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "PublicDescription": "Counts far branch instructions retired.",
+        "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
     },
@@ -106,7 +110,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
-        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -115,7 +119,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2"
     },
@@ -124,7 +128,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "Counts return instructions retired.",
+        "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -133,7 +137,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts taken branch instructions retired.",
+        "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
     },
@@ -142,7 +146,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "400009"
     },
     {
@@ -150,7 +154,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
-        "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11"
     },
@@ -159,7 +163,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
+        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10"
     },
@@ -168,7 +172,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1"
     },
@@ -177,7 +181,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
-        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -186,7 +190,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
-        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
+        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x2"
     },
@@ -195,7 +199,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
     },
@@ -204,7 +208,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -213,7 +217,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C01",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -222,7 +226,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C02",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -231,7 +235,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C0_WAIT",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x70"
     },
@@ -240,7 +244,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED",
-        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -249,7 +253,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.",
+        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0",
         "SampleAfterValue": "25003",
         "UMask": "0x2"
     },
@@ -258,6 +262,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40"
     },
@@ -268,6 +273,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE_INST",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40"
     },
@@ -276,7 +282,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED",
-        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -293,7 +299,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
-        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -310,7 +316,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -319,6 +325,7 @@
         "CounterMask": "8",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -328,6 +335,7 @@
         "CounterMask": "1",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -337,6 +345,7 @@
         "CounterMask": "16",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -346,6 +355,7 @@
         "CounterMask": "12",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc"
     },
@@ -355,6 +365,7 @@
         "CounterMask": "5",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -364,15 +375,25 @@
         "CounterMask": "4",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "PublicDescription": "Total execution stalls. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
     {
+        "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb7",
+        "EventName": "EXE.AMX_BUSY",
+        "PublicDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation. Available PDIST counters: 0",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
+    },
+    {
         "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -381,6 +402,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0xc"
     },
@@ -389,7 +411,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -398,7 +420,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -407,7 +429,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -417,6 +439,7 @@
         "CounterMask": "5",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS",
+        "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x21"
     },
@@ -426,7 +449,7 @@
         "CounterMask": "2",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
-        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.",
+        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -435,7 +458,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
-        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.",
+        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80"
     },
@@ -444,7 +467,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x75",
         "EventName": "INST_DECODED.DECODERS",
-        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.",
+        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -452,7 +475,7 @@
         "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -469,6 +492,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -477,7 +501,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
-        "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions",
+        "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -485,7 +509,7 @@
         "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.PREC_DIST",
-        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
+        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -494,7 +518,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -505,7 +529,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEARS_COUNT",
-        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears",
+        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -514,7 +538,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
-        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
+        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x80"
     },
@@ -523,6 +547,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.MBA_STALLS",
+        "PublicDescription": "INT_MISC.MBA_STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -531,7 +556,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.RECOVERY_CYCLES",
-        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -542,6 +567,7 @@
         "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x7",
+        "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -550,7 +576,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.UOP_DROPPING",
-        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons",
+        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -559,6 +585,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.128BIT",
+        "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x13"
     },
@@ -567,6 +594,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.256BIT",
+        "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xac"
     },
@@ -575,7 +603,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_128",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -584,7 +612,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_256",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc"
     },
@@ -593,6 +621,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.MUL_256",
+        "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80"
     },
@@ -601,6 +630,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.SHUFFLES",
+        "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -609,6 +639,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_128",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -617,6 +648,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_256",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -625,7 +657,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
-        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.",
+        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -634,7 +666,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.NO_SR",
-        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x88"
     },
@@ -643,7 +675,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.STORE_FORWARD",
-        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
+        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x82"
     },
@@ -652,7 +684,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x4c",
         "EventName": "LOAD_HIT_PREFETCH.SWPF",
-        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -662,7 +694,7 @@
         "CounterMask": "1",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_ACTIVE",
-        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -672,7 +704,7 @@
         "CounterMask": "6",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_OK",
-        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -681,7 +713,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa8",
         "EventName": "LSD.UOPS",
-        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -692,7 +724,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.COUNT",
-        "PublicDescription": "Counts the number of machine clears (nukes) of any type.",
+        "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -701,7 +733,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SMC",
-        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -710,7 +742,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe0",
         "EventName": "MISC2_RETIRED.LFENCE",
-        "PublicDescription": "number of LFENCE retired instructions",
+        "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
     },
@@ -719,7 +751,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcc",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
-        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -728,7 +760,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SB",
-        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -737,15 +769,69 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SCOREBOARD",
+        "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_COUNT",
+        "Invert": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_RESOURCE",
+        "PublicDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "Deprecated": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS_EMPTY.COUNT",
+        "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "Deprecated": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS_EMPTY.CYCLES",
+        "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7"
+    },
+    {
         "BriefDescription": "TMA slots where no uops were being issued due to lack of back-end resources.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
-        "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.",
+        "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x2"
     },
@@ -754,7 +840,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BAD_SPEC_SLOTS",
-        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.",
+        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x4"
     },
@@ -763,7 +849,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
-        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.",
+        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x8"
     },
@@ -772,6 +858,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS",
+        "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x10"
     },
@@ -788,7 +875,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.SLOTS_P",
-        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.",
+        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x1"
     },
@@ -797,6 +884,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x76",
         "EventName": "UOPS_DECODED.DEC0_UOPS",
+        "PublicDescription": "UOPS_DECODED.DEC0_UOPS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -805,7 +893,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_0",
-        "PublicDescription": "Number of uops dispatch to execution  port 0.",
+        "PublicDescription": "Number of uops dispatch to execution  port 0. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -814,7 +902,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_1",
-        "PublicDescription": "Number of uops dispatch to execution  port 1.",
+        "PublicDescription": "Number of uops dispatch to execution  port 1. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -823,7 +911,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_2_3_10",
-        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10",
+        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -832,7 +920,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_4_9",
-        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9",
+        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -841,7 +929,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_5_11",
-        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11",
+        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -850,7 +938,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_6",
-        "PublicDescription": "Number of uops dispatch to execution  port 6.",
+        "PublicDescription": "Number of uops dispatch to execution  port 6. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40"
     },
@@ -859,7 +947,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_7_8",
-        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8.",
+        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x80"
     },
@@ -868,7 +956,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE",
-        "PublicDescription": "Counts the number of uops executed from any thread.",
+        "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -878,7 +966,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -888,7 +976,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -898,7 +986,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -908,7 +996,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -918,7 +1006,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_1",
-        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -928,7 +1016,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_2",
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -938,7 +1026,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_3",
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -948,7 +1036,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_4",
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -959,7 +1047,7 @@
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.STALLS",
         "Invert": "1",
-        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -971,6 +1059,7 @@
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.STALL_CYCLES",
         "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -979,6 +1068,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.THREAD",
+        "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -987,7 +1077,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.X87",
-        "PublicDescription": "Counts the number of x87 uops executed.",
+        "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -996,7 +1086,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.ANY",
-        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1006,6 +1096,7 @@
         "CounterMask": "1",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.CYCLES",
+        "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1015,7 +1106,7 @@
         "CounterMask": "1",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.CYCLES",
-        "PublicDescription": "Counts cycles where at least one uop has retired.",
+        "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -1024,7 +1115,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.HEAVY",
-        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.",
+        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1035,6 +1126,7 @@
         "EventName": "UOPS_RETIRED.MS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -1043,7 +1135,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.SLOTS",
-        "PublicDescription": "Counts the retirement slots used each cycle.",
+        "PublicDescription": "Counts the retirement slots used each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -1054,7 +1146,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.STALLS",
         "Invert": "1",
-        "PublicDescription": "This event counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -1066,6 +1158,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     }
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
index b59fae4a887d..fe3f288be10e 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
@@ -360,7 +360,7 @@
         "ScaleUnit": "1per_instr"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -372,7 +372,7 @@
         "MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks",
         "MetricGroup": "BvCB;Compute;HPC;Server;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_amx_busy",
-        "MetricThreshold": "tma_amx_busy > 0.5 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_amx_busy > 0.5 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -380,12 +380,12 @@
         "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
         "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
@@ -395,7 +395,7 @@
     {
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -411,12 +411,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -431,7 +431,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -439,7 +439,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -447,22 +447,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * tma_amx_busy / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -470,7 +470,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -478,7 +478,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
@@ -486,7 +486,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -498,10 +498,10 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -510,7 +510,7 @@
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -523,24 +523,24 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
         "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c01_wait",
-        "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
         "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c02_wait",
-        "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -548,7 +548,7 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS",
         "ScaleUnit": "100%"
     },
@@ -557,24 +557,24 @@
         "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
         "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -582,7 +582,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -590,32 +590,33 @@
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricExpr": "((81 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(76.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 74.6 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -626,24 +627,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricExpr": "(79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "74.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
@@ -652,7 +654,7 @@
         "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
@@ -661,7 +663,7 @@
         "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -671,7 +673,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -679,34 +681,34 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
-        "MetricExpr": "(170 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks",
+        "MetricExpr": "(170 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_MISS@offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -727,7 +729,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -738,7 +740,7 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -756,7 +758,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -765,15 +767,15 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -781,8 +783,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -790,8 +792,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.VECTOR + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -799,8 +801,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -808,8 +810,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -817,8 +819,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_512b",
-        "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -829,27 +831,27 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%"
     },
     {
@@ -857,8 +859,8 @@
         "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -869,28 +871,28 @@
         "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -918,7 +920,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -926,7 +928,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -934,10 +936,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -998,11 +1001,11 @@
         "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -1015,20 +1018,20 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency"
     },
@@ -1065,13 +1068,13 @@
     },
     {
         "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
-        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed",
         "MetricName": "tma_info_frontend_unknown_branch_cost",
-        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node"
+        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node."
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -1089,7 +1092,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -1097,7 +1100,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -1105,7 +1108,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -1113,7 +1116,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx512",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -1121,7 +1124,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate)",
@@ -1129,7 +1132,7 @@
         "MetricGroup": "Flops;FpScalar;InsType;Server",
         "MetricName": "tma_info_inst_mix_iparith_scalar_hp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_hp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -1137,7 +1140,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -1192,7 +1195,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 13",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -1329,7 +1332,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp"
     },
@@ -1394,21 +1397,21 @@
         "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_soc_r2c_dram_bw",
-        "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW"
+        "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW."
     },
     {
         "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)",
         "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_soc_r2c_l3m_bw",
-        "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW"
+        "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW."
     },
     {
         "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)",
         "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_soc_r2c_offcore_bw",
-        "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches"
+        "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches."
     },
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
@@ -1436,8 +1439,8 @@
         "MetricName": "tma_info_memory_tlb_store_stlb_mpki"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -1458,18 +1461,18 @@
         "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "MicroSeq;Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1"
@@ -1532,14 +1535,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1550,7 +1552,7 @@
     },
     {
         "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]",
-        "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@",
+        "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@",
         "MetricGroup": "MemOffcore;MemoryLat;Server;SoC",
         "MetricName": "tma_info_system_mem_dram_read_latency",
         "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches"
@@ -1560,11 +1562,11 @@
         "MetricExpr": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH / UNC_CHA_CLOCKTICKS",
         "MetricGroup": "LockCont;MemOffcore;Server;SoC",
         "MetricName": "tma_info_system_mem_irq_duplicate_address",
-        "MetricThreshold": "(tma_info_system_mem_irq_duplicate_address > 0.1)"
+        "MetricThreshold": "tma_info_system_mem_irq_duplicate_address > 0.1"
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@",
+        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
@@ -1598,7 +1600,7 @@
     },
     {
         "BriefDescription": "Socket actual clocks when any core is active on that socket",
-        "MetricExpr": "cha_0@event\\=0x0@",
+        "MetricExpr": "uncore_cha_0@event\\=0x1@",
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_socket_clks"
     },
@@ -1628,7 +1630,7 @@
         "MetricName": "tma_info_system_upi_data_transmit_bw"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1637,15 +1639,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1655,13 +1656,13 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "TOPDOWN.SLOTS",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots"
     },
     {
         "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
+        "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)",
         "MetricGroup": "SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots_utilization"
     },
@@ -1677,14 +1678,14 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 9"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1693,7 +1694,7 @@
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_int_operations",
         "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.",
         "ScaleUnit": "100%"
     },
     {
@@ -1701,8 +1702,8 @@
         "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_128b",
-        "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1710,8 +1711,8 @@
         "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_256b",
-        "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1719,8 +1720,8 @@
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1728,7 +1729,7 @@
         "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -1737,7 +1738,7 @@
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
@@ -1746,16 +1747,17 @@
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "4.4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1764,17 +1766,18 @@
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(37 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "32.6 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1782,19 +1785,19 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "DefaultMetricgroupName": "TopdownL2",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1811,7 +1814,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1819,39 +1822,39 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory",
-        "MetricExpr": "(109 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "72 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
         "ScaleUnit": "100%"
     },
@@ -1860,7 +1863,7 @@
         "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1876,19 +1879,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling)",
+        "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).",
         "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group",
         "MetricName": "tma_mba_stalls",
-        "MetricThreshold": "tma_mba_stalls > 0.1 & tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mba_stalls > 0.1 & (tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1897,32 +1900,32 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
-        "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -1943,7 +1946,7 @@
         "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -1957,17 +1960,17 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
-        "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
+        "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
         "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
@@ -1975,10 +1978,10 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
-        "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks",
+        "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
@@ -1988,7 +1991,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%"
     },
     {
@@ -1996,7 +1999,7 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%"
     },
@@ -2010,19 +2013,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -2031,7 +2034,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_page_faults",
         "MetricThreshold": "tma_page_faults > 0.05",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.",
         "ScaleUnit": "100%"
     },
     {
@@ -2040,7 +2043,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -2049,7 +2052,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -2058,7 +2061,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -2066,8 +2069,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
@@ -2075,8 +2078,8 @@
         "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(RS.EMPTY_RESOURCE - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
@@ -2084,7 +2087,7 @@
         "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -2094,8 +2097,8 @@
         "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
@@ -2104,32 +2107,32 @@
         "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues",
-        "MetricExpr": "((170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory",
-        "MetricExpr": "(190 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "153 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2142,7 +2145,7 @@
         "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks + tma_c02_wait",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -2151,8 +2154,8 @@
         "MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_shuffles_256b",
-        "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+        "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.",
         "ScaleUnit": "100%"
     },
     {
@@ -2161,7 +2164,7 @@
         "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
         "ScaleUnit": "100%"
     },
@@ -2171,7 +2174,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -2179,8 +2182,8 @@
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -2188,7 +2191,7 @@
         "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -2197,8 +2200,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -2206,8 +2209,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -2215,8 +2218,8 @@
         "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -2233,7 +2236,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -2241,31 +2244,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -2273,7 +2276,7 @@
         "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%"
     },
@@ -2282,7 +2285,7 @@
         "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "ScaleUnit": "100%"
     },
@@ -2291,8 +2294,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json
index 609a9549cbf3..3d3f88600e26 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
-        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
+        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -14,7 +14,7 @@
         "CounterMask": "1",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -23,7 +23,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
@@ -32,7 +32,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -41,7 +41,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -50,7 +50,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -59,7 +59,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -68,7 +68,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.STLB_HIT",
-        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
+        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -78,7 +78,7 @@
         "CounterMask": "1",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -87,7 +87,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
@@ -96,7 +96,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -105,7 +105,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -114,7 +114,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -123,7 +123,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -132,7 +132,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.STLB_HIT",
-        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
+        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -142,7 +142,7 @@
         "CounterMask": "1",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -151,7 +151,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
@@ -160,7 +160,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -169,7 +169,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -178,7 +178,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     }
diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/cache.json b/tools/perf/pmu-events/arch/x86/sierraforest/cache.json
index 072df00aff92..877052db1490 100644
--- a/tools/perf/pmu-events/arch/x86/sierraforest/cache.json
+++ b/tools/perf/pmu-events/arch/x86/sierraforest/cache.json
@@ -467,12 +467,24 @@
         "UMask": "0x6"
     },
     {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -483,6 +495,18 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -493,6 +517,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/memory.json b/tools/perf/pmu-events/arch/x86/sierraforest/memory.json
index 22d23077618e..dc850a179517 100644
--- a/tools/perf/pmu-events/arch/x86/sierraforest/memory.json
+++ b/tools/perf/pmu-events/arch/x86/sierraforest/memory.json
@@ -79,6 +79,29 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to this socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x730000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to another socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -89,6 +112,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/other.json b/tools/perf/pmu-events/arch/x86/sierraforest/other.json
index 4c77dac8ec78..ea34103a8292 100644
--- a/tools/perf/pmu-events/arch/x86/sierraforest/other.json
+++ b/tools/perf/pmu-events/arch/x86/sierraforest/other.json
@@ -9,61 +9,14 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x730000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "200003",
-        "UMask": "0x4"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json b/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json
index df2c7bb474a0..f56d8d816e53 100644
--- a/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json
@@ -225,6 +225,7 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Fixed Counter: Counts the number of instructions retired Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -301,6 +302,14 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x73",
diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json b/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json
index 83c86afd2960..ef629e4e91ce 100644
--- a/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json
@@ -288,15 +288,17 @@
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions",
         "MetricExpr": "tma_core_bound",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_core_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_allocation_restriction",
+        "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls",
         "MetricExpr": "TOPDOWN_BE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
+        "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
+        "MetricThreshold": "tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
         "ScaleUnit": "100%"
@@ -304,92 +306,104 @@
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
+        "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear",
+        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend",
         "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_detect",
-        "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches",
+        "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
+        "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
+        "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
         "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_resteer",
+        "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS)",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).",
         "MetricExpr": "TOPDOWN_FE_BOUND.CISC / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_cisc",
+        "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of cycles due to backend bound stalls that are bounded by core restrictions and not attributed to an outstanding load or stores, or resource limitation",
         "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.",
         "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_decode",
+        "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that does not require the use of microcode, classified as a fast nuke, due to memory ordering, memory disambiguation and memory renaming",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
+        "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls",
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.",
         "MetricExpr": "TOPDOWN_FE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
+        "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
+        "MetricThreshold": "tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.",
         "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_icache_misses",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
         "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_bandwidth",
+        "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations.",
         "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_latency",
+        "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -420,33 +434,28 @@
     {
         "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss",
         "MetricExpr": "100 * (LD_HEAD.DTLB_MISS_AT_RET + LD_HEAD.PGWALK_AT_RET) / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Cycles",
-        "MetricName": "tma_info_bottleneck_dtlb_miss_bound_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_bottleneck_%_dtlb_miss_bound_cycles"
     },
     {
         "BriefDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss",
         "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.ALL / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Cycles;Ifetch",
-        "MetricName": "tma_info_bottleneck_ifetch_miss_bound_cycles",
-        "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound",
-        "ScaleUnit": "100%"
+        "MetricGroup": "Ifetch",
+        "MetricName": "tma_info_bottleneck_%_ifetch_miss_bound_cycles",
+        "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound"
     },
     {
         "BriefDescription": "Percentage of time that retirement is stalled due to an L1 miss",
         "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.ALL / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Cycles;Load_Store_Miss",
-        "MetricName": "tma_info_bottleneck_load_miss_bound_cycles",
-        "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound",
-        "ScaleUnit": "100%"
+        "MetricGroup": "Load_Store_Miss",
+        "MetricName": "tma_info_bottleneck_%_load_miss_bound_cycles",
+        "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound"
     },
     {
         "BriefDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall",
         "MetricExpr": "100 * LD_HEAD.ANY_AT_RET / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Cycles;Mem_Exec",
-        "MetricName": "tma_info_bottleneck_mem_exec_bound_cycles",
-        "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound",
-        "ScaleUnit": "100%"
+        "MetricGroup": "Mem_Exec",
+        "MetricName": "tma_info_bottleneck_%_mem_exec_bound_cycles",
+        "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound"
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -501,26 +510,22 @@
     {
         "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full",
         "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.LD_BUF / CPU_CLK_UNHALTED.CORE",
-        "MetricName": "tma_info_buffer_stalls_load_buffer_stall_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_buffer_stalls_%_load_buffer_stall_cycles"
     },
     {
         "BriefDescription": "Percentage of time that allocation is stalled due to memory reservation stations full",
         "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.RSV / CPU_CLK_UNHALTED.CORE",
-        "MetricName": "tma_info_buffer_stalls_mem_rsv_stall_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_buffer_stalls_%_mem_rsv_stall_cycles"
     },
     {
         "BriefDescription": "Percentage of time that allocation is stalled due to store buffer full",
         "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.ST_BUF / CPU_CLK_UNHALTED.CORE",
-        "MetricName": "tma_info_buffer_stalls_store_buffer_stall_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_buffer_stalls_%_store_buffer_stall_cycles"
     },
     {
         "BriefDescription": "Cycles Per Instruction",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE / INST_RETIRED.ANY",
-        "MetricName": "tma_info_core_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_core_cpi"
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
@@ -541,28 +546,46 @@
     {
         "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2",
         "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.L2_HIT / MEM_BOUND_STALLS_IFETCH.ALL",
-        "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l2hit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit"
+    },
+    {
+        "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss doesn't hit in the L2",
+        "MetricExpr": "100 * (MEM_BOUND_STALLS_IFETCH.LLC_HIT + MEM_BOUND_STALLS_IFETCH.LLC_MISS) / MEM_BOUND_STALLS_IFETCH.ALL",
+        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2miss"
     },
     {
         "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3",
         "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_HIT / MEM_BOUND_STALLS_IFETCH.ALL",
-        "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l3hit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3hit"
+    },
+    {
+        "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss subsequently misses in the L3",
+        "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_MISS / MEM_BOUND_STALLS_IFETCH.ALL",
+        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3miss"
     },
     {
         "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2",
         "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.L2_HIT / MEM_BOUND_STALLS_LOAD.ALL",
         "MetricGroup": "load_store_bound",
-        "MetricName": "tma_info_load_miss_bound_loadmissbound_with_l2hit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit"
+    },
+    {
+        "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses in the L2",
+        "MetricExpr": "100 * (MEM_BOUND_STALLS_LOAD.LLC_HIT + MEM_BOUND_STALLS_LOAD.LLC_MISS) / MEM_BOUND_STALLS_LOAD.ALL",
+        "MetricGroup": "load_store_bound",
+        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2miss"
     },
     {
         "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3",
         "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_HIT / MEM_BOUND_STALLS_LOAD.ALL",
         "MetricGroup": "load_store_bound",
-        "MetricName": "tma_info_load_miss_bound_loadmissbound_with_l3hit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3hit"
+    },
+    {
+        "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses the L3",
+        "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_MISS / MEM_BOUND_STALLS_LOAD.ALL",
+        "MetricGroup": "load_store_bound",
+        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3miss"
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a pipeline block",
@@ -600,44 +623,37 @@
     {
         "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block",
         "MetricExpr": "100 * LD_BLOCKS.ADDRESS_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricName": "tma_info_mem_exec_blocks_loads_with_adressaliasing",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_blocks_%_loads_with_adressaliasing"
     },
     {
         "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block",
         "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricName": "tma_info_mem_exec_blocks_loads_with_storefwdblk",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_blocks_%_loads_with_storefwdblk"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss",
         "MetricExpr": "100 * LD_HEAD.L1_MISS_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_l1miss",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_l1miss"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to other block cases, such as pipeline conflicts, fences, etc",
         "MetricExpr": "100 * LD_HEAD.OTHER_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_otherpipelineblks",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_otherpipelineblks"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a pagewalk",
         "MetricExpr": "100 * LD_HEAD.PGWALK_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_pagewalk",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_pagewalk"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a second level TLB miss",
         "MetricExpr": "100 * LD_HEAD.DTLB_MISS_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_stlbhit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_stlbhit"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a store forward address match",
         "MetricExpr": "100 * LD_HEAD.ST_ADDR_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_storefwding",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_storefwding"
     },
     {
         "BriefDescription": "Instructions per Load",
@@ -667,8 +683,7 @@
     {
         "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction",
         "MetricExpr": "100 * SERIALIZATION.C01_MS_SCB / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricName": "tma_info_serialization_tpause_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_serialization_%_tpause_cycles"
     },
     {
         "BriefDescription": "Average CPU Utilization",
@@ -684,17 +699,20 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.CORE_P:k / CPU_CLK_UNHALTED.CORE",
+        "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE_P@k / CPU_CLK_UNHALTED.CORE",
+        "MetricGroup": "Summary",
         "MetricName": "tma_info_system_kernel_utilization"
     },
     {
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE",
-        "MetricName": "tma_info_system_mux"
+        "MetricName": "tma_info_system_mux",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
     },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
         "MetricName": "tma_info_system_turbo_utilization"
     },
     {
@@ -718,90 +736,102 @@
         "MetricName": "tma_info_uop_mix_x87_uop_ratio"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.",
         "MetricExpr": "TOPDOWN_FE_BOUND.ITLB_MISS / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_itlb_misses",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
+        "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops",
         "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
+        "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops",
         "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
+        "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that requires the use of microcode (slow nuke)",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
+        "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.",
         "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_other_fb",
+        "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.",
         "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_predecode",
+        "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls)",
         "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
+        "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls)",
         "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
+        "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a resource limitation",
         "MetricExpr": "tma_backend_bound - tma_core_bound",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_resource_bound",
+        "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that result in retirement slots",
         "MetricExpr": "TOPDOWN_RETIRING.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
+        "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
+        "MetricThreshold": "tma_retiring > 0.75",
         "MetricgroupNoGroup": "TopdownL1",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS)",
         "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
+        "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cache.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cache.json
index a779a1a73ea5..7182ca00ef8d 100644
--- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cache.json
@@ -874,6 +874,38 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x3d",
+        "EventName": "UNC_CHA_SF_EVICTION.E_STATE",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "Snoop Filter Capacity Evictions : E state",
+        "UMask": "0x2",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x3d",
+        "EventName": "UNC_CHA_SF_EVICTION.M_STATE",
+        "PerPkg": "1",
+        "PublicDescription": "Snoop Filter Capacity Evictions : M state",
+        "UMask": "0x1",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x3d",
+        "EventName": "UNC_CHA_SF_EVICTION.S_STATE",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "Snoop Filter Capacity Evictions : S state",
+        "UMask": "0x4",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "All TOR Inserts",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json
index ae9c62b32e92..c7e9dbe02eb0 100644
--- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json
@@ -189,6 +189,94 @@
         "Unit": "IMC"
     },
     {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
         "BriefDescription": "# of cycles a given rank is in Power Down Mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x47",
@@ -287,6 +375,70 @@
         "Unit": "IMC"
     },
     {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x89",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x89",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "MR4 temp reading is throttling",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.MR4BLKEN",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "RAPL is throttling",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RAPLBLK",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
         "BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.",
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
@@ -481,6 +633,94 @@
         "Unit": "IMC"
     },
     {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8e",
+        "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8e",
+        "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at High level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8d",
+        "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at High level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8d",
+        "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8b",
+        "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8b",
+        "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8c",
+        "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8c",
+        "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
         "BriefDescription": "Write Pending Queue Allocations",
         "Counter": "0,1,2,3",
         "EventCode": "0x22",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
index 2a76dd01fb52..2d3a037e88b5 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
@@ -74,12 +74,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -91,7 +91,7 @@
         "MetricExpr": "34 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
@@ -102,7 +102,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
     {
@@ -112,12 +112,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -132,7 +132,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -140,7 +140,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -148,22 +148,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -171,7 +171,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -179,15 +179,15 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
-        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears"
+        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache"
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -199,10 +199,10 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -224,8 +224,8 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -233,8 +233,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -242,7 +242,7 @@
         "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -251,7 +251,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -259,33 +259,33 @@
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "((22 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + (20 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(18.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 16.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -296,25 +296,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(20 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "16.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
@@ -323,7 +323,7 @@
         "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
@@ -333,7 +333,7 @@
         "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -343,7 +343,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -351,27 +351,27 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+        "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -380,18 +380,18 @@
         "MetricExpr": "22 * tma_info_system_core_frequency * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
     {
@@ -401,7 +401,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -411,7 +411,7 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -431,7 +431,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -440,7 +440,7 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%"
     },
     {
@@ -448,8 +448,8 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -458,8 +458,8 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -467,8 +467,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -476,8 +476,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -487,35 +487,35 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
-        "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / tma_info_thread_clks",
+        "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -526,11 +526,11 @@
         "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -555,7 +555,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -564,7 +564,7 @@
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -572,10 +572,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -604,7 +605,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -632,11 +633,11 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -649,20 +650,20 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@ + 2",
+        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency"
     },
@@ -698,7 +699,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -717,7 +718,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -725,7 +726,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -733,7 +734,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -741,7 +742,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -749,7 +750,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -799,7 +800,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -974,8 +975,8 @@
         "MetricName": "tma_info_memory_tlb_store_stlb_mpki"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -996,12 +997,12 @@
         "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -1043,14 +1044,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1061,7 +1061,7 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@cmask\\=0x1@",
+        "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@cmask\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
@@ -1112,7 +1112,7 @@
         "MetricName": "tma_info_system_turbo_utilization"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1121,15 +1121,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1155,15 +1154,15 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 6"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1171,7 +1170,7 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -1180,17 +1179,17 @@
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
+        "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1199,7 +1198,7 @@
         "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1208,17 +1207,17 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(10 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+        "MetricExpr": "6.5 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1226,18 +1225,18 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1255,7 +1254,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1263,31 +1262,31 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -1295,7 +1294,7 @@
         "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (9 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1307,15 +1306,15 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1324,7 +1323,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -1336,11 +1335,11 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -1362,7 +1361,7 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -1376,12 +1375,12 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
@@ -1389,7 +1388,7 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
@@ -1399,7 +1398,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%"
     },
     {
@@ -1407,8 +1406,8 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1421,19 +1420,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -1442,7 +1441,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1451,7 +1450,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1487,7 +1486,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1496,7 +1495,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1513,8 +1512,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
@@ -1522,8 +1521,8 @@
         "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
@@ -1531,7 +1530,7 @@
         "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -1540,16 +1539,16 @@
         "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
         "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1567,7 +1566,7 @@
         "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -1578,7 +1577,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1586,8 +1585,8 @@
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -1595,7 +1594,7 @@
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1604,8 +1603,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1613,8 +1612,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -1623,8 +1622,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1640,7 +1639,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1648,31 +1647,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -1680,7 +1679,7 @@
         "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -1689,8 +1688,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
index 2ce070629c52..7aeeb5725630 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/cache.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
@@ -1,5 +1,79 @@
 [
     {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x20"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITI",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITI",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x40"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x8"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xFE",
+        "EventName": "IDI_MISC.WB_DOWNGRADE",
+        "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xFE",
+        "EventName": "IDI_MISC.WB_UPGRADE",
+        "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2"
+    },
+    {
         "BriefDescription": "L1D data line replacements",
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/other.json b/tools/perf/pmu-events/arch/x86/skylakex/other.json
index 44c820518e12..adf7b6bb5838 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/other.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/other.json
@@ -36,62 +36,6 @@
         "UMask": "0x40"
     },
     {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x20"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x10"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITI",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITI",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x40"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x8"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x4"
-    },
-    {
         "BriefDescription": "Number of hardware interrupts received by the processor.",
         "Counter": "0,1,2,3",
         "EventCode": "0xCB",
@@ -101,24 +45,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xFE",
-        "EventName": "IDI_MISC.WB_DOWNGRADE",
-        "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.",
-        "SampleAfterValue": "100003",
-        "UMask": "0x4"
-    },
-    {
-        "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xFE",
-        "EventName": "IDI_MISC.WB_UPGRADE",
-        "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.",
-        "SampleAfterValue": "100003",
-        "UMask": "0x2"
-    },
-    {
         "BriefDescription": "MEMORY_DISAMBIGUATION.HISTORY_RESET",
         "Counter": "0,1,2,3",
         "EventCode": "0x09",
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index 2fe630cd4927..7cc7b076c3e2 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -295,12 +295,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -312,7 +312,7 @@
         "MetricExpr": "34 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
@@ -323,7 +323,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
     {
@@ -333,12 +333,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -353,7 +353,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -361,7 +361,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -369,22 +369,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -392,7 +392,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -400,7 +400,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
@@ -408,7 +408,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -420,10 +420,10 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -445,8 +445,8 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -454,8 +454,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -463,7 +463,7 @@
         "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -472,7 +472,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -480,33 +480,33 @@
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "((47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 44 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -517,25 +517,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
@@ -544,7 +544,7 @@
         "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
@@ -554,7 +554,7 @@
         "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -564,7 +564,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -572,27 +572,27 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+        "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -601,18 +601,18 @@
         "MetricExpr": "(110 * tma_info_system_core_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM + OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_system_core_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
     {
@@ -622,7 +622,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -632,7 +632,7 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -652,7 +652,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -661,7 +661,7 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%"
     },
     {
@@ -669,17 +669,17 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@ / UOPS_RETIRED.RETIRE_SLOTS",
+        "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -688,7 +688,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -697,7 +697,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -706,7 +706,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_512b",
-        "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -717,35 +717,35 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
-        "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / tma_info_thread_clks",
+        "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -756,11 +756,11 @@
         "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -785,7 +785,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -794,7 +794,7 @@
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -802,10 +802,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -834,7 +835,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -859,14 +860,14 @@
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@) / (2 * tma_info_core_core_clks)",
+        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -879,20 +880,20 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@ + 2",
+        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency"
     },
@@ -928,7 +929,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -943,11 +944,11 @@
     {
         "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@)",
+        "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -955,7 +956,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -963,7 +964,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -971,7 +972,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx512",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -979,7 +980,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -987,7 +988,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -1037,7 +1038,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -1224,8 +1225,8 @@
         "MetricName": "tma_info_memory_tlb_store_stlb_mpki"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -1246,12 +1247,12 @@
         "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -1307,14 +1308,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1332,7 +1332,7 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@",
+        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
@@ -1362,7 +1362,7 @@
         "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks)",
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license0_utilization",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
@@ -1370,7 +1370,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license1_utilization",
         "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)",
@@ -1378,7 +1378,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license2_utilization",
         "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
@@ -1412,7 +1412,7 @@
         "MetricName": "tma_info_system_uncore_frequency"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1421,15 +1421,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1455,15 +1454,15 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 6"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1471,7 +1470,7 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -1480,17 +1479,17 @@
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
+        "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1499,7 +1498,7 @@
         "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1508,17 +1507,17 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(20.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+        "MetricExpr": "17 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1526,18 +1525,18 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1555,7 +1554,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1563,39 +1562,39 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory",
-        "MetricExpr": "(80 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "59.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
         "ScaleUnit": "100%"
     },
@@ -1604,7 +1603,7 @@
         "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1621,10 +1620,10 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1633,7 +1632,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -1645,11 +1644,11 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -1671,7 +1670,7 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -1685,12 +1684,12 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
@@ -1698,7 +1697,7 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
@@ -1708,7 +1707,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%"
     },
     {
@@ -1716,8 +1715,8 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1730,19 +1729,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -1751,7 +1750,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1760,7 +1759,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1796,7 +1795,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1805,7 +1804,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1822,8 +1821,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
@@ -1831,8 +1830,8 @@
         "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
@@ -1840,7 +1839,7 @@
         "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -1849,35 +1848,35 @@
         "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
         "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "((110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory",
-        "MetricExpr": "(147.5 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "127 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1895,7 +1894,7 @@
         "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -1906,7 +1905,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1914,8 +1913,8 @@
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -1923,7 +1922,7 @@
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1932,8 +1931,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1941,8 +1940,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -1951,8 +1950,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1968,7 +1967,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1976,31 +1975,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -2008,7 +2007,7 @@
         "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -2017,8 +2016,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/cache.json b/tools/perf/pmu-events/arch/x86/snowridgex/cache.json
index 7882dca9d5e1..3410caf8a57a 100644
--- a/tools/perf/pmu-events/arch/x86/snowridgex/cache.json
+++ b/tools/perf/pmu-events/arch/x86/snowridgex/cache.json
@@ -161,6 +161,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x80"
     },
@@ -171,6 +172,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x20"
     },
@@ -181,6 +183,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -191,6 +194,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
     },
@@ -201,6 +205,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -211,6 +216,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x10"
     },
@@ -221,6 +227,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -231,7 +238,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL",
         "PEBS": "1",
-        "PublicDescription": "Counts the number of memory uops retired.  A single uop that performs both a load AND a store will be counted as 1, not 2 (e.g. ADD [mem], CONST)",
+        "PublicDescription": "Counts the number of memory uops retired.  A single uop that performs both a load AND a store will be counted as 1, not 2 (e.g. ADD [mem], CONST) Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x83"
     },
@@ -242,7 +249,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of load uops retired.",
+        "PublicDescription": "Counts the total number of load uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x81"
     },
@@ -253,7 +260,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of store uops retired.",
+        "PublicDescription": "Counts the total number of store uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x82"
     },
@@ -264,6 +271,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that performed one or more locks. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21"
     },
@@ -274,6 +282,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of memory uops retired that were splits. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x43"
     },
@@ -284,6 +293,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x41"
     },
@@ -294,6 +304,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired split store uops. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x42"
     },
@@ -304,6 +315,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -314,6 +326,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -324,6 +337,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -334,6 +348,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -344,6 +359,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -354,6 +370,18 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3000000010000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -364,6 +392,29 @@
         "EventName": "OCR.COREWB_M.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3001F803C0000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.COREWB_M.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8003000000000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -374,6 +425,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -384,6 +436,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -394,6 +447,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -404,6 +458,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -414,6 +469,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -424,6 +480,18 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -434,6 +502,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -444,6 +513,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -454,6 +524,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -464,6 +535,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -474,6 +546,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -484,6 +557,30 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE",
+        "Counter": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -495,6 +592,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -506,6 +604,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HITM Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -517,6 +616,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_NO_FWD Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -528,6 +628,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_WITH_FWD Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -539,6 +640,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_MISS Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -550,6 +652,30 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_NOT_NEEDED Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING",
+        "Counter": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -560,6 +686,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -570,6 +697,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -580,6 +708,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -590,6 +719,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -600,6 +730,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -610,6 +741,18 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_RFO.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -620,6 +763,18 @@
         "EventName": "OCR.FULL_STREAMING_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x801F803C0000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10400",
+        "PublicDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -630,6 +785,18 @@
         "EventName": "OCR.HWPF_L1D_AND_SWPF.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0400",
+        "PublicDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -640,6 +807,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -650,6 +818,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -660,6 +829,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -670,6 +840,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -680,6 +851,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -690,6 +862,29 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_CODE_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -700,6 +895,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -710,6 +906,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -720,6 +917,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -730,6 +928,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -740,6 +939,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -750,6 +950,18 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -760,6 +972,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -770,6 +983,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -780,6 +994,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -790,6 +1005,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -800,6 +1016,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -810,6 +1027,29 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_RFO.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.L1WB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000000010000",
+        "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -820,6 +1060,18 @@
         "EventName": "OCR.L1WB_M.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1001F803C0000",
+        "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.L2WB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000000010000",
+        "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -830,6 +1082,7 @@
         "EventName": "OCR.L2WB_M.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2001F803C0000",
+        "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -840,6 +1093,18 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x401F803C0000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -850,6 +1115,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -860,6 +1126,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -870,6 +1137,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -880,6 +1148,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -890,6 +1159,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -900,6 +1170,18 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.READS_TO_CORE.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -910,6 +1192,7 @@
         "EventName": "OCR.STREAMING_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0800",
+        "PublicDescription": "Counts streaming stores that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -920,6 +1203,7 @@
         "EventName": "OCR.UC_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x101F803C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -930,6 +1214,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1010003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -940,6 +1225,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1004003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -950,6 +1236,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -960,6 +1247,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1002003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -970,6 +1258,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1001003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -980,6 +1269,7 @@
         "EventName": "OCR.UC_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x201F803C0000",
+        "PublicDescription": "Counts uncached memory writes that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/floating-point.json b/tools/perf/pmu-events/arch/x86/snowridgex/floating-point.json
index 79a4beba4b78..f47d97dfe0d9 100644
--- a/tools/perf/pmu-events/arch/x86/snowridgex/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/snowridgex/floating-point.json
@@ -23,6 +23,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.FPDIV",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     }
diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/memory.json b/tools/perf/pmu-events/arch/x86/snowridgex/memory.json
index 34306ec24e9b..417cd78fc048 100644
--- a/tools/perf/pmu-events/arch/x86/snowridgex/memory.json
+++ b/tools/perf/pmu-events/arch/x86/snowridgex/memory.json
@@ -13,6 +13,7 @@
         "EventCode": "0x13",
         "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of misaligned load uops that are 4K page splits. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -22,16 +23,29 @@
         "EventCode": "0x13",
         "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of misaligned store uops that are 4K page splits. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
     {
+        "BriefDescription": "Counts all code reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.ALL_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000044",
+        "PublicDescription": "Counts all code reads that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all code reads that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0XB7",
         "EventName": "OCR.ALL_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000044",
+        "PublicDescription": "Counts all code reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -42,6 +56,18 @@
         "EventName": "OCR.ALL_CODE_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000044",
+        "PublicDescription": "Counts all code reads that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all code reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.ALL_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000044",
+        "PublicDescription": "Counts all code reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -52,6 +78,7 @@
         "EventName": "OCR.COREWB_M.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3002184000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -62,6 +89,18 @@
         "EventName": "OCR.COREWB_M.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3002184000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -72,6 +111,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -82,6 +122,29 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -92,6 +155,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -102,6 +166,30 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM",
+        "Counter": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -113,6 +201,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -124,6 +213,30 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS_LOCAL Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM",
+        "Counter": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -134,6 +247,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -144,6 +258,18 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -154,6 +280,7 @@
         "EventName": "OCR.FULL_STREAMING_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x802184000000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -164,6 +291,18 @@
         "EventName": "OCR.FULL_STREAMING_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x802184000000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -174,6 +313,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -184,6 +324,29 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -194,6 +357,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -204,6 +368,29 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -214,6 +401,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -224,6 +412,18 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -234,6 +434,7 @@
         "EventName": "OCR.L1WB_M.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1002184000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -244,6 +445,7 @@
         "EventName": "OCR.L1WB_M.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1002184000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -254,6 +456,7 @@
         "EventName": "OCR.L2WB_M.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2002184000000",
+        "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -264,6 +467,7 @@
         "EventName": "OCR.L2WB_M.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2002184000000",
+        "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -274,6 +478,7 @@
         "EventName": "OCR.OTHER.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184008000",
+        "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -284,6 +489,7 @@
         "EventName": "OCR.OTHER.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184008000",
+        "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -294,6 +500,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x402184000000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -304,6 +511,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x402184000000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -314,6 +522,18 @@
         "EventName": "OCR.PREFETCHES.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000470",
+        "PublicDescription": "Counts all hardware and software prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.READS_TO_CORE.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -324,6 +544,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -334,6 +555,18 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -344,6 +577,7 @@
         "EventName": "OCR.STREAMING_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000800",
+        "PublicDescription": "Counts streaming stores that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -354,6 +588,18 @@
         "EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000800",
+        "PublicDescription": "Counts streaming stores that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.UC_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100184000000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -364,6 +610,7 @@
         "EventName": "OCR.UC_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x102184000000",
+        "PublicDescription": "Counts uncached memory reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -374,6 +621,18 @@
         "EventName": "OCR.UC_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x102184000000",
+        "PublicDescription": "Counts uncached memory reads that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.UC_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100184000000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -384,6 +643,7 @@
         "EventName": "OCR.UC_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x202184000000",
+        "PublicDescription": "Counts uncached memory writes that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -394,6 +654,7 @@
         "EventName": "OCR.UC_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x202184000000",
+        "PublicDescription": "Counts uncached memory writes that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/other.json b/tools/perf/pmu-events/arch/x86/snowridgex/other.json
index 57613207f7ad..2cdc6b64f31d 100644
--- a/tools/perf/pmu-events/arch/x86/snowridgex/other.json
+++ b/tools/perf/pmu-events/arch/x86/snowridgex/other.json
@@ -113,26 +113,7 @@
         "EventName": "OCR.ALL_CODE_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10044",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all code reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.ALL_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000044",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all code reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.ALL_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000044",
+        "PublicDescription": "Counts all code reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -143,180 +124,7 @@
         "EventName": "OCR.ALL_CODE_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "MSRValue": "0x8000000000000044",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3000000010000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.COREWB_M.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8003000000000000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE",
-        "Counter": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM",
-        "Counter": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM",
-        "Counter": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING",
-        "Counter": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_RFO.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000002",
+        "PublicDescription": "Counts all code reads that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -327,146 +135,7 @@
         "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x800000010000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10040",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000040",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000040",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_CODE_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000040",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_RFO.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.L1WB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1000000010000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.L2WB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x2000000010000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -477,6 +146,7 @@
         "EventName": "OCR.OTHER.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x18000",
+        "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -487,6 +157,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x400000010000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -497,46 +168,7 @@
         "EventName": "OCR.PREFETCHES.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10470",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.READS_TO_CORE.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.READS_TO_CORE.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000477",
+        "PublicDescription": "Counts all hardware and software prefetches that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -547,6 +179,7 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -557,26 +190,7 @@
         "EventName": "OCR.UC_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x100000010000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.UC_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100184000000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.UC_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100184000000",
+        "PublicDescription": "Counts uncached memory reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -587,6 +201,7 @@
         "EventName": "OCR.UC_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "MSRValue": "0x8000100000000000",
+        "PublicDescription": "Counts uncached memory reads that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -597,6 +212,7 @@
         "EventName": "OCR.UC_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x200000010000",
+        "PublicDescription": "Counts uncached memory writes that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/pipeline.json b/tools/perf/pmu-events/arch/x86/snowridgex/pipeline.json
index e4e7902c1162..0fc2e821b14a 100644
--- a/tools/perf/pmu-events/arch/x86/snowridgex/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/snowridgex/pipeline.json
@@ -5,7 +5,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for.",
+        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for. Available PDIST counters: 0",
         "SampleAfterValue": "200003"
     },
     {
@@ -14,6 +14,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.CALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf9"
     },
@@ -23,6 +24,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xbf"
     },
@@ -32,6 +34,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.IND_CALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -41,6 +44,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.JCC",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -50,6 +54,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NON_RETURN_IND",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -59,6 +64,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.REL_CALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near relative CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfd"
     },
@@ -68,6 +74,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.RETURN",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7"
     },
@@ -77,6 +84,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.TAKEN_JCC",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -86,7 +94,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
+        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "200003"
     },
     {
@@ -95,6 +103,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.IND_CALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -104,6 +113,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.JCC",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -113,6 +123,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -122,6 +133,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RETURN",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7"
     },
@@ -131,6 +143,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.TAKEN_JCC",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -206,7 +219,7 @@
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -216,7 +229,7 @@
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -225,6 +238,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.4K_ALIAS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -234,6 +248,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked for any of the following reasons:  DTLB miss, address alias, store forward or data unknown (includes memory disambiguation blocks and ESP consuming load blocks). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -243,6 +258,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.DATA_UNKNOWN",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -252,6 +268,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.STORE_FORWARD",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked because its address partially overlapped with an older store. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -464,6 +481,7 @@
         "EventCode": "0xc2",
         "EventName": "TOPDOWN_RETIRING.ALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the total number of consumed retirement slots. Available PDIST counters: 0",
         "SampleAfterValue": "1000003"
     },
     {
@@ -480,6 +498,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.ALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the total number of uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -488,6 +507,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.IDIV",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of integer divide uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -497,7 +517,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.MS",
         "PEBS": "1",
-        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.",
+        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -507,6 +527,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.X87",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of x87 uops retired, includes those in MS flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     }
diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/snowridgex/virtual-memory.json
index f9a6caed8776..bf56d72bb4a7 100644
--- a/tools/perf/pmu-events/arch/x86/snowridgex/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/snowridgex/virtual-memory.json
@@ -242,6 +242,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.DTLB_MISS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked due to a first level TLB miss. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -252,6 +253,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of memory uops retired that missed in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x13"
     },
@@ -262,6 +264,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that miss in the second Level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x11"
     },
@@ -272,6 +275,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of store uops retired that miss in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x12"
     }
diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
index 8c0cd6e63a2a..2db7a70f7a07 100644
--- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
@@ -89,12 +89,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -106,7 +106,7 @@
         "MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
@@ -129,12 +129,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -149,7 +149,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -157,7 +157,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -165,22 +165,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -188,7 +188,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -196,15 +196,15 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
-        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears"
+        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache"
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -216,17 +216,17 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
         "MetricThreshold": "tma_bottleneck_useful_work > 20"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.",
         "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_branch_instructions",
@@ -248,8 +248,8 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -257,8 +257,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -266,24 +266,24 @@
         "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
         "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -291,7 +291,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -299,33 +299,33 @@
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "((54 * tma_info_system_core_frequency - 5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (53 * tma_info_system_core_frequency - 5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(49 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 48 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -335,25 +335,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(53 * tma_info_system_core_frequency - 5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "48 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
@@ -362,7 +362,7 @@
         "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
@@ -372,7 +372,7 @@
         "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -382,7 +382,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -390,26 +390,26 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -417,8 +417,8 @@
         "MetricExpr": "54 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -437,7 +437,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -447,7 +447,7 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -465,7 +465,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -474,15 +474,15 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "ARITH.FP_DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -490,7 +490,7 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -499,7 +499,7 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -508,7 +508,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -517,7 +517,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -526,7 +526,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_512b",
-        "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -538,17 +538,17 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
-        "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
@@ -556,8 +556,8 @@
         "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -569,28 +569,28 @@
         "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -619,7 +619,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -628,7 +628,7 @@
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -637,10 +637,11 @@
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -701,11 +702,11 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -718,20 +719,20 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency"
     },
@@ -773,7 +774,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -791,7 +792,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -799,7 +800,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -807,7 +808,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -815,7 +816,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx512",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -823,7 +824,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -831,7 +832,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -886,7 +887,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 5 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 11",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -1011,7 +1012,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp"
     },
@@ -1074,7 +1075,7 @@
     },
     {
         "BriefDescription": "",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -1101,12 +1102,12 @@
         "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -1147,14 +1148,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1195,7 +1195,7 @@
         "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks",
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license0_utilization",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
@@ -1203,7 +1203,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license1_utilization",
         "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)",
@@ -1211,7 +1211,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license2_utilization",
         "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
@@ -1239,7 +1239,7 @@
         "MetricName": "tma_info_system_turbo_utilization"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1248,15 +1248,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1266,13 +1265,13 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "TOPDOWN.SLOTS",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots"
     },
     {
         "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
+        "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)",
         "MetricGroup": "SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots_utilization"
     },
@@ -1288,14 +1287,14 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 5 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 7.5"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1303,8 +1302,8 @@
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1312,7 +1311,7 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -1321,7 +1320,7 @@
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
@@ -1331,7 +1330,7 @@
         "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1340,7 +1339,7 @@
         "MetricExpr": "5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1350,17 +1349,17 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(22.5 * tma_info_system_core_frequency - 5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+        "MetricExpr": "17.5 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1368,18 +1367,18 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1396,7 +1395,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1404,31 +1403,31 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -1437,7 +1436,7 @@
         "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1447,7 +1446,7 @@
         "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_lsd",
         "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.",
         "ScaleUnit": "100%"
     },
     {
@@ -1457,15 +1456,15 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1474,7 +1473,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -1485,11 +1484,11 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
@@ -1511,7 +1510,7 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -1526,24 +1525,24 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline",
-        "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / tma_info_thread_clks",
+        "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group",
         "MetricName": "tma_mite_4wide",
-        "MetricThreshold": "tma_mite_4wide > 0.05 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
-        "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=0x1@ / tma_info_core_core_clks / 2",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
+        "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 2",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
         "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
@@ -1554,7 +1553,7 @@
         "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
@@ -1563,7 +1562,7 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%"
     },
@@ -1578,19 +1577,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -1634,8 +1633,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
@@ -1643,8 +1642,8 @@
         "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
@@ -1652,7 +1651,7 @@
         "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -1661,7 +1660,7 @@
         "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
@@ -1670,14 +1669,14 @@
         "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -1690,7 +1689,7 @@
         "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -1699,7 +1698,7 @@
         "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST",
         "ScaleUnit": "100%"
     },
@@ -1709,7 +1708,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1718,8 +1717,8 @@
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -1727,7 +1726,7 @@
         "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1736,8 +1735,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1746,8 +1745,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -1755,8 +1754,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1773,7 +1772,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1781,31 +1780,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -1813,7 +1812,7 @@
         "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%"
     },
@@ -1822,7 +1821,7 @@
         "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -1831,8 +1830,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json b/tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json
index 30845c7dbf08..f6f95f3ff301 100644
--- a/tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json
+++ b/tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json
@@ -120,6 +120,38 @@
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "L1I instruction fetch stall cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.CYCLES_STALLED",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "L1I instruction fetch hits",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.HITS",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "L1I instruction fetch misses",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.MISSES",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "L1I Instruction fetches",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.READS",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x3"
+    },
+    {
         "BriefDescription": "All L2 data requests",
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
diff --git a/tools/perf/pmu-events/arch/x86/westmereep-dp/other.json b/tools/perf/pmu-events/arch/x86/westmereep-dp/other.json
index bcf5bcf637c0..c0cf8bae8074 100644
--- a/tools/perf/pmu-events/arch/x86/westmereep-dp/other.json
+++ b/tools/perf/pmu-events/arch/x86/westmereep-dp/other.json
@@ -16,46 +16,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "L1I instruction fetch stall cycles",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.CYCLES_STALLED",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x4"
-    },
-    {
-        "BriefDescription": "L1I instruction fetch hits",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.HITS",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "L1I instruction fetch misses",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.MISSES",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "L1I Instruction fetches",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.READS",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x3"
-    },
-    {
-        "BriefDescription": "Large ITLB hit",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x82",
-        "EventName": "LARGE_ITLB.HIT",
-        "SampleAfterValue": "200000",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Loads that partially overlap an earlier store",
         "Counter": "0,1,2,3",
         "EventCode": "0x3",
diff --git a/tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json b/tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json
index 53d7f76325a3..84c920637b12 100644
--- a/tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json
@@ -153,6 +153,14 @@
         "UMask": "0x20"
     },
     {
+        "BriefDescription": "Large ITLB hit",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x82",
+        "EventName": "LARGE_ITLB.HIT",
+        "SampleAfterValue": "200000",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Retired loads that miss the DTLB (Precise Event)",
         "Counter": "0,1,2,3",
         "EventCode": "0xCB",
diff --git a/tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json b/tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json
index 90cb367f5798..0cd571472dca 100644
--- a/tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json
+++ b/tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json
@@ -120,6 +120,38 @@
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "L1I instruction fetch stall cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.CYCLES_STALLED",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "L1I instruction fetch hits",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.HITS",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "L1I instruction fetch misses",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.MISSES",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "L1I Instruction fetches",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.READS",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x3"
+    },
+    {
         "BriefDescription": "All L2 data requests",
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
diff --git a/tools/perf/pmu-events/arch/x86/westmereep-sp/other.json b/tools/perf/pmu-events/arch/x86/westmereep-sp/other.json
index bcf5bcf637c0..c0cf8bae8074 100644
--- a/tools/perf/pmu-events/arch/x86/westmereep-sp/other.json
+++ b/tools/perf/pmu-events/arch/x86/westmereep-sp/other.json
@@ -16,46 +16,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "L1I instruction fetch stall cycles",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.CYCLES_STALLED",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x4"
-    },
-    {
-        "BriefDescription": "L1I instruction fetch hits",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.HITS",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "L1I instruction fetch misses",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.MISSES",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "L1I Instruction fetches",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.READS",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x3"
-    },
-    {
-        "BriefDescription": "Large ITLB hit",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x82",
-        "EventName": "LARGE_ITLB.HIT",
-        "SampleAfterValue": "200000",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Loads that partially overlap an earlier store",
         "Counter": "0,1,2,3",
         "EventCode": "0x3",
diff --git a/tools/perf/pmu-events/arch/x86/westmereep-sp/virtual-memory.json b/tools/perf/pmu-events/arch/x86/westmereep-sp/virtual-memory.json
index e7affdf7f41b..a1b22c82a9bf 100644
--- a/tools/perf/pmu-events/arch/x86/westmereep-sp/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/westmereep-sp/virtual-memory.json
@@ -129,6 +129,14 @@
         "UMask": "0x20"
     },
     {
+        "BriefDescription": "Large ITLB hit",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x82",
+        "EventName": "LARGE_ITLB.HIT",
+        "SampleAfterValue": "200000",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Retired loads that miss the DTLB (Precise Event)",
         "Counter": "0,1,2,3",
         "EventCode": "0xCB",
diff --git a/tools/perf/pmu-events/arch/x86/westmereex/cache.json b/tools/perf/pmu-events/arch/x86/westmereex/cache.json
index 9f922370ee8b..2a677d10f688 100644
--- a/tools/perf/pmu-events/arch/x86/westmereex/cache.json
+++ b/tools/perf/pmu-events/arch/x86/westmereex/cache.json
@@ -120,6 +120,38 @@
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "L1I instruction fetch stall cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.CYCLES_STALLED",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "L1I instruction fetch hits",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.HITS",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "L1I instruction fetch misses",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.MISSES",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "L1I Instruction fetches",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "L1I.READS",
+        "SampleAfterValue": "2000000",
+        "UMask": "0x3"
+    },
+    {
         "BriefDescription": "All L2 data requests",
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
diff --git a/tools/perf/pmu-events/arch/x86/westmereex/other.json b/tools/perf/pmu-events/arch/x86/westmereex/other.json
index bcf5bcf637c0..c0cf8bae8074 100644
--- a/tools/perf/pmu-events/arch/x86/westmereex/other.json
+++ b/tools/perf/pmu-events/arch/x86/westmereex/other.json
@@ -16,46 +16,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "L1I instruction fetch stall cycles",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.CYCLES_STALLED",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x4"
-    },
-    {
-        "BriefDescription": "L1I instruction fetch hits",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.HITS",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "L1I instruction fetch misses",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.MISSES",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "L1I Instruction fetches",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x80",
-        "EventName": "L1I.READS",
-        "SampleAfterValue": "2000000",
-        "UMask": "0x3"
-    },
-    {
-        "BriefDescription": "Large ITLB hit",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x82",
-        "EventName": "LARGE_ITLB.HIT",
-        "SampleAfterValue": "200000",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Loads that partially overlap an earlier store",
         "Counter": "0,1,2,3",
         "EventCode": "0x3",
diff --git a/tools/perf/pmu-events/arch/x86/westmereex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/westmereex/virtual-memory.json
index 0c3501e6e5a3..1800c6ecbf80 100644
--- a/tools/perf/pmu-events/arch/x86/westmereex/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/westmereex/virtual-memory.json
@@ -153,6 +153,14 @@
         "UMask": "0x20"
     },
     {
+        "BriefDescription": "Large ITLB hit",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x82",
+        "EventName": "LARGE_ITLB.HIT",
+        "SampleAfterValue": "200000",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Retired loads that miss the DTLB (Precise Event)",
         "Counter": "0,1,2,3",
         "EventCode": "0xCB",
diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 0cb7ba7912e8..d4017007a991 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -20,73 +20,73 @@ struct pmu_table_entry {
 
 static const char *const big_c_string =
 /* offset=0 */ "tool\000"
-/* offset=5 */ "duration_time\000tool\000Wall clock interval time in nanoseconds\000config=1\000\00000\000\000"
-/* offset=78 */ "user_time\000tool\000User (non-kernel) time in nanoseconds\000config=2\000\00000\000\000"
-/* offset=145 */ "system_time\000tool\000System/kernel time in nanoseconds\000config=3\000\00000\000\000"
-/* offset=210 */ "has_pmem\000tool\0001 if persistent memory installed otherwise 0\000config=4\000\00000\000\000"
-/* offset=283 */ "num_cores\000tool\000Number of cores. A core consists of 1 or more thread, with each thread being associated with a logical Linux CPU\000config=5\000\00000\000\000"
-/* offset=425 */ "num_cpus\000tool\000Number of logical Linux CPUs. There may be multiple such CPUs on a core\000config=6\000\00000\000\000"
-/* offset=525 */ "num_cpus_online\000tool\000Number of online logical Linux CPUs. There may be multiple such CPUs on a core\000config=7\000\00000\000\000"
-/* offset=639 */ "num_dies\000tool\000Number of dies. Each die has 1 or more cores\000config=8\000\00000\000\000"
-/* offset=712 */ "num_packages\000tool\000Number of packages. Each package has 1 or more die\000config=9\000\00000\000\000"
-/* offset=795 */ "slots\000tool\000Number of functional units that in parallel can execute parts of an instruction\000config=0xa\000\00000\000\000"
-/* offset=902 */ "smt_on\000tool\0001 if simultaneous multithreading (aka hyperthreading) is enable otherwise 0\000config=0xb\000\00000\000\000"
-/* offset=1006 */ "system_tsc_freq\000tool\000The amount a Time Stamp Counter (TSC) increases per second\000config=0xc\000\00000\000\000"
-/* offset=1102 */ "default_core\000"
-/* offset=1115 */ "bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000"
-/* offset=1174 */ "bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000"
-/* offset=1233 */ "l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000Attributable Level 3 cache access, read\000"
-/* offset=1328 */ "segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000"
-/* offset=1427 */ "dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000"
-/* offset=1557 */ "eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000"
-/* offset=1672 */ "hisi_sccl,ddrc\000"
-/* offset=1687 */ "uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000DDRC write commands\000"
-/* offset=1773 */ "uncore_cbox\000"
-/* offset=1785 */ "unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000"
-/* offset=2016 */ "event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000UNC_CBO_HYPHEN\000"
-/* offset=2081 */ "event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000UNC_CBO_TWO_HYPH\000"
-/* offset=2152 */ "hisi_sccl,l3c\000"
-/* offset=2166 */ "uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000Total read hits\000"
-/* offset=2246 */ "uncore_imc_free_running\000"
-/* offset=2270 */ "uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000Total cache misses\000"
-/* offset=2365 */ "uncore_imc\000"
-/* offset=2376 */ "uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000Total cache hits\000"
-/* offset=2454 */ "uncore_sys_ddr_pmu\000"
-/* offset=2473 */ "sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000"
-/* offset=2546 */ "uncore_sys_ccn_pmu\000"
-/* offset=2565 */ "sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000"
-/* offset=2639 */ "uncore_sys_cmn_pmu\000"
-/* offset=2658 */ "sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000"
-/* offset=2798 */ "CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000"
-/* offset=2820 */ "IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000"
-/* offset=2883 */ "Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000"
-/* offset=3049 */ "dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
-/* offset=3113 */ "icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
-/* offset=3180 */ "cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000"
-/* offset=3251 */ "DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000"
-/* offset=3345 */ "DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000"
-/* offset=3479 */ "DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000"
-/* offset=3543 */ "DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000"
-/* offset=3611 */ "DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000"
-/* offset=3681 */ "M1\000\000ipc + M2\000\000\000\000\000\000\000\00000"
-/* offset=3703 */ "M2\000\000ipc + M1\000\000\000\000\000\000\000\00000"
-/* offset=3725 */ "M3\000\0001 / M3\000\000\000\000\000\000\000\00000"
-/* offset=3745 */ "L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000"
+/* offset=5 */ "duration_time\000tool\000Wall clock interval time in nanoseconds\000config=1\000\00000\000\000\000\000\000"
+/* offset=81 */ "user_time\000tool\000User (non-kernel) time in nanoseconds\000config=2\000\00000\000\000\000\000\000"
+/* offset=151 */ "system_time\000tool\000System/kernel time in nanoseconds\000config=3\000\00000\000\000\000\000\000"
+/* offset=219 */ "has_pmem\000tool\0001 if persistent memory installed otherwise 0\000config=4\000\00000\000\000\000\000\000"
+/* offset=295 */ "num_cores\000tool\000Number of cores. A core consists of 1 or more thread, with each thread being associated with a logical Linux CPU\000config=5\000\00000\000\000\000\000\000"
+/* offset=440 */ "num_cpus\000tool\000Number of logical Linux CPUs. There may be multiple such CPUs on a core\000config=6\000\00000\000\000\000\000\000"
+/* offset=543 */ "num_cpus_online\000tool\000Number of online logical Linux CPUs. There may be multiple such CPUs on a core\000config=7\000\00000\000\000\000\000\000"
+/* offset=660 */ "num_dies\000tool\000Number of dies. Each die has 1 or more cores\000config=8\000\00000\000\000\000\000\000"
+/* offset=736 */ "num_packages\000tool\000Number of packages. Each package has 1 or more die\000config=9\000\00000\000\000\000\000\000"
+/* offset=822 */ "slots\000tool\000Number of functional units that in parallel can execute parts of an instruction\000config=0xa\000\00000\000\000\000\000\000"
+/* offset=932 */ "smt_on\000tool\0001 if simultaneous multithreading (aka hyperthreading) is enable otherwise 0\000config=0xb\000\00000\000\000\000\000\000"
+/* offset=1039 */ "system_tsc_freq\000tool\000The amount a Time Stamp Counter (TSC) increases per second\000config=0xc\000\00000\000\000\000\000\000"
+/* offset=1138 */ "default_core\000"
+/* offset=1151 */ "bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000\000\000\000"
+/* offset=1213 */ "bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000\000\000\000"
+/* offset=1275 */ "l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000\000\000\000Attributable Level 3 cache access, read\000"
+/* offset=1373 */ "segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000\000\000\000"
+/* offset=1475 */ "dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000\000\000\000"
+/* offset=1608 */ "eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000\000\000\000"
+/* offset=1726 */ "hisi_sccl,ddrc\000"
+/* offset=1741 */ "uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000\000\000\000DDRC write commands\000"
+/* offset=1830 */ "uncore_cbox\000"
+/* offset=1842 */ "unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000\000\000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000"
+/* offset=2076 */ "event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000\000\000\000UNC_CBO_HYPHEN\000"
+/* offset=2144 */ "event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000\000\000\000UNC_CBO_TWO_HYPH\000"
+/* offset=2218 */ "hisi_sccl,l3c\000"
+/* offset=2232 */ "uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000\000\000\000Total read hits\000"
+/* offset=2315 */ "uncore_imc_free_running\000"
+/* offset=2339 */ "uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000\000\000\000Total cache misses\000"
+/* offset=2437 */ "uncore_imc\000"
+/* offset=2448 */ "uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000\000\000\000Total cache hits\000"
+/* offset=2529 */ "uncore_sys_ddr_pmu\000"
+/* offset=2548 */ "sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000\000\000\000"
+/* offset=2624 */ "uncore_sys_ccn_pmu\000"
+/* offset=2643 */ "sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000\000\000\000"
+/* offset=2720 */ "uncore_sys_cmn_pmu\000"
+/* offset=2739 */ "sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000\000\000\000"
+/* offset=2882 */ "CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000"
+/* offset=2904 */ "IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000"
+/* offset=2967 */ "Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000"
+/* offset=3133 */ "dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
+/* offset=3197 */ "icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000"
+/* offset=3264 */ "cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000"
+/* offset=3335 */ "DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000"
+/* offset=3429 */ "DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000"
+/* offset=3563 */ "DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000"
+/* offset=3627 */ "DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000"
+/* offset=3695 */ "DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000"
+/* offset=3765 */ "M1\000\000ipc + M2\000\000\000\000\000\000\000\00000"
+/* offset=3787 */ "M2\000\000ipc + M1\000\000\000\000\000\000\000\00000"
+/* offset=3809 */ "M3\000\0001 / M3\000\000\000\000\000\000\000\00000"
+/* offset=3829 */ "L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000"
 ;
 
 static const struct compact_pmu_event pmu_events__common_tool[] = {
-{ 5 }, /* duration_time\000tool\000Wall clock interval time in nanoseconds\000config=1\000\00000\000\000 */
-{ 210 }, /* has_pmem\000tool\0001 if persistent memory installed otherwise 0\000config=4\000\00000\000\000 */
-{ 283 }, /* num_cores\000tool\000Number of cores. A core consists of 1 or more thread, with each thread being associated with a logical Linux CPU\000config=5\000\00000\000\000 */
-{ 425 }, /* num_cpus\000tool\000Number of logical Linux CPUs. There may be multiple such CPUs on a core\000config=6\000\00000\000\000 */
-{ 525 }, /* num_cpus_online\000tool\000Number of online logical Linux CPUs. There may be multiple such CPUs on a core\000config=7\000\00000\000\000 */
-{ 639 }, /* num_dies\000tool\000Number of dies. Each die has 1 or more cores\000config=8\000\00000\000\000 */
-{ 712 }, /* num_packages\000tool\000Number of packages. Each package has 1 or more die\000config=9\000\00000\000\000 */
-{ 795 }, /* slots\000tool\000Number of functional units that in parallel can execute parts of an instruction\000config=0xa\000\00000\000\000 */
-{ 902 }, /* smt_on\000tool\0001 if simultaneous multithreading (aka hyperthreading) is enable otherwise 0\000config=0xb\000\00000\000\000 */
-{ 145 }, /* system_time\000tool\000System/kernel time in nanoseconds\000config=3\000\00000\000\000 */
-{ 1006 }, /* system_tsc_freq\000tool\000The amount a Time Stamp Counter (TSC) increases per second\000config=0xc\000\00000\000\000 */
-{ 78 }, /* user_time\000tool\000User (non-kernel) time in nanoseconds\000config=2\000\00000\000\000 */
+{ 5 }, /* duration_time\000tool\000Wall clock interval time in nanoseconds\000config=1\000\00000\000\000\000\000\000 */
+{ 219 }, /* has_pmem\000tool\0001 if persistent memory installed otherwise 0\000config=4\000\00000\000\000\000\000\000 */
+{ 295 }, /* num_cores\000tool\000Number of cores. A core consists of 1 or more thread, with each thread being associated with a logical Linux CPU\000config=5\000\00000\000\000\000\000\000 */
+{ 440 }, /* num_cpus\000tool\000Number of logical Linux CPUs. There may be multiple such CPUs on a core\000config=6\000\00000\000\000\000\000\000 */
+{ 543 }, /* num_cpus_online\000tool\000Number of online logical Linux CPUs. There may be multiple such CPUs on a core\000config=7\000\00000\000\000\000\000\000 */
+{ 660 }, /* num_dies\000tool\000Number of dies. Each die has 1 or more cores\000config=8\000\00000\000\000\000\000\000 */
+{ 736 }, /* num_packages\000tool\000Number of packages. Each package has 1 or more die\000config=9\000\00000\000\000\000\000\000 */
+{ 822 }, /* slots\000tool\000Number of functional units that in parallel can execute parts of an instruction\000config=0xa\000\00000\000\000\000\000\000 */
+{ 932 }, /* smt_on\000tool\0001 if simultaneous multithreading (aka hyperthreading) is enable otherwise 0\000config=0xb\000\00000\000\000\000\000\000 */
+{ 151 }, /* system_time\000tool\000System/kernel time in nanoseconds\000config=3\000\00000\000\000\000\000\000 */
+{ 1039 }, /* system_tsc_freq\000tool\000The amount a Time Stamp Counter (TSC) increases per second\000config=0xc\000\00000\000\000\000\000\000 */
+{ 81 }, /* user_time\000tool\000User (non-kernel) time in nanoseconds\000config=2\000\00000\000\000\000\000\000 */
 
 };
 
@@ -99,29 +99,29 @@ const struct pmu_table_entry pmu_events__common[] = {
 };
 
 static const struct compact_pmu_event pmu_events__test_soc_cpu_default_core[] = {
-{ 1115 }, /* bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000 */
-{ 1174 }, /* bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000 */
-{ 1427 }, /* dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000 */
-{ 1557 }, /* eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000 */
-{ 1233 }, /* l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000Attributable Level 3 cache access, read\000 */
-{ 1328 }, /* segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000 */
+{ 1151 }, /* bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000\000\000\000 */
+{ 1213 }, /* bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000\000\000\000 */
+{ 1475 }, /* dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000\000\000\000 */
+{ 1608 }, /* eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000\000\000\000 */
+{ 1275 }, /* l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000\000\000\000Attributable Level 3 cache access, read\000 */
+{ 1373 }, /* segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000\000\000\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_cpu_hisi_sccl_ddrc[] = {
-{ 1687 }, /* uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000DDRC write commands\000 */
+{ 1741 }, /* uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000\000\000\000DDRC write commands\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_cpu_hisi_sccl_l3c[] = {
-{ 2166 }, /* uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000Total read hits\000 */
+{ 2232 }, /* uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000\000\000\000Total read hits\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_cpu_uncore_cbox[] = {
-{ 2016 }, /* event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000UNC_CBO_HYPHEN\000 */
-{ 2081 }, /* event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000UNC_CBO_TWO_HYPH\000 */
-{ 1785 }, /* unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000 */
+{ 2076 }, /* event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000\000\000\000UNC_CBO_HYPHEN\000 */
+{ 2144 }, /* event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000\000\000\000UNC_CBO_TWO_HYPH\000 */
+{ 1842 }, /* unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000\000\000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_cpu_uncore_imc[] = {
-{ 2376 }, /* uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000Total cache hits\000 */
+{ 2448 }, /* uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000\000\000\000Total cache hits\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_cpu_uncore_imc_free_running[] = {
-{ 2270 }, /* uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000Total cache misses\000 */
+{ 2339 }, /* uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000\000\000\000Total cache misses\000 */
 
 };
 
@@ -129,51 +129,51 @@ const struct pmu_table_entry pmu_events__test_soc_cpu[] = {
 {
      .entries = pmu_events__test_soc_cpu_default_core,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_default_core),
-     .pmu_name = { 1102 /* default_core\000 */ },
+     .pmu_name = { 1138 /* default_core\000 */ },
 },
 {
      .entries = pmu_events__test_soc_cpu_hisi_sccl_ddrc,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_hisi_sccl_ddrc),
-     .pmu_name = { 1672 /* hisi_sccl,ddrc\000 */ },
+     .pmu_name = { 1726 /* hisi_sccl,ddrc\000 */ },
 },
 {
      .entries = pmu_events__test_soc_cpu_hisi_sccl_l3c,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_hisi_sccl_l3c),
-     .pmu_name = { 2152 /* hisi_sccl,l3c\000 */ },
+     .pmu_name = { 2218 /* hisi_sccl,l3c\000 */ },
 },
 {
      .entries = pmu_events__test_soc_cpu_uncore_cbox,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_uncore_cbox),
-     .pmu_name = { 1773 /* uncore_cbox\000 */ },
+     .pmu_name = { 1830 /* uncore_cbox\000 */ },
 },
 {
      .entries = pmu_events__test_soc_cpu_uncore_imc,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_uncore_imc),
-     .pmu_name = { 2365 /* uncore_imc\000 */ },
+     .pmu_name = { 2437 /* uncore_imc\000 */ },
 },
 {
      .entries = pmu_events__test_soc_cpu_uncore_imc_free_running,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_uncore_imc_free_running),
-     .pmu_name = { 2246 /* uncore_imc_free_running\000 */ },
+     .pmu_name = { 2315 /* uncore_imc_free_running\000 */ },
 },
 };
 
 static const struct compact_pmu_event pmu_metrics__test_soc_cpu_default_core[] = {
-{ 2798 }, /* CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000 */
-{ 3479 }, /* DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000 */
-{ 3251 }, /* DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000 */
-{ 3345 }, /* DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000 */
-{ 3543 }, /* DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
-{ 3611 }, /* DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
-{ 2883 }, /* Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000 */
-{ 2820 }, /* IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000 */
-{ 3745 }, /* L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000 */
-{ 3681 }, /* M1\000\000ipc + M2\000\000\000\000\000\000\000\00000 */
-{ 3703 }, /* M2\000\000ipc + M1\000\000\000\000\000\000\000\00000 */
-{ 3725 }, /* M3\000\0001 / M3\000\000\000\000\000\000\000\00000 */
-{ 3180 }, /* cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000 */
-{ 3049 }, /* dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
-{ 3113 }, /* icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
+{ 2882 }, /* CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000 */
+{ 3563 }, /* DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000 */
+{ 3335 }, /* DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000 */
+{ 3429 }, /* DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000 */
+{ 3627 }, /* DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
+{ 3695 }, /* DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000 */
+{ 2967 }, /* Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000 */
+{ 2904 }, /* IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000 */
+{ 3829 }, /* L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000 */
+{ 3765 }, /* M1\000\000ipc + M2\000\000\000\000\000\000\000\00000 */
+{ 3787 }, /* M2\000\000ipc + M1\000\000\000\000\000\000\000\00000 */
+{ 3809 }, /* M3\000\0001 / M3\000\000\000\000\000\000\000\00000 */
+{ 3264 }, /* cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000 */
+{ 3133 }, /* dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
+{ 3197 }, /* icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */
 
 };
 
@@ -181,18 +181,18 @@ const struct pmu_table_entry pmu_metrics__test_soc_cpu[] = {
 {
      .entries = pmu_metrics__test_soc_cpu_default_core,
      .num_entries = ARRAY_SIZE(pmu_metrics__test_soc_cpu_default_core),
-     .pmu_name = { 1102 /* default_core\000 */ },
+     .pmu_name = { 1138 /* default_core\000 */ },
 },
 };
 
 static const struct compact_pmu_event pmu_events__test_soc_sys_uncore_sys_ccn_pmu[] = {
-{ 2565 }, /* sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000 */
+{ 2643 }, /* sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000\000\000\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_sys_uncore_sys_cmn_pmu[] = {
-{ 2658 }, /* sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000 */
+{ 2739 }, /* sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000\000\000\000 */
 };
 static const struct compact_pmu_event pmu_events__test_soc_sys_uncore_sys_ddr_pmu[] = {
-{ 2473 }, /* sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000 */
+{ 2548 }, /* sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000\000\000\000 */
 
 };
 
@@ -200,17 +200,17 @@ const struct pmu_table_entry pmu_events__test_soc_sys[] = {
 {
      .entries = pmu_events__test_soc_sys_uncore_sys_ccn_pmu,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_sys_uncore_sys_ccn_pmu),
-     .pmu_name = { 2546 /* uncore_sys_ccn_pmu\000 */ },
+     .pmu_name = { 2624 /* uncore_sys_ccn_pmu\000 */ },
 },
 {
      .entries = pmu_events__test_soc_sys_uncore_sys_cmn_pmu,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_sys_uncore_sys_cmn_pmu),
-     .pmu_name = { 2639 /* uncore_sys_cmn_pmu\000 */ },
+     .pmu_name = { 2720 /* uncore_sys_cmn_pmu\000 */ },
 },
 {
      .entries = pmu_events__test_soc_sys_uncore_sys_ddr_pmu,
      .num_entries = ARRAY_SIZE(pmu_events__test_soc_sys_uncore_sys_ddr_pmu),
-     .pmu_name = { 2454 /* uncore_sys_ddr_pmu\000 */ },
+     .pmu_name = { 2529 /* uncore_sys_ddr_pmu\000 */ },
 },
 };
 
@@ -316,6 +316,12 @@ static void decompress_event(int offset, struct pmu_event *pe)
 	p++;
 	pe->unit = (*p == '\0' ? NULL : p);
 	while (*p++);
+	pe->retirement_latency_mean = (*p == '\0' ? NULL : p);
+	while (*p++);
+	pe->retirement_latency_min = (*p == '\0' ? NULL : p);
+	while (*p++);
+	pe->retirement_latency_max = (*p == '\0' ? NULL : p);
+	while (*p++);
 	pe->long_desc = (*p == '\0' ? NULL : p);
 }
 
@@ -443,7 +449,7 @@ int pmu_events_table__find_event(const struct pmu_events_table *table,
                 const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
                 int ret;
 
-                if (!perf_pmu__name_wildcard_match(pmu, pmu_name))
+                if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name))
                         continue;
 
                 ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data);
@@ -489,6 +495,49 @@ static int pmu_metrics_table__for_each_metric_pmu(const struct pmu_metrics_table
         return 0;
 }
 
+static int pmu_metrics_table__find_metric_pmu(const struct pmu_metrics_table *table,
+                                            const struct pmu_table_entry *pmu,
+                                            const char *metric,
+                                            pmu_metric_iter_fn fn,
+                                            void *data)
+{
+        struct pmu_metric pm = {
+                .pmu = &big_c_string[pmu->pmu_name.offset],
+        };
+        int low = 0, high = pmu->num_entries - 1;
+
+        while (low <= high) {
+                int cmp, mid = (low + high) / 2;
+
+                decompress_metric(pmu->entries[mid].offset, &pm);
+
+                if (!pm.metric_name && !metric)
+                        goto do_call;
+
+                if (!pm.metric_name && metric) {
+                        low = mid + 1;
+                        continue;
+                }
+                if (pm.metric_name && !metric) {
+                        high = mid - 1;
+                        continue;
+                }
+
+                cmp = strcmp(pm.metric_name, metric);
+                if (cmp < 0) {
+                        low = mid + 1;
+                        continue;
+                }
+                if (cmp > 0) {
+                        high = mid - 1;
+                        continue;
+                }
+  do_call:
+                return fn ? fn(&pm, table, data) : 0;
+        }
+        return PMU_METRICS__NOT_FOUND;
+}
+
 int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
                                      pmu_metric_iter_fn fn,
                                      void *data)
@@ -503,6 +552,27 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
         return 0;
 }
 
+int pmu_metrics_table__find_metric(const struct pmu_metrics_table *table,
+                                 struct perf_pmu *pmu,
+                                 const char *metric,
+                                 pmu_metric_iter_fn fn,
+                                 void *data)
+{
+        for (size_t i = 0; i < table->num_pmus; i++) {
+                const struct pmu_table_entry *table_pmu = &table->pmus[i];
+                const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
+                int ret;
+
+                if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name))
+                        continue;
+
+                ret = pmu_metrics_table__find_metric_pmu(table, table_pmu, metric, fn, data);
+                if (ret != PMU_METRICS__NOT_FOUND)
+                        return ret;
+        }
+        return PMU_METRICS__NOT_FOUND;
+}
+
 static const struct pmu_events_map *map_for_cpu(struct perf_cpu cpu)
 {
         static struct {
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 7499a35bfadd..a1899f35ec74 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -47,6 +47,9 @@ _json_event_attributes = [
     'event',
     # Short things in alphabetical order.
     'compat', 'deprecated', 'perpkg', 'unit',
+    # Retirement latency specific to Intel granite rapids currently.
+    'retirement_latency_mean', 'retirement_latency_min',
+    'retirement_latency_max',
     # Longer things (the last won't be iterated over during decompress).
     'long_desc'
 ]
@@ -341,6 +344,9 @@ class JsonEvent:
     self.perpkg = jd.get('PerPkg')
     self.aggr_mode = convert_aggr_mode(jd.get('AggregationMode'))
     self.deprecated = jd.get('Deprecated')
+    self.retirement_latency_mean = jd.get('RetirementLatencyMean')
+    self.retirement_latency_min = jd.get('RetirementLatencyMin')
+    self.retirement_latency_max = jd.get('RetirementLatencyMax')
     self.metric_name = jd.get('MetricName')
     self.metric_group = jd.get('MetricGroup')
     self.metricgroup_no_group = jd.get('MetricgroupNoGroup')
@@ -966,7 +972,7 @@ int pmu_events_table__find_event(const struct pmu_events_table *table,
                 const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
                 int ret;
 
-                if (!perf_pmu__name_wildcard_match(pmu, pmu_name))
+                if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name))
                         continue;
 
                 ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data);
@@ -1012,6 +1018,49 @@ static int pmu_metrics_table__for_each_metric_pmu(const struct pmu_metrics_table
         return 0;
 }
 
+static int pmu_metrics_table__find_metric_pmu(const struct pmu_metrics_table *table,
+                                            const struct pmu_table_entry *pmu,
+                                            const char *metric,
+                                            pmu_metric_iter_fn fn,
+                                            void *data)
+{
+        struct pmu_metric pm = {
+                .pmu = &big_c_string[pmu->pmu_name.offset],
+        };
+        int low = 0, high = pmu->num_entries - 1;
+
+        while (low <= high) {
+                int cmp, mid = (low + high) / 2;
+
+                decompress_metric(pmu->entries[mid].offset, &pm);
+
+                if (!pm.metric_name && !metric)
+                        goto do_call;
+
+                if (!pm.metric_name && metric) {
+                        low = mid + 1;
+                        continue;
+                }
+                if (pm.metric_name && !metric) {
+                        high = mid - 1;
+                        continue;
+                }
+
+                cmp = strcmp(pm.metric_name, metric);
+                if (cmp < 0) {
+                        low = mid + 1;
+                        continue;
+                }
+                if (cmp > 0) {
+                        high = mid - 1;
+                        continue;
+                }
+  do_call:
+                return fn ? fn(&pm, table, data) : 0;
+        }
+        return PMU_METRICS__NOT_FOUND;
+}
+
 int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
                                      pmu_metric_iter_fn fn,
                                      void *data)
@@ -1026,6 +1075,27 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
         return 0;
 }
 
+int pmu_metrics_table__find_metric(const struct pmu_metrics_table *table,
+                                 struct perf_pmu *pmu,
+                                 const char *metric,
+                                 pmu_metric_iter_fn fn,
+                                 void *data)
+{
+        for (size_t i = 0; i < table->num_pmus; i++) {
+                const struct pmu_table_entry *table_pmu = &table->pmus[i];
+                const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
+                int ret;
+
+                if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name))
+                        continue;
+
+                ret = pmu_metrics_table__find_metric_pmu(table, table_pmu, metric, fn, data);
+                if (ret != PMU_METRICS__NOT_FOUND)
+                        return ret;
+        }
+        return PMU_METRICS__NOT_FOUND;
+}
+
 static const struct pmu_events_map *map_for_cpu(struct perf_cpu cpu)
 {
         static struct {
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 675562e6f770..a523936846e0 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -47,6 +47,9 @@ struct pmu_event {
 	const char *long_desc;
 	const char *pmu;
 	const char *unit;
+	const char *retirement_latency_mean;
+	const char *retirement_latency_min;
+	const char *retirement_latency_max;
 	bool perpkg;
 	bool deprecated;
 };
@@ -71,6 +74,7 @@ struct pmu_events_table;
 struct pmu_metrics_table;
 
 #define PMU_EVENTS__NOT_FOUND -1000
+#define PMU_METRICS__NOT_FOUND -1000
 
 typedef int (*pmu_event_iter_fn)(const struct pmu_event *pe,
 				 const struct pmu_events_table *table,
@@ -85,11 +89,11 @@ int pmu_events_table__for_each_event(const struct pmu_events_table *table,
 				    pmu_event_iter_fn fn,
 				    void *data);
 /*
- * Search for table and entry matching with pmu__name_match. Each matching event
- * has fn called on it. 0 implies to success/continue the search while non-zero
- * means to terminate. The special value PMU_EVENTS__NOT_FOUND is used to
- * indicate no event was found in one of the tables which doesn't terminate the
- * search of all tables.
+ * Search for a table and entry matching with pmu__name_wildcard_match or any
+ * tables if pmu is NULL. Each matching event has fn called on it. 0 implies to
+ * success/continue the search while non-zero means to terminate. The special
+ * value PMU_EVENTS__NOT_FOUND is used to indicate no event was found in one of
+ * the tables which doesn't terminate the search of all tables.
  */
 int pmu_events_table__find_event(const struct pmu_events_table *table,
                                  struct perf_pmu *pmu,
@@ -101,6 +105,18 @@ size_t pmu_events_table__num_events(const struct pmu_events_table *table,
 
 int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
 				     void *data);
+/*
+ * Search for a table and entry matching with pmu__name_wildcard_match or any
+ * tables if pmu is NULL. Each matching metric has fn called on it. 0 implies to
+ * success/continue the search while non-zero means to terminate. The special
+ * value PMU_METRICS__NOT_FOUND is used to indicate no metric was found in one
+ * of the tables which doesn't terminate the search of all tables.
+ */
+int pmu_metrics_table__find_metric(const struct pmu_metrics_table *table,
+				   struct perf_pmu *pmu,
+				   const char *metric,
+				   pmu_metric_iter_fn fn,
+				   void *data);
 
 const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu);
 const struct pmu_metrics_table *pmu_metrics_table__find(void);
diff --git a/tools/perf/python/counting.py b/tools/perf/python/counting.py
new file mode 100755
index 000000000000..02121d2bb11d
--- /dev/null
+++ b/tools/perf/python/counting.py
@@ -0,0 +1,36 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+# -*- python -*-
+# -*- coding: utf-8 -*-
+
+import argparse
+import perf
+
+def main(event: str):
+    evlist = perf.parse_events(event)
+
+    for evsel in evlist:
+        evsel.read_format = perf.FORMAT_TOTAL_TIME_ENABLED | perf.FORMAT_TOTAL_TIME_RUNNING
+
+    evlist.open()
+    evlist.enable()
+
+    count = 100000
+    while count > 0:
+        count -= 1
+
+    evlist.disable()
+
+    for evsel in evlist:
+        for cpu in evsel.cpus():
+            for thread in evsel.threads():
+                counts = evsel.read(cpu, thread)
+                print(f"For {evsel} val: {counts.val} enable: {counts.ena} run: {counts.run}")
+
+    evlist.close()
+
+if __name__ == '__main__':
+    ap = argparse.ArgumentParser()
+    ap.add_argument('-e', '--event', help="Events to open", default="cpu-clock,task-clock")
+    args = ap.parse_args()
+    main(args.event)
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 121cf61ba1b3..e0b2e7268ef6 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -680,7 +680,10 @@ class CallGraphModelBase(TreeModel):
 				s = value.replace("%", "\\%")
 				s = s.replace("_", "\\_")
 				# Translate * and ? into SQL LIKE pattern characters % and _
-				trans = string.maketrans("*?", "%_")
+				if sys.version_info[0] == 3:
+					trans = str.maketrans("*?", "%_")
+				else:
+					trans = string.maketrans("*?", "%_")
 				match = " LIKE '" + str(s).translate(trans) + "'"
 			else:
 				match = " GLOB '" + str(value) + "'"
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 934f32090553..2181f5a92148 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -56,6 +56,7 @@ perf-test-y += genelf.o
 perf-test-y += api-io.o
 perf-test-y += demangle-java-test.o
 perf-test-y += demangle-ocaml-test.o
+perf-test-y += demangle-rust-v0-test.o
 perf-test-y += pfm.o
 perf-test-y += parse-metric.o
 perf-test-y += pe-file-parsing.o
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 14d30a5053be..45d3d8b3317a 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -126,6 +126,7 @@ static struct test_suite *generic_tests[] = {
 	&suite__maps__merge_in,
 	&suite__demangle_java,
 	&suite__demangle_ocaml,
+	&suite__demangle_rust,
 	&suite__parse_metric,
 	&suite__pe_file_parsing,
 	&suite__expand_cgroup_events,
diff --git a/tools/perf/tests/demangle-java-test.c b/tools/perf/tests/demangle-java-test.c
index 93c94408bdc8..0fb3e5a4a0ed 100644
--- a/tools/perf/tests/demangle-java-test.c
+++ b/tools/perf/tests/demangle-java-test.c
@@ -3,10 +3,9 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <linux/kernel.h>
-#include "tests.h"
-#include "session.h"
 #include "debug.h"
-#include "demangle-java.h"
+#include "symbol.h"
+#include "tests.h"
 
 static int test__demangle_java(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
@@ -18,19 +17,24 @@ static int test__demangle_java(struct test_suite *test __maybe_unused, int subte
 		const char *mangled, *demangled;
 	} test_cases[] = {
 		{ "Ljava/lang/StringLatin1;equals([B[B)Z",
-		  "boolean java.lang.StringLatin1.equals(byte[], byte[])" },
+		  "java.lang.StringLatin1.equals(byte[], byte[])" },
 		{ "Ljava/util/zip/ZipUtils;CENSIZ([BI)J",
-		  "long java.util.zip.ZipUtils.CENSIZ(byte[], int)" },
+		  "java.util.zip.ZipUtils.CENSIZ(byte[], int)" },
 		{ "Ljava/util/regex/Pattern$BmpCharProperty;match(Ljava/util/regex/Matcher;ILjava/lang/CharSequence;)Z",
-		  "boolean java.util.regex.Pattern$BmpCharProperty.match(java.util.regex.Matcher, int, java.lang.CharSequence)" },
+		  "java.util.regex.Pattern$BmpCharProperty.match(java.util.regex.Matcher, int, java.lang.CharSequence)" },
 		{ "Ljava/lang/AbstractStringBuilder;appendChars(Ljava/lang/String;II)V",
-		  "void java.lang.AbstractStringBuilder.appendChars(java.lang.String, int, int)" },
+		  "java.lang.AbstractStringBuilder.appendChars(java.lang.String, int, int)" },
 		{ "Ljava/lang/Object;<init>()V",
-		  "void java.lang.Object<init>()" },
+		  "java.lang.Object<init>()" },
 	};
 
 	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
-		buf = java_demangle_sym(test_cases[i].mangled, 0);
+		buf = dso__demangle_sym(/*dso=*/NULL, /*kmodule=*/0, test_cases[i].mangled);
+		if (!buf) {
+			pr_debug("FAILED to demangle: \"%s\"\n \"%s\"\n", test_cases[i].mangled,
+				 test_cases[i].demangled);
+			continue;
+		}
 		if (strcmp(buf, test_cases[i].demangled)) {
 			pr_debug("FAILED: %s: %s != %s\n", test_cases[i].mangled,
 				 buf, test_cases[i].demangled);
diff --git a/tools/perf/tests/demangle-ocaml-test.c b/tools/perf/tests/demangle-ocaml-test.c
index 90a4285e2ad5..612c788b7e0d 100644
--- a/tools/perf/tests/demangle-ocaml-test.c
+++ b/tools/perf/tests/demangle-ocaml-test.c
@@ -2,10 +2,9 @@
 #include <string.h>
 #include <stdlib.h>
 #include <stdio.h>
-#include "tests.h"
-#include "session.h"
 #include "debug.h"
-#include "demangle-ocaml.h"
+#include "symbol.h"
+#include "tests.h"
 
 static int test__demangle_ocaml(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
@@ -27,7 +26,7 @@ static int test__demangle_ocaml(struct test_suite *test __maybe_unused, int subt
 	};
 
 	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
-		buf = ocaml_demangle_sym(test_cases[i].mangled);
+		buf = dso__demangle_sym(/*dso=*/NULL, /*kmodule=*/0, test_cases[i].mangled);
 		if ((buf == NULL && test_cases[i].demangled != NULL)
 				|| (buf != NULL && test_cases[i].demangled == NULL)
 				|| (buf != NULL && strcmp(buf, test_cases[i].demangled))) {
diff --git a/tools/perf/tests/demangle-rust-v0-test.c b/tools/perf/tests/demangle-rust-v0-test.c
new file mode 100644
index 000000000000..904f966c65d7
--- /dev/null
+++ b/tools/perf/tests/demangle-rust-v0-test.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+#include "tests.h"
+#include "debug.h"
+#include "symbol.h"
+#include <linux/kernel.h>
+#include <stdlib.h>
+#include <string.h>
+
+static int test__demangle_rust(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+	int ret = TEST_OK;
+	char *buf = NULL;
+	size_t i;
+
+	struct {
+		const char *mangled, *demangled;
+	} test_cases[] = {
+		{ "_RNvMsr_NtCs3ssYzQotkvD_3std4pathNtB5_7PathBuf3newCs15kBYyAo9fc_7mycrate",
+		  "<std::path::PathBuf>::new" },
+		{ "_RNvCs15kBYyAo9fc_7mycrate7example",
+		  "mycrate::example" },
+		{ "_RNvMs_Cs4Cv8Wi1oAIB_7mycrateNtB4_7Example3foo",
+		  "<mycrate::Example>::foo" },
+		{ "_RNvXCs15kBYyAo9fc_7mycrateNtB2_7ExampleNtB2_5Trait3foo",
+		  "<mycrate::Example as mycrate::Trait>::foo" },
+		{ "_RNvMCs7qp2U7fqm6G_7mycrateNtB2_7Example3foo",
+		  "<mycrate::Example>::foo" },
+		{ "_RNvMs_Cs7qp2U7fqm6G_7mycrateNtB4_7Example3bar",
+		  "<mycrate::Example>::bar" },
+		{ "_RNvYNtCs15kBYyAo9fc_7mycrate7ExampleNtB4_5Trait7exampleB4_",
+		  "<mycrate::Example as mycrate::Trait>::example" },
+		{ "_RNCNvCsgStHSCytQ6I_7mycrate4main0B3_",
+		  "mycrate::main::{closure#0}" },
+		{ "_RNCNvCsgStHSCytQ6I_7mycrate4mains_0B3_",
+		  "mycrate::main::{closure#1}" },
+		{ "_RINvCsgStHSCytQ6I_7mycrate7examplelKj1_EB2_",
+		  "mycrate::example::<i32, 1>" },
+		{ "_RINvCs7qp2U7fqm6G_7mycrate7exampleFG0_RL1_hRL0_tEuEB2_",
+		  "mycrate::example::<for<'a, 'b> fn(&'a u8, &'b u16)>",
+		},
+		{ "_RINvCs7qp2U7fqm6G_7mycrate7exampleKy12345678_EB2_",
+		  "mycrate::example::<305419896>" },
+		{ "_RNvNvMCsd9PVOYlP1UU_7mycrateINtB4_7ExamplepKpE3foo14EXAMPLE_STATIC",
+		  "<mycrate::Example<_, _>>::foo::EXAMPLE_STATIC",
+		},
+		{ "_RINvCs7qp2U7fqm6G_7mycrate7exampleAtj8_EB2_",
+		  "mycrate::example::<[u16; 8]>" },
+		{ "_RINvCs7qp2U7fqm6G_7mycrate7exampleNtB2_7ExampleBw_EB2_",
+		  "mycrate::example::<mycrate::Example, mycrate::Example>" },
+		{ "_RINvMsY_NtCseXNvpPnDBDp_3std4pathNtB6_4Path3neweECs7qp2U7fqm6G_7mycrate",
+		  "<std::path::Path>::new::<str>" },
+		{ "_RNvNvNvCs7qp2U7fqm6G_7mycrate7EXAMPLE7___getit5___KEY",
+		  "mycrate::EXAMPLE::__getit::__KEY" },
+	};
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		buf = dso__demangle_sym(/*dso=*/NULL, /*kmodule=*/0, test_cases[i].mangled);
+		if (!buf) {
+			pr_debug("FAILED to demangle: \"%s\"\n \"%s\"\n", test_cases[i].mangled,
+				 test_cases[i].demangled);
+			continue;
+		}
+		if (strcmp(buf, test_cases[i].demangled)) {
+			pr_debug("FAILED: %s: %s != %s\n", test_cases[i].mangled,
+				 buf, test_cases[i].demangled);
+			ret = TEST_FAIL;
+		}
+		free(buf);
+	}
+
+	return ret;
+}
+
+DEFINE_SUITE("Demangle Rust", demangle_rust);
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 4803ab2d97ba..525c46b7971a 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -15,7 +15,6 @@
 #include "symbol.h"
 #include "thread.h"
 #include "callchain.h"
-#include "util/synthetic-events.h"
 
 /* For bsearch. We try to unwind functions in shared object. */
 #include <stdlib.h>
@@ -37,24 +36,6 @@
 #define NO_TAIL_CALL_BARRIER __asm__ __volatile__("" : : : "memory");
 #endif
 
-static int mmap_handler(const struct perf_tool *tool __maybe_unused,
-			union perf_event *event,
-			struct perf_sample *sample,
-			struct machine *machine)
-{
-	return machine__process_mmap2_event(machine, event, sample);
-}
-
-static int init_live_machine(struct machine *machine)
-{
-	union perf_event event;
-	pid_t pid = getpid();
-
-	memset(&event, 0, sizeof(event));
-	return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
-						  mmap_handler, machine, true);
-}
-
 /*
  * We need to keep these functions global, despite the
  * fact that they are used only locally in this object,
@@ -202,8 +183,12 @@ noinline int test__dwarf_unwind(struct test_suite *test __maybe_unused,
 	struct machine *machine;
 	struct thread *thread;
 	int err = -1;
+	pid_t pid = getpid();
 
-	machine = machine__new_host();
+	callchain_param.record_mode = CALLCHAIN_DWARF;
+	dwarf_callchain_users = true;
+
+	machine = machine__new_live(/*kernel_maps=*/true, pid);
 	if (!machine) {
 		pr_err("Could not get machine\n");
 		return -1;
@@ -214,18 +199,10 @@ noinline int test__dwarf_unwind(struct test_suite *test __maybe_unused,
 		return -1;
 	}
 
-	callchain_param.record_mode = CALLCHAIN_DWARF;
-	dwarf_callchain_users = true;
-
-	if (init_live_machine(machine)) {
-		pr_err("Could not init machine\n");
-		goto out;
-	}
-
 	if (verbose > 1)
 		machine__fprintf(machine, stderr);
 
-	thread = machine__find_thread(machine, getpid(), getpid());
+	thread = machine__find_thread(machine, pid, pid);
 	if (!thread) {
 		pr_err("Could not get thread\n");
 		goto out;
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index db004d26fcb0..815b40097428 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -38,7 +38,9 @@ struct perf_pmu_test_event {
 };
 
 struct perf_pmu_test_pmu {
-	struct perf_pmu pmu;
+	const char *pmu_name;
+	bool pmu_is_uncore;
+	const char *pmu_id;
 	struct perf_pmu_test_event const *aliases[10];
 };
 
@@ -553,11 +555,10 @@ static int __test_core_pmu_event_aliases(const char *pmu_name, int *count)
 	if (!pmu)
 		return -1;
 
-	INIT_LIST_HEAD(&pmu->format);
-	INIT_LIST_HEAD(&pmu->aliases);
-	INIT_LIST_HEAD(&pmu->caps);
-	INIT_LIST_HEAD(&pmu->list);
-	pmu->name = strdup(pmu_name);
+	if (perf_pmu__init(pmu, PERF_PMU_TYPE_FAKE, pmu_name) != 0) {
+		perf_pmu__delete(pmu);
+		return -1;
+	}
 	pmu->is_core = true;
 
 	pmu->events_table = table;
@@ -594,14 +595,30 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 {
 	int alias_count = 0, to_match_count = 0, matched_count = 0;
 	struct perf_pmu_test_event const **table;
-	struct perf_pmu *pmu = &test_pmu->pmu;
-	const char *pmu_name = pmu->name;
+	struct perf_pmu *pmu;
 	const struct pmu_events_table *events_table;
 	int res = 0;
 
 	events_table = find_core_events_table("testarch", "testcpu");
 	if (!events_table)
 		return -1;
+
+	pmu = zalloc(sizeof(*pmu));
+	if (!pmu)
+		return -1;
+
+	if (perf_pmu__init(pmu, PERF_PMU_TYPE_FAKE, test_pmu->pmu_name) != 0) {
+		perf_pmu__delete(pmu);
+		return -1;
+	}
+	pmu->is_uncore = test_pmu->pmu_is_uncore;
+	if (test_pmu->pmu_id) {
+		pmu->id = strdup(test_pmu->pmu_id);
+		if (!pmu->id) {
+			perf_pmu__delete(pmu);
+			return -1;
+		}
+	}
 	pmu->events_table = events_table;
 	pmu_add_cpu_aliases_table(pmu, events_table);
 	pmu->cpu_aliases_added = true;
@@ -617,7 +634,8 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 
 	if (alias_count != to_match_count) {
 		pr_debug("testing aliases uncore PMU %s: mismatch expected aliases (%d) vs found (%d)\n",
-			 pmu_name, to_match_count, alias_count);
+			 pmu->name, to_match_count, alias_count);
+		perf_pmu__delete(pmu);
 		return -1;
 	}
 
@@ -630,9 +648,10 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 			.count = &matched_count,
 		};
 
-		if (strcmp(pmu_name, test_event.matching_pmu)) {
+		if (strcmp(pmu->name, test_event.matching_pmu)) {
 			pr_debug("testing aliases uncore PMU %s: mismatched matching_pmu, %s vs %s\n",
-					pmu_name, test_event.matching_pmu, pmu_name);
+					pmu->name, test_event.matching_pmu, pmu->name);
+			perf_pmu__delete(pmu);
 			return -1;
 		}
 
@@ -641,34 +660,32 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
 		if (err) {
 			res = err;
 			pr_debug("testing aliases uncore PMU %s: could not match alias %s\n",
-				 pmu_name, event->name);
+				 pmu->name, event->name);
+			perf_pmu__delete(pmu);
 			return -1;
 		}
 	}
 
 	if (alias_count != matched_count) {
 		pr_debug("testing aliases uncore PMU %s: mismatch found aliases (%d) vs matched (%d)\n",
-			 pmu_name, matched_count, alias_count);
+			 pmu->name, matched_count, alias_count);
 		res = -1;
 	}
+	perf_pmu__delete(pmu);
 	return res;
 }
 
 static struct perf_pmu_test_pmu test_pmus[] = {
 	{
-		.pmu = {
-			.name = "hisi_sccl1_ddrc2",
-			.is_uncore = 1,
-		},
+		.pmu_name = "hisi_sccl1_ddrc2",
+		.pmu_is_uncore = 1,
 		.aliases = {
 			&uncore_hisi_ddrc_flux_wcmd,
 		},
 	},
 	{
-		.pmu = {
-			.name = "uncore_cbox_0",
-			.is_uncore = 1,
-		},
+		.pmu_name = "uncore_cbox_0",
+		.pmu_is_uncore = 1,
 		.aliases = {
 			&unc_cbo_xsnp_response_miss_eviction,
 			&uncore_hyphen,
@@ -676,88 +693,70 @@ static struct perf_pmu_test_pmu test_pmus[] = {
 		},
 	},
 	{
-		.pmu = {
-			.name = "hisi_sccl3_l3c7",
-			.is_uncore = 1,
-		},
+		.pmu_name = "hisi_sccl3_l3c7",
+		.pmu_is_uncore = 1,
 		.aliases = {
 			&uncore_hisi_l3c_rd_hit_cpipe,
 		},
 	},
 	{
-		.pmu = {
-			.name = "uncore_imc_free_running_0",
-			.is_uncore = 1,
-		},
+		.pmu_name = "uncore_imc_free_running_0",
+		.pmu_is_uncore = 1,
 		.aliases = {
 			&uncore_imc_free_running_cache_miss,
 		},
 	},
 	{
-		.pmu = {
-			.name = "uncore_imc_0",
-			.is_uncore = 1,
-		},
+		.pmu_name = "uncore_imc_0",
+		.pmu_is_uncore = 1,
 		.aliases = {
 			&uncore_imc_cache_hits,
 		},
 	},
 	{
-		.pmu = {
-			.name = "uncore_sys_ddr_pmu0",
-			.is_uncore = 1,
-			.id = "v8",
-		},
+		.pmu_name = "uncore_sys_ddr_pmu0",
+		.pmu_is_uncore = 1,
+		.pmu_id = "v8",
 		.aliases = {
 			&sys_ddr_pmu_write_cycles,
 		},
 	},
 	{
-		.pmu = {
-			.name = "uncore_sys_ccn_pmu4",
-			.is_uncore = 1,
-			.id = "0x01",
-		},
+		.pmu_name = "uncore_sys_ccn_pmu4",
+		.pmu_is_uncore = 1,
+		.pmu_id = "0x01",
 		.aliases = {
 			&sys_ccn_pmu_read_cycles,
 		},
 	},
 	{
-		.pmu = {
-			.name = (char *)"uncore_sys_cmn_pmu0",
-			.is_uncore = 1,
-			.id = (char *)"43401",
-		},
+		.pmu_name = "uncore_sys_cmn_pmu0",
+		.pmu_is_uncore = 1,
+		.pmu_id = "43401",
 		.aliases = {
 			&sys_cmn_pmu_hnf_cache_miss,
 		},
 	},
 	{
-		.pmu = {
-			.name = (char *)"uncore_sys_cmn_pmu0",
-			.is_uncore = 1,
-			.id = (char *)"43602",
-		},
+		.pmu_name = "uncore_sys_cmn_pmu0",
+		.pmu_is_uncore = 1,
+		.pmu_id = "43602",
 		.aliases = {
 			&sys_cmn_pmu_hnf_cache_miss,
 		},
 	},
 	{
-		.pmu = {
-			.name = (char *)"uncore_sys_cmn_pmu0",
-			.is_uncore = 1,
-			.id = (char *)"43c03",
-		},
+		.pmu_name = "uncore_sys_cmn_pmu0",
+		.pmu_is_uncore = 1,
+		.pmu_id = "43c03",
 		.aliases = {
 			&sys_cmn_pmu_hnf_cache_miss,
 		},
 	},
 	{
-		.pmu = {
-			.name = (char *)"uncore_sys_cmn_pmu0",
-			.is_uncore = 1,
-			.id = (char *)"43a01",
-		},
+		.pmu_name = "uncore_sys_cmn_pmu0",
+		.pmu_is_uncore = 1,
+		.pmu_id = "43a01",
 		.aliases = {
 			&sys_cmn_pmu_hnf_cache_miss,
 		},
@@ -796,10 +795,6 @@ static int test__aliases(struct test_suite *test __maybe_unused,
 	for (i = 0; i < ARRAY_SIZE(test_pmus); i++) {
 		int res;
 
-		INIT_LIST_HEAD(&test_pmus[i].pmu.format);
-		INIT_LIST_HEAD(&test_pmus[i].pmu.aliases);
-		INIT_LIST_HEAD(&test_pmus[i].pmu.caps);
-
 		res = __test_uncore_pmu_event_aliases(&test_pmus[i]);
 		if (res)
 			return res;
diff --git a/tools/perf/tests/shell/amd-ibs-swfilt.sh b/tools/perf/tests/shell/amd-ibs-swfilt.sh
new file mode 100755
index 000000000000..83937aa687cc
--- /dev/null
+++ b/tools/perf/tests/shell/amd-ibs-swfilt.sh
@@ -0,0 +1,67 @@
+#!/bin/sh
+# AMD IBS software filtering
+
+echo "check availability of IBS swfilt"
+
+# check if IBS PMU is available
+if [ ! -d /sys/bus/event_source/devices/ibs_op ]; then
+    echo "[SKIP] IBS PMU does not exist"
+    exit 2
+fi
+
+# check if IBS PMU has swfilt format
+if [ ! -f /sys/bus/event_source/devices/ibs_op/format/swfilt ]; then
+    echo "[SKIP] IBS PMU does not have swfilt"
+    exit 2
+fi
+
+echo "run perf record with modifier and swfilt"
+
+# setting any modifiers should fail
+perf record -B -e ibs_op//u -o /dev/null true 2> /dev/null
+if [ $? -eq 0 ]; then
+    echo "[FAIL] IBS PMU should not accept exclude_kernel"
+    exit 1
+fi
+
+# setting it with swfilt should be fine
+perf record -B -e ibs_op/swfilt/u -o /dev/null true
+if [ $? -ne 0 ]; then
+    echo "[FAIL] IBS op PMU cannot handle swfilt for exclude_kernel"
+    exit 1
+fi
+
+# setting it with swfilt=1 should be fine
+perf record -B -e ibs_op/swfilt=1/k -o /dev/null true
+if [ $? -ne 0 ]; then
+    echo "[FAIL] IBS op PMU cannot handle swfilt for exclude_user"
+    exit 1
+fi
+
+# check ibs_fetch PMU as well
+perf record -B -e ibs_fetch/swfilt/u -o /dev/null true
+if [ $? -ne 0 ]; then
+    echo "[FAIL] IBS fetch PMU cannot handle swfilt for exclude_kernel"
+    exit 1
+fi
+
+# check system wide recording
+perf record -aB --synth=no -e ibs_op/swfilt/k -o /dev/null true
+if [ $? -ne 0 ]; then
+    echo "[FAIL] IBS op PMU cannot handle swfilt in system-wide mode"
+    exit 1
+fi
+
+echo "check number of samples with swfilt"
+
+kernel_sample=$(perf record -e ibs_op/swfilt/u -o- true | perf script -i- -F misc | grep -c ^K)
+if [ ${kernel_sample} -ne 0 ]; then
+    echo "[FAIL] unexpected kernel samples: " ${kernel_sample}
+    exit 1
+fi
+
+user_sample=$(perf record -e ibs_fetch/swfilt/k -o- true | perf script -i- -F misc | grep -c ^U)
+if [ ${user_sample} -ne 0 ]; then
+    echo "[FAIL] unexpected user samples: " ${user_sample}
+    exit 1
+fi
diff --git a/tools/perf/tests/shell/lib/perf_metric_validation.py b/tools/perf/tests/shell/lib/perf_metric_validation.py
index 0b94216c9c46..dea8ef1977bf 100644
--- a/tools/perf/tests/shell/lib/perf_metric_validation.py
+++ b/tools/perf/tests/shell/lib/perf_metric_validation.py
@@ -35,7 +35,8 @@ class TestError:
 
 
 class Validator:
-    def __init__(self, rulefname, reportfname='', t=5, debug=False, datafname='', fullrulefname='', workload='true', metrics=''):
+    def __init__(self, rulefname, reportfname='', t=5, debug=False, datafname='', fullrulefname='',
+                 workload='true', metrics='', cputype='cpu'):
         self.rulefname = rulefname
         self.reportfname = reportfname
         self.rules = None
@@ -43,6 +44,7 @@ class Validator:
         self.metrics = self.__set_metrics(metrics)
         self.skiplist = set()
         self.tolerance = t
+        self.cputype = cputype
 
         self.workloads = [x for x in workload.split(",") if x]
         self.wlidx = 0  # idx of current workloads
@@ -377,7 +379,7 @@ class Validator:
 
     def _run_perf(self, metric, workload: str):
         tool = 'perf'
-        command = [tool, 'stat', '-j', '-M', f"{metric}", "-a"]
+        command = [tool, 'stat', '--cputype', self.cputype, '-j', '-M', f"{metric}", "-a"]
         wl = workload.split()
         command.extend(wl)
         print(" ".join(command))
@@ -443,6 +445,8 @@ class Validator:
                 if 'MetricName' not in m:
                     print("Warning: no metric name")
                     continue
+                if 'Unit' in m and m['Unit'] != self.cputype:
+                    continue
                 name = m['MetricName'].lower()
                 self.metrics.add(name)
                 if 'ScaleUnit' in m and (m['ScaleUnit'] == '1%' or m['ScaleUnit'] == '100%'):
@@ -578,6 +582,8 @@ def main() -> None:
     parser.add_argument(
         "-wl", help="Workload to run while data collection", default="true")
     parser.add_argument("-m", help="Metric list to validate", default="")
+    parser.add_argument("-cputype", help="Only test metrics for the given CPU/PMU type",
+                        default="cpu")
     args = parser.parse_args()
     outpath = Path(args.output_dir)
     reportf = Path.joinpath(outpath, 'perf_report.json')
@@ -586,7 +592,7 @@ def main() -> None:
 
     validator = Validator(args.rule, reportf, debug=args.debug,
                           datafname=datafile, fullrulefname=fullrule, workload=args.wl,
-                          metrics=args.m)
+                          metrics=args.m, cputype=args.cputype)
     ret = validator.test()
 
     return ret
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
index 5c33ec7a5a63..58debce9ab42 100644
--- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -13,14 +13,28 @@ cleanup_probe_vfs_getname() {
 add_probe_vfs_getname() {
 	add_probe_verbose=$1
 	if [ $had_vfs_getname -eq 1 ] ; then
-		result_filename_re="[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*"
-		line=$(perf probe -L getname_flags 2>&1 | grep -E "$result_filename_re" | sed -r "s/$result_filename_re/\1/")
+		result_initname_re="[[:space:]]+([[:digit:]]+)[[:space:]]+initname.*"
+		line=$(perf probe -L getname_flags 2>&1 | grep -E "$result_initname_re" | sed -r "s/$result_initname_re/\1/")
+
+		# Search the old regular expressions so that this will
+		# pass on older kernels as well.
+		if [ -z "$line" ] ; then
+			result_filename_re="[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*"
+			line=$(perf probe -L getname_flags 2>&1 | grep -E "$result_filename_re" | sed -r "s/$result_filename_re/\1/")
+		fi
+
 		if [ -z "$line" ] ; then
 			result_aname_re="[[:space:]]+([[:digit:]]+)[[:space:]]+result->aname = NULL;"
 			line=$(perf probe -L getname_flags 2>&1 | grep -E "$result_aname_re" | sed -r "s/$result_aname_re/\1/")
 		fi
+
+		if [ -z "$line" ] ; then
+			echo "Could not find probeable line"
+			return 2
+		fi
+
 		perf probe -q       "vfs_getname=getname_flags:${line} pathname=result->name:string" || \
-		perf probe $add_probe_verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring"
+		perf probe $add_probe_verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring" || return 1
 	fi
 }
 
diff --git a/tools/perf/tests/shell/lib/stat_output.sh b/tools/perf/tests/shell/lib/stat_output.sh
index 4d4aac547f01..c2ec7881ec1d 100644
--- a/tools/perf/tests/shell/lib/stat_output.sh
+++ b/tools/perf/tests/shell/lib/stat_output.sh
@@ -151,6 +151,11 @@ check_per_socket()
 check_metric_only()
 {
 	echo -n "Checking $1 output: metric only "
+	if [ "$(uname -m)" = "s390x" ] && ! grep '^facilities' /proc/cpuinfo  | grep -qw 67
+	then
+		echo "[Skip] CPU-measurement counter facility not installed"
+		return
+	fi
 	perf stat --metric-only $2 -e instructions,cycles true
 	commachecker --metric-only
 	echo "[Success]"
diff --git a/tools/perf/tests/shell/perf-report-hierarchy.sh b/tools/perf/tests/shell/perf-report-hierarchy.sh
new file mode 100755
index 000000000000..02e3b6aee4ed
--- /dev/null
+++ b/tools/perf/tests/shell/perf-report-hierarchy.sh
@@ -0,0 +1,43 @@
+#!/bin/sh
+# perf report --hierarchy
+# SPDX-License-Identifier: GPL-2.0
+# Arnaldo Carvalho de Melo <acme@redhat.com> 
+
+set -e
+
+temp_dir=$(mktemp -d /tmp/perf-test-report.XXXXXXXXXX)
+
+cleanup()
+{
+	trap - EXIT TERM INT
+	sane=$(echo "${temp_dir}" | cut -b 1-21)
+	if [ "${sane}" = "/tmp/perf-test-report" ] ; then
+		echo "--- Cleaning up ---"
+		rm -rf "${temp_dir:?}/"*
+		rmdir "${temp_dir}"
+	fi
+}
+
+trap_cleanup()
+{
+	cleanup
+	exit 1
+}
+
+trap trap_cleanup EXIT TERM INT
+
+test_report_hierarchy()
+{
+	echo "perf report --hierarchy"
+
+	perf_data="${temp_dir}/perf-report-hierarchy-perf.data"
+	perf record -o "${perf_data}" uname
+	perf report --hierarchy -i "${perf_data}" > /dev/null
+	echo "perf report --hierarchy test [Success]"
+}
+
+test_report_hierarchy
+
+cleanup
+
+exit 0
diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh
index c51a32931af6..0f52654c914a 100755
--- a/tools/perf/tests/shell/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/probe_vfs_getname.sh
@@ -13,7 +13,13 @@ skip_if_no_perf_probe || exit 2
 # shellcheck source=lib/probe_vfs_getname.sh
 . "$(dirname $0)"/lib/probe_vfs_getname.sh
 
-add_probe_vfs_getname || skip_if_no_debuginfo
+add_probe_vfs_getname
 err=$?
+
+if [ $err -eq 1 ] ; then
+	skip_if_no_debuginfo
+	err=$?
+fi
+
 cleanup_probe_vfs_getname
 exit $err
diff --git a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
index fd5b10d46915..1ad252f0d36e 100755
--- a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
@@ -35,8 +35,14 @@ perf_script_filenames() {
 	grep -E " +touch +[0-9]+ +\[[0-9]+\] +[0-9]+\.[0-9]+: +probe:vfs_getname[_0-9]*: +\([[:xdigit:]]+\) +pathname=\"${file}\""
 }
 
-add_probe_vfs_getname || skip_if_no_debuginfo
+add_probe_vfs_getname
 err=$?
+
+if [ $err -eq 1 ] ; then
+        skip_if_no_debuginfo
+        err=$?
+fi
+
 if [ $err -ne 0 ] ; then
 	exit $err
 fi
diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index ba8d873d3ca7..587f62e34414 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -34,13 +34,15 @@ default_fd_limit=$(ulimit -Sn)
 min_fd_limit=$(($(getconf _NPROCESSORS_ONLN) * 16))
 
 cleanup() {
-  rm -rf "${perfdata}"
-  rm -rf "${perfdata}".old
+  rm -f "${perfdata}"
+  rm -f "${perfdata}".old
+  rm -f "${script_output}"
 
   trap - EXIT TERM INT
 }
 
 trap_cleanup() {
+  echo "Unexpected signal in ${FUNCNAME[1]}"
   cleanup
   exit 1
 }
@@ -238,22 +240,43 @@ test_leader_sampling() {
     err=1
     return
   fi
+  perf script -i "${perfdata}" | grep brstack > $script_output
+  # Check if the two instruction counts are equal in each record.
+  # However, the throttling code doesn't consider event grouping. During throttling, only the
+  # leader is stopped, causing the slave's counts significantly higher. To temporarily solve this,
+  # let's set the tolerance rate to 80%.
+  # TODO: Revert the code for tolerance once the throttling mechanism is fixed.
   index=0
-  perf script -i "${perfdata}" > $script_output
+  valid_counts=0
+  invalid_counts=0
+  tolerance_rate=0.8
   while IFS= read -r line
   do
-    # Check if the two instruction counts are equal in each record
     cycles=$(echo $line | awk '{for(i=1;i<=NF;i++) if($i=="cycles:") print $(i-1)}')
     if [ $(($index%2)) -ne 0 ] && [ ${cycles}x != ${prev_cycles}x ]
     then
-      echo "Leader sampling [Failed inconsistent cycles count]"
-      err=1
-      return
+      invalid_counts=$(($invalid_counts+1))
+    else
+      valid_counts=$(($valid_counts+1))
     fi
     index=$(($index+1))
     prev_cycles=$cycles
-  done < $script_output
-  echo "Basic leader sampling test [Success]"
+  done < "${script_output}"
+  total_counts=$(bc <<< "$invalid_counts+$valid_counts")
+  if (( $(bc <<< "$total_counts <= 0") ))
+  then
+    echo "Leader sampling [No sample generated]"
+    err=1
+    return
+  fi
+  isok=$(bc <<< "scale=2; if (($invalid_counts/$total_counts) < (1-$tolerance_rate)) { 0 } else { 1 };")
+  if [ $isok -eq 1 ]
+  then
+     echo "Leader sampling [Failed inconsistent cycles count]"
+     err=1
+  else
+    echo "Basic leader sampling test [Success]"
+  fi
 }
 
 test_topdown_leader_sampling() {
diff --git a/tools/perf/tests/shell/record_lbr.sh b/tools/perf/tests/shell/record_lbr.sh
index 8d750ee631f8..6fcb5e52b9b4 100755
--- a/tools/perf/tests/shell/record_lbr.sh
+++ b/tools/perf/tests/shell/record_lbr.sh
@@ -4,7 +4,8 @@
 
 set -e
 
-if [ ! -f /sys/devices/cpu/caps/branches ] && [ ! -f /sys/devices/cpu_core/caps/branches ]
+if [ ! -f /sys/bus/event_source/devices/cpu/caps/branches ] &&
+   [ ! -f /sys/bus/event_source/devices/cpu_core/caps/branches ]
 then
   echo "Skip: only x86 CPUs support LBR"
   exit 2
@@ -93,7 +94,7 @@ lbr_test() {
     return
   fi
 
-  zero_nr=$(echo "$out" | grep -c 'branch stack: nr:0' || true)
+  zero_nr=$(echo "$out" | grep -A3 'branch stack: nr:0' | grep thread | grep -cv swapper || true)
   r=$(($zero_nr * 100 / $bs_nr))
   if [ $r -gt $threshold ]; then
     echo "$test [Failed empty br stack ratio exceed $threshold%: $r%]"
diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh
index 678947fe69ee..21a22efe08f5 100755
--- a/tools/perf/tests/shell/record_offcpu.sh
+++ b/tools/perf/tests/shell/record_offcpu.sh
@@ -7,6 +7,9 @@ set -e
 err=0
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 
+ts=$(printf "%u" $((~0 << 32))) # OFF_CPU_TIMESTAMP
+dummy_timestamp=${ts%???} # remove the last 3 digits to match perf script
+
 cleanup() {
   rm -f ${perfdata}
   rm -f ${perfdata}.old
@@ -19,6 +22,9 @@ trap_cleanup() {
 }
 trap trap_cleanup EXIT TERM INT
 
+test_above_thresh="Threshold test (above threshold)"
+test_below_thresh="Threshold test (below threshold)"
+
 test_offcpu_priv() {
   echo "Checking off-cpu privilege"
 
@@ -88,6 +94,63 @@ test_offcpu_child() {
   echo "Child task off-cpu test [Success]"
 }
 
+# task blocks longer than the --off-cpu-thresh, perf should collect a direct sample
+test_offcpu_above_thresh() {
+  echo "${test_above_thresh}"
+
+  # collect direct off-cpu samples for tasks blocked for more than 999ms
+  if ! perf record -e dummy --off-cpu --off-cpu-thresh 999 -o ${perfdata} -- sleep 1 2> /dev/null
+  then
+    echo "${test_above_thresh} [Failed record]"
+    err=1
+    return
+  fi
+  # direct sample's timestamp should be lower than the dummy_timestamp of the at-the-end sample
+  # check if a direct sample exists
+  if ! perf script --time "0, ${dummy_timestamp}" -i ${perfdata} -F event | grep -q "offcpu-time"
+  then
+    echo "${test_above_thresh} [Failed missing direct samples]"
+    err=1
+    return
+  fi
+  # there should only be one direct sample, and its period should be higher than off-cpu-thresh
+  if ! perf script --time "0, ${dummy_timestamp}" -i ${perfdata} -F period | \
+       awk '{ if (int($1) > 999000000) exit 0; else exit 1; }'
+  then
+    echo "${test_above_thresh} [Failed off-cpu time too short]"
+    err=1
+    return
+  fi
+  echo "${test_above_thresh} [Success]"
+}
+
+# task blocks shorter than the --off-cpu-thresh, perf should collect an at-the-end sample
+test_offcpu_below_thresh() {
+  echo "${test_below_thresh}"
+
+  # collect direct off-cpu samples for tasks blocked for more than 1.2s
+  if ! perf record -e dummy --off-cpu --off-cpu-thresh 1200 -o ${perfdata} -- sleep 1 2> /dev/null
+  then
+    echo "${test_below_thresh} [Failed record]"
+    err=1
+    return
+  fi
+  # see if there's an at-the-end sample
+  if ! perf script --time "${dummy_timestamp}," -i ${perfdata} -F event | grep -q 'offcpu-time'
+  then
+    echo "${test_below_thresh} [Failed at-the-end samples cannot be found]"
+    err=1
+    return
+  fi
+  # plus there shouldn't be any direct samples
+  if perf script --time "0, ${dummy_timestamp}" -i ${perfdata} -F event | grep -q 'offcpu-time'
+  then
+    echo "${test_below_thresh} [Failed direct samples are found when they shouldn't be]"
+    err=1
+    return
+  fi
+  echo "${test_below_thresh} [Success]"
+}
 
 test_offcpu_priv
 
@@ -99,5 +162,13 @@ if [ $err = 0 ]; then
   test_offcpu_child
 fi
 
+if [ $err = 0 ]; then
+  test_offcpu_above_thresh
+fi
+
+if [ $err = 0 ]; then
+  test_offcpu_below_thresh
+fi
+
 cleanup
 exit $err
diff --git a/tools/perf/tests/shell/stat+event_uniquifying.sh b/tools/perf/tests/shell/stat+event_uniquifying.sh
new file mode 100755
index 000000000000..5ec35c52b7d9
--- /dev/null
+++ b/tools/perf/tests/shell/stat+event_uniquifying.sh
@@ -0,0 +1,69 @@
+#!/bin/bash
+# perf stat events uniquifying
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+stat_output=$(mktemp /tmp/__perf_test.stat_output.XXXXX)
+perf_tool=perf
+err=0
+
+test_event_uniquifying() {
+  # We use `clockticks` to verify the uniquify behavior.
+  event="clockticks"
+
+  # If the `-A` option is added, the event should be uniquified.
+  #
+  # $perf list -v clockticks
+  #
+  # List of pre-defined events (to be used in -e or -M):
+  #
+  #   uncore_imc_0/clockticks/                           [Kernel PMU event]
+  #   uncore_imc_1/clockticks/                           [Kernel PMU event]
+  #   uncore_imc_2/clockticks/                           [Kernel PMU event]
+  #   uncore_imc_3/clockticks/                           [Kernel PMU event]
+  #   uncore_imc_4/clockticks/                           [Kernel PMU event]
+  #   uncore_imc_5/clockticks/                           [Kernel PMU event]
+  #
+  #   ...
+  #
+  # $perf stat -e clockticks -A -- true
+  #
+  #  Performance counter stats for 'system wide':
+  #
+  # CPU0            3,773,018      uncore_imc_0/clockticks/
+  # CPU0            3,609,025      uncore_imc_1/clockticks/
+  # CPU0                    0      uncore_imc_2/clockticks/
+  # CPU0            3,230,009      uncore_imc_3/clockticks/
+  # CPU0            3,049,897      uncore_imc_4/clockticks/
+  # CPU0                    0      uncore_imc_5/clockticks/
+  #
+  #        0.002029828 seconds time elapsed
+
+  echo "stat event uniquifying test"
+  uniquified_event_array=()
+
+  # Check how many uniquified events.
+  while IFS= read -r line; do
+    uniquified_event=$(echo "$line" | awk '{print $1}')
+    uniquified_event_array+=("${uniquified_event}")
+  done < <(${perf_tool} list -v ${event} | grep "\[Kernel PMU event\]")
+
+  perf_command="${perf_tool} stat -e $event -A -o ${stat_output} -- true"
+  $perf_command
+
+  # Check the output contains all uniquified events.
+  for uniquified_event in "${uniquified_event_array[@]}"; do
+    if ! cat "${stat_output}" | grep -q "${uniquified_event}"; then
+      echo "Event is not uniquified [Failed]"
+      echo "${perf_command}"
+      cat "${stat_output}"
+      err=1
+      break
+    fi
+  done
+}
+
+test_event_uniquifying
+rm -f "${stat_output}"
+exit $err
diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh
index a4f257ea839e..98fb65274ac4 100755
--- a/tools/perf/tests/shell/stat+json_output.sh
+++ b/tools/perf/tests/shell/stat+json_output.sh
@@ -176,6 +176,11 @@ check_per_socket()
 check_metric_only()
 {
 	echo -n "Checking json output: metric only "
+	if [ "$(uname -m)" = "s390x" ] && ! grep '^facilities' /proc/cpuinfo  | grep -qw 67
+	then
+		echo "[Skip] CPU-measurement counter facility not installed"
+		return
+	fi
 	perf stat -j --metric-only -e instructions,cycles -o "${stat_output}" true
 	$PYTHON $pythonchecker --metric-only --file "${stat_output}"
 	echo "[Success]"
diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh
index ee817c66da06..6fa585a1e34c 100755
--- a/tools/perf/tests/shell/stat_all_metrics.sh
+++ b/tools/perf/tests/shell/stat_all_metrics.sh
@@ -7,86 +7,96 @@ ParanoidAndNotRoot()
   [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ]
 }
 
+test_prog="sleep 0.01"
 system_wide_flag="-a"
 if ParanoidAndNotRoot 0
 then
   system_wide_flag=""
+  test_prog="perf test -w noploop"
 fi
 
 err=0
 for m in $(perf list --raw-dump metrics); do
   echo "Testing $m"
-  result=$(perf stat -M "$m" $system_wide_flag -- sleep 0.01 2>&1)
+  result=$(perf stat -M "$m" $system_wide_flag -- $test_prog 2>&1)
   result_err=$?
-  if [[ $result_err -gt 0 ]]
+  if [[ $result_err -eq 0 && "$result" =~ ${m:0:50} ]]
   then
-    if [[ "$result" =~ "Cannot resolve IDs for" ]]
-    then
-      echo "Metric contains missing events"
-      echo $result
-      err=1 # Fail
-      continue
-    elif [[ "$result" =~ \
-          "Access to performance monitoring and observability operations is limited" ]]
+    # No error result and metric shown.
+    continue
+  fi
+  if [[ "$result" =~ "Cannot resolve IDs for" ]]
+  then
+    echo "Metric contains missing events"
+    echo $result
+    err=1 # Fail
+    continue
+  elif [[ "$result" =~ \
+        "Access to performance monitoring and observability operations is limited" ]]
+  then
+    echo "Permission failure"
+    echo $result
+    if [[ $err -eq 0 ]]
     then
-      echo "Permission failure"
-      echo $result
-      if [[ $err -eq 0 ]]
-      then
-        err=2 # Skip
-      fi
-      continue
-    elif [[ "$result" =~ "in per-thread mode, enable system wide" ]]
+      err=2 # Skip
+    fi
+    continue
+  elif [[ "$result" =~ "in per-thread mode, enable system wide" ]]
+  then
+    echo "Permissions - need system wide mode"
+    echo $result
+    if [[ $err -eq 0 ]]
     then
-      echo "Permissions - need system wide mode"
-      echo $result
-      if [[ $err -eq 0 ]]
-      then
-        err=2 # Skip
-      fi
-      continue
-    elif [[ "$result" =~ "<not supported>" ]]
+      err=2 # Skip
+    fi
+    continue
+  elif [[ "$result" =~ "<not supported>" ]]
+  then
+    echo "Not supported events"
+    echo $result
+    if [[ $err -eq 0 ]]
     then
-      echo "Not supported events"
-      echo $result
-      if [[ $err -eq 0 ]]
-      then
-        err=2 # Skip
-      fi
-      continue
-    elif [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]]
+      err=2 # Skip
+    fi
+    continue
+  elif [[ "$result" =~ "<not counted>" ]]
+  then
+    echo "Not counted events"
+    echo $result
+    if [[ $err -eq 0 ]]
     then
-      echo "FP issues"
-      echo $result
-      if [[ $err -eq 0 ]]
-      then
-        err=2 # Skip
-      fi
-      continue
-    elif [[ "$result" =~ "PMM" ]]
+      err=2 # Skip
+    fi
+    continue
+  elif [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]]
+  then
+    echo "FP issues"
+    echo $result
+    if [[ $err -eq 0 ]]
     then
-      echo "Optane memory issues"
-      echo $result
-      if [[ $err -eq 0 ]]
-      then
-        err=2 # Skip
-      fi
-      continue
+      err=2 # Skip
     fi
-  fi
-
-  if [[ "$result" =~ ${m:0:50} ]]
+    continue
+  elif [[ "$result" =~ "PMM" ]]
   then
+    echo "Optane memory issues"
+    echo $result
+    if [[ $err -eq 0 ]]
+    then
+      err=2 # Skip
+    fi
     continue
   fi
 
   # Failed, possibly the workload was too small so retry with something longer.
   result=$(perf stat -M "$m" $system_wide_flag -- perf bench internals synthesize 2>&1)
-  if [[ "$result" =~ ${m:0:50} ]]
+  result_err=$?
+  if [[ $result_err -eq 0 && "$result" =~ ${m:0:50} ]]
   then
+    # No error result and metric shown.
     continue
   fi
-  echo "Metric '$m' not printed in:"
+  echo "Metric '$m' has non-zero error '$result_err' or not printed in:"
   echo "$result"
   err=1
 done
diff --git a/tools/perf/tests/shell/stat_metrics_values.sh b/tools/perf/tests/shell/stat_metrics_values.sh
index 279f19c5919a..30566f0b5427 100755
--- a/tools/perf/tests/shell/stat_metrics_values.sh
+++ b/tools/perf/tests/shell/stat_metrics_values.sh
@@ -16,11 +16,16 @@ workload="perf bench futex hash -r 2 -s"
 # Add -debug, save data file and full rule file
 echo "Launch python validation script $pythonvalidator"
 echo "Output will be stored in: $tmpdir"
-$PYTHON $pythonvalidator -rule $rulefile -output_dir $tmpdir -wl "${workload}"
-ret=$?
-rm -rf $tmpdir
-if [ $ret -ne 0 ]; then
-	echo "Metric validation return with erros. Please check metrics reported with errors."
-fi
+for cputype in /sys/bus/event_source/devices/cpu_*; do
+	cputype=$(basename "$cputype")
+	echo "Testing metrics for: $cputype"
+	$PYTHON $pythonvalidator -rule $rulefile -output_dir $tmpdir -wl "${workload}" \
+		-cputype "${cputype}"
+	ret=$?
+	rm -rf $tmpdir
+	if [ $ret -ne 0 ]; then
+		echo "Metric validation return with errors. Please check metrics reported with errors."
+	fi
+done
 exit $ret
 
diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
index e01df7581393..9138fa83bf36 100755
--- a/tools/perf/tests/shell/test_brstack.sh
+++ b/tools/perf/tests/shell/test_brstack.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # Check branch stack sampling
 
 # SPDX-License-Identifier: GPL-2.0
@@ -17,35 +17,50 @@ fi
 
 skip_test_missing_symbol brstack_bench
 
+err=0
 TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX)
 TESTPROG="perf test -w brstack"
 
 cleanup() {
 	rm -rf $TMPDIR
+	trap - EXIT TERM INT
 }
 
-trap cleanup EXIT TERM INT
+trap_cleanup() {
+	set +e
+	echo "Unexpected signal in ${FUNCNAME[1]}"
+	cleanup
+	exit 1
+}
+trap trap_cleanup EXIT TERM INT
 
 test_user_branches() {
 	echo "Testing user branch stack sampling"
 
-	perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- ${TESTPROG} > /dev/null 2>&1
-	perf script -i $TMPDIR/perf.data --fields brstacksym | tr -s ' ' '\n' > $TMPDIR/perf.script
+	perf record -o "$TMPDIR/perf.data" --branch-filter any,save_type,u -- ${TESTPROG} > "$TMPDIR/record.txt" 2>&1
+	perf script -i "$TMPDIR/perf.data" --fields brstacksym > "$TMPDIR/perf.script"
 
 	# example of branch entries:
 	# 	brstack_foo+0x14/brstack_bar+0x40/P/-/-/0/CALL
 
-	set -x
-	grep -E -m1 "^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/IND_CALL/.*$"	$TMPDIR/perf.script
-	grep -E -m1 "^brstack_foo\+[^ ]*/brstack_bar\+[^ ]*/CALL/.*$"	$TMPDIR/perf.script
-	grep -E -m1 "^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/CALL/.*$"	$TMPDIR/perf.script
-	grep -E -m1 "^brstack_bench\+[^ ]*/brstack_bar\+[^ ]*/CALL/.*$"	$TMPDIR/perf.script
-	grep -E -m1 "^brstack_bar\+[^ ]*/brstack_foo\+[^ ]*/RET/.*$"		$TMPDIR/perf.script
-	grep -E -m1 "^brstack_foo\+[^ ]*/brstack_bench\+[^ ]*/RET/.*$"	$TMPDIR/perf.script
-	grep -E -m1 "^brstack_bench\+[^ ]*/brstack_bench\+[^ ]*/COND/.*$"	$TMPDIR/perf.script
-	grep -E -m1 "^brstack\+[^ ]*/brstack\+[^ ]*/UNCOND/.*$"		$TMPDIR/perf.script
-	set +x
-
+	expected=(
+		"^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/IND_CALL/.*$"
+		"^brstack_foo\+[^ ]*/brstack_bar\+[^ ]*/CALL/.*$"
+		"^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/CALL/.*$"
+		"^brstack_bench\+[^ ]*/brstack_bar\+[^ ]*/CALL/.*$"
+		"^brstack_bar\+[^ ]*/brstack_foo\+[^ ]*/RET/.*$"
+		"^brstack_foo\+[^ ]*/brstack_bench\+[^ ]*/RET/.*$"
+		"^brstack_bench\+[^ ]*/brstack_bench\+[^ ]*/COND/.*$"
+		"^brstack\+[^ ]*/brstack\+[^ ]*/UNCOND/.*$"
+	)
+	for x in "${expected[@]}"
+	do
+		if ! tr -s ' ' '\n' < "$TMPDIR/perf.script" | grep -E -m1 -q "$x"
+		then
+			echo "Branches missing $x"
+			err=1
+		fi
+	done
 	# some branch types are still not being tested:
 	# IND COND_CALL COND_RET SYSCALL SYSRET IRQ SERROR NO_TX
 }
@@ -57,14 +72,28 @@ test_filter() {
 	test_filter_expect=$2
 
 	echo "Testing branch stack filtering permutation ($test_filter_filter,$test_filter_expect)"
-
-	perf record -o $TMPDIR/perf.data --branch-filter $test_filter_filter,save_type,u -- ${TESTPROG} > /dev/null 2>&1
-	perf script -i $TMPDIR/perf.data --fields brstack | tr -s ' ' '\n' | grep '.' > $TMPDIR/perf.script
+	perf record -o "$TMPDIR/perf.data" --branch-filter "$test_filter_filter,save_type,u" -- ${TESTPROG}  > "$TMPDIR/record.txt" 2>&1
+	perf script -i "$TMPDIR/perf.data" --fields brstack > "$TMPDIR/perf.script"
 
 	# fail if we find any branch type that doesn't match any of the expected ones
 	# also consider UNKNOWN branch types (-)
-	if grep -E -vm1 "^[^ ]*/($test_filter_expect|-|( *))/.*$" $TMPDIR/perf.script; then
-		return 1
+	if [ ! -s "$TMPDIR/perf.script" ]
+	then
+		echo "Empty script output"
+		err=1
+		return
+	fi
+	# Look for lines not matching test_filter_expect ignoring issues caused
+	# by empty output
+	tr -s ' ' '\n' < "$TMPDIR/perf.script" | grep '.' | \
+	  grep -E -vm1 "^[^ ]*/($test_filter_expect|-|( *))/.*$" \
+	  > "$TMPDIR/perf.script-filtered" || true
+	if [ -s "$TMPDIR/perf.script-filtered" ]
+	then
+		echo "Unexpected branch filter in script output"
+		cat "$TMPDIR/perf.script"
+		err=1
+		return
 	fi
 }
 
@@ -80,3 +109,6 @@ test_filter "any_ret"	"RET|COND_RET|SYSRET|ERET"
 test_filter "call,cond"		"CALL|SYSCALL|COND"
 test_filter "any_call,cond"		"CALL|IND_CALL|COND_CALL|IRQ|SYSCALL|COND"
 test_filter "cond,any_call,any_ret"	"COND|CALL|IND_CALL|COND_CALL|SYSCALL|IRQ|RET|COND_RET|SYSRET|ERET"
+
+cleanup
+exit $err
diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh
index bbe8277496ae..d61b5659a46d 100755
--- a/tools/perf/tests/shell/test_data_symbol.sh
+++ b/tools/perf/tests/shell/test_data_symbol.sh
@@ -54,11 +54,34 @@ trap cleanup_files exit term int
 
 echo "Recording workload..."
 
-# perf mem/c2c internally uses IBS PMU on AMD CPU which doesn't support
-# user/kernel filtering and per-process monitoring, spin program on
-# specific CPU and test in per-CPU mode.
 is_amd=$(grep -E -c 'vendor_id.*AuthenticAMD' /proc/cpuinfo)
 if (($is_amd >= 1)); then
+	mem_events="$(perf mem record -v -e list 2>&1)"
+	if ! [[ "$mem_events" =~ ^mem\-ldst.*ibs_op/(.*)/.*available ]]; then
+		echo "ERROR: mem-ldst event is not matching"
+		exit 1
+	fi
+
+	# --ldlat on AMD:
+	# o Zen4 and earlier uarch does not support ldlat
+	# o Even on supported platforms, it's disabled (--ldlat=0) by default.
+	ldlat=${BASH_REMATCH[1]}
+	if [[ -n $ldlat ]]; then
+		if ! [[ "$ldlat" =~ ldlat=0 ]]; then
+			echo "ERROR: ldlat not initialized to 0?"
+			exit 1
+		fi
+
+		mem_events="$(perf mem record -v --ldlat=150 -e list 2>&1)"
+		if ! [[ "$mem_events" =~ ^mem-ldst.*ibs_op/ldlat=150/.*available ]]; then
+			echo "ERROR: --ldlat not honored?"
+			exit 1
+		fi
+	fi
+
+	# perf mem/c2c internally uses IBS PMU on AMD CPU which doesn't
+	# support user/kernel filtering and per-process monitoring on older
+	# kernels, spin program on specific CPU and test in per-CPU mode.
 	perf mem record -vvv -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM 2>"${ERR_FILE}"
 else
 	perf mem record -vvv --all-user -o ${PERF_DATA} -- $TEST_PROGRAM 2>"${ERR_FILE}"
diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh
index f3a9a040bacc..32a9b8dcb200 100755
--- a/tools/perf/tests/shell/test_intel_pt.sh
+++ b/tools/perf/tests/shell/test_intel_pt.sh
@@ -288,6 +288,11 @@ test_jitdump()
 	jitdump_incl_dir="${script_dir}/../../util"
 	jitdump_h="${jitdump_incl_dir}/jitdump.h"
 
+        if ! perf check feature -q libelf ; then
+		echo "SKIP: libelf is needed for jitdump"
+		return 2
+	fi
+
 	if [ ! -e "${jitdump_h}" ] ; then
 		echo "SKIP: Include file jitdump.h not found"
 		return 2
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 60fccb62c540..5d5019988d61 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -25,9 +25,14 @@ trace_open_vfs_getname() {
 	grep -E " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +\"?${file}\"?, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
 
-
-add_probe_vfs_getname || skip_if_no_debuginfo
+add_probe_vfs_getname
 err=$?
+
+if [ $err -eq 1 ] ; then
+        skip_if_no_debuginfo
+        err=$?
+fi
+
 if [ $err -ne 0 ] ; then
 	exit $err
 fi
diff --git a/tools/perf/tests/shell/trace_summary.sh b/tools/perf/tests/shell/trace_summary.sh
new file mode 100755
index 000000000000..f9bb7f9388be
--- /dev/null
+++ b/tools/perf/tests/shell/trace_summary.sh
@@ -0,0 +1,77 @@
+#!/bin/sh
+# perf trace summary (exclusive)
+# SPDX-License-Identifier: GPL-2.0
+
+# Check that perf trace works with various summary mode
+
+# shellcheck source=lib/probe.sh
+. "$(dirname $0)"/lib/probe.sh
+
+skip_if_no_perf_trace || exit 2
+[ "$(id -u)" = 0 ] || exit 2
+
+OUTPUT=$(mktemp /tmp/perf_trace_test.XXXXX)
+
+test_perf_trace() {
+    args=$1
+    workload="true"
+    search="^\s*(open|read|close).*[0-9]+%$"
+
+    echo "testing: perf trace ${args} -- ${workload}"
+    perf trace ${args} -- ${workload} >${OUTPUT} 2>&1
+    if [ $? -ne 0 ]; then
+        echo "Error: perf trace ${args} failed unexpectedly"
+        cat ${OUTPUT}
+        rm -f ${OUTPUT}
+        exit 1
+    fi
+
+    count=$(grep -E -c -m 3 "${search}" ${OUTPUT})
+    if [ "${count}" != "3" ]; then
+	echo "Error: cannot find enough pattern ${search} in the output"
+	cat ${OUTPUT}
+	rm -f ${OUTPUT}
+	exit 1
+    fi
+}
+
+# summary only for a process
+test_perf_trace "-s"
+
+# normal output with summary at the end
+test_perf_trace "-S"
+
+# summary only with an explicit summary mode
+test_perf_trace "-s --summary-mode=thread"
+
+# summary with normal output - total summary mode
+test_perf_trace "-S --summary-mode=total"
+
+# summary only for system wide - per-thread summary
+test_perf_trace "-as --summary-mode=thread --no-bpf-summary"
+
+# summary only for system wide - total summary mode
+test_perf_trace "-as --summary-mode=total --no-bpf-summary"
+
+if ! perf check feature -q bpf; then
+    echo "Skip --bpf-summary tests as perf built without libbpf"
+    rm -f ${OUTPUT}
+    exit 2
+fi
+
+# summary only for system wide - per-thread summary with BPF
+test_perf_trace "-as --summary-mode=thread --bpf-summary"
+
+# summary only for system wide - total summary mode with BPF
+test_perf_trace "-as --summary-mode=total --bpf-summary"
+
+# summary with normal output for system wide - total summary mode with BPF
+test_perf_trace "-aS --summary-mode=total --bpf-summary"
+
+# summary only for system wide - cgroup summary mode with BPF
+test_perf_trace "-as --summary-mode=cgroup --bpf-summary"
+
+# summary with normal output for system wide - cgroup summary mode with BPF
+test_perf_trace "-aS --summary-mode=cgroup --bpf-summary"
+
+rm -f ${OUTPUT}
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 8df3f9d9ffd2..6b3aac283c37 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -264,7 +264,7 @@ static int compar(const void *a, const void *b)
 	const struct event_node *nodeb = b;
 	s64 cmp = nodea->event_time - nodeb->event_time;
 
-	return cmp;
+	return cmp < 0 ? -1 : (cmp > 0 ? 1 : 0);
 }
 
 static int process_events(struct evlist *evlist,
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 8aea344536b8..bb7951c61971 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -157,6 +157,7 @@ DECLARE_SUITE(jit_write_elf);
 DECLARE_SUITE(api_io);
 DECLARE_SUITE(demangle_java);
 DECLARE_SUITE(demangle_ocaml);
+DECLARE_SUITE(demangle_rust);
 DECLARE_SUITE(pfm);
 DECLARE_SUITE(parse_metric);
 DECLARE_SUITE(pe_file_parsing);
diff --git a/tools/perf/trace/beauty/include/uapi/linux/vhost.h b/tools/perf/trace/beauty/include/uapi/linux/vhost.h
index b95dd84eef2d..d4b3e2ae1314 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/vhost.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/vhost.h
@@ -28,10 +28,10 @@
 
 /* Set current process as the (exclusive) owner of this file descriptor.  This
  * must be called before any other vhost command.  Further calls to
- * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
+ * VHOST_SET_OWNER fail until VHOST_RESET_OWNER is called. */
 #define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
 /* Give up ownership, and reset the device to default values.
- * Allows subsequent call to VHOST_OWNER_SET to succeed. */
+ * Allows subsequent call to VHOST_SET_OWNER to succeed. */
 #define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
 
 /* Set up/modify memory layout */
diff --git a/tools/perf/ui/Build b/tools/perf/ui/Build
index d2ecd9290600..6005f813c9e3 100644
--- a/tools/perf/ui/Build
+++ b/tools/perf/ui/Build
@@ -8,5 +8,6 @@ perf-ui-y += stdio/hist.o
 CFLAGS_setup.o += -DLIBDIR="BUILD_STR($(LIBDIR))"
 
 perf-ui-$(CONFIG_SLANG) += browser.o
+perf-ui-$(CONFIG_SLANG) += keysyms.o
 perf-ui-$(CONFIG_SLANG) += browsers/
 perf-ui-$(CONFIG_SLANG) += tui/
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 19503e838738..dc88427b4ae5 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -233,6 +233,14 @@ int ui_browser__warning(struct ui_browser *browser, int timeout,
 	return key;
 }
 
+int ui_browser__warn_unhandled_hotkey(struct ui_browser *browser, int key, int timeout, const char *help)
+{
+	char kname[32];
+
+	key_name(key, kname, sizeof(kname));
+	return ui_browser__warning(browser, timeout, "\n'%s' key not associated%s!\n", kname, help ?: "");
+}
+
 int ui_browser__help_window(struct ui_browser *browser, const char *text)
 {
 	int key;
@@ -451,6 +459,8 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
 				goto out;
 			if (browser->horiz_scroll != 0)
 				--browser->horiz_scroll;
+			else
+				goto out;
 			break;
 		case K_PGDN:
 		case ' ':
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 6e98d5f8f71c..f59ad4f14d33 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -66,6 +66,7 @@ void __ui_browser__vline(struct ui_browser *browser, unsigned int column,
 
 int ui_browser__warning(struct ui_browser *browser, int timeout,
 			const char *format, ...);
+int ui_browser__warn_unhandled_hotkey(struct ui_browser *browser, int key, int timeout, const char *help);
 int ui_browser__help_window(struct ui_browser *browser, const char *text);
 bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text);
 int ui_browser__input_window(const char *title, const char *text, char *input,
diff --git a/tools/perf/ui/browsers/annotate-data.c b/tools/perf/ui/browsers/annotate-data.c
index cd562a8822b7..aa8c89fe2e82 100644
--- a/tools/perf/ui/browsers/annotate-data.c
+++ b/tools/perf/ui/browsers/annotate-data.c
@@ -558,6 +558,7 @@ static int annotated_data_browser__run(struct annotated_data_browser *browser,
 		case CTRL('c'):
 			goto out;
 		default:
+			ui_browser__warn_unhandled_hotkey(&browser->b, key, delay_secs, ", use 'h'/F1 to see actions");
 			continue;
 		}
 	}
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 135d6ce88fb3..ab776b1ed2d5 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -406,6 +406,9 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 		browser->b.index = al->idx_asm;
 	}
 
+	if (annotate_opts.hide_src_code_on_title)
+		annotate_opts.hide_src_code_on_title = false;
+
 	return true;
 }
 
@@ -704,6 +707,18 @@ switch_percent_type(struct annotation_options *opts, bool base)
 	}
 }
 
+static int annotate__scnprintf_title(struct hists *hists, char *bf, size_t size)
+{
+	int printed = hists__scnprintf_title(hists, bf, size);
+
+	if (!annotate_opts.hide_src_code_on_title) {
+		printed += scnprintf(bf + printed, size - printed, " [source: %s]",
+				     annotate_opts.hide_src_code ? "OFF" : "On");
+	}
+
+	return printed;
+}
+
 static int annotate_browser__run(struct annotate_browser *browser,
 				 struct evsel *evsel,
 				 struct hist_browser_timer *hbt)
@@ -719,7 +734,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 	char title[256];
 	int key;
 
-	hists__scnprintf_title(hists, title, sizeof(title));
+	annotate__scnprintf_title(hists, title, sizeof(title));
 	if (annotate_browser__show(&browser->b, title, help) < 0)
 		return -1;
 
@@ -755,7 +770,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 
 			if (delay_secs != 0) {
 				symbol__annotate_decay_histogram(sym, evsel);
-				hists__scnprintf_title(hists, title, sizeof(title));
+				annotate__scnprintf_title(hists, title, sizeof(title));
 				annotate_browser__show(&browser->b, title, help);
 			}
 			continue;
@@ -820,6 +835,8 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		case 's':
 			if (annotate_browser__toggle_source(browser))
 				ui_helpline__puts(help);
+			annotate__scnprintf_title(hists, title, sizeof(title));
+			annotate_browser__show(&browser->b, title, help);
 			continue;
 		case 'o':
 			annotate_opts.use_offset = !annotate_opts.use_offset;
@@ -906,7 +923,7 @@ show_sup_ins:
 		case 'p':
 		case 'b':
 			switch_percent_type(&annotate_opts, key == 'b');
-			hists__scnprintf_title(hists, title, sizeof(title));
+			annotate__scnprintf_title(hists, title, sizeof(title));
 			annotate_browser__show(&browser->b, title, help);
 			continue;
 		case 'B':
@@ -928,6 +945,7 @@ show_sup_ins:
 		case CTRL('c'):
 			goto out;
 		default:
+			ui_browser__warn_unhandled_hotkey(&browser->b, key, delay_secs, ", use 'h'/F1 to see actions");
 			continue;
 		}
 
diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c
index 57e6e4332f74..2213b4661600 100644
--- a/tools/perf/ui/browsers/header.c
+++ b/tools/perf/ui/browsers/header.c
@@ -69,6 +69,7 @@ static int list_menu__run(struct ui_browser *menu)
 			key = -1;
 			break;
 		default:
+			ui_browser__warn_unhandled_hotkey(menu, key, 0, ", use 'h'/'?'/F1 to see actions");
 			continue;
 		}
 
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 35c10509b797..d26b925e3d7f 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1266,6 +1266,16 @@ hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 			_fmttype);					\
 }
 
+#define __HPP_COLOR_MEM_STAT_FN(_name, _type)				\
+static int								\
+hist_browser__hpp_color_mem_stat_##_name(struct perf_hpp_fmt *fmt,	\
+					 struct perf_hpp *hpp,		\
+					 struct hist_entry *he)		\
+{									\
+	return hpp__fmt_mem_stat(fmt, hpp, he, PERF_MEM_STAT_##_type,	\
+				 " %5.1f%%", __hpp__slsmg_color_printf);\
+}
+
 __HPP_COLOR_PERCENT_FN(overhead, period, PERF_HPP_FMT_TYPE__PERCENT)
 __HPP_COLOR_PERCENT_FN(latency, latency, PERF_HPP_FMT_TYPE__LATENCY)
 __HPP_COLOR_PERCENT_FN(overhead_sys, period_sys, PERF_HPP_FMT_TYPE__PERCENT)
@@ -1274,9 +1284,15 @@ __HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys, PERF_HPP_FMT_TYPE__
 __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, PERF_HPP_FMT_TYPE__PERCENT)
 __HPP_COLOR_ACC_PERCENT_FN(overhead_acc, period, PERF_HPP_FMT_TYPE__PERCENT)
 __HPP_COLOR_ACC_PERCENT_FN(latency_acc, latency, PERF_HPP_FMT_TYPE__LATENCY)
+__HPP_COLOR_MEM_STAT_FN(op, OP)
+__HPP_COLOR_MEM_STAT_FN(cache, CACHE)
+__HPP_COLOR_MEM_STAT_FN(memory, MEMORY)
+__HPP_COLOR_MEM_STAT_FN(snoop, SNOOP)
+__HPP_COLOR_MEM_STAT_FN(dtlb, DTLB)
 
 #undef __HPP_COLOR_PERCENT_FN
 #undef __HPP_COLOR_ACC_PERCENT_FN
+#undef __HPP_COLOR_MEM_STAT_FN
 
 void hist_browser__init_hpp(void)
 {
@@ -1296,6 +1312,16 @@ void hist_browser__init_hpp(void)
 				hist_browser__hpp_color_overhead_acc;
 	perf_hpp__format[PERF_HPP__LATENCY_ACC].color =
 				hist_browser__hpp_color_latency_acc;
+	perf_hpp__format[PERF_HPP__MEM_STAT_OP].color =
+				hist_browser__hpp_color_mem_stat_op;
+	perf_hpp__format[PERF_HPP__MEM_STAT_CACHE].color =
+				hist_browser__hpp_color_mem_stat_cache;
+	perf_hpp__format[PERF_HPP__MEM_STAT_MEMORY].color =
+				hist_browser__hpp_color_mem_stat_memory;
+	perf_hpp__format[PERF_HPP__MEM_STAT_SNOOP].color =
+				hist_browser__hpp_color_mem_stat_snoop;
+	perf_hpp__format[PERF_HPP__MEM_STAT_DTLB].color =
+				hist_browser__hpp_color_mem_stat_dtlb;
 
 	res_sample_init();
 }
@@ -1686,7 +1712,8 @@ hists_browser__scnprintf_headers(struct hist_browser *browser, char *buf,
 	return ret;
 }
 
-static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *browser, char *buf, size_t size)
+static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *browser,
+						      char *buf, size_t size, int line)
 {
 	struct hists *hists = browser->hists;
 	struct perf_hpp dummy_hpp = {
@@ -1712,7 +1739,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 		if (column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->header(fmt, &dummy_hpp, hists, 0, NULL);
+		ret = fmt->header(fmt, &dummy_hpp, hists, line, NULL);
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
 
@@ -1723,6 +1750,9 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 		first_node = false;
 	}
 
+	if (line < hists->hpp_list->nr_header_lines - 1)
+		return ret;
+
 	if (!first_node) {
 		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s",
 				indent * HIERARCHY_INDENT, "");
@@ -1753,7 +1783,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 			}
 			first_col = false;
 
-			ret = fmt->header(fmt, &dummy_hpp, hists, 0, NULL);
+			ret = fmt->header(fmt, &dummy_hpp, hists, line, NULL);
 			dummy_hpp.buf[ret] = '\0';
 
 			start = strim(dummy_hpp.buf);
@@ -1772,14 +1802,18 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 
 static void hists_browser__hierarchy_headers(struct hist_browser *browser)
 {
+	struct perf_hpp_list *hpp_list = browser->hists->hpp_list;
 	char headers[1024];
+	int line;
 
-	hists_browser__scnprintf_hierarchy_headers(browser, headers,
-						   sizeof(headers));
+	for (line = 0; line < hpp_list->nr_header_lines; line++) {
+		hists_browser__scnprintf_hierarchy_headers(browser, headers,
+							   sizeof(headers), line);
 
-	ui_browser__gotorc_title(&browser->b, 0, 0);
-	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
-	ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
+		ui_browser__gotorc_title(&browser->b, line, 0);
+		ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
+		ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
+	}
 }
 
 static void hists_browser__headers(struct hist_browser *browser)
@@ -2422,7 +2456,6 @@ close_file_and_continue:
 struct popup_action {
 	unsigned long		time;
 	struct thread 		*thread;
-	struct evsel	*evsel;
 	int (*fn)(struct hist_browser *browser, struct popup_action *act);
 	struct map_symbol 	ms;
 	int			socket;
@@ -2489,8 +2522,7 @@ static struct symbol *symbol__new_unresolved(u64 addr, struct map *map)
 }
 
 static int
-add_annotate_opt(struct hist_browser *browser __maybe_unused,
-		 struct popup_action *act, char **optstr,
+add_annotate_opt(struct popup_action *act, char **optstr,
 		 struct map_symbol *ms,
 		 u64 addr)
 {
@@ -2514,18 +2546,17 @@ add_annotate_opt(struct hist_browser *browser __maybe_unused,
 }
 
 static int
-do_annotate_type(struct hist_browser *browser, struct popup_action *act)
+do_annotate_type(struct hist_browser *browser, struct popup_action *act __maybe_unused)
 {
 	struct hist_entry *he = browser->he_selection;
 
-	hist_entry__annotate_data_tui(he, act->evsel, browser->hbt);
+	hist_entry__annotate_data_tui(he, hists_to_evsel(browser->hists), browser->hbt);
 	ui_browser__handle_resize(&browser->b);
 	return 0;
 }
 
 static int
-add_annotate_type_opt(struct hist_browser *browser,
-		      struct popup_action *act, char **optstr,
+add_annotate_type_opt(struct popup_action *act, char **optstr,
 		      struct hist_entry *he)
 {
 	if (he == NULL || he->mem_type == NULL || he->mem_type->histograms == NULL)
@@ -2534,7 +2565,6 @@ add_annotate_type_opt(struct hist_browser *browser,
 	if (asprintf(optstr, "Annotate type %s", he->mem_type->self.type_name) < 0)
 		return 0;
 
-	act->evsel = hists_to_evsel(browser->hists);
 	act->fn = do_annotate_type;
 	return 1;
 }
@@ -2695,7 +2725,7 @@ add_map_opt(struct hist_browser *browser,
 }
 
 static int
-do_run_script(struct hist_browser *browser __maybe_unused,
+do_run_script(struct hist_browser *browser,
 	      struct popup_action *act)
 {
 	char *script_opt;
@@ -2734,27 +2764,26 @@ do_run_script(struct hist_browser *browser __maybe_unused,
 		n += snprintf(script_opt + n, len - n, " --time %s,%s", start, end);
 	}
 
-	script_browse(script_opt, act->evsel);
+	script_browse(script_opt, hists_to_evsel(browser->hists));
 	free(script_opt);
 	return 0;
 }
 
 static int
-do_res_sample_script(struct hist_browser *browser __maybe_unused,
+do_res_sample_script(struct hist_browser *browser,
 		     struct popup_action *act)
 {
 	struct hist_entry *he;
 
 	he = hist_browser__selected_entry(browser);
-	res_sample_browse(he->res_samples, he->num_res, act->evsel, act->rstype);
+	res_sample_browse(he->res_samples, he->num_res, hists_to_evsel(browser->hists), act->rstype);
 	return 0;
 }
 
 static int
-add_script_opt_2(struct hist_browser *browser __maybe_unused,
-	       struct popup_action *act, char **optstr,
+add_script_opt_2(struct popup_action *act, char **optstr,
 	       struct thread *thread, struct symbol *sym,
-	       struct evsel *evsel, const char *tstr)
+	       const char *tstr)
 {
 
 	if (thread) {
@@ -2772,7 +2801,6 @@ add_script_opt_2(struct hist_browser *browser __maybe_unused,
 
 	act->thread = thread;
 	act->ms.sym = sym;
-	act->evsel = evsel;
 	act->fn = do_run_script;
 	return 1;
 }
@@ -2780,13 +2808,12 @@ add_script_opt_2(struct hist_browser *browser __maybe_unused,
 static int
 add_script_opt(struct hist_browser *browser,
 	       struct popup_action *act, char **optstr,
-	       struct thread *thread, struct symbol *sym,
-	       struct evsel *evsel)
+	       struct thread *thread, struct symbol *sym)
 {
 	int n, j;
 	struct hist_entry *he;
 
-	n = add_script_opt_2(browser, act, optstr, thread, sym, evsel, "");
+	n = add_script_opt_2(act, optstr, thread, sym, "");
 
 	he = hist_browser__selected_entry(browser);
 	if (sort_order && strstr(sort_order, "time")) {
@@ -2800,8 +2827,7 @@ add_script_opt(struct hist_browser *browser,
 		j += sprintf(tstr + j, "-");
 		timestamp__scnprintf_usec(he->time + symbol_conf.time_quantum,
 				          tstr + j, sizeof tstr - j);
-		n += add_script_opt_2(browser, act, optstr, thread, sym,
-					  evsel, tstr);
+		n += add_script_opt_2(act, optstr, thread, sym, tstr);
 		act->time = he->time;
 	}
 	return n;
@@ -2811,7 +2837,6 @@ static int
 add_res_sample_opt(struct hist_browser *browser __maybe_unused,
 		   struct popup_action *act, char **optstr,
 		   struct res_sample *res_sample,
-		   struct evsel *evsel,
 		   enum rstype type)
 {
 	if (!res_sample)
@@ -2823,7 +2848,6 @@ add_res_sample_opt(struct hist_browser *browser __maybe_unused,
 		return 0;
 
 	act->fn = do_res_sample_script;
-	act->evsel = evsel;
 	act->rstype = type;
 	return 1;
 }
@@ -3274,10 +3298,10 @@ do_hotkey:		 // key came straight from options ui__popup_menu()
 				/*
 				 * No need to set actions->dso here since
 				 * it's just to remove the current filter.
-				 * Ditto for thread below.
 				 */
 				do_zoom_dso(browser, actions);
 			} else if (top == &browser->hists->thread_filter) {
+				actions->thread = thread;
 				do_zoom_thread(browser, actions);
 			} else if (top == &browser->hists->socket_filter) {
 				do_zoom_socket(browser, actions);
@@ -3308,6 +3332,8 @@ do_hotkey:		 // key came straight from options ui__popup_menu()
 			/* Fall thru */
 		default:
 			helpline = "Press '?' for help on key bindings";
+			ui_browser__warn_unhandled_hotkey(&browser->b, key, delay_secs,
+							  ", use 'h'/'?'/F1 to see actions");
 			continue;
 		}
 
@@ -3322,27 +3348,23 @@ do_hotkey:		 // key came straight from options ui__popup_menu()
 			if (bi == NULL)
 				goto skip_annotation;
 
-			nr_options += add_annotate_opt(browser,
-						       &actions[nr_options],
+			nr_options += add_annotate_opt(&actions[nr_options],
 						       &options[nr_options],
 						       &bi->from.ms,
 						       bi->from.al_addr);
 			if (bi->to.ms.sym != bi->from.ms.sym)
-				nr_options += add_annotate_opt(browser,
-							&actions[nr_options],
+				nr_options += add_annotate_opt(&actions[nr_options],
 							&options[nr_options],
 							&bi->to.ms,
 							bi->to.al_addr);
 		} else if (browser->he_selection) {
-			nr_options += add_annotate_opt(browser,
-						       &actions[nr_options],
+			nr_options += add_annotate_opt(&actions[nr_options],
 						       &options[nr_options],
 						       browser->selection,
 						       browser->he_selection->ip);
 		}
 skip_annotation:
-		nr_options += add_annotate_type_opt(browser,
-						    &actions[nr_options],
+		nr_options += add_annotate_type_opt(&actions[nr_options],
 						    &options[nr_options],
 						    browser->he_selection);
 		nr_options += add_thread_opt(browser, &actions[nr_options],
@@ -3366,7 +3388,7 @@ skip_annotation:
 				nr_options += add_script_opt(browser,
 							     &actions[nr_options],
 							     &options[nr_options],
-							     thread, NULL, evsel);
+							     thread, NULL);
 			}
 			/*
 			 * Note that browser->selection != NULL
@@ -3381,24 +3403,23 @@ skip_annotation:
 				nr_options += add_script_opt(browser,
 							     &actions[nr_options],
 							     &options[nr_options],
-							     NULL, browser->selection->sym,
-							     evsel);
+							     NULL, browser->selection->sym);
 			}
 		}
 		nr_options += add_script_opt(browser, &actions[nr_options],
-					     &options[nr_options], NULL, NULL, evsel);
+					     &options[nr_options], NULL, NULL);
 		nr_options += add_res_sample_opt(browser, &actions[nr_options],
 						 &options[nr_options],
 						 hist_browser__selected_res_sample(browser),
-						 evsel, A_NORMAL);
+						 A_NORMAL);
 		nr_options += add_res_sample_opt(browser, &actions[nr_options],
 						 &options[nr_options],
 						 hist_browser__selected_res_sample(browser),
-						 evsel, A_ASM);
+						 A_ASM);
 		nr_options += add_res_sample_opt(browser, &actions[nr_options],
 						 &options[nr_options],
 						 hist_browser__selected_res_sample(browser),
-						 evsel, A_SOURCE);
+						 A_SOURCE);
 		nr_options += add_switch_opt(browser, &actions[nr_options],
 					     &options[nr_options]);
 skip_scripting:
@@ -3568,6 +3589,7 @@ browse_hists:
 		case CTRL('c'):
 			goto out;
 		default:
+			ui_browser__warn_unhandled_hotkey(&menu->b, key, delay_secs, NULL);
 			continue;
 		}
 	}
@@ -3693,7 +3715,7 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
 	struct popup_action action;
 	char *br_cntr_text = NULL;
 	static const char help[] =
-	" q             Quit \n"
+	" q/ESC         Quit \n"
 	" B             Branch counter abbr list (Optional)\n";
 
 	browser = hist_browser__new(hists);
@@ -3720,6 +3742,7 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
 
 		switch (key) {
 		case 'q':
+		case K_ESC:
 			goto out;
 		case '?':
 			ui_browser__help_window(&browser->b, help);
@@ -3746,7 +3769,9 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
 			}
 			continue;
 		default:
-			break;
+			ui_browser__warn_unhandled_hotkey(&browser->b, key, 0,
+							  ", use '?' to see actions");
+			continue;
 		}
 	}
 
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index fba55175a935..c61ba3174a24 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -88,8 +88,10 @@ static int map_browser__run(struct map_browser *browser)
 		case '/':
 			if (verbose > 0)
 				map_browser__search(browser);
+			/* fall thru */
 		default:
-			break;
+			ui_browser__warn_unhandled_hotkey(&browser->b, key, 0, NULL);
+			continue;
                 case K_LEFT:
                 case K_ESC:
                 case 'q':
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index ae3b7fe1dadc..b085eb0de849 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -11,6 +11,8 @@
 #include "../util/sort.h"
 #include "../util/evsel.h"
 #include "../util/evlist.h"
+#include "../util/mem-events.h"
+#include "../util/string2.h"
 #include "../util/thread.h"
 #include "../util/util.h"
 
@@ -150,6 +152,48 @@ int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return hpp__fmt(fmt, hpp, he, get_field, fmtstr, print_fn, fmtype);
 }
 
+int hpp__fmt_mem_stat(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
+		      struct hist_entry *he, enum mem_stat_type mst,
+		      const char *fmtstr, hpp_snprint_fn print_fn)
+{
+	struct hists *hists = he->hists;
+	int mem_stat_idx = -1;
+	char *buf = hpp->buf;
+	size_t size = hpp->size;
+	u64 total = 0;
+	int ret = 0;
+
+	for (int i = 0; i < hists->nr_mem_stats; i++) {
+		if (hists->mem_stat_types[i] == mst) {
+			mem_stat_idx = i;
+			break;
+		}
+	}
+	assert(mem_stat_idx != -1);
+
+	for (int i = 0; i < MEM_STAT_LEN; i++)
+		total += hists->mem_stat_total[mem_stat_idx].entries[i];
+	assert(total != 0);
+
+	for (int i = 0; i < MEM_STAT_LEN; i++) {
+		u64 val = he->mem_stat[mem_stat_idx].entries[i];
+
+		if (hists->mem_stat_total[mem_stat_idx].entries[i] == 0)
+			continue;
+
+		ret += hpp__call_print_fn(hpp, print_fn, fmtstr, 100.0 * val / total);
+	}
+
+	/*
+	 * Restore original buf and size as it's where caller expects
+	 * the result will be saved.
+	 */
+	hpp->buf = buf;
+	hpp->size = size;
+
+	return ret;
+}
+
 static int field_cmp(u64 field_a, u64 field_b)
 {
 	if (field_a > field_b)
@@ -294,6 +338,37 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
 	return ret;
 }
 
+static bool perf_hpp__is_mem_stat_entry(struct perf_hpp_fmt *fmt);
+
+static enum mem_stat_type hpp__mem_stat_type(struct perf_hpp_fmt *fmt)
+{
+	if (!perf_hpp__is_mem_stat_entry(fmt))
+		return -1;
+
+	switch (fmt->idx) {
+	case PERF_HPP__MEM_STAT_OP:
+		return PERF_MEM_STAT_OP;
+	case PERF_HPP__MEM_STAT_CACHE:
+		return PERF_MEM_STAT_CACHE;
+	case PERF_HPP__MEM_STAT_MEMORY:
+		return PERF_MEM_STAT_MEMORY;
+	case PERF_HPP__MEM_STAT_SNOOP:
+		return PERF_MEM_STAT_SNOOP;
+	case PERF_HPP__MEM_STAT_DTLB:
+		return PERF_MEM_STAT_DTLB;
+	default:
+		break;
+	}
+	pr_debug("Should not reach here\n");
+	return -1;
+}
+
+static int64_t hpp__sort_mem_stat(struct perf_hpp_fmt *fmt __maybe_unused,
+				  struct hist_entry *a, struct hist_entry *b)
+{
+	return a->stat.period - b->stat.period;
+}
+
 static int hpp__width_fn(struct perf_hpp_fmt *fmt,
 			 struct perf_hpp *hpp __maybe_unused,
 			 struct hists *hists)
@@ -321,11 +396,78 @@ static int hpp__width_fn(struct perf_hpp_fmt *fmt,
 }
 
 static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			  struct hists *hists, int line __maybe_unused,
+			  struct hists *hists, int line,
 			  int *span __maybe_unused)
 {
 	int len = hpp__width_fn(fmt, hpp, hists);
-	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
+	const char *hdr = "";
+
+	if (line == hists->hpp_list->nr_header_lines - 1)
+		hdr = fmt->name;
+
+	return scnprintf(hpp->buf, hpp->size, "%*s", len, hdr);
+}
+
+static int hpp__header_mem_stat_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+				   struct hists *hists, int line,
+				   int *span __maybe_unused)
+{
+	char *buf = hpp->buf;
+	int ret = 0;
+	int len;
+	enum mem_stat_type mst = hpp__mem_stat_type(fmt);
+	int mem_stat_idx = -1;
+
+	for (int i = 0; i < hists->nr_mem_stats; i++) {
+		if (hists->mem_stat_types[i] == mst) {
+			mem_stat_idx = i;
+			break;
+		}
+	}
+	assert(mem_stat_idx != -1);
+
+	if (line == 0) {
+		int left, right;
+
+		len = 0;
+		/* update fmt->len for acutally used columns only */
+		for (int i = 0; i < MEM_STAT_LEN; i++) {
+			if (hists->mem_stat_total[mem_stat_idx].entries[i])
+				len += MEM_STAT_PRINT_LEN;
+		}
+		fmt->len = len;
+
+		/* print header directly if single column only */
+		if (len == MEM_STAT_PRINT_LEN)
+			return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
+
+		left = (len - strlen(fmt->name)) / 2 - 1;
+		right = len - left - strlen(fmt->name) - 2;
+
+		if (left < 0)
+			left = 0;
+		if (right < 0)
+			right = 0;
+
+		return scnprintf(hpp->buf, hpp->size, "%.*s %s %.*s",
+				 left, graph_dotted_line, fmt->name, right, graph_dotted_line);
+	}
+
+
+	len = hpp->size;
+	for (int i = 0; i < MEM_STAT_LEN; i++) {
+		int printed;
+
+		if (hists->mem_stat_total[mem_stat_idx].entries[i] == 0)
+			continue;
+
+		printed = scnprintf(buf, len, "%*s", MEM_STAT_PRINT_LEN,
+				    mem_stat_name(mst, i));
+		ret += printed;
+		buf += printed;
+		len -= printed;
+	}
+	return ret;
 }
 
 int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
@@ -453,6 +595,23 @@ static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, 	\
 	return __hpp__sort(a, b, he_get_##_field);				\
 }
 
+#define __HPP_COLOR_MEM_STAT_FN(_name, _type)					\
+static int hpp__color_mem_stat_##_name(struct perf_hpp_fmt *fmt,		\
+				       struct perf_hpp *hpp,			\
+				       struct hist_entry *he)			\
+{										\
+	return hpp__fmt_mem_stat(fmt, hpp, he, PERF_MEM_STAT_##_type,		\
+				 " %5.1f%%", hpp_color_scnprintf);		\
+}
+
+#define __HPP_ENTRY_MEM_STAT_FN(_name, _type)					\
+static int hpp__entry_mem_stat_##_name(struct perf_hpp_fmt *fmt, 		\
+				       struct perf_hpp *hpp,			\
+				       struct hist_entry *he)			\
+{										\
+	return hpp__fmt_mem_stat(fmt, hpp, he, PERF_MEM_STAT_##_type,		\
+				 " %5.1f%%", hpp_entry_scnprintf);		\
+}
 
 #define HPP_PERCENT_FNS(_type, _field, _fmttype)			\
 __HPP_COLOR_PERCENT_FN(_type, _field, _fmttype)				\
@@ -472,6 +631,10 @@ __HPP_SORT_RAW_FN(_type, _field)
 __HPP_ENTRY_AVERAGE_FN(_type, _field)					\
 __HPP_SORT_AVERAGE_FN(_type, _field)
 
+#define HPP_MEM_STAT_FNS(_name, _type)					\
+__HPP_COLOR_MEM_STAT_FN(_name, _type)					\
+__HPP_ENTRY_MEM_STAT_FN(_name, _type)
+
 HPP_PERCENT_FNS(overhead, period, PERF_HPP_FMT_TYPE__PERCENT)
 HPP_PERCENT_FNS(latency, latency, PERF_HPP_FMT_TYPE__LATENCY)
 HPP_PERCENT_FNS(overhead_sys, period_sys, PERF_HPP_FMT_TYPE__PERCENT)
@@ -488,6 +651,12 @@ HPP_AVERAGE_FNS(weight1, weight1)
 HPP_AVERAGE_FNS(weight2, weight2)
 HPP_AVERAGE_FNS(weight3, weight3)
 
+HPP_MEM_STAT_FNS(op, OP)
+HPP_MEM_STAT_FNS(cache, CACHE)
+HPP_MEM_STAT_FNS(memory, MEMORY)
+HPP_MEM_STAT_FNS(snoop, SNOOP)
+HPP_MEM_STAT_FNS(dtlb, DTLB)
+
 static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 			    struct hist_entry *a __maybe_unused,
 			    struct hist_entry *b __maybe_unused)
@@ -495,6 +664,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 	return 0;
 }
 
+static bool perf_hpp__is_mem_stat_entry(struct perf_hpp_fmt *fmt)
+{
+	return fmt->sort == hpp__sort_mem_stat;
+}
+
 static bool perf_hpp__is_hpp_entry(struct perf_hpp_fmt *a)
 {
 	return a->header == hpp__header_fn;
@@ -508,6 +682,14 @@ static bool hpp__equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
 	return a->idx == b->idx;
 }
 
+static bool hpp__equal_mem_stat(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	if (!perf_hpp__is_mem_stat_entry(a) || !perf_hpp__is_mem_stat_entry(b))
+		return false;
+
+	return a->entry == b->entry;
+}
+
 #define HPP__COLOR_PRINT_FNS(_name, _fn, _idx)		\
 	{						\
 		.name   = _name,			\
@@ -549,6 +731,20 @@ static bool hpp__equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
 		.equal	= hpp__equal,			\
 	}
 
+#define HPP__MEM_STAT_PRINT_FNS(_name, _fn, _type)	\
+	{						\
+		.name   = _name,			\
+		.header	= hpp__header_mem_stat_fn,	\
+		.width	= hpp__width_fn,		\
+		.color	= hpp__color_mem_stat_ ## _fn,	\
+		.entry	= hpp__entry_mem_stat_ ## _fn,	\
+		.cmp	= hpp__nop_cmp,			\
+		.collapse = hpp__nop_cmp,		\
+		.sort	= hpp__sort_mem_stat,		\
+		.idx	= PERF_HPP__MEM_STAT_ ## _type,	\
+		.equal	= hpp__equal_mem_stat,		\
+	}
+
 struct perf_hpp_fmt perf_hpp__format[] = {
 	HPP__COLOR_PRINT_FNS("Overhead", overhead, OVERHEAD),
 	HPP__COLOR_PRINT_FNS("Latency", latency, LATENCY),
@@ -563,6 +759,11 @@ struct perf_hpp_fmt perf_hpp__format[] = {
 	HPP__PRINT_FNS("Weight1", weight1, WEIGHT1),
 	HPP__PRINT_FNS("Weight2", weight2, WEIGHT2),
 	HPP__PRINT_FNS("Weight3", weight3, WEIGHT3),
+	HPP__MEM_STAT_PRINT_FNS("Mem Op", op, OP),
+	HPP__MEM_STAT_PRINT_FNS("Cache", cache, CACHE),
+	HPP__MEM_STAT_PRINT_FNS("Memory", memory, MEMORY),
+	HPP__MEM_STAT_PRINT_FNS("Snoop", snoop, SNOOP),
+	HPP__MEM_STAT_PRINT_FNS("D-TLB", dtlb, DTLB),
 };
 
 struct perf_hpp_list perf_hpp_list = {
@@ -574,11 +775,13 @@ struct perf_hpp_list perf_hpp_list = {
 #undef HPP__COLOR_PRINT_FNS
 #undef HPP__COLOR_ACC_PRINT_FNS
 #undef HPP__PRINT_FNS
+#undef HPP__MEM_STAT_PRINT_FNS
 
 #undef HPP_PERCENT_FNS
 #undef HPP_PERCENT_ACC_FNS
 #undef HPP_RAW_FNS
 #undef HPP_AVERAGE_FNS
+#undef HPP_MEM_STAT_FNS
 
 #undef __HPP_HEADER_FN
 #undef __HPP_WIDTH_FN
@@ -588,6 +791,9 @@ struct perf_hpp_list perf_hpp_list = {
 #undef __HPP_ENTRY_ACC_PERCENT_FN
 #undef __HPP_ENTRY_RAW_FN
 #undef __HPP_ENTRY_AVERAGE_FN
+#undef __HPP_COLOR_MEM_STAT_FN
+#undef __HPP_ENTRY_MEM_STAT_FN
+
 #undef __HPP_SORT_FN
 #undef __HPP_SORT_ACC_FN
 #undef __HPP_SORT_RAW_FN
@@ -696,12 +902,14 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
 static void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
 	list_del_init(&format->list);
+	list_del_init(&format->sort_list);
 	fmt_free(format);
 }
 
-void perf_hpp__cancel_cumulate(void)
+void perf_hpp__cancel_cumulate(struct evlist *evlist)
 {
 	struct perf_hpp_fmt *fmt, *acc, *ovh, *acc_lat, *tmp;
+	struct evsel *evsel;
 
 	if (is_strict_order(field_order))
 		return;
@@ -719,11 +927,29 @@ void perf_hpp__cancel_cumulate(void)
 		if (fmt_equal(ovh, fmt))
 			fmt->name = "Overhead";
 	}
+
+	evlist__for_each_entry(evlist, evsel) {
+		struct hists *hists = evsel__hists(evsel);
+		struct perf_hpp_list_node *node;
+
+		list_for_each_entry(node, &hists->hpp_formats, list) {
+			perf_hpp_list__for_each_format_safe(&node->hpp, fmt, tmp) {
+				if (fmt_equal(acc, fmt) || fmt_equal(acc_lat, fmt)) {
+					perf_hpp__column_unregister(fmt);
+					continue;
+				}
+
+				if (fmt_equal(ovh, fmt))
+					fmt->name = "Overhead";
+			}
+		}
+	}
 }
 
-void perf_hpp__cancel_latency(void)
+void perf_hpp__cancel_latency(struct evlist *evlist)
 {
 	struct perf_hpp_fmt *fmt, *lat, *acc, *tmp;
+	struct evsel *evsel;
 
 	if (is_strict_order(field_order))
 		return;
@@ -737,6 +963,18 @@ void perf_hpp__cancel_latency(void)
 		if (fmt_equal(lat, fmt) || fmt_equal(acc, fmt))
 			perf_hpp__column_unregister(fmt);
 	}
+
+	evlist__for_each_entry(evlist, evsel) {
+		struct hists *hists = evsel__hists(evsel);
+		struct perf_hpp_list_node *node;
+
+		list_for_each_entry(node, &hists->hpp_formats, list) {
+			perf_hpp_list__for_each_format_safe(&node->hpp, fmt, tmp) {
+				if (fmt_equal(lat, fmt) || fmt_equal(acc, fmt))
+					perf_hpp__column_unregister(fmt);
+			}
+		}
+	}
 }
 
 void perf_hpp__setup_output_field(struct perf_hpp_list *list)
@@ -787,18 +1025,12 @@ void perf_hpp__reset_output_field(struct perf_hpp_list *list)
 	struct perf_hpp_fmt *fmt, *tmp;
 
 	/* reset output fields */
-	perf_hpp_list__for_each_format_safe(list, fmt, tmp) {
-		list_del_init(&fmt->list);
-		list_del_init(&fmt->sort_list);
-		fmt_free(fmt);
-	}
+	perf_hpp_list__for_each_format_safe(list, fmt, tmp)
+		perf_hpp__column_unregister(fmt);
 
 	/* reset sort keys */
-	perf_hpp_list__for_each_sort_list_safe(list, fmt, tmp) {
-		list_del_init(&fmt->list);
-		list_del_init(&fmt->sort_list);
-		fmt_free(fmt);
-	}
+	perf_hpp_list__for_each_sort_list_safe(list, fmt, tmp)
+		perf_hpp__column_unregister(fmt);
 }
 
 /*
@@ -886,6 +1118,14 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 		fmt->len = 8;
 		break;
 
+	case PERF_HPP__MEM_STAT_OP:
+	case PERF_HPP__MEM_STAT_CACHE:
+	case PERF_HPP__MEM_STAT_MEMORY:
+	case PERF_HPP__MEM_STAT_SNOOP:
+	case PERF_HPP__MEM_STAT_DTLB:
+		fmt->len = MEM_STAT_LEN * MEM_STAT_PRINT_LEN;
+		break;
+
 	default:
 		break;
 	}
@@ -991,3 +1231,42 @@ int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
 
 	return 0;
 }
+
+int perf_hpp__alloc_mem_stats(struct perf_hpp_list *list, struct evlist *evlist)
+{
+	struct perf_hpp_fmt *fmt;
+	struct evsel *evsel;
+	enum mem_stat_type mst[16];
+	unsigned nr_mem_stats = 0;
+
+	perf_hpp_list__for_each_format(list, fmt) {
+		if (!perf_hpp__is_mem_stat_entry(fmt))
+			continue;
+
+		assert(nr_mem_stats < ARRAY_SIZE(mst));
+		mst[nr_mem_stats++] = hpp__mem_stat_type(fmt);
+	}
+
+	if (nr_mem_stats == 0)
+		return 0;
+
+	list->nr_header_lines = 2;
+
+	evlist__for_each_entry(evlist, evsel) {
+		struct hists *hists = evsel__hists(evsel);
+
+		hists->mem_stat_types = calloc(nr_mem_stats,
+					       sizeof(*hists->mem_stat_types));
+		if (hists->mem_stat_types == NULL)
+			return -ENOMEM;
+
+		hists->mem_stat_total = calloc(nr_mem_stats,
+					       sizeof(*hists->mem_stat_total));
+		if (hists->mem_stat_total == NULL)
+			return -ENOMEM;
+
+		memcpy(hists->mem_stat_types, mst, nr_mem_stats * sizeof(*mst));
+		hists->nr_mem_stats = nr_mem_stats;
+	}
+	return 0;
+}
diff --git a/tools/perf/ui/keysyms.c b/tools/perf/ui/keysyms.c
new file mode 100644
index 000000000000..b64564b07f2f
--- /dev/null
+++ b/tools/perf/ui/keysyms.c
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include "keysyms.h"
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+
+const char *key_name(int key, char *bf, size_t size)
+{
+	if (isprint(key)) {
+		scnprintf(bf, size, "%c", key); 
+	} else if (key < 32) {
+		scnprintf(bf, size, "Ctrl+%c", key + '@'); 
+	} else {
+		const char *name = NULL;
+
+		switch (key) {
+		case K_DOWN:	name = "Down";	    break;
+		case K_END:	name = "End";	    break;
+		case K_ENTER:	name = "Enter";	    break;
+		case K_ESC:	name = "ESC";	    break;
+		case K_F1:	name = "F1";	    break;
+		case K_HOME:	name = "Home";	    break;
+		case K_LEFT:	name = "Left";	    break;
+		case K_PGDN:	name = "PgDown";    break;
+		case K_PGUP:	name = "PgUp";	    break;
+		case K_RIGHT:	name = "Right";	    break;
+		case K_TAB:	name = "Tab";	    break;
+		case K_UNTAB:	name = "Untab";	    break;
+		case K_UP:	name = "Up";	    break;
+		case K_BKSPC:	name = "Backspace"; break;
+		case K_DEL:	name = "Del";	    break;
+		default:
+			if (key >= SL_KEY_F(1) && key <= SL_KEY_F(63))
+				scnprintf(bf, size, "F%d", key - SL_KEY_F(0));
+			else
+				scnprintf(bf, size, "Unknown (%d)", key);
+		}
+
+		if (name)
+			scnprintf(bf, size, "%s", name);
+	}
+
+	return bf;
+}
diff --git a/tools/perf/ui/keysyms.h b/tools/perf/ui/keysyms.h
index 04cc4e5c031f..969060edc362 100644
--- a/tools/perf/ui/keysyms.h
+++ b/tools/perf/ui/keysyms.h
@@ -27,4 +27,6 @@
 #define K_SWITCH_INPUT_DATA -4
 #define K_RELOAD -5
 
+const char *key_name(int key, char *bf, size_t size);
+
 #endif /* _PERF_KEYSYMS_H_ */
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 7ac4b98e28bc..8c4c8925df2c 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -643,45 +643,58 @@ static int hists__fprintf_hierarchy_headers(struct hists *hists,
 	unsigned header_width = 0;
 	struct perf_hpp_fmt *fmt;
 	struct perf_hpp_list_node *fmt_node;
+	struct perf_hpp_list *hpp_list = hists->hpp_list;
 	const char *sep = symbol_conf.field_sep;
 
 	indent = hists->nr_hpp_node;
 
-	/* preserve max indent depth for column headers */
-	print_hierarchy_indent(sep, indent, " ", fp);
-
 	/* the first hpp_list_node is for overhead columns */
 	fmt_node = list_first_entry(&hists->hpp_formats,
 				    struct perf_hpp_list_node, list);
 
-	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
-		fmt->header(fmt, hpp, hists, 0, NULL);
-		fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
-	}
+	for (int line = 0; line < hpp_list->nr_header_lines; line++) {
+		/* first # is displayed one level up */
+		if (line)
+			fprintf(fp, "# ");
 
-	/* combine sort headers with ' / ' */
-	first_node = true;
-	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
-		if (!first_node)
-			header_width += fprintf(fp, " / ");
-		first_node = false;
+		/* preserve max indent depth for column headers */
+		print_hierarchy_indent(sep, indent, " ", fp);
 
-		first_col = true;
 		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
-			if (perf_hpp__should_skip(fmt, hists))
-				continue;
+			fmt->header(fmt, hpp, hists, line, NULL);
+			fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
+		}
 
-			if (!first_col)
-				header_width += fprintf(fp, "+");
-			first_col = false;
+		if (line < hpp_list->nr_header_lines - 1)
+			goto next_line;
+
+		/* combine sort headers with ' / ' */
+		first_node = true;
+		list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+			if (!first_node)
+				header_width += fprintf(fp, " / ");
+			first_node = false;
 
-			fmt->header(fmt, hpp, hists, 0, NULL);
+			first_col = true;
+			perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+				if (perf_hpp__should_skip(fmt, hists))
+					continue;
 
-			header_width += fprintf(fp, "%s", strim(hpp->buf));
+				if (!first_col)
+					header_width += fprintf(fp, "+");
+				first_col = false;
+
+				fmt->header(fmt, hpp, hists, line, NULL);
+
+				header_width += fprintf(fp, "%s", strim(hpp->buf));
+			}
 		}
+
+next_line:
+		fprintf(fp, "\n");
 	}
 
-	fprintf(fp, "\n# ");
+	fprintf(fp, "# ");
 
 	/* preserve max indent depth for initial dots */
 	print_hierarchy_indent(sep, indent, dots, fp);
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 946bce6628f3..7910d908c814 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -161,7 +161,7 @@ perf-util-y += clockid.o
 perf-util-y += list_sort.o
 perf-util-y += mutex.o
 perf-util-y += sharded_mutex.o
-perf-util-$(CONFIG_X86_64) += intel-tpebs.o
+perf-util-y += intel-tpebs.o
 
 perf-util-$(CONFIG_LIBBPF) += bpf_map.o
 perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o
@@ -173,6 +173,10 @@ perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-flex.o
 perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-bison.o
 perf-util-$(CONFIG_PERF_BPF_SKEL) += btf.o
 
+ifeq ($(CONFIG_TRACE),y)
+  perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-trace-summary.o
+endif
+
 ifeq ($(CONFIG_LIBTRACEEVENT),y)
   perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o
 endif
@@ -237,9 +241,12 @@ perf-util-y += cap.o
 perf-util-$(CONFIG_CXX_DEMANGLE) += demangle-cxx.o
 perf-util-y += demangle-ocaml.o
 perf-util-y += demangle-java.o
-perf-util-y += demangle-rust.o
+perf-util-y += demangle-rust-v0.o
 perf-util-$(CONFIG_LIBLLVM) += llvm-c-helpers.o
 
+CFLAGS_demangle-rust-v0.o += -Wno-shadow -Wno-declaration-after-statement \
+    -Wno-switch-default -Wno-switch-enum -Wno-missing-field-initializers
+
 ifdef CONFIG_JITDUMP
 perf-util-$(CONFIG_LIBELF) += jitdump.o
 perf-util-$(CONFIG_LIBELF) += genelf.o
diff --git a/tools/perf/util/amd-sample-raw.c b/tools/perf/util/amd-sample-raw.c
index 456ce64ad822..4b540e6fb42d 100644
--- a/tools/perf/util/amd-sample-raw.c
+++ b/tools/perf/util/amd-sample-raw.c
@@ -19,6 +19,8 @@
 
 static u32 cpu_family, cpu_model, ibs_fetch_type, ibs_op_type;
 static bool zen4_ibs_extensions;
+static bool ldlat_cap;
+static bool dtlb_pgsize_cap;
 
 static void pr_ibs_fetch_ctl(union ibs_fetch_ctl reg)
 {
@@ -78,14 +80,20 @@ static void pr_ic_ibs_extd_ctl(union ic_ibs_extd_ctl reg)
 static void pr_ibs_op_ctl(union ibs_op_ctl reg)
 {
 	char l3_miss_only[sizeof(" L3MissOnly _")] = "";
+	char ldlat[sizeof(" LdLatThrsh __ LdLatEn _")] = "";
 
 	if (zen4_ibs_extensions)
 		snprintf(l3_miss_only, sizeof(l3_miss_only), " L3MissOnly %d", reg.l3_miss_only);
 
-	printf("ibs_op_ctl:\t%016llx MaxCnt %9d%s En %d Val %d CntCtl %d=%s CurCnt %9d\n",
+	if (ldlat_cap) {
+		snprintf(ldlat, sizeof(ldlat), " LdLatThrsh %2d LdLatEn %d",
+			 reg.ldlat_thrsh, reg.ldlat_en);
+	}
+
+	printf("ibs_op_ctl:\t%016llx MaxCnt %9d%s En %d Val %d CntCtl %d=%s CurCnt %9d%s\n",
 		reg.val, ((reg.opmaxcnt_ext << 16) | reg.opmaxcnt) << 4, l3_miss_only,
 		reg.op_en, reg.op_val, reg.cnt_ctl,
-		reg.cnt_ctl ? "uOps" : "cycles", reg.opcurcnt);
+		reg.cnt_ctl ? "uOps" : "cycles", reg.opcurcnt, ldlat);
 }
 
 static void pr_ibs_op_data(union ibs_op_data reg)
@@ -154,9 +162,20 @@ static void pr_ibs_op_data2(union ibs_op_data2 reg)
 
 static void pr_ibs_op_data3(union ibs_op_data3 reg)
 {
-	char l2_miss_str[sizeof(" L2Miss _")] = "";
-	char op_mem_width_str[sizeof(" OpMemWidth _____ bytes")] = "";
+	static const char * const dc_page_sizes[] = {
+		"  4K",
+		"  2M",
+		"  1G",
+		"  ??",
+	};
 	char op_dc_miss_open_mem_reqs_str[sizeof(" OpDcMissOpenMemReqs __")] = "";
+	char dc_l1_l2tlb_miss_str[sizeof(" DcL1TlbMiss _ DcL2TlbMiss _")] = "";
+	char dc_l1tlb_hit_str[sizeof(" DcL1TlbHit2M _ DcL1TlbHit1G _")] = "";
+	char op_mem_width_str[sizeof(" OpMemWidth _____ bytes")] = "";
+	char dc_l2tlb_hit_2m_str[sizeof(" DcL2TlbHit2M _")] = "";
+	char dc_l2tlb_hit_1g_str[sizeof(" DcL2TlbHit1G _")] = "";
+	char dc_page_size_str[sizeof(" DcPageSize ____")] = "";
+	char l2_miss_str[sizeof(" L2Miss _")] = "";
 
 	/*
 	 * Erratum #1293
@@ -172,16 +191,40 @@ static void pr_ibs_op_data3(union ibs_op_data3 reg)
 		snprintf(op_mem_width_str, sizeof(op_mem_width_str),
 			 " OpMemWidth %2d bytes", 1 << (reg.op_mem_width - 1));
 
-	printf("ibs_op_data3:\t%016llx LdOp %d StOp %d DcL1TlbMiss %d DcL2TlbMiss %d "
-		"DcL1TlbHit2M %d DcL1TlbHit1G %d DcL2TlbHit2M %d DcMiss %d DcMisAcc %d "
-		"DcWcMemAcc %d DcUcMemAcc %d DcLockedOp %d DcMissNoMabAlloc %d DcLinAddrValid %d "
-		"DcPhyAddrValid %d DcL2TlbHit1G %d%s SwPf %d%s%s DcMissLat %5d TlbRefillLat %5d\n",
-		reg.val, reg.ld_op, reg.st_op, reg.dc_l1tlb_miss, reg.dc_l2tlb_miss,
-		reg.dc_l1tlb_hit_2m, reg.dc_l1tlb_hit_1g, reg.dc_l2tlb_hit_2m, reg.dc_miss,
-		reg.dc_mis_acc, reg.dc_wc_mem_acc, reg.dc_uc_mem_acc, reg.dc_locked_op,
-		reg.dc_miss_no_mab_alloc, reg.dc_lin_addr_valid, reg.dc_phy_addr_valid,
-		reg.dc_l2_tlb_hit_1g, l2_miss_str, reg.sw_pf, op_mem_width_str,
-		op_dc_miss_open_mem_reqs_str, reg.dc_miss_lat, reg.tlb_refill_lat);
+	if (dtlb_pgsize_cap) {
+		if (reg.dc_phy_addr_valid) {
+			int idx = (reg.dc_l1tlb_hit_1g << 1) | reg.dc_l1tlb_hit_2m;
+
+			snprintf(dc_l1_l2tlb_miss_str, sizeof(dc_l1_l2tlb_miss_str),
+				 " DcL1TlbMiss %d DcL2TlbMiss %d",
+				 reg.dc_l1tlb_miss, reg.dc_l2tlb_miss);
+			snprintf(dc_page_size_str, sizeof(dc_page_size_str),
+				 " DcPageSize %4s", dc_page_sizes[idx]);
+		}
+	} else {
+		snprintf(dc_l1_l2tlb_miss_str, sizeof(dc_l1_l2tlb_miss_str),
+			 " DcL1TlbMiss %d DcL2TlbMiss %d",
+			 reg.dc_l1tlb_miss, reg.dc_l2tlb_miss);
+		snprintf(dc_l1tlb_hit_str, sizeof(dc_l1tlb_hit_str),
+			 " DcL1TlbHit2M %d DcL1TlbHit1G %d",
+			 reg.dc_l1tlb_hit_2m, reg.dc_l1tlb_hit_1g);
+		snprintf(dc_l2tlb_hit_2m_str, sizeof(dc_l2tlb_hit_2m_str),
+			 " DcL2TlbHit2M %d", reg.dc_l2tlb_hit_2m);
+		snprintf(dc_l2tlb_hit_1g_str, sizeof(dc_l2tlb_hit_1g_str),
+			 " DcL2TlbHit1G %d", reg.dc_l2_tlb_hit_1g);
+	}
+
+	printf("ibs_op_data3:\t%016llx LdOp %d StOp %d%s%s%s DcMiss %d DcMisAcc %d "
+		"DcWcMemAcc %d DcUcMemAcc %d DcLockedOp %d DcMissNoMabAlloc %d "
+		"DcLinAddrValid %d DcPhyAddrValid %d%s%s SwPf %d%s%s "
+		"DcMissLat %5d TlbRefillLat %5d\n",
+		reg.val, reg.ld_op, reg.st_op, dc_l1_l2tlb_miss_str,
+		dtlb_pgsize_cap ? dc_page_size_str : dc_l1tlb_hit_str,
+		dc_l2tlb_hit_2m_str, reg.dc_miss, reg.dc_mis_acc, reg.dc_wc_mem_acc,
+		reg.dc_uc_mem_acc, reg.dc_locked_op, reg.dc_miss_no_mab_alloc,
+		reg.dc_lin_addr_valid, reg.dc_phy_addr_valid, dc_l2tlb_hit_1g_str,
+		l2_miss_str, reg.sw_pf, op_mem_width_str, op_dc_miss_open_mem_reqs_str,
+		reg.dc_miss_lat, reg.tlb_refill_lat);
 }
 
 /*
@@ -331,6 +374,12 @@ bool evlist__has_amd_ibs(struct evlist *evlist)
 	if (perf_env__find_pmu_cap(env, "ibs_op", "zen4_ibs_extensions"))
 		zen4_ibs_extensions = 1;
 
+	if (perf_env__find_pmu_cap(env, "ibs_op", "ldlat"))
+		ldlat_cap = 1;
+
+	if (perf_env__find_pmu_cap(env, "ibs_op", "dtlb_pgsize"))
+		dtlb_pgsize_cap = 1;
+
 	if (ibs_fetch_type || ibs_op_type) {
 		if (!cpu_family)
 			parse_cpuid(env);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 1e59b9e5339d..264a212b47df 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2280,6 +2280,7 @@ void annotation_options__init(void)
 	opt->annotate_src = true;
 	opt->offset_level = ANNOTATION__OFFSET_JUMP_TARGETS;
 	opt->percent_type = PERCENT_PERIOD_LOCAL;
+	opt->hide_src_code_on_title = true;
 }
 
 void annotation_options__exit(void)
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 0e6e3f60a897..bbb89b32f398 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -44,6 +44,7 @@ enum perf_disassembler {
 
 struct annotation_options {
 	bool hide_src_code,
+	     hide_src_code_on_title,
 	     use_offset,
 	     jump_arrows,
 	     print_lines,
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
index 5d232188643b..881d9f29c138 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
@@ -82,6 +82,23 @@ enum arm_spe_ampereone_data_source {
 	ARM_SPE_AMPEREONE_L2D                           = 0x9,
 };
 
+enum arm_spe_hisi_hip_data_source {
+	ARM_SPE_HISI_HIP_PEER_CPU		= 0,
+	ARM_SPE_HISI_HIP_PEER_CPU_HITM		= 1,
+	ARM_SPE_HISI_HIP_L3			= 2,
+	ARM_SPE_HISI_HIP_L3_HITM		= 3,
+	ARM_SPE_HISI_HIP_PEER_CLUSTER		= 4,
+	ARM_SPE_HISI_HIP_PEER_CLUSTER_HITM	= 5,
+	ARM_SPE_HISI_HIP_REMOTE_SOCKET		= 6,
+	ARM_SPE_HISI_HIP_REMOTE_SOCKET_HITM	= 7,
+	ARM_SPE_HISI_HIP_LOCAL_MEM		= 8,
+	ARM_SPE_HISI_HIP_REMOTE_MEM		= 9,
+	ARM_SPE_HISI_HIP_NC_DEV			= 13,
+	ARM_SPE_HISI_HIP_L2			= 16,
+	ARM_SPE_HISI_HIP_L2_HITM		= 17,
+	ARM_SPE_HISI_HIP_L1			= 18,
+};
+
 struct arm_spe_record {
 	enum arm_spe_sample_type type;
 	int err;
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 2a9775649cc2..d46e0cccac99 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -571,6 +571,11 @@ static const struct midr_range ampereone_ds_encoding_cpus[] = {
 	{},
 };
 
+static const struct midr_range hisi_hip_ds_encoding_cpus[] = {
+	MIDR_ALL_VERSIONS(MIDR_HISI_HIP12),
+	{},
+};
+
 static void arm_spe__sample_flags(struct arm_spe_queue *speq)
 {
 	const struct arm_spe_record *record = &speq->decoder->record;
@@ -718,9 +723,100 @@ static void arm_spe__synth_data_source_ampereone(const struct arm_spe_record *re
 	arm_spe__synth_data_source_common(&common_record, data_src);
 }
 
+static void arm_spe__synth_data_source_hisi_hip(const struct arm_spe_record *record,
+						union perf_mem_data_src *data_src)
+{
+	/* Use common synthesis method to handle store operations */
+	if (record->op & ARM_SPE_OP_ST) {
+		arm_spe__synth_data_source_common(record, data_src);
+		return;
+	}
+
+	switch (record->source) {
+	case ARM_SPE_HISI_HIP_PEER_CPU:
+		data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
+		data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
+		break;
+	case ARM_SPE_HISI_HIP_PEER_CPU_HITM:
+		data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
+		data_src->mem_snoop = PERF_MEM_SNOOP_HITM;
+		data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
+		break;
+	case ARM_SPE_HISI_HIP_L3:
+		data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3;
+		data_src->mem_snoop = PERF_MEM_SNOOP_HIT;
+		break;
+	case ARM_SPE_HISI_HIP_L3_HITM:
+		data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3;
+		data_src->mem_snoop = PERF_MEM_SNOOP_HITM;
+		break;
+	case ARM_SPE_HISI_HIP_PEER_CLUSTER:
+		data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1 | PERF_MEM_LVL_HIT;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3;
+		data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
+		break;
+	case ARM_SPE_HISI_HIP_PEER_CLUSTER_HITM:
+		data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1 | PERF_MEM_LVL_HIT;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3;
+		data_src->mem_snoop = PERF_MEM_SNOOP_HITM;
+		data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
+		break;
+	case ARM_SPE_HISI_HIP_REMOTE_SOCKET:
+		data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_ANY_CACHE;
+		data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
+		data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
+		break;
+	case ARM_SPE_HISI_HIP_REMOTE_SOCKET_HITM:
+		data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_ANY_CACHE;
+		data_src->mem_snoop = PERF_MEM_SNOOP_HITM;
+		data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
+		data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
+		break;
+	case ARM_SPE_HISI_HIP_LOCAL_MEM:
+		data_src->mem_lvl = PERF_MEM_LVL_LOC_RAM | PERF_MEM_LVL_HIT;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_RAM;
+		data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
+		break;
+	case ARM_SPE_HISI_HIP_REMOTE_MEM:
+		data_src->mem_lvl = PERF_MEM_LVL_REM_RAM1 | PERF_MEM_LVL_HIT;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_RAM;
+		data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
+		break;
+	case ARM_SPE_HISI_HIP_NC_DEV:
+		data_src->mem_lvl = PERF_MEM_LVL_IO | PERF_MEM_LVL_HIT;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_IO;
+		data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
+		break;
+	case ARM_SPE_HISI_HIP_L2:
+		data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
+		data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
+		break;
+	case ARM_SPE_HISI_HIP_L2_HITM:
+		data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
+		data_src->mem_snoop = PERF_MEM_SNOOP_HITM;
+		break;
+	case ARM_SPE_HISI_HIP_L1:
+		data_src->mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_L1;
+		data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
+		break;
+	default:
+		break;
+	}
+}
+
 static const struct data_source_handle data_source_handles[] = {
 	DS(common_ds_encoding_cpus, data_source_common),
 	DS(ampereone_ds_encoding_cpus, data_source_ampereone),
+	DS(hisi_hip_ds_encoding_cpus, data_source_hisi_hip),
 };
 
 static void arm_spe__synth_memory_level(const struct arm_spe_record *record,
diff --git a/tools/perf/util/bpf-trace-summary.c b/tools/perf/util/bpf-trace-summary.c
new file mode 100644
index 000000000000..69fb165da206
--- /dev/null
+++ b/tools/perf/util/bpf-trace-summary.c
@@ -0,0 +1,458 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <inttypes.h>
+#include <math.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "dwarf-regs.h" /* for EM_HOST */
+#include "syscalltbl.h"
+#include "util/cgroup.h"
+#include "util/hashmap.h"
+#include "util/trace.h"
+#include "util/util.h"
+#include <bpf/bpf.h>
+#include <linux/rbtree.h>
+#include <linux/time64.h>
+#include <tools/libc_compat.h> /* reallocarray */
+
+#include "bpf_skel/syscall_summary.h"
+#include "bpf_skel/syscall_summary.skel.h"
+
+
+static struct syscall_summary_bpf *skel;
+static struct rb_root cgroups = RB_ROOT;
+
+int trace_prepare_bpf_summary(enum trace_summary_mode mode)
+{
+	skel = syscall_summary_bpf__open();
+	if (skel == NULL) {
+		fprintf(stderr, "failed to open syscall summary bpf skeleton\n");
+		return -1;
+	}
+
+	if (mode == SUMMARY__BY_THREAD)
+		skel->rodata->aggr_mode = SYSCALL_AGGR_THREAD;
+	else if (mode == SUMMARY__BY_CGROUP)
+		skel->rodata->aggr_mode = SYSCALL_AGGR_CGROUP;
+	else
+		skel->rodata->aggr_mode = SYSCALL_AGGR_CPU;
+
+	if (cgroup_is_v2("perf_event") > 0)
+		skel->rodata->use_cgroup_v2 = 1;
+
+	if (syscall_summary_bpf__load(skel) < 0) {
+		fprintf(stderr, "failed to load syscall summary bpf skeleton\n");
+		return -1;
+	}
+
+	if (syscall_summary_bpf__attach(skel) < 0) {
+		fprintf(stderr, "failed to attach syscall summary bpf skeleton\n");
+		return -1;
+	}
+
+	if (mode == SUMMARY__BY_CGROUP)
+		read_all_cgroups(&cgroups);
+
+	return 0;
+}
+
+void trace_start_bpf_summary(void)
+{
+	skel->bss->enabled = 1;
+}
+
+void trace_end_bpf_summary(void)
+{
+	skel->bss->enabled = 0;
+}
+
+struct syscall_node {
+	int syscall_nr;
+	struct syscall_stats stats;
+};
+
+static double rel_stddev(struct syscall_stats *stat)
+{
+	double variance, average;
+
+	if (stat->count < 2)
+		return 0;
+
+	average = (double)stat->total_time / stat->count;
+
+	variance = stat->squared_sum;
+	variance -= (stat->total_time * stat->total_time) / stat->count;
+	variance /= stat->count - 1;
+
+	return 100 * sqrt(variance / stat->count) / average;
+}
+
+/*
+ * The syscall_data is to maintain syscall stats ordered by total time.
+ * It supports different summary modes like per-thread or global.
+ *
+ * For per-thread stats, it uses two-level data strurcture -
+ * syscall_data is keyed by TID and has an array of nodes which
+ * represents each syscall for the thread.
+ *
+ * For global stats, it's still two-level technically but we don't need
+ * per-cpu analysis so it's keyed by the syscall number to combine stats
+ * from different CPUs.  And syscall_data always has a syscall_node so
+ * it can effectively work as flat hierarchy.
+ *
+ * For per-cgroup stats, it uses two-level data structure like thread
+ * syscall_data is keyed by CGROUP and has an array of node which
+ * represents each syscall for the cgroup.
+ */
+struct syscall_data {
+	u64 key; /* tid if AGGR_THREAD, syscall-nr if AGGR_CPU, cgroup if AGGR_CGROUP */
+	int nr_events;
+	int nr_nodes;
+	u64 total_time;
+	struct syscall_node *nodes;
+};
+
+static int datacmp(const void *a, const void *b)
+{
+	const struct syscall_data * const *sa = a;
+	const struct syscall_data * const *sb = b;
+
+	return (*sa)->total_time > (*sb)->total_time ? -1 : 1;
+}
+
+static int nodecmp(const void *a, const void *b)
+{
+	const struct syscall_node *na = a;
+	const struct syscall_node *nb = b;
+
+	return na->stats.total_time > nb->stats.total_time ? -1 : 1;
+}
+
+static size_t sc_node_hash(long key, void *ctx __maybe_unused)
+{
+	return key;
+}
+
+static bool sc_node_equal(long key1, long key2, void *ctx __maybe_unused)
+{
+	return key1 == key2;
+}
+
+static int print_common_stats(struct syscall_data *data, FILE *fp)
+{
+	int printed = 0;
+
+	for (int i = 0; i < data->nr_nodes; i++) {
+		struct syscall_node *node = &data->nodes[i];
+		struct syscall_stats *stat = &node->stats;
+		double total = (double)(stat->total_time) / NSEC_PER_MSEC;
+		double min = (double)(stat->min_time) / NSEC_PER_MSEC;
+		double max = (double)(stat->max_time) / NSEC_PER_MSEC;
+		double avg = total / stat->count;
+		const char *name;
+
+		/* TODO: support other ABIs */
+		name = syscalltbl__name(EM_HOST, node->syscall_nr);
+		if (name)
+			printed += fprintf(fp, "   %-15s", name);
+		else
+			printed += fprintf(fp, "   syscall:%-7d", node->syscall_nr);
+
+		printed += fprintf(fp, " %8u %6u %9.3f %9.3f %9.3f %9.3f %9.2f%%\n",
+				   stat->count, stat->error, total, min, avg, max,
+				   rel_stddev(stat));
+	}
+	return printed;
+}
+
+static int update_thread_stats(struct hashmap *hash, struct syscall_key *map_key,
+			       struct syscall_stats *map_data)
+{
+	struct syscall_data *data;
+	struct syscall_node *nodes;
+
+	if (!hashmap__find(hash, map_key->cpu_or_tid, &data)) {
+		data = zalloc(sizeof(*data));
+		if (data == NULL)
+			return -ENOMEM;
+
+		data->key = map_key->cpu_or_tid;
+		if (hashmap__add(hash, data->key, data) < 0) {
+			free(data);
+			return -ENOMEM;
+		}
+	}
+
+	/* update thread total stats */
+	data->nr_events += map_data->count;
+	data->total_time += map_data->total_time;
+
+	nodes = reallocarray(data->nodes, data->nr_nodes + 1, sizeof(*nodes));
+	if (nodes == NULL)
+		return -ENOMEM;
+
+	data->nodes = nodes;
+	nodes = &data->nodes[data->nr_nodes++];
+	nodes->syscall_nr = map_key->nr;
+
+	/* each thread has an entry for each syscall, just use the stat */
+	memcpy(&nodes->stats, map_data, sizeof(*map_data));
+	return 0;
+}
+
+static int print_thread_stat(struct syscall_data *data, FILE *fp)
+{
+	int printed = 0;
+
+	qsort(data->nodes, data->nr_nodes, sizeof(*data->nodes), nodecmp);
+
+	printed += fprintf(fp, " thread (%d), ", (int)data->key);
+	printed += fprintf(fp, "%d events\n\n", data->nr_events);
+
+	printed += fprintf(fp, "   syscall            calls  errors  total       min       avg       max       stddev\n");
+	printed += fprintf(fp, "                                     (msec)    (msec)    (msec)    (msec)        (%%)\n");
+	printed += fprintf(fp, "   --------------- --------  ------ -------- --------- --------- ---------     ------\n");
+
+	printed += print_common_stats(data, fp);
+	printed += fprintf(fp, "\n\n");
+
+	return printed;
+}
+
+static int print_thread_stats(struct syscall_data **data, int nr_data, FILE *fp)
+{
+	int printed = 0;
+
+	for (int i = 0; i < nr_data; i++)
+		printed += print_thread_stat(data[i], fp);
+
+	return printed;
+}
+
+static int update_total_stats(struct hashmap *hash, struct syscall_key *map_key,
+			      struct syscall_stats *map_data)
+{
+	struct syscall_data *data;
+	struct syscall_stats *stat;
+
+	if (!hashmap__find(hash, map_key->nr, &data)) {
+		data = zalloc(sizeof(*data));
+		if (data == NULL)
+			return -ENOMEM;
+
+		data->nodes = zalloc(sizeof(*data->nodes));
+		if (data->nodes == NULL) {
+			free(data);
+			return -ENOMEM;
+		}
+
+		data->nr_nodes = 1;
+		data->key = map_key->nr;
+		data->nodes->syscall_nr = data->key;
+
+		if (hashmap__add(hash, data->key, data) < 0) {
+			free(data->nodes);
+			free(data);
+			return -ENOMEM;
+		}
+	}
+
+	/* update total stats for this syscall */
+	data->nr_events += map_data->count;
+	data->total_time += map_data->total_time;
+
+	/* This is sum of the same syscall from different CPUs */
+	stat = &data->nodes->stats;
+
+	stat->total_time += map_data->total_time;
+	stat->squared_sum += map_data->squared_sum;
+	stat->count += map_data->count;
+	stat->error += map_data->error;
+
+	if (stat->max_time < map_data->max_time)
+		stat->max_time = map_data->max_time;
+	if (stat->min_time > map_data->min_time || stat->min_time == 0)
+		stat->min_time = map_data->min_time;
+
+	return 0;
+}
+
+static int print_total_stats(struct syscall_data **data, int nr_data, FILE *fp)
+{
+	int printed = 0;
+	int nr_events = 0;
+
+	for (int i = 0; i < nr_data; i++)
+		nr_events += data[i]->nr_events;
+
+	printed += fprintf(fp, " total, %d events\n\n", nr_events);
+
+	printed += fprintf(fp, "   syscall            calls  errors  total       min       avg       max       stddev\n");
+	printed += fprintf(fp, "                                     (msec)    (msec)    (msec)    (msec)        (%%)\n");
+	printed += fprintf(fp, "   --------------- --------  ------ -------- --------- --------- ---------     ------\n");
+
+	for (int i = 0; i < nr_data; i++)
+		printed += print_common_stats(data[i], fp);
+
+	printed += fprintf(fp, "\n\n");
+	return printed;
+}
+
+static int update_cgroup_stats(struct hashmap *hash, struct syscall_key *map_key,
+			       struct syscall_stats *map_data)
+{
+	struct syscall_data *data;
+	struct syscall_node *nodes;
+
+	if (!hashmap__find(hash, map_key->cgroup, &data)) {
+		data = zalloc(sizeof(*data));
+		if (data == NULL)
+			return -ENOMEM;
+
+		data->key = map_key->cgroup;
+		if (hashmap__add(hash, data->key, data) < 0) {
+			free(data);
+			return -ENOMEM;
+		}
+	}
+
+	/* update thread total stats */
+	data->nr_events += map_data->count;
+	data->total_time += map_data->total_time;
+
+	nodes = reallocarray(data->nodes, data->nr_nodes + 1, sizeof(*nodes));
+	if (nodes == NULL)
+		return -ENOMEM;
+
+	data->nodes = nodes;
+	nodes = &data->nodes[data->nr_nodes++];
+	nodes->syscall_nr = map_key->nr;
+
+	/* each thread has an entry for each syscall, just use the stat */
+	memcpy(&nodes->stats, map_data, sizeof(*map_data));
+	return 0;
+}
+
+static int print_cgroup_stat(struct syscall_data *data, FILE *fp)
+{
+	int printed = 0;
+	struct cgroup *cgrp = __cgroup__find(&cgroups, data->key);
+
+	qsort(data->nodes, data->nr_nodes, sizeof(*data->nodes), nodecmp);
+
+	if (cgrp)
+		printed += fprintf(fp, " cgroup %s,", cgrp->name);
+	else
+		printed += fprintf(fp, " cgroup id:%lu,", (unsigned long)data->key);
+
+	printed += fprintf(fp, " %d events\n\n", data->nr_events);
+
+	printed += fprintf(fp, "   syscall            calls  errors  total       min       avg       max       stddev\n");
+	printed += fprintf(fp, "                                     (msec)    (msec)    (msec)    (msec)        (%%)\n");
+	printed += fprintf(fp, "   --------------- --------  ------ -------- --------- --------- ---------     ------\n");
+
+	printed += print_common_stats(data, fp);
+	printed += fprintf(fp, "\n\n");
+
+	return printed;
+}
+
+static int print_cgroup_stats(struct syscall_data **data, int nr_data, FILE *fp)
+{
+	int printed = 0;
+
+	for (int i = 0; i < nr_data; i++)
+		printed += print_cgroup_stat(data[i], fp);
+
+	return printed;
+}
+
+int trace_print_bpf_summary(FILE *fp)
+{
+	struct bpf_map *map = skel->maps.syscall_stats_map;
+	struct syscall_key *prev_key, key;
+	struct syscall_data **data = NULL;
+	struct hashmap schash;
+	struct hashmap_entry *entry;
+	int nr_data = 0;
+	int printed = 0;
+	int i;
+	size_t bkt;
+
+	hashmap__init(&schash, sc_node_hash, sc_node_equal, /*ctx=*/NULL);
+
+	printed = fprintf(fp, "\n Summary of events:\n\n");
+
+	/* get stats from the bpf map */
+	prev_key = NULL;
+	while (!bpf_map__get_next_key(map, prev_key, &key, sizeof(key))) {
+		struct syscall_stats stat;
+
+		if (!bpf_map__lookup_elem(map, &key, sizeof(key), &stat, sizeof(stat), 0)) {
+			switch (skel->rodata->aggr_mode) {
+			case SYSCALL_AGGR_THREAD:
+				update_thread_stats(&schash, &key, &stat);
+				break;
+			case SYSCALL_AGGR_CPU:
+				update_total_stats(&schash, &key, &stat);
+				break;
+			case SYSCALL_AGGR_CGROUP:
+				update_cgroup_stats(&schash, &key, &stat);
+				break;
+			default:
+				break;
+			}
+		}
+
+		prev_key = &key;
+	}
+
+	nr_data = hashmap__size(&schash);
+	data = calloc(nr_data, sizeof(*data));
+	if (data == NULL)
+		goto out;
+
+	i = 0;
+	hashmap__for_each_entry(&schash, entry, bkt)
+		data[i++] = entry->pvalue;
+
+	qsort(data, nr_data, sizeof(*data), datacmp);
+
+	switch (skel->rodata->aggr_mode) {
+	case SYSCALL_AGGR_THREAD:
+		printed += print_thread_stats(data, nr_data, fp);
+		break;
+	case SYSCALL_AGGR_CPU:
+		printed += print_total_stats(data, nr_data, fp);
+		break;
+	case SYSCALL_AGGR_CGROUP:
+		printed += print_cgroup_stats(data, nr_data, fp);
+		break;
+	default:
+		break;
+	}
+
+	for (i = 0; i < nr_data && data; i++) {
+		free(data[i]->nodes);
+		free(data[i]);
+	}
+	free(data);
+
+out:
+	hashmap__clear(&schash);
+	return printed;
+}
+
+void trace_cleanup_bpf_summary(void)
+{
+	if (!RB_EMPTY_ROOT(&cgroups)) {
+		struct cgroup *cgrp, *tmp;
+
+		rbtree_postorder_for_each_entry_safe(cgrp, tmp, &cgroups, node)
+			cgroup__put(cgrp);
+
+		cgroups = RB_ROOT;
+	}
+
+	syscall_summary_bpf__destroy(skel);
+}
diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
index 5af8f6d1bc95..60b81d586323 100644
--- a/tools/perf/util/bpf_lock_contention.c
+++ b/tools/perf/util/bpf_lock_contention.c
@@ -12,6 +12,7 @@
 #include "util/lock-contention.h"
 #include <linux/zalloc.h>
 #include <linux/string.h>
+#include <api/fs/fs.h>
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
 #include <inttypes.h>
@@ -35,28 +36,26 @@ static bool slab_cache_equal(long key1, long key2, void *ctx __maybe_unused)
 
 static void check_slab_cache_iter(struct lock_contention *con)
 {
-	struct btf *btf = btf__load_vmlinux_btf();
 	s32 ret;
 
 	hashmap__init(&slab_hash, slab_cache_hash, slab_cache_equal, /*ctx=*/NULL);
 
-	if (btf == NULL) {
+	con->btf = btf__load_vmlinux_btf();
+	if (con->btf == NULL) {
 		pr_debug("BTF loading failed: %s\n", strerror(errno));
 		return;
 	}
 
-	ret = btf__find_by_name_kind(btf, "bpf_iter__kmem_cache", BTF_KIND_STRUCT);
+	ret = btf__find_by_name_kind(con->btf, "bpf_iter__kmem_cache", BTF_KIND_STRUCT);
 	if (ret < 0) {
 		bpf_program__set_autoload(skel->progs.slab_cache_iter, false);
 		pr_debug("slab cache iterator is not available: %d\n", ret);
-		goto out;
+		return;
 	}
 
 	has_slab_iter = true;
 
 	bpf_map__set_max_entries(skel->maps.slab_caches, con->map_nr_entries);
-out:
-	btf__free(btf);
 }
 
 static void run_slab_cache_iter(void)
@@ -109,6 +108,75 @@ static void exit_slab_cache_iter(void)
 	hashmap__clear(&slab_hash);
 }
 
+static void init_numa_data(struct lock_contention *con)
+{
+	struct symbol *sym;
+	struct map *kmap;
+	char *buf = NULL, *p;
+	size_t len;
+	long last = -1;
+	int ret;
+
+	/*
+	 * 'struct zone' is embedded in 'struct pglist_data' as an array.
+	 * As we may not have full information of the struct zone in the
+	 * (fake) vmlinux.h, let's get the actual size from BTF.
+	 */
+	ret = btf__find_by_name_kind(con->btf, "zone", BTF_KIND_STRUCT);
+	if (ret < 0) {
+		pr_debug("cannot get type of struct zone: %d\n", ret);
+		return;
+	}
+
+	ret = btf__resolve_size(con->btf, ret);
+	if (ret < 0) {
+		pr_debug("cannot get size of struct zone: %d\n", ret);
+		return;
+	}
+	skel->rodata->sizeof_zone = ret;
+
+	/* UMA system doesn't have 'node_data[]' - just use contig_page_data. */
+	sym = machine__find_kernel_symbol_by_name(con->machine,
+						  "contig_page_data",
+						  &kmap);
+	if (sym) {
+		skel->rodata->contig_page_data_addr = map__unmap_ip(kmap, sym->start);
+		map__put(kmap);
+		return;
+	}
+
+	/*
+	 * The 'node_data' is an array of pointers to struct pglist_data.
+	 * It needs to follow the pointer for each node in BPF to get the
+	 * address of struct pglist_data and its zones.
+	 */
+	sym = machine__find_kernel_symbol_by_name(con->machine,
+						  "node_data",
+						  &kmap);
+	if (sym == NULL)
+		return;
+
+	skel->rodata->node_data_addr = map__unmap_ip(kmap, sym->start);
+	map__put(kmap);
+
+	/* get the number of online nodes using the last node number + 1 */
+	ret = sysfs__read_str("devices/system/node/online", &buf, &len);
+	if (ret < 0) {
+		pr_debug("failed to read online node: %d\n", ret);
+		return;
+	}
+
+	p = buf;
+	while (p && *p) {
+		last = strtol(p, &p, 0);
+
+		if (p && (*p == ',' || *p == '-' || *p == '\n'))
+			p++;
+	}
+	skel->rodata->nr_nodes = last + 1;
+	free(buf);
+}
+
 int lock_contention_prepare(struct lock_contention *con)
 {
 	int i, fd;
@@ -193,6 +261,27 @@ int lock_contention_prepare(struct lock_contention *con)
 		skel->rodata->has_addr = 1;
 	}
 
+	/* resolve lock name in delays */
+	if (con->nr_delays) {
+		struct symbol *sym;
+		struct map *kmap;
+
+		for (i = 0; i < con->nr_delays; i++) {
+			sym = machine__find_kernel_symbol_by_name(con->machine,
+								  con->delays[i].sym,
+								  &kmap);
+			if (sym == NULL) {
+				pr_warning("ignore unknown symbol: %s\n",
+					   con->delays[i].sym);
+				continue;
+			}
+
+			con->delays[i].addr = map__unmap_ip(kmap, sym->start);
+		}
+		skel->rodata->lock_delay = 1;
+		bpf_map__set_max_entries(skel->maps.lock_delays, con->nr_delays);
+	}
+
 	bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
 	bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
 	bpf_map__set_max_entries(skel->maps.type_filter, ntypes);
@@ -218,6 +307,8 @@ int lock_contention_prepare(struct lock_contention *con)
 
 	bpf_map__set_max_entries(skel->maps.slab_filter, nslabs);
 
+	init_numa_data(con);
+
 	if (lock_contention_bpf__load(skel) < 0) {
 		pr_err("Failed to load lock-contention BPF skeleton\n");
 		return -1;
@@ -282,6 +373,13 @@ int lock_contention_prepare(struct lock_contention *con)
 			bpf_map_update_elem(fd, &con->filters->cgrps[i], &val, BPF_ANY);
 	}
 
+	if (con->nr_delays) {
+		fd = bpf_map__fd(skel->maps.lock_delays);
+
+		for (i = 0; i < con->nr_delays; i++)
+			bpf_map_update_elem(fd, &con->delays[i].addr, &con->delays[i].time, BPF_ANY);
+	}
+
 	if (con->aggr_mode == LOCK_AGGR_CGROUP)
 		read_all_cgroups(&con->cgroups);
 
@@ -505,6 +603,11 @@ static const char *lock_contention_get_name(struct lock_contention *con,
 				return "rq_lock";
 		}
 
+		if (!bpf_map_lookup_elem(lock_fd, &key->lock_addr_or_cgroup, &flags)) {
+			if (flags == LOCK_CLASS_ZONE_LOCK)
+				return "zone_lock";
+		}
+
 		/* look slab_hash for dynamic locks in a slab object */
 		if (hashmap__find(&slab_hash, flags & LCB_F_SLAB_ID_MASK, &slab_data)) {
 			snprintf(name_buf, sizeof(name_buf), "&%s", slab_data->name);
@@ -743,6 +846,7 @@ int lock_contention_finish(struct lock_contention *con)
 	}
 
 	exit_slab_cache_iter();
+	btf__free(con->btf);
 
 	return 0;
 }
diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
index 4269b41d1771..c367fefe6ecb 100644
--- a/tools/perf/util/bpf_off_cpu.c
+++ b/tools/perf/util/bpf_off_cpu.c
@@ -13,6 +13,8 @@
 #include "util/cgroup.h"
 #include "util/strlist.h"
 #include <bpf/bpf.h>
+#include <internal/xyarray.h>
+#include <linux/time64.h>
 
 #include "bpf_skel/off_cpu.skel.h"
 
@@ -36,34 +38,25 @@ union off_cpu_data {
 	u64 array[1024 / sizeof(u64)];
 };
 
+u64 off_cpu_raw[MAX_STACKS + 5];
+
 static int off_cpu_config(struct evlist *evlist)
 {
+	char off_cpu_event[64];
 	struct evsel *evsel;
-	struct perf_event_attr attr = {
-		.type	= PERF_TYPE_SOFTWARE,
-		.config = PERF_COUNT_SW_BPF_OUTPUT,
-		.size	= sizeof(attr), /* to capture ABI version */
-	};
-	char *evname = strdup(OFFCPU_EVENT);
 
-	if (evname == NULL)
-		return -ENOMEM;
-
-	evsel = evsel__new(&attr);
-	if (!evsel) {
-		free(evname);
-		return -ENOMEM;
+	scnprintf(off_cpu_event, sizeof(off_cpu_event), "bpf-output/name=%s/", OFFCPU_EVENT);
+	if (parse_event(evlist, off_cpu_event)) {
+		pr_err("Failed to open off-cpu event\n");
+		return -1;
 	}
 
-	evsel->core.attr.freq = 1;
-	evsel->core.attr.sample_period = 1;
-	/* off-cpu analysis depends on stack trace */
-	evsel->core.attr.sample_type = PERF_SAMPLE_CALLCHAIN;
-
-	evlist__add(evlist, evsel);
-
-	free(evsel->name);
-	evsel->name = evname;
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel__is_offcpu_event(evsel)) {
+			evsel->core.system_wide = true;
+			break;
+		}
+	}
 
 	return 0;
 }
@@ -71,6 +64,9 @@ static int off_cpu_config(struct evlist *evlist)
 static void off_cpu_start(void *arg)
 {
 	struct evlist *evlist = arg;
+	struct evsel *evsel;
+	struct perf_cpu pcpu;
+	int i;
 
 	/* update task filter for the given workload */
 	if (skel->rodata->has_task && skel->rodata->uses_tgid &&
@@ -84,6 +80,26 @@ static void off_cpu_start(void *arg)
 		bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
 	}
 
+	/* update BPF perf_event map */
+	evsel = evlist__find_evsel_by_str(evlist, OFFCPU_EVENT);
+	if (evsel == NULL) {
+		pr_err("%s evsel not found\n", OFFCPU_EVENT);
+		return;
+	}
+
+	perf_cpu_map__for_each_cpu(pcpu, i, evsel->core.cpus) {
+		int err;
+		int cpu_nr = pcpu.cpu;
+
+		err = bpf_map__update_elem(skel->maps.offcpu_output, &cpu_nr, sizeof(int),
+					   xyarray__entry(evsel->core.fd, cpu_nr, 0),
+					   sizeof(int), BPF_ANY);
+		if (err) {
+			pr_err("Failed to update perf event map for direct off-cpu dumping\n");
+			return;
+		}
+	}
+
 	skel->bss->enabled = 1;
 }
 
@@ -277,6 +293,8 @@ int off_cpu_prepare(struct evlist *evlist, struct target *target,
 		}
 	}
 
+	skel->bss->offcpu_thresh_ns = opts->off_cpu_thresh_ns;
+
 	err = off_cpu_bpf__attach(skel);
 	if (err) {
 		pr_err("Failed to attach off-cpu BPF skeleton\n");
@@ -300,6 +318,7 @@ int off_cpu_write(struct perf_session *session)
 {
 	int bytes = 0, size;
 	int fd, stack;
+	u32 raw_size;
 	u64 sample_type, val, sid = 0;
 	struct evsel *evsel;
 	struct perf_data_file *file = &session->data->file;
@@ -339,46 +358,54 @@ int off_cpu_write(struct perf_session *session)
 
 	while (!bpf_map_get_next_key(fd, &prev, &key)) {
 		int n = 1;  /* start from perf_event_header */
-		int ip_pos = -1;
 
 		bpf_map_lookup_elem(fd, &key, &val);
 
+		/* zero-fill some of the fields, will be overwritten by raw_data when parsing */
 		if (sample_type & PERF_SAMPLE_IDENTIFIER)
 			data.array[n++] = sid;
-		if (sample_type & PERF_SAMPLE_IP) {
-			ip_pos = n;
+		if (sample_type & PERF_SAMPLE_IP)
 			data.array[n++] = 0;  /* will be updated */
-		}
 		if (sample_type & PERF_SAMPLE_TID)
-			data.array[n++] = (u64)key.pid << 32 | key.tgid;
+			data.array[n++] = 0;
 		if (sample_type & PERF_SAMPLE_TIME)
 			data.array[n++] = tstamp;
-		if (sample_type & PERF_SAMPLE_ID)
-			data.array[n++] = sid;
 		if (sample_type & PERF_SAMPLE_CPU)
 			data.array[n++] = 0;
 		if (sample_type & PERF_SAMPLE_PERIOD)
-			data.array[n++] = val;
-		if (sample_type & PERF_SAMPLE_CALLCHAIN) {
-			int len = 0;
-
-			/* data.array[n] is callchain->nr (updated later) */
-			data.array[n + 1] = PERF_CONTEXT_USER;
-			data.array[n + 2] = 0;
-
-			bpf_map_lookup_elem(stack, &key.stack_id, &data.array[n + 2]);
-			while (data.array[n + 2 + len])
+			data.array[n++] = 0;
+		if (sample_type & PERF_SAMPLE_RAW) {
+			/*
+			 *  [ size ][ data ]
+			 *  [     data     ]
+			 *  [     data     ]
+			 *  [     data     ]
+			 *  [ data ][ empty]
+			 */
+			int len = 0, i = 0;
+			void *raw_data = (void *)data.array + n * sizeof(u64);
+
+			off_cpu_raw[i++] = (u64)key.pid << 32 | key.tgid;
+			off_cpu_raw[i++] = val;
+
+			/* off_cpu_raw[i] is callchain->nr (updated later) */
+			off_cpu_raw[i + 1] = PERF_CONTEXT_USER;
+			off_cpu_raw[i + 2] = 0;
+
+			bpf_map_lookup_elem(stack, &key.stack_id, &off_cpu_raw[i + 2]);
+			while (off_cpu_raw[i + 2 + len])
 				len++;
 
-			/* update length of callchain */
-			data.array[n] = len + 1;
+			off_cpu_raw[i] = len + 1;
+			i += len + 2;
+
+			off_cpu_raw[i++] = key.cgroup_id;
 
-			/* update sample ip with the first callchain entry */
-			if (ip_pos >= 0)
-				data.array[ip_pos] = data.array[n + 2];
+			raw_size = i * sizeof(u64) + sizeof(u32); /* 4 bytes for alignment */
+			memcpy(raw_data, &raw_size, sizeof(raw_size));
+			memcpy(raw_data + sizeof(u32), off_cpu_raw, i * sizeof(u64));
 
-			/* calculate sample callchain data array length */
-			n += len + 2;
+			n += i + 1;
 		}
 		if (sample_type & PERF_SAMPLE_CGROUP)
 			data.array[n++] = key.cgroup_id;
diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index 69be7a4234e0..96e7d853b9ed 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -11,6 +11,12 @@
 /* for collect_lock_syms().  4096 was rejected by the verifier */
 #define MAX_CPUS  1024
 
+/* for collect_zone_lock().  It should be more than the actual zones. */
+#define MAX_ZONES  10
+
+/* for do_lock_delay().  Arbitrarily set to 1 million. */
+#define MAX_LOOP  (1U << 20)
+
 /* lock contention flags from include/trace/events/lock.h */
 #define LCB_F_SPIN	(1U << 0)
 #define LCB_F_READ	(1U << 1)
@@ -146,6 +152,13 @@ struct {
 	__uint(max_entries, 1);
 } slab_caches SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u64));
+	__uint(value_size, sizeof(__u64));
+	__uint(max_entries, 1);
+} lock_delays SEC(".maps");
+
 struct rw_semaphore___old {
 	struct task_struct *owner;
 } __attribute__((preserve_access_index));
@@ -176,6 +189,7 @@ const volatile int stack_skip;
 const volatile int lock_owner;
 const volatile int use_cgroup_v2;
 const volatile int max_stack;
+const volatile int lock_delay;
 
 /* determine the key of lock stat */
 const volatile int aggr_mode;
@@ -384,6 +398,35 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags)
 	return 0;
 }
 
+static inline long delay_callback(__u64 idx, void *arg)
+{
+	__u64 target = *(__u64 *)arg;
+
+	if (target <= bpf_ktime_get_ns())
+		return 1;
+
+	/* just to kill time */
+	(void)bpf_get_prandom_u32();
+
+	return 0;
+}
+
+static inline void do_lock_delay(__u64 duration)
+{
+	__u64 target = bpf_ktime_get_ns() + duration;
+
+	bpf_loop(MAX_LOOP, delay_callback, &target, /*flags=*/0);
+}
+
+static inline void check_lock_delay(__u64 lock)
+{
+	__u64 *delay;
+
+	delay = bpf_map_lookup_elem(&lock_delays, &lock);
+	if (delay)
+		do_lock_delay(*delay);
+}
+
 static inline struct tstamp_data *get_tstamp_elem(__u32 flags)
 {
 	__u32 pid;
@@ -793,6 +836,9 @@ found:
 	update_contention_data(data, duration, 1);
 
 out:
+	if (lock_delay)
+		check_lock_delay(pelem->lock);
+
 	pelem->lock = 0;
 	if (need_delete)
 		bpf_map_delete_elem(&tstamp, &pid);
@@ -801,6 +847,11 @@ out:
 
 extern struct rq runqueues __ksym;
 
+const volatile __u64 contig_page_data_addr;
+const volatile __u64 node_data_addr;
+const volatile int nr_nodes;
+const volatile int sizeof_zone;
+
 struct rq___old {
 	raw_spinlock_t lock;
 } __attribute__((preserve_access_index));
@@ -809,6 +860,59 @@ struct rq___new {
 	raw_spinlock_t __lock;
 } __attribute__((preserve_access_index));
 
+static void collect_zone_lock(void)
+{
+	__u64 nr_zones, zone_off;
+	__u64 lock_addr, lock_off;
+	__u32 lock_flag = LOCK_CLASS_ZONE_LOCK;
+
+	zone_off = offsetof(struct pglist_data, node_zones);
+	lock_off = offsetof(struct zone, lock);
+
+	if (contig_page_data_addr) {
+		struct pglist_data *contig_page_data;
+
+		contig_page_data = (void *)(long)contig_page_data_addr;
+		nr_zones = BPF_CORE_READ(contig_page_data, nr_zones);
+
+		for (int i = 0; i < MAX_ZONES; i++) {
+			__u64 zone_addr;
+
+			if (i >= nr_zones)
+				break;
+
+			zone_addr = contig_page_data_addr + (sizeof_zone * i) + zone_off;
+			lock_addr = zone_addr + lock_off;
+
+			bpf_map_update_elem(&lock_syms, &lock_addr, &lock_flag, BPF_ANY);
+		}
+	} else if (nr_nodes > 0) {
+		struct pglist_data **node_data = (void *)(long)node_data_addr;
+
+		for (int i = 0; i < nr_nodes; i++) {
+			struct pglist_data *pgdat = NULL;
+			int err;
+
+			err = bpf_core_read(&pgdat, sizeof(pgdat), &node_data[i]);
+			if (err < 0 || pgdat == NULL)
+				break;
+
+			nr_zones = BPF_CORE_READ(pgdat, nr_zones);
+			for (int k = 0; k < MAX_ZONES; k++) {
+				__u64 zone_addr;
+
+				if (k >= nr_zones)
+					break;
+
+				zone_addr = (__u64)(void *)pgdat + (sizeof_zone * k) + zone_off;
+				lock_addr = zone_addr + lock_off;
+
+				bpf_map_update_elem(&lock_syms, &lock_addr, &lock_flag, BPF_ANY);
+			}
+		}
+	}
+}
+
 SEC("raw_tp/bpf_test_finish")
 int BPF_PROG(collect_lock_syms)
 {
@@ -830,6 +934,9 @@ int BPF_PROG(collect_lock_syms)
 		lock_flag = LOCK_CLASS_RQLOCK;
 		bpf_map_update_elem(&lock_syms, &lock_addr, &lock_flag, BPF_ANY);
 	}
+
+	collect_zone_lock();
+
 	return 0;
 }
 
diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h
index 15f5743bd409..28c5e5aced7f 100644
--- a/tools/perf/util/bpf_skel/lock_data.h
+++ b/tools/perf/util/bpf_skel/lock_data.h
@@ -67,6 +67,7 @@ enum lock_aggr_mode {
 enum lock_class_sym {
 	LOCK_CLASS_NONE,
 	LOCK_CLASS_RQLOCK,
+	LOCK_CLASS_ZONE_LOCK,
 };
 
 struct slab_cache_data {
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index c152116df72f..72763bb8d1de 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -18,10 +18,19 @@
 #define MAX_STACKS   32
 #define MAX_ENTRIES  102400
 
+#define MAX_CPUS  4096
+#define MAX_OFFCPU_LEN 37
+
+// We have a 'struct stack' in vmlinux.h when building with GEN_VMLINUX_H=1
+struct __stack {
+	u64 array[MAX_STACKS];
+};
+
 struct tstamp_data {
 	__u32 stack_id;
 	__u32 state;
 	__u64 timestamp;
+	struct __stack stack;
 };
 
 struct offcpu_key {
@@ -39,6 +48,24 @@ struct {
 	__uint(max_entries, MAX_ENTRIES);
 } stacks SEC(".maps");
 
+struct offcpu_data {
+	u64 array[MAX_OFFCPU_LEN];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+	__uint(max_entries, MAX_CPUS);
+} offcpu_output SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct offcpu_data));
+	__uint(max_entries, 1);
+} offcpu_payload SEC(".maps");
+
 struct {
 	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
 	__uint(map_flags, BPF_F_NO_PREALLOC);
@@ -97,6 +124,8 @@ const volatile bool uses_cgroup_v1 = false;
 
 int perf_subsys_id = -1;
 
+__u64 offcpu_thresh_ns;
+
 /*
  * Old kernel used to call it task_struct->state and now it's '__state'.
  * Use BPF CO-RE "ignored suffix rule" to deal with it like below:
@@ -183,6 +212,47 @@ static inline int can_record(struct task_struct *t, int state)
 	return 1;
 }
 
+static inline int copy_stack(struct __stack *from, struct offcpu_data *to, int n)
+{
+	int len = 0;
+
+	for (int i = 0; i < MAX_STACKS && from->array[i]; ++i, ++len)
+		to->array[n + 2 + i] = from->array[i];
+
+	return len;
+}
+
+/**
+ * off_cpu_dump - dump off-cpu samples to ring buffer
+ * @data: payload for dumping off-cpu samples
+ * @key: off-cpu data
+ * @stack: stack trace of the task before being scheduled out
+ *
+ * If the threshold of off-cpu time is reached, acquire tid, period, callchain, and cgroup id
+ * information of the task, and dump it as a raw sample to perf ring buffer
+ */
+static int off_cpu_dump(void *ctx, struct offcpu_data *data, struct offcpu_key *key,
+			struct __stack *stack, __u64 delta)
+{
+	int n = 0, len = 0;
+
+	data->array[n++] = (u64)key->tgid << 32 | key->pid;
+	data->array[n++] = delta;
+
+	/* data->array[n] is callchain->nr (updated later) */
+	data->array[n + 1] = PERF_CONTEXT_USER;
+	data->array[n + 2] = 0;
+	len = copy_stack(stack, data, n);
+
+	/* update length of callchain */
+	data->array[n] = len + 1;
+	n += len + 2;
+
+	data->array[n++] = key->cgroup_id;
+
+	return bpf_perf_event_output(ctx, &offcpu_output, BPF_F_CURRENT_CPU, data, n * sizeof(u64));
+}
+
 static int off_cpu_stat(u64 *ctx, struct task_struct *prev,
 			struct task_struct *next, int state)
 {
@@ -207,6 +277,16 @@ static int off_cpu_stat(u64 *ctx, struct task_struct *prev,
 	pelem->state = state;
 	pelem->stack_id = stack_id;
 
+	/*
+	 * If stacks are successfully collected by bpf_get_stackid(), collect them once more
+	 * in task_storage for direct off-cpu sample dumping
+	 */
+	if (stack_id > 0 && bpf_get_stack(ctx, &pelem->stack, MAX_STACKS * sizeof(u64), BPF_F_USER_STACK)) {
+		/*
+		 * This empty if block is used to avoid 'result unused warning' from bpf_get_stack().
+		 * If the collection fails, continue with the logic for the next task.
+		 */
+	}
 next:
 	pelem = bpf_task_storage_get(&tstamp, next, NULL, 0);
 
@@ -221,11 +301,19 @@ next:
 		__u64 delta = ts - pelem->timestamp;
 		__u64 *total;
 
-		total = bpf_map_lookup_elem(&off_cpu, &key);
-		if (total)
-			*total += delta;
-		else
-			bpf_map_update_elem(&off_cpu, &key, &delta, BPF_ANY);
+		if (delta >= offcpu_thresh_ns) {
+			int zero = 0;
+			struct offcpu_data *data = bpf_map_lookup_elem(&offcpu_payload, &zero);
+
+			if (data)
+				off_cpu_dump(ctx, data, &key, &pelem->stack, delta);
+		} else {
+			total = bpf_map_lookup_elem(&off_cpu, &key);
+			if (total)
+				*total += delta;
+			else
+				bpf_map_update_elem(&off_cpu, &key, &delta, BPF_ANY);
+		}
 
 		/* prevent to reuse the timestamp later */
 		pelem->timestamp = 0;
diff --git a/tools/perf/util/bpf_skel/syscall_summary.bpf.c b/tools/perf/util/bpf_skel/syscall_summary.bpf.c
new file mode 100644
index 000000000000..1bcd066a5199
--- /dev/null
+++ b/tools/perf/util/bpf_skel/syscall_summary.bpf.c
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Trace raw_syscalls tracepoints to collect system call statistics.
+ */
+
+#include "vmlinux.h"
+#include "syscall_summary.h"
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+/* This is to calculate a delta between sys-enter and sys-exit for each thread */
+struct syscall_trace {
+	int nr; /* syscall number is only available at sys-enter */
+	int unused;
+	u64 timestamp;
+};
+
+#define MAX_ENTRIES	(128 * 1024)
+
+struct syscall_trace_map {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, int); /* tid */
+	__type(value, struct syscall_trace);
+	__uint(max_entries, MAX_ENTRIES);
+} syscall_trace_map SEC(".maps");
+
+struct syscall_stats_map {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, struct syscall_key);
+	__type(value, struct syscall_stats);
+	__uint(max_entries, MAX_ENTRIES);
+} syscall_stats_map SEC(".maps");
+
+int enabled; /* controlled from userspace */
+
+const volatile enum syscall_aggr_mode aggr_mode;
+const volatile int use_cgroup_v2;
+
+int perf_subsys_id = -1;
+
+static inline __u64 get_current_cgroup_id(void)
+{
+	struct task_struct *task;
+	struct cgroup *cgrp;
+
+	if (use_cgroup_v2)
+		return bpf_get_current_cgroup_id();
+
+	task = bpf_get_current_task_btf();
+
+	if (perf_subsys_id == -1) {
+#if __has_builtin(__builtin_preserve_enum_value)
+		perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id,
+						     perf_event_cgrp_id);
+#else
+		perf_subsys_id = perf_event_cgrp_id;
+#endif
+	}
+
+	cgrp = BPF_CORE_READ(task, cgroups, subsys[perf_subsys_id], cgroup);
+	return BPF_CORE_READ(cgrp, kn, id);
+}
+
+static void update_stats(int cpu_or_tid, u64 cgroup_id, int nr, s64 duration,
+			 long ret)
+{
+	struct syscall_key key = {
+		.cpu_or_tid = cpu_or_tid,
+		.cgroup = cgroup_id,
+		.nr = nr,
+	};
+	struct syscall_stats *stats;
+
+	stats = bpf_map_lookup_elem(&syscall_stats_map, &key);
+	if (stats == NULL) {
+		struct syscall_stats zero = {};
+
+		bpf_map_update_elem(&syscall_stats_map, &key, &zero, BPF_NOEXIST);
+		stats = bpf_map_lookup_elem(&syscall_stats_map, &key);
+		if (stats == NULL)
+			return;
+	}
+
+	__sync_fetch_and_add(&stats->count, 1);
+	if (ret < 0)
+		__sync_fetch_and_add(&stats->error, 1);
+
+	if (duration > 0) {
+		__sync_fetch_and_add(&stats->total_time, duration);
+		__sync_fetch_and_add(&stats->squared_sum, duration * duration);
+		if (stats->max_time < duration)
+			stats->max_time = duration;
+		if (stats->min_time > duration || stats->min_time == 0)
+			stats->min_time = duration;
+	}
+
+	return;
+}
+
+SEC("tp_btf/sys_enter")
+int sys_enter(u64 *ctx)
+{
+	int tid;
+	struct syscall_trace st;
+
+	if (!enabled)
+		return 0;
+
+	st.nr = ctx[1]; /* syscall number */
+	st.unused = 0;
+	st.timestamp = bpf_ktime_get_ns();
+
+	tid = bpf_get_current_pid_tgid();
+	bpf_map_update_elem(&syscall_trace_map, &tid, &st, BPF_ANY);
+
+	return 0;
+}
+
+SEC("tp_btf/sys_exit")
+int sys_exit(u64 *ctx)
+{
+	int tid;
+	int key = 0;
+	u64 cgroup = 0;
+	long ret = ctx[1]; /* return value of the syscall */
+	struct syscall_trace *st;
+	s64 delta;
+
+	if (!enabled)
+		return 0;
+
+	tid = bpf_get_current_pid_tgid();
+	st = bpf_map_lookup_elem(&syscall_trace_map, &tid);
+	if (st == NULL)
+		return 0;
+
+	if (aggr_mode == SYSCALL_AGGR_THREAD)
+		key = tid;
+	else if (aggr_mode == SYSCALL_AGGR_CGROUP)
+		cgroup = get_current_cgroup_id();
+	else
+		key = bpf_get_smp_processor_id();
+
+	delta = bpf_ktime_get_ns() - st->timestamp;
+	update_stats(key, cgroup, st->nr, delta, ret);
+
+	bpf_map_delete_elem(&syscall_trace_map, &tid);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/perf/util/bpf_skel/syscall_summary.h b/tools/perf/util/bpf_skel/syscall_summary.h
new file mode 100644
index 000000000000..72ccccb45925
--- /dev/null
+++ b/tools/perf/util/bpf_skel/syscall_summary.h
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Data structures shared between BPF and tools. */
+#ifndef UTIL_BPF_SKEL_SYSCALL_SUMMARY_H
+#define UTIL_BPF_SKEL_SYSCALL_SUMMARY_H
+
+enum syscall_aggr_mode {
+	SYSCALL_AGGR_THREAD,
+	SYSCALL_AGGR_CPU,
+	SYSCALL_AGGR_CGROUP,
+};
+
+struct syscall_key {
+	u64 cgroup;
+	int cpu_or_tid;
+	int nr;
+};
+
+struct syscall_stats {
+	u64 total_time;
+	u64 squared_sum;
+	u64 max_time;
+	u64 min_time;
+	u32 count;
+	u32 error;
+};
+
+#endif /* UTIL_BPF_SKEL_SYSCALL_SUMMARY_H */
diff --git a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
index 7b81d3173917..a59ce912be18 100644
--- a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
+++ b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
@@ -203,4 +203,13 @@ struct bpf_iter__kmem_cache {
 	struct kmem_cache *s;
 } __attribute__((preserve_access_index));
 
+struct zone {
+	spinlock_t lock;
+} __attribute__((preserve_access_index));
+
+struct pglist_data {
+	struct zone node_zones[6]; /* value for all possible config */
+	int nr_zones;
+} __attribute__((preserve_access_index));
+
 #endif // __VMLINUX_H
diff --git a/tools/perf/util/demangle-cxx.h b/tools/perf/util/demangle-cxx.h
index 26b5b66c0b4e..9359937a881a 100644
--- a/tools/perf/util/demangle-cxx.h
+++ b/tools/perf/util/demangle-cxx.h
@@ -2,6 +2,8 @@
 #ifndef __PERF_DEMANGLE_CXX
 #define __PERF_DEMANGLE_CXX 1
 
+#include <stdbool.h>
+
 #ifdef __cplusplus
 extern "C" {
 #endif
diff --git a/tools/perf/util/demangle-rust-v0.c b/tools/perf/util/demangle-rust-v0.c
new file mode 100644
index 000000000000..19924d85407d
--- /dev/null
+++ b/tools/perf/util/demangle-rust-v0.c
@@ -0,0 +1,2042 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+// The contents of this file come from the Rust rustc-demangle library, hosted
+// in the <https://github.com/rust-lang/rustc-demangle> repository, licensed
+// under "Apache-2.0 OR MIT". For copyright details, see
+// <https://github.com/rust-lang/rustc-demangle/blob/main/README.md>.
+// Please note that the file should be kept as close as possible to upstream.
+
+// Code for demangling Rust symbols. This code is mostly
+// a line-by-line translation of the Rust code in `rustc-demangle`.
+
+// you can find the latest version of this code in https://github.com/rust-lang/rustc-demangle
+
+#include <stdint.h>
+#include <stddef.h>
+#include <string.h>
+#include <stdbool.h>
+#include <sys/param.h>
+#include <stdio.h>
+
+#include "demangle-rust-v0.h"
+
+#if defined(__GNUC__) || defined(__clang__)
+#define NODISCARD __attribute__((warn_unused_result))
+#else
+#define NODISCARD
+#endif
+
+#define MAX_DEPTH 500
+
+typedef enum {
+    DemangleOk,
+    DemangleInvalid,
+    DemangleRecursed,
+    DemangleBug,
+} demangle_status;
+
+struct demangle_v0 {
+    const char *mangled;
+    size_t mangled_len;
+};
+
+struct demangle_legacy {
+    const char *mangled;
+    size_t mangled_len;
+    size_t elements;
+};
+
+// private version of memrchr to avoid _GNU_SOURCE
+static void *demangle_memrchr(const void *s, int c, size_t n) {
+    const uint8_t *s_ = s;
+    for (; n != 0; n--) {
+        if (s_[n-1] == c) {
+            return (void*)&s_[n-1];
+        }
+    }
+    return NULL;
+}
+
+
+static bool unicode_iscontrol(uint32_t ch) {
+    // this is *technically* a unicode table, but
+    // some unicode properties are simpler than you might think
+    return ch < 0x20 || (ch >= 0x7f && ch < 0xa0);
+}
+
+// "good enough" tables, the only consequence is that when printing
+// *constant strings*, some characters are printed as `\u{abcd}` rather than themselves.
+//
+// I'm leaving these here to allow easily replacing them with actual
+// tables if desired.
+static bool unicode_isprint(uint32_t ch) {
+    if (ch < 0x20) {
+        return false;
+    }
+    if (ch < 0x7f) {
+        return true;
+    }
+    return false;
+}
+
+static bool unicode_isgraphemextend(uint32_t ch) {
+    (void)ch;
+    return false;
+}
+
+static bool str_isascii(const char *s, size_t s_len) {
+    for (size_t i = 0; i < s_len; i++) {
+        if (s[i] & 0x80) {
+            return false;
+        }
+    }
+
+    return true;
+}
+
+typedef enum {
+    PunycodeOk,
+    PunycodeError
+} punycode_status;
+
+struct parser {
+    // the parser assumes that `sym` has a safe "terminating byte". It might be NUL,
+    // but it might also be something else if a symbol is "truncated".
+    const char *sym;
+    size_t sym_len;
+    size_t next;
+    uint32_t depth;
+};
+
+struct printer {
+    demangle_status status; // if status == 0 parser is valid
+    struct parser parser;
+    char *out; // NULL for no output [in which case out_len is not decremented]
+    size_t out_len;
+    uint32_t bound_lifetime_depth;
+    bool alternate;
+};
+
+static NODISCARD overflow_status printer_print_path(struct printer *printer, bool in_value);
+static NODISCARD overflow_status printer_print_type(struct printer *printer);
+static NODISCARD overflow_status printer_print_const(struct printer *printer, bool in_value);
+
+static NODISCARD demangle_status try_parse_path(struct parser *parser) {
+    struct printer printer = {
+        DemangleOk,
+        *parser,
+        NULL,
+        SIZE_MAX,
+        0,
+        false
+    };
+    overflow_status ignore = printer_print_path(&printer, false); // can't fail since no output
+    (void)ignore;
+    *parser = printer.parser;
+    return printer.status;
+}
+
+NODISCARD static demangle_status rust_demangle_v0_demangle(const char *s, size_t s_len, struct demangle_v0 *res, const char **rest) {
+    if (s_len > strlen(s)) {
+        // s_len only exists to shorten the string, this is not a buffer API
+        return DemangleInvalid;
+    }
+
+    const char *inner;
+    size_t inner_len;
+    if (s_len >= 2 && !strncmp(s, "_R", strlen("_R"))) {
+        inner = s+2;
+        inner_len = s_len - 2;
+    } else if (s_len >= 1 && !strncmp(s, "R", strlen("R"))) {
+        // On Windows, dbghelp strips leading underscores, so we accept "R..."
+        // form too.
+        inner = s+1;
+        inner_len = s_len - 1;
+    } else if (s_len >= 3 && !strncmp(s, "__R", strlen("__R"))) {
+        // On OSX, symbols are prefixed with an extra _
+        inner = s+3;
+        inner_len = s_len - 3;
+    } else {
+        return DemangleInvalid;
+    }
+
+    // Paths always start with uppercase characters.
+    if (*inner < 'A' || *inner > 'Z') {
+        return DemangleInvalid;
+    }
+
+    if (!str_isascii(inner, inner_len)) {
+        return DemangleInvalid;
+    }
+
+    struct parser parser = { inner, inner_len, 0, 0 };
+
+    demangle_status status = try_parse_path(&parser);
+    if (status != DemangleOk) return status;
+    char next = parser.sym[parser.next];
+
+    // Instantiating crate (paths always start with uppercase characters).
+    if (parser.next < parser.sym_len && next >= 'A' && next <= 'Z') {
+        status = try_parse_path(&parser);
+        if (status != DemangleOk) return status;
+    }
+
+    res->mangled = inner;
+    res->mangled_len = inner_len;
+    if (rest) {
+        *rest = parser.sym + parser.next;
+    }
+
+    return DemangleOk;
+}
+
+// This might require `len` to be up to 3 characters bigger than the real output len in case of utf-8
+NODISCARD static overflow_status rust_demangle_v0_display_demangle(struct demangle_v0 res, char *out, size_t len, bool alternate) {
+    struct printer printer = {
+        DemangleOk,
+        {
+            res.mangled,
+            res.mangled_len,
+            0,
+            0
+        },
+        out,
+        len,
+        0,
+        alternate
+    };
+    if (printer_print_path(&printer, true) == OverflowOverflow) {
+        return OverflowOverflow;
+    }
+    if (printer.out_len < OVERFLOW_MARGIN) {
+        return OverflowOverflow;
+    }
+    *printer.out = '\0';
+    return OverflowOk;
+}
+
+static size_t code_to_utf8(unsigned char *buffer, uint32_t code)
+{
+    if (code <= 0x7F) {
+        buffer[0] = code;
+        return 1;
+    }
+    if (code <= 0x7FF) {
+        buffer[0] = 0xC0 | (code >> 6);            /* 110xxxxx */
+        buffer[1] = 0x80 | (code & 0x3F);          /* 10xxxxxx */
+        return 2;
+    }
+    if (code <= 0xFFFF) {
+        buffer[0] = 0xE0 | (code >> 12);           /* 1110xxxx */
+        buffer[1] = 0x80 | ((code >> 6) & 0x3F);   /* 10xxxxxx */
+        buffer[2] = 0x80 | (code & 0x3F);          /* 10xxxxxx */
+        return 3;
+    }
+    if (code <= 0x10FFFF) {
+        buffer[0] = 0xF0 | (code >> 18);           /* 11110xxx */
+        buffer[1] = 0x80 | ((code >> 12) & 0x3F);  /* 10xxxxxx */
+        buffer[2] = 0x80 | ((code >> 6) & 0x3F);   /* 10xxxxxx */
+        buffer[3] = 0x80 | (code & 0x3F);          /* 10xxxxxx */
+        return 4;
+    }
+    return 0;
+}
+
+
+// return length of char at byte, or SIZE_MAX if invalid. buf should have 4 valid characters
+static NODISCARD size_t utf8_next_char(uint8_t *s, uint32_t *ch) {
+    uint8_t byte = *s;
+    // UTF8-1      = %x00-7F
+    // UTF8-2      = %xC2-DF UTF8-tail
+    // UTF8-3      = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
+    //               %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
+    // UTF8-4      = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
+    //               %xF4 %x80-8F 2( UTF8-tail )
+    if (byte < 0x80) {
+        *ch = byte;
+        return 1;
+    } else if (byte < 0xc2) {
+        return SIZE_MAX;
+    } else if (byte < 0xe0) {
+        if (s[1] >= 0x80 && s[1] < 0xc0) {
+            *ch = ((byte&0x1f)<<6) + (s[1] & 0x3f);
+            return 2;
+        }
+        return SIZE_MAX;
+    } if (byte < 0xf0) {
+        if (!(s[1] >= 0x80 && s[1] < 0xc0) || !(s[2] >= 0x80 && s[2] < 0xc0)) {
+            return SIZE_MAX; // basic validation
+        }
+        if (byte == 0xe0 && s[1] < 0xa0) {
+            return SIZE_MAX; // overshort
+        }
+        if (byte == 0xed && s[1] >= 0xa0) {
+            return SIZE_MAX; // surrogate
+        }
+        *ch = ((byte&0x0f)<<12) + ((s[1] & 0x3f)<<6) + (s[2] & 0x3f);
+        return 3;
+    } else if (byte < 0xf5) {
+        if (!(s[1] >= 0x80 && s[1] < 0xc0) || !(s[2] >= 0x80 && s[2] < 0xc0) || !(s[3] >= 0x80 && s[3] < 0xc0)) {
+            return SIZE_MAX; // basic validation
+        }
+        if (byte == 0xf0 && s[1] < 0x90) {
+            return SIZE_MAX; // overshort
+        }
+        if (byte == 0xf4 && s[1] >= 0x90) {
+            return SIZE_MAX; // over max
+        }
+        *ch = ((byte&0x07)<<18) + ((s[1] & 0x3f)<<12) + ((s[2] & 0x3f)<<6) + (s[3]&0x3f);
+        return 4;
+    } else {
+        return SIZE_MAX;
+    }
+}
+
+static NODISCARD bool validate_char(uint32_t n) {
+    return ((n ^ 0xd800) - 0x800) < 0x110000 - 0x800;
+}
+
+#define SMALL_PUNYCODE_LEN 128
+
+static NODISCARD punycode_status punycode_decode(const char *start, size_t ascii_len, const char *punycode_start, size_t punycode_len, uint32_t (*out_)[SMALL_PUNYCODE_LEN], size_t *out_len) {
+    uint32_t *out = *out_;
+
+    if (punycode_len == 0) {
+        return PunycodeError;
+    }
+
+    if (ascii_len > SMALL_PUNYCODE_LEN) {
+        return PunycodeError;
+    }
+    for (size_t i = 0; i < ascii_len; i++) {
+        out[i] = start[i];
+    }
+    size_t len = ascii_len;
+
+    size_t base = 36, t_min = 1, t_max = 26, skew = 38, damp = 700, bias = 72, i = 0, n = 0x80;
+    for (;;) {
+        size_t delta = 0, w = 1, k = 0;
+        for (;;) {
+            k += base;
+            size_t biased = k < bias ? 0 : k - bias;
+            size_t t = MIN(MAX(biased, t_min), t_max);
+            size_t d;
+            if (punycode_len == 0) {
+                return PunycodeError;
+            }
+            char nx = *punycode_start++;
+            punycode_len--;
+            if ('a' <= nx && nx <= 'z') {
+                d = nx - 'a';
+            } else if ('0' <= nx && nx <= '9') {
+                d = 26 + (nx - '0');
+            } else {
+                return PunycodeError;
+            }
+            if (w == 0 || d > SIZE_MAX / w || d*w > SIZE_MAX - delta) {
+                return PunycodeError;
+            }
+            delta += d * w;
+            if (d < t) {
+                break;
+            }
+            if (base < t || w == 0 || (base - t) > SIZE_MAX / w) {
+                return PunycodeError;
+            }
+            w *= (base - t);
+        }
+
+        len += 1;
+        if (i > SIZE_MAX - delta) {
+            return PunycodeError;
+        }
+        i += delta;
+        if (n > SIZE_MAX - i / len) {
+            return PunycodeError;
+        }
+        n += i / len;
+        i %= len;
+
+        // char validation
+        if (n > UINT32_MAX || !validate_char((uint32_t)n)) {
+            return PunycodeError;
+        }
+
+        // insert new character
+        if (len > SMALL_PUNYCODE_LEN) {
+            return PunycodeError;
+        }
+        memmove(out + i + 1, out + i, (len - i - 1) * sizeof(uint32_t));
+        out[i] = (uint32_t)n;
+
+        // start i index at incremented position
+        i++;
+
+        // If there are no more deltas, decoding is complete.
+        if (punycode_len == 0) {
+            *out_len = len;
+            return PunycodeOk;
+        }
+
+        // Perform bias adaptation.
+        delta /= damp;
+        damp = 2;
+
+        delta += delta / len;
+        k = 0;
+        while (delta > ((base - t_min) * t_max) / 2) {
+            delta /= base - t_min;
+            k += base;
+        }
+        bias = k + ((base - t_min + 1) * delta) / (delta + skew);
+    }
+}
+
+struct ident {
+    const char *ascii_start;
+    size_t ascii_len;
+    const char *punycode_start;
+    size_t punycode_len;
+};
+
+static NODISCARD overflow_status display_ident(const char *ascii_start, size_t ascii_len, const char *punycode_start, size_t punycode_len, uint8_t *out, size_t *out_len) {
+    uint32_t outbuf[SMALL_PUNYCODE_LEN];
+
+    size_t wide_len;
+    size_t out_buflen = *out_len;
+
+    if (punycode_len == 0) {
+        if (ascii_len > out_buflen) {
+            return OverflowOverflow;
+        }
+        memcpy(out, ascii_start, ascii_len);
+        *out_len = ascii_len;
+    } else if (punycode_decode(ascii_start, ascii_len, punycode_start, punycode_len, &outbuf, &wide_len) == PunycodeOk) {
+        size_t narrow_len = 0;
+        for (size_t i = 0; i < wide_len; i++) {
+            if (out_buflen - narrow_len < 4) {
+                return OverflowOverflow;
+            }
+            unsigned char *pos = &out[narrow_len];
+            narrow_len += code_to_utf8(pos, outbuf[i]);
+        }
+        *out_len = narrow_len;
+    } else {
+        size_t narrow_len = 0;
+        if (out_buflen < strlen("punycode{")) {
+            return OverflowOverflow;
+        }
+        memcpy(out, "punycode{", strlen("punycode{"));
+        narrow_len = strlen("punycode{");
+        if (ascii_len > 0) {
+            if (out_buflen - narrow_len < ascii_len || out_buflen - narrow_len - ascii_len < 1) {
+                return OverflowOverflow;
+            }
+            memcpy(out + narrow_len, ascii_start, ascii_len);
+            narrow_len += ascii_len;
+            out[narrow_len] = '-';
+            narrow_len++;
+        }
+        if (out_buflen - narrow_len < punycode_len || out_buflen - narrow_len - punycode_len < 1) {
+            return OverflowOverflow;
+        }
+        memcpy(out + narrow_len, punycode_start, punycode_len);
+        narrow_len += punycode_len;
+        out[narrow_len] = '}';
+        narrow_len++;
+        *out_len = narrow_len;
+    }
+
+    return OverflowOk;
+}
+
+static NODISCARD bool try_parse_uint(const char *buf, size_t len, uint64_t *result) {
+    size_t cur = 0;
+    for(;cur < len && buf[cur] == '0';cur++);
+    uint64_t result_val = 0;
+    if (len - cur > 16) return false;
+    for(;cur < len;cur++) {
+        char c = buf[cur];
+        result_val <<= 4;
+        if ('0' <= c && c <= '9') {
+            result_val += c - '0';
+        } else if ('a' <= c && c <= 'f') {
+            result_val += 10 + (c - 'a');
+        } else {
+            return false;
+        }
+    }
+    *result = result_val;
+    return true;
+}
+
+static NODISCARD bool dinibble2int(const char *buf, uint8_t *result) {
+    uint8_t result_val = 0;
+    for (int i = 0; i < 2; i++) {
+        char c = buf[i];
+        result_val <<= 4;
+        if ('0' <= c && c <= '9') {
+            result_val += c - '0';
+        } else if ('a' <= c && c <= 'f') {
+            result_val += 10 + (c - 'a');
+        } else {
+            return false;
+        }
+    }
+    *result = result_val;
+    return true;
+}
+
+
+typedef enum {
+    NtsOk = 0,
+    NtsOverflow = 1,
+    NtsInvalid = 2
+} nibbles_to_string_status;
+
+// '\u{10ffff}', +margin
+#define ESCAPED_SIZE 12
+
+static NODISCARD size_t char_to_string(uint32_t ch, uint8_t quote, bool first, char (*buf)[ESCAPED_SIZE]) {
+    // encode the character
+    char *escaped_buf = *buf;
+    escaped_buf[0] = '\\';
+    size_t escaped_len = 2;
+    switch (ch) {
+        case '\0':
+        escaped_buf[1] = '0';
+        break;
+        case '\t':
+        escaped_buf[1] = 't';
+        break;
+        case '\r':
+        escaped_buf[1] = 'r';
+        break;
+        case '\n':
+        escaped_buf[1] = 'n';
+        break;
+        case '\\':
+        escaped_buf[1] = '\\';
+        break;
+        default:
+        if (ch == quote) {
+            escaped_buf[1] = ch;
+        } else if (!unicode_isprint(ch) || (first && unicode_isgraphemextend(ch))) {
+            int hexlen = snprintf(escaped_buf, ESCAPED_SIZE, "\\u{%x}", (unsigned int)ch);
+            if (hexlen < 0) {
+                return 0; // (snprintf shouldn't fail!)
+            }
+            escaped_len = hexlen;
+        } else {
+            // printable character
+            escaped_buf[0] = ch;
+            escaped_len = 1;
+        }
+        break;
+    }
+
+    return escaped_len;
+}
+
+// convert nibbles to a single/double-quoted string
+static NODISCARD nibbles_to_string_status nibbles_to_string(const char *buf, size_t len, uint8_t *out, size_t *out_len) {
+    uint8_t quote = '"';
+    bool first = true;
+
+    if ((len % 2) != 0) {
+        return NtsInvalid; // odd number of nibbles
+    }
+
+    size_t cur_out_len = 0;
+
+    // write starting quote
+    if (out != NULL) {
+        cur_out_len = *out_len;
+        if (cur_out_len == 0) {
+            return NtsOverflow;
+        }
+        *out++ = quote;
+        cur_out_len--;
+    }
+
+    uint8_t conv_buf[4] = {0};
+    size_t conv_buf_len = 0;
+    while (len > 1 || conv_buf_len > 0) {
+        while (len > 1 && conv_buf_len < sizeof(conv_buf)) {
+            if (!dinibble2int(buf, &conv_buf[conv_buf_len])) {
+                return NtsInvalid;
+            }
+            conv_buf_len++;
+            buf += 2;
+            len -= 2;
+        }
+
+        // conv_buf is full here if possible, process 1 UTF-8 character
+        uint32_t ch = 0;
+        size_t consumed = utf8_next_char(conv_buf, &ch);
+        if (consumed > conv_buf_len) {
+            // either SIZE_MAX (invalid UTF-8) or finished input buffer and
+            // there are still bytes remaining, in both cases invalid
+            return NtsInvalid;
+        }
+
+        // "consume" the character
+        memmove(conv_buf, conv_buf+consumed, conv_buf_len-consumed);
+        conv_buf_len -= consumed;
+
+        char escaped_buf[ESCAPED_SIZE];
+        size_t escaped_len = char_to_string(ch, '"', first, &escaped_buf);
+        if (out != NULL) {
+            if (cur_out_len < escaped_len) {
+                return NtsOverflow;
+            }
+            memcpy(out, escaped_buf, escaped_len);
+            out += escaped_len;
+            cur_out_len -= escaped_len;
+        }
+        first = false;
+    }
+
+    // write ending quote
+    if (out != NULL) {
+        if (cur_out_len == 0) {
+            return NtsOverflow;
+        }
+        *out++ = quote;
+        cur_out_len--;
+        *out_len -= cur_out_len; // subtract remaining space to get used space
+    }
+
+    return NtsOk;
+}
+
+static const char* basic_type(uint8_t tag) {
+    switch(tag) {
+        case 'b':
+        return "bool";
+        case 'c':
+        return "char";
+        case 'e':
+        return "str";
+        case 'u':
+        return "()";
+        case 'a':
+        return "i8";
+        case 's':
+        return "i16";
+        case 'l':
+        return "i32";
+        case 'x':
+        return "i64";
+        case 'n':
+        return "i128";
+        case 'i':
+        return "isize";
+        case 'h':
+        return "u8";
+        case 't':
+        return "u16";
+        case 'm':
+        return "u32";
+        case 'y':
+        return "u64";
+        case 'o':
+        return "u128";
+        case 'j':
+        return "usize";
+        case 'f':
+        return "f32";
+        case 'd':
+        return "f64";
+        case 'z':
+        return "!";
+        case 'p':
+        return "_";
+        case 'v':
+        return "...";
+        default:
+        return NULL;
+    }
+}
+
+static NODISCARD demangle_status parser_push_depth(struct parser *parser) {
+    parser->depth++;
+    if (parser->depth > MAX_DEPTH) {
+        return DemangleRecursed;
+    } else {
+        return DemangleOk;
+    }
+}
+
+static demangle_status parser_pop_depth(struct parser *parser) {
+    parser->depth--;
+    return DemangleOk;
+}
+
+static uint8_t parser_peek(struct parser const *parser) {
+    if (parser->next == parser->sym_len) {
+        return 0; // add a "pseudo nul terminator" to avoid peeking past the end of a symbol
+    } else {
+        return parser->sym[parser->next];
+    }
+}
+
+static bool parser_eat(struct parser *parser, uint8_t ch) {
+    if (parser_peek(parser) == ch) {
+        if (ch != 0) { // safety: make sure we don't skip past the NUL terminator
+            parser->next++;
+        }
+        return true;
+    } else {
+        return false;
+    }
+}
+
+static uint8_t parser_next(struct parser *parser) {
+    // don't advance after end of input, and return an imaginary NUL terminator
+    if (parser->next == parser->sym_len) {
+        return 0;
+    } else {
+        return parser->sym[parser->next++];
+    }
+}
+
+static NODISCARD demangle_status parser_ch(struct parser *parser, uint8_t *next) {
+    // don't advance after end of input
+    if (parser->next == parser->sym_len) {
+        return DemangleInvalid;
+    } else {
+        *next = parser->sym[parser->next++];
+        return DemangleOk;
+    }
+}
+
+struct buf {
+    const char *start;
+    size_t len;
+};
+
+static NODISCARD demangle_status parser_hex_nibbles(struct parser *parser, struct buf *buf) {
+    size_t start = parser->next;
+    for (;;) {
+        uint8_t ch = parser_next(parser);
+        if (ch == '_') {
+            break;
+        }
+        if (!(('0' <= ch && ch <= '9') || ('a' <= ch && ch <= 'f'))) {
+            return DemangleInvalid;
+        }
+    }
+    buf->start = parser->sym + start;
+    buf->len = parser->next - start - 1; // skip final _
+    return DemangleOk;
+}
+
+static NODISCARD demangle_status parser_digit_10(struct parser *parser, uint8_t *out) {
+    uint8_t ch = parser_peek(parser);
+    if ('0' <= ch && ch <= '9') {
+        *out = ch - '0';
+        parser->next++;
+        return DemangleOk;
+    } else {
+        return DemangleInvalid;
+    }
+}
+
+static NODISCARD demangle_status parser_digit_62(struct parser *parser, uint64_t *out) {
+    uint8_t ch = parser_peek(parser);
+    if ('0' <= ch && ch <= '9') {
+        *out = ch - '0';
+        parser->next++;
+        return DemangleOk;
+    } else if ('a' <= ch && ch <= 'z') {
+        *out = 10 + (ch - 'a');
+        parser->next++;
+        return DemangleOk;
+    } else if ('A' <= ch && ch <= 'Z') {
+        *out = 10 + 26 + (ch - 'A');
+        parser->next++;
+        return DemangleOk;
+    } else {
+        return DemangleInvalid;
+    }
+}
+
+static NODISCARD demangle_status parser_integer_62(struct parser *parser, uint64_t *out) {
+    if (parser_eat(parser, '_')) {
+        *out = 0;
+        return DemangleOk;
+    }
+
+    uint64_t x = 0;
+    demangle_status status;
+    while (!parser_eat(parser, '_')) {
+        uint64_t d;
+        if ((status = parser_digit_62(parser, &d)) != DemangleOk) {
+            return status;
+        }
+        if (x > UINT64_MAX / 62) {
+            return DemangleInvalid;
+        }
+        x *= 62;
+        if (x > UINT64_MAX - d) {
+            return DemangleInvalid;
+        }
+        x += d;
+    }
+    if (x == UINT64_MAX) {
+        return DemangleInvalid;
+    }
+    *out = x + 1;
+    return DemangleOk;
+}
+
+static NODISCARD demangle_status parser_opt_integer_62(struct parser *parser, uint8_t tag, uint64_t *out) {
+    if (!parser_eat(parser, tag)) {
+        *out = 0;
+        return DemangleOk;
+    }
+
+    demangle_status status;
+    if ((status = parser_integer_62(parser, out)) != DemangleOk) {
+        return status;
+    }
+    if (*out == UINT64_MAX) {
+        return DemangleInvalid;
+    }
+    *out = *out + 1;
+    return DemangleOk;
+}
+
+static NODISCARD demangle_status parser_disambiguator(struct parser *parser, uint64_t *out) {
+    return parser_opt_integer_62(parser, 's', out);
+}
+
+typedef uint8_t parser_namespace_type;
+
+static NODISCARD demangle_status parser_namespace(struct parser *parser, parser_namespace_type *out) {
+    uint8_t next = parser_next(parser);
+    if ('A' <= next && next <= 'Z') {
+        *out = next;
+        return DemangleOk;
+    } else if ('a' <= next && next <= 'z') {
+        *out = 0;
+        return DemangleOk;
+    } else {
+        return DemangleInvalid;
+    }
+}
+
+static NODISCARD demangle_status parser_backref(struct parser *parser, struct parser *out) {
+    size_t start = parser->next;
+    if (start == 0) {
+        return DemangleBug;
+    }
+    size_t s_start = start - 1;
+    uint64_t i;
+    demangle_status status = parser_integer_62(parser, &i);
+    if (status != DemangleOk) {
+        return status;
+    }
+    if (i >= s_start) {
+        return DemangleInvalid;
+    }
+    struct parser res = {
+        .sym = parser->sym,
+        .sym_len = parser->sym_len,
+        .next = (size_t)i,
+        .depth = parser->depth
+    };
+    status = parser_push_depth(&res);
+    if (status != DemangleOk) {
+        return status;
+    }
+    *out = res;
+    return DemangleOk;
+}
+
+static NODISCARD demangle_status parser_ident(struct parser *parser, struct ident *out) {
+    bool is_punycode = parser_eat(parser, 'u');
+    size_t len;
+    uint8_t d;
+    demangle_status status = parser_digit_10(parser, &d);
+    len = d;
+    if (status != DemangleOk) {
+        return status;
+    }
+    if (len) {
+        for (;;) {
+            status = parser_digit_10(parser, &d);
+            if (status != DemangleOk) {
+                break;
+            }
+            if (len > SIZE_MAX / 10) {
+                return DemangleInvalid;
+            }
+            len *= 10;
+            if (len > SIZE_MAX - d) {
+                return DemangleInvalid;
+            }
+            len += d;
+        }
+    }
+
+    // Skip past the optional `_` separator.
+    parser_eat(parser, '_');
+
+    size_t start = parser->next;
+    if (parser->sym_len - parser->next < len) {
+        return DemangleInvalid;
+    }
+    parser->next += len;
+
+    const char *ident = &parser->sym[start];
+
+    if (is_punycode) {
+        const char *underscore = demangle_memrchr(ident, '_', (size_t)len);
+        if (underscore == NULL) {
+            *out = (struct ident){
+                .ascii_start="",
+                .ascii_len=0,
+                .punycode_start=ident,
+                .punycode_len=len
+            };
+        } else {
+            size_t ascii_len = underscore - ident;
+            // ascii_len <= len - 1 since `_` is in the first len bytes
+            size_t punycode_len = len - 1 - ascii_len;
+            *out = (struct ident){
+                .ascii_start=ident,
+                .ascii_len=ascii_len,
+                .punycode_start=underscore + 1,
+                .punycode_len=punycode_len
+            };
+        }
+        if (out->punycode_len == 0) {
+            return DemangleInvalid;
+        }
+        return DemangleOk;
+    } else {
+        *out = (struct ident) {
+            .ascii_start=ident,
+            .ascii_len=(size_t)len,
+            .punycode_start="",
+            .punycode_len=0,
+        };
+        return DemangleOk;
+    }
+}
+
+#define INVALID_SYNTAX "{invalid syntax}"
+
+static const char *demangle_error_message(demangle_status status) {
+    switch (status) {
+        case DemangleInvalid:
+        return INVALID_SYNTAX;
+        case DemangleBug:
+        return "{bug}";
+        case DemangleRecursed:
+        return "{recursion limit reached}";
+        default:
+        return "{unknown error}";
+    }
+}
+
+#define PRINT(print_fn) \
+ do { \
+   if ((print_fn) == OverflowOverflow) { \
+    return OverflowOverflow; \
+   } \
+ } while(0)
+
+#define PRINT_CH(printer, s) PRINT(printer_print_ch((printer), (s)))
+#define PRINT_STR(printer, s) PRINT(printer_print_str((printer), (s)))
+#define PRINT_U64(printer, s) PRINT(printer_print_u64((printer), (s)))
+#define PRINT_IDENT(printer, s) PRINT(printer_print_ident((printer), (s)))
+
+#define INVALID(printer) \
+  do { \
+    PRINT_STR((printer), INVALID_SYNTAX); \
+    (printer)->status = DemangleInvalid; \
+    return OverflowOk; \
+  } while(0)
+
+#define PARSE(printer, method, ...) \
+  do { \
+    if ((printer)->status != DemangleOk) { \
+      PRINT_STR((printer), "?"); \
+      return OverflowOk; \
+    } else { \
+      demangle_status _parse_status = method(&(printer)->parser, ## __VA_ARGS__); \
+      if (_parse_status != DemangleOk) { \
+        PRINT_STR((printer), demangle_error_message(_parse_status)); \
+        (printer)->status = _parse_status; \
+        return OverflowOk; \
+      } \
+    } \
+  } while(0)
+
+#define PRINT_SEP_LIST(printer, body, sep) \
+  do { \
+    size_t _sep_list_i; \
+    PRINT_SEP_LIST_COUNT(printer, _sep_list_i, body, sep); \
+  } while(0)
+
+#define PRINT_SEP_LIST_COUNT(printer, count, body, sep) \
+  do { \
+    count = 0; \
+    while ((printer)->status == DemangleOk && !printer_eat((printer), 'E')) { \
+      if (count > 0) { PRINT_STR(printer, sep); } \
+      body; \
+      count++; \
+    } \
+  } while(0)
+
+static bool printer_eat(struct printer *printer, uint8_t b) {
+    if (printer->status != DemangleOk) {
+        return false;
+    }
+
+    return parser_eat(&printer->parser, b);
+}
+
+static void printer_pop_depth(struct printer *printer) {
+    if (printer->status == DemangleOk) {
+        parser_pop_depth(&printer->parser);
+    }
+}
+
+static NODISCARD overflow_status printer_print_buf(struct printer *printer, const char *start, size_t len) {
+    if (printer->out == NULL) {
+        return OverflowOk;
+    }
+    if (printer->out_len < len) {
+        return OverflowOverflow;
+    }
+
+    memcpy(printer->out, start, len);
+    printer->out += len;
+    printer->out_len -= len;
+    return OverflowOk;
+}
+
+static NODISCARD overflow_status printer_print_str(struct printer *printer, const char *buf) {
+    return printer_print_buf(printer, buf, strlen(buf));
+}
+
+static NODISCARD overflow_status printer_print_ch(struct printer *printer, char ch) {
+    return printer_print_buf(printer, &ch, 1);
+}
+
+static NODISCARD overflow_status printer_print_u64(struct printer *printer, uint64_t n) {
+    char buf[32] = {0};
+    sprintf(buf, "%llu", (unsigned long long)n); // printing uint64 uses 21 < 32 chars
+    return printer_print_str(printer, buf);
+}
+
+static NODISCARD overflow_status printer_print_ident(struct printer *printer, struct ident *ident) {
+    if (printer->out == NULL) {
+        return OverflowOk;
+    }
+
+    size_t out_len = printer->out_len;
+    overflow_status status;
+    if ((status = display_ident(ident->ascii_start, ident->ascii_len, ident->punycode_start, ident->punycode_len, (uint8_t*)printer->out, &out_len)) != OverflowOk) {
+        return status;
+    }
+    printer->out += out_len;
+    printer->out_len -= out_len;
+    return OverflowOk;
+}
+
+typedef overflow_status (*printer_fn)(struct printer *printer);
+typedef overflow_status (*backref_fn)(struct printer *printer, bool *arg);
+
+static NODISCARD overflow_status printer_print_backref(struct printer *printer, backref_fn func, bool *arg) {
+    struct parser backref;
+    PARSE(printer, parser_backref, &backref);
+
+    if (printer->out == NULL) {
+        return OverflowOk;
+    }
+
+    struct parser orig_parser = printer->parser;
+    demangle_status orig_status = printer->status; // fixme not sure this is needed match for Ok on the Rust side
+    printer->parser = backref;
+    printer->status = DemangleOk;
+    overflow_status status = func(printer, arg);
+    printer->parser = orig_parser;
+    printer->status = orig_status;
+
+    return status;
+}
+
+static NODISCARD overflow_status printer_print_lifetime_from_index(struct printer *printer, uint64_t lt) {
+    // Bound lifetimes aren't tracked when skipping printing.
+    if (printer->out == NULL) {
+        return OverflowOk;
+    }
+
+    PRINT_STR(printer, "'");
+    if (lt == 0) {
+        PRINT_STR(printer, "_");
+        return OverflowOk;
+    }
+
+    if (printer->bound_lifetime_depth < lt) {
+        INVALID(printer);
+    } else {
+        uint64_t depth = printer->bound_lifetime_depth - lt;
+        if (depth < 26) {
+            PRINT_CH(printer, 'a' + depth);
+        } else {
+            PRINT_STR(printer, "_");
+            PRINT_U64(printer, depth);
+        }
+
+        return OverflowOk;
+    }
+}
+
+static NODISCARD overflow_status printer_in_binder(struct printer *printer, printer_fn func) {
+    uint64_t bound_lifetimes;
+    PARSE(printer, parser_opt_integer_62, 'G', &bound_lifetimes);
+
+    // Don't track bound lifetimes when skipping printing.
+    if (printer->out == NULL) {
+        return func(printer);
+    }
+
+    if (bound_lifetimes > 0) {
+        PRINT_STR(printer, "for<");
+        for (uint64_t i = 0; i < bound_lifetimes; i++) {
+            if (i > 0) {
+                PRINT_STR(printer, ", ");
+            }
+            printer->bound_lifetime_depth++;
+            PRINT(printer_print_lifetime_from_index(printer, 1));
+        }
+        PRINT_STR(printer, "> ");
+    }
+
+    overflow_status r = func(printer);
+    printer->bound_lifetime_depth -= bound_lifetimes;
+
+    return r;
+}
+
+static NODISCARD overflow_status printer_print_generic_arg(struct printer *printer) {
+    if (printer_eat(printer, 'L')) {
+        uint64_t lt;
+        PARSE(printer, parser_integer_62, &lt);
+        return printer_print_lifetime_from_index(printer, lt);
+    } else if (printer_eat(printer, 'K')) {
+        return printer_print_const(printer, false);
+    } else {
+        return printer_print_type(printer);
+    }
+}
+
+static NODISCARD overflow_status printer_print_generic_args(struct printer *printer) {
+    PRINT_STR(printer, "<");
+    PRINT_SEP_LIST(printer, PRINT(printer_print_generic_arg(printer)), ", ");
+    PRINT_STR(printer, ">");
+    return OverflowOk;
+}
+
+static NODISCARD overflow_status printer_print_path_out_of_value(struct printer *printer, bool *_arg) {
+    (void)_arg;
+    return printer_print_path(printer, false);
+}
+
+static NODISCARD overflow_status printer_print_path_in_value(struct printer *printer, bool *_arg) {
+    (void)_arg;
+    return printer_print_path(printer, true);
+}
+
+static NODISCARD overflow_status printer_print_path(struct printer *printer, bool in_value) {
+    PARSE(printer, parser_push_depth);
+    uint8_t tag;
+    PARSE(printer, parser_ch, &tag);
+
+    overflow_status st;
+    uint64_t dis;
+    struct ident name;
+    parser_namespace_type ns;
+    char *orig_out;
+
+    switch(tag) {
+    case 'C':
+        PARSE(printer, parser_disambiguator, &dis);
+        PARSE(printer, parser_ident, &name);
+
+        PRINT_IDENT(printer, &name);
+
+        if (printer->out != NULL && !printer->alternate && dis != 0) {
+            PRINT_STR(printer, "[");
+            char buf[24] = {0};
+            sprintf(buf, "%llx", (unsigned long long)dis);
+            PRINT_STR(printer, buf);
+            PRINT_STR(printer, "]");
+        }
+        break;
+    case 'N':
+        PARSE(printer, parser_namespace, &ns);
+        if ((st = printer_print_path(printer, in_value)) != OverflowOk) {
+            return st;
+        }
+
+        // HACK(eddyb) if the parser is already marked as having errored,
+        // `parse!` below will print a `?` without its preceding `::`
+        // (because printing the `::` is skipped in certain conditions,
+        // i.e. a lowercase namespace with an empty identifier),
+        // so in order to get `::?`, the `::` has to be printed here.
+        if (printer->status != DemangleOk) {
+            PRINT_STR(printer, "::");
+        }
+
+        PARSE(printer, parser_disambiguator, &dis);
+        PARSE(printer, parser_ident, &name);
+        // Special namespace, like closures and shims
+        if (ns) {
+            PRINT_STR(printer, "::{");
+            if (ns == 'C') {
+                PRINT_STR(printer, "closure");
+            } else if (ns == 'S') {
+                PRINT_STR(printer, "shim");
+            } else {
+                PRINT_CH(printer, ns);
+            }
+            if (name.ascii_len != 0 || name.punycode_len != 0) {
+                PRINT_STR(printer, ":");
+                PRINT_IDENT(printer, &name);
+            }
+            PRINT_STR(printer, "#");
+            PRINT_U64(printer, dis);
+            PRINT_STR(printer, "}");
+        } else {
+            // Implementation-specific/unspecified namespaces
+            if (name.ascii_len != 0 || name.punycode_len != 0) {
+                PRINT_STR(printer, "::");
+                PRINT_IDENT(printer, &name);
+            }
+        }
+        break;
+    case 'M':
+    case 'X':
+    // for impls, ignore the impls own path
+    PARSE(printer, parser_disambiguator, &dis);
+    orig_out = printer->out;
+    printer->out = NULL;
+    PRINT(printer_print_path(printer, false));
+    printer->out = orig_out;
+
+    // fallthru
+    case 'Y':
+    PRINT_STR(printer, "<");
+    PRINT(printer_print_type(printer));
+    if (tag != 'M') {
+        PRINT_STR(printer, " as ");
+        PRINT(printer_print_path(printer, false));
+    }
+    PRINT_STR(printer, ">");
+    break;
+    case 'I':
+    PRINT(printer_print_path(printer, in_value));
+    if (in_value) {
+        PRINT_STR(printer, "::");
+    }
+    PRINT(printer_print_generic_args(printer));
+    break;
+    case 'B':
+    PRINT(printer_print_backref(printer, in_value ? printer_print_path_in_value : printer_print_path_out_of_value, NULL));
+    break;
+    default:
+    INVALID(printer);
+    break;
+    }
+
+    printer_pop_depth(printer);
+    return OverflowOk;
+}
+
+static NODISCARD overflow_status printer_print_const_uint(struct printer *printer, uint8_t tag) {
+    struct buf hex;
+    PARSE(printer, parser_hex_nibbles, &hex);
+
+    uint64_t val;
+    if (try_parse_uint(hex.start, hex.len, &val)) {
+        PRINT_U64(printer, val);
+    } else {
+        PRINT_STR(printer, "0x");
+        PRINT(printer_print_buf(printer, hex.start, hex.len));
+    }
+
+    if (printer->out != NULL && !printer->alternate) {
+        const char *ty = basic_type(tag);
+        if (/* safety */ ty != NULL) {
+            PRINT_STR(printer, ty);
+        }
+    }
+
+    return OverflowOk;
+}
+
+static NODISCARD overflow_status printer_print_const_str_literal(struct printer *printer) {
+    struct buf hex;
+    PARSE(printer, parser_hex_nibbles, &hex);
+
+    size_t out_len = SIZE_MAX;
+    nibbles_to_string_status nts_status = nibbles_to_string(hex.start, hex.len, NULL, &out_len);
+    switch (nts_status) {
+    case NtsOk:
+        if (printer->out != NULL) {
+            out_len = printer->out_len;
+            nts_status = nibbles_to_string(hex.start, hex.len, (uint8_t*)printer->out, &out_len);
+            if (nts_status != NtsOk) {
+                return OverflowOverflow;
+            }
+            printer->out += out_len;
+            printer->out_len -= out_len;
+        }
+        return OverflowOk;
+    case NtsOverflow:
+        // technically if there is a string of size `SIZE_MAX/6` whose escaped version overflows
+        // SIZE_MAX but has an invalid char, this will be a "fake" overflow. In practice,
+        // that is not going to happen and a fuzzer will not generate strings of this length.
+        return OverflowOverflow;
+    case NtsInvalid:
+    default:
+        INVALID(printer);
+    }
+}
+
+static NODISCARD overflow_status printer_print_const_struct(struct printer *printer) {
+    uint64_t dis;
+    struct ident name;
+    PARSE(printer, parser_disambiguator, &dis);
+    PARSE(printer, parser_ident, &name);
+    PRINT_IDENT(printer, &name);
+    PRINT_STR(printer, ": ");
+    return printer_print_const(printer, true);
+}
+
+static NODISCARD overflow_status printer_print_const_out_of_value(struct printer *printer, bool *_arg) {
+    (void)_arg;
+    return printer_print_const(printer, false);
+}
+
+static NODISCARD overflow_status printer_print_const_in_value(struct printer *printer, bool *_arg) {
+    (void)_arg;
+    return printer_print_const(printer, true);
+}
+
+static NODISCARD overflow_status printer_print_const(struct printer *printer, bool in_value) {
+    uint8_t tag;
+
+    PARSE(printer, parser_ch, &tag);
+    PARSE(printer, parser_push_depth);
+
+    struct buf hex;
+    uint64_t val;
+    size_t count;
+
+    bool opened_brace = false;
+#define OPEN_BRACE_IF_OUTSIDE_EXPR \
+        do { if (!in_value) { \
+            opened_brace = true; \
+            PRINT_STR(printer, "{"); \
+        } } while(0)
+
+    switch(tag) {
+    case 'p':
+        PRINT_STR(printer, "_");
+        break;
+    // Primitive leaves with hex-encoded values (see `basic_type`).
+    case 'a':
+    case 's':
+    case 'l':
+    case 'x':
+    case 'n':
+    case 'i':
+        if (printer_eat(printer, 'n')) {
+            PRINT_STR(printer, "-");
+        }
+        /* fallthrough */
+    case 'h':
+    case 't':
+    case 'm':
+    case 'y':
+    case 'o':
+    case 'j':
+        PRINT(printer_print_const_uint(printer, tag));
+        break;
+    case 'b':
+        PARSE(printer, parser_hex_nibbles, &hex);
+        if (try_parse_uint(hex.start, hex.len, &val)) {
+            if (val == 0) {
+                PRINT_STR(printer, "false");
+            } else if (val == 1) {
+                PRINT_STR(printer, "true");
+            } else {
+                INVALID(printer);
+            }
+        } else {
+            INVALID(printer);
+        }
+        break;
+    case 'c':
+        PARSE(printer, parser_hex_nibbles, &hex);
+        if (try_parse_uint(hex.start, hex.len, &val)
+            && val < UINT32_MAX
+            && validate_char((uint32_t)val))
+        {
+            char escaped_buf[ESCAPED_SIZE];
+            size_t escaped_size = char_to_string((uint32_t)val, '\'', true, &escaped_buf);
+
+            PRINT_STR(printer, "'");
+            PRINT(printer_print_buf(printer, escaped_buf, escaped_size));
+            PRINT_STR(printer, "'");
+        } else {
+            INVALID(printer);
+        }
+        break;
+    case 'e':
+        OPEN_BRACE_IF_OUTSIDE_EXPR;
+        PRINT_STR(printer, "*");
+        PRINT(printer_print_const_str_literal(printer));
+        break;
+    case 'R':
+    case 'Q':
+        if (tag == 'R' && printer_eat(printer, 'e')) {
+            PRINT(printer_print_const_str_literal(printer));
+        } else {
+            OPEN_BRACE_IF_OUTSIDE_EXPR;
+            PRINT_STR(printer, "&");
+            if (tag != 'R') {
+                PRINT_STR(printer, "mut ");
+            }
+            PRINT(printer_print_const(printer, true));
+        }
+        break;
+    case 'A':
+        OPEN_BRACE_IF_OUTSIDE_EXPR;
+        PRINT_STR(printer, "[");
+        PRINT_SEP_LIST(printer, PRINT(printer_print_const(printer, true)), ", ");
+        PRINT_STR(printer, "]");
+        break;
+    case 'T':
+        OPEN_BRACE_IF_OUTSIDE_EXPR;
+        PRINT_STR(printer, "(");
+        PRINT_SEP_LIST_COUNT(printer, count, PRINT(printer_print_const(printer, true)), ", ");
+        if (count == 1) {
+            PRINT_STR(printer, ",");
+        }
+        PRINT_STR(printer, ")");
+        break;
+    case 'V':
+        OPEN_BRACE_IF_OUTSIDE_EXPR;
+        PRINT(printer_print_path(printer, true));
+        PARSE(printer, parser_ch, &tag);
+        switch(tag) {
+        case 'U':
+        break;
+        case 'T':
+        PRINT_STR(printer, "(");
+        PRINT_SEP_LIST(printer, PRINT(printer_print_const(printer, true)), ", ");
+        PRINT_STR(printer, ")");
+        break;
+        case 'S':
+        PRINT_STR(printer, " { ");
+        PRINT_SEP_LIST(printer, PRINT(printer_print_const_struct(printer)), ", ");
+        PRINT_STR(printer, " }");
+        break;
+        default:
+        INVALID(printer);
+        }
+        break;
+    case 'B':
+        PRINT(printer_print_backref(printer, in_value ? printer_print_const_in_value : printer_print_const_out_of_value, NULL));
+        break;
+    default:
+        INVALID(printer);
+    }
+#undef OPEN_BRACE_IF_OUTSIDE_EXPR
+
+    if (opened_brace) {
+        PRINT_STR(printer, "}");
+    }
+    printer_pop_depth(printer);
+
+    return OverflowOk;
+}
+
+/// A trait in a trait object may have some "existential projections"
+/// (i.e. associated type bindings) after it, which should be printed
+/// in the `<...>` of the trait, e.g. `dyn Trait<T, U, Assoc=X>`.
+/// To this end, this method will keep the `<...>` of an 'I' path
+/// open, by omitting the `>`, and return `Ok(true)` in that case.
+static NODISCARD overflow_status printer_print_maybe_open_generics(struct printer *printer, bool *open) {
+    if (printer_eat(printer, 'B')) {
+        // NOTE(eddyb) the closure may not run if printing is being skipped,
+        // but in that case the returned boolean doesn't matter.
+        *open = false;
+        return printer_print_backref(printer, printer_print_maybe_open_generics, open);
+    } else if(printer_eat(printer, 'I')) {
+        PRINT(printer_print_path(printer, false));
+        PRINT_STR(printer, "<");
+        PRINT_SEP_LIST(printer, PRINT(printer_print_generic_arg(printer)), ", ");
+        *open = true;
+        return OverflowOk;
+    } else {
+        PRINT(printer_print_path(printer, false));
+        *open = false;
+        return OverflowOk;
+    }
+}
+
+static NODISCARD overflow_status printer_print_dyn_trait(struct printer *printer) {
+    bool open;
+    PRINT(printer_print_maybe_open_generics(printer, &open));
+
+    while (printer_eat(printer, 'p')) {
+        if (!open) {
+            PRINT_STR(printer, "<");
+            open = true;
+        } else {
+            PRINT_STR(printer, ", ");
+        }
+
+        struct ident name;
+        PARSE(printer, parser_ident, &name);
+
+        PRINT_IDENT(printer, &name);
+        PRINT_STR(printer, " = ");
+        PRINT(printer_print_type(printer));
+    }
+
+    if (open) {
+        PRINT_STR(printer, ">");
+    }
+
+    return OverflowOk;
+}
+
+static NODISCARD overflow_status printer_print_object_bounds(struct printer *printer) {
+    PRINT_SEP_LIST(printer, PRINT(printer_print_dyn_trait(printer)), " + ");
+    return OverflowOk;
+}
+
+static NODISCARD overflow_status printer_print_function_type(struct printer *printer) {
+    bool is_unsafe = printer_eat(printer, 'U');
+    const char *abi;
+    size_t abi_len;
+    if (printer_eat(printer, 'K')) {
+        if (printer_eat(printer, 'C')) {
+            abi = "C";
+            abi_len = 1;
+        } else {
+            struct ident abi_ident;
+            PARSE(printer, parser_ident, &abi_ident);
+            if (abi_ident.ascii_len == 0 || abi_ident.punycode_len != 0) {
+                INVALID(printer);
+            }
+            abi = abi_ident.ascii_start;
+            abi_len = abi_ident.ascii_len;
+        }
+    } else {
+        abi = NULL;
+        abi_len = 0;
+    }
+
+    if (is_unsafe) {
+        PRINT_STR(printer, "unsafe ");
+    }
+
+    if (abi != NULL) {
+        PRINT_STR(printer, "extern \"");
+
+        // replace _ with -
+        while (abi_len > 0) {
+            const char *minus = memchr(abi, '_', abi_len);
+            if (minus == NULL) {
+                PRINT(printer_print_buf(printer, (const char*)abi, abi_len));
+                break;
+            } else {
+                size_t space_to_minus = minus - abi;
+                PRINT(printer_print_buf(printer, (const char*)abi, space_to_minus));
+                PRINT_STR(printer, "-");
+                abi = minus + 1;
+                abi_len -= (space_to_minus + 1);
+            }
+        }
+
+        PRINT_STR(printer, "\" ");
+    }
+
+    PRINT_STR(printer, "fn(");
+    PRINT_SEP_LIST(printer, PRINT(printer_print_type(printer)), ", ");
+    PRINT_STR(printer, ")");
+
+    if (printer_eat(printer, 'u')) {
+        // Skip printing the return type if it's 'u', i.e. `()`.
+    } else {
+        PRINT_STR(printer, " -> ");
+        PRINT(printer_print_type(printer));
+    }
+
+    return OverflowOk;
+}
+
+static NODISCARD overflow_status printer_print_type_backref(struct printer *printer, bool *_arg) {
+    (void)_arg;
+    return printer_print_type(printer);
+}
+
+static NODISCARD overflow_status printer_print_type(struct printer *printer) {
+    uint8_t tag;
+    PARSE(printer, parser_ch, &tag);
+
+    const char *basic_ty = basic_type(tag);
+    if (basic_ty) {
+        return printer_print_str(printer, basic_ty);
+    }
+
+    uint64_t count;
+    uint64_t lt;
+
+    PARSE(printer, parser_push_depth);
+    switch (tag) {
+    case 'R':
+    case 'Q':
+        PRINT_STR(printer, "&");
+        if (printer_eat(printer, 'L')) {
+            PARSE(printer, parser_integer_62, &lt);
+            if (lt != 0) {
+                PRINT(printer_print_lifetime_from_index(printer, lt));
+                PRINT_STR(printer, " ");
+            }
+        }
+        if (tag != 'R') {
+            PRINT_STR(printer, "mut ");
+        }
+        PRINT(printer_print_type(printer));
+        break;
+    case 'P':
+    case 'O':
+        PRINT_STR(printer, "*");
+        if (tag != 'P') {
+            PRINT_STR(printer, "mut ");
+        } else {
+            PRINT_STR(printer, "const ");
+        }
+        PRINT(printer_print_type(printer));
+        break;
+    case 'A':
+    case 'S':
+        PRINT_STR(printer, "[");
+        PRINT(printer_print_type(printer));
+        if (tag == 'A') {
+            PRINT_STR(printer, "; ");
+            PRINT(printer_print_const(printer, true));
+        }
+        PRINT_STR(printer, "]");
+        break;
+    case 'T':
+        PRINT_STR(printer, "(");
+        PRINT_SEP_LIST_COUNT(printer, count, PRINT(printer_print_type(printer)), ", ");
+        if (count == 1) {
+            PRINT_STR(printer, ",");
+        }
+        PRINT_STR(printer, ")");
+        break;
+    case 'F':
+        PRINT(printer_in_binder(printer, printer_print_function_type));
+        break;
+    case 'D':
+        PRINT_STR(printer, "dyn ");
+        PRINT(printer_in_binder(printer, printer_print_object_bounds));
+
+        if (!printer_eat(printer, 'L')) {
+            INVALID(printer);
+        }
+        PARSE(printer, parser_integer_62, &lt);
+
+        if (lt != 0) {
+            PRINT_STR(printer, " + ");
+            PRINT(printer_print_lifetime_from_index(printer, lt));
+        }
+        break;
+    case 'B':
+        PRINT(printer_print_backref(printer, printer_print_type_backref, NULL));
+        break;
+    default:
+        // Go back to the tag, so `print_path` also sees it.
+        if (printer->status == DemangleOk && /* safety */ printer->parser.next > 0) {
+            printer->parser.next--;
+        }
+        PRINT(printer_print_path(printer, false));
+    }
+
+    printer_pop_depth(printer);
+    return OverflowOk;
+}
+
+NODISCARD static demangle_status rust_demangle_legacy_demangle(const char *s, size_t s_len, struct demangle_legacy *res, const char **rest)
+{
+    if (s_len > strlen(s)) {
+        // s_len only exists to shorten the string, this is not a buffer API
+        return DemangleInvalid;
+    }
+
+    const char *inner;
+    size_t inner_len;
+    if (s_len >= 3 && !strncmp(s, "_ZN", 3)) {
+        inner = s + 3;
+        inner_len = s_len - 3;
+    } else if (s_len >= 2 && !strncmp(s, "ZN", 2)) {
+        // On Windows, dbghelp strips leading underscores, so we accept "ZN...E"
+        // form too.
+        inner = s + 2;
+        inner_len = s_len - 2;
+    } else if (s_len >= 4 && !strncmp(s, "__ZN", 4)) {
+        // On OSX, symbols are prefixed with an extra _
+        inner = s + 4;
+        inner_len = s_len - 4;
+    } else {
+        return DemangleInvalid;
+    }
+
+    if (!str_isascii(inner, inner_len)) {
+        return DemangleInvalid;
+    }
+
+    size_t elements = 0;
+    const char *chars = inner;
+    size_t chars_len = inner_len;
+    if (chars_len == 0) {
+        return DemangleInvalid;
+    }
+    char c;
+    while ((c = *chars) != 'E') {
+        // Decode an identifier element's length
+        if (c < '0' || c > '9') {
+            return DemangleInvalid;
+        }
+        size_t len = 0;
+        while (c >= '0' && c <= '9') {
+            size_t d = c - '0';
+            if (len > SIZE_MAX / 10) {
+                return DemangleInvalid;
+            }
+            len *= 10;
+            if (len > SIZE_MAX - d) {
+                return DemangleInvalid;
+            }
+            len += d;
+
+            chars++;
+            chars_len--;
+            if (chars_len == 0) {
+                return DemangleInvalid;
+            }
+            c = *chars;
+        }
+
+        // Advance by the length
+        if (chars_len <= len) {
+            return DemangleInvalid;
+        }
+        chars += len;
+        chars_len -= len;
+        elements++;
+    }
+    *res = (struct demangle_legacy) { inner, inner_len, elements };
+    *rest = chars + 1;
+    return DemangleOk;
+}
+
+static bool is_rust_hash(const char *s, size_t len) {
+    if (len == 0 || s[0] != 'h') {
+        return false;
+    }
+
+    for (size_t i = 1; i < len; i++) {
+        if (!((s[i] >= '0' && s[i] <= '9') || (s[i] >= 'a' && s[i] <= 'f') || (s[i] >= 'A' && s[i] <= 'F'))) {
+            return false;
+        }
+    }
+
+    return true;
+}
+
+NODISCARD static overflow_status rust_demangle_legacy_display_demangle(struct demangle_legacy res, char *out, size_t len, bool alternate)
+{
+    struct printer printer = {
+        // not actually using the parser part of the printer, just keeping it to share the format functions
+        DemangleOk,
+        { NULL },
+        out,
+        len,
+        0,
+        alternate
+    };
+    const char *inner = res.mangled;
+    for (size_t element = 0; element < res.elements; element++) {
+        size_t i = 0;
+        const char *rest;
+        for (rest = inner; rest < res.mangled + res.mangled_len && *rest >= '0' && *rest <= '9'; rest++) {
+            i *= 10;
+            i += *rest - '0';
+        }
+        if ((size_t)(res.mangled + res.mangled_len - rest) < i) {
+            // safety: shouldn't reach this place if the input string is validated. bail out.
+            // safety: we knwo rest <= res.mangled + res.mangled_len from the for-loop above
+            break;
+        }
+
+        size_t len = i;
+        inner = rest + len;
+
+        // From here on, inner contains a pointer to the next element, rest[:len] to the current one
+        if (alternate && element + 1 == res.elements && is_rust_hash(rest, i)) {
+            break;
+        }
+        if (element != 0) {
+            PRINT_STR(&printer, "::");
+        }
+
+        if (len >= 2 && !strncmp(rest, "_$", 2)) {
+            rest++;
+            len--;
+        }
+
+        while (len > 0) {
+            if (rest[0] == '.') {
+                if (len >= 2 && rest[1] == '.') {
+                    PRINT_STR(&printer, "::");
+                    rest += 2;
+                    len -= 2;
+                } else {
+                    PRINT_STR(&printer, ".");
+                    rest += 1;
+                    len -= 1;
+                }
+            } else if (rest[0] == '$') {
+                const char *escape = memchr(rest + 1, '$', len - 1);
+                if (escape == NULL) {
+                    break;
+                }
+                const char *escape_start = rest + 1;
+                size_t escape_len = escape - (rest + 1);
+
+                size_t next_len = len - (escape + 1 - rest);
+                const char *next_rest = escape + 1;
+
+                char ch;
+                if ((escape_len == 2 && escape_start[0] == 'S' && escape_start[1] == 'P')) {
+                    ch = '@';
+                } else if ((escape_len == 2 && escape_start[0] == 'B' && escape_start[1] == 'P')) {
+                    ch = '*';
+                } else if ((escape_len == 2 && escape_start[0] == 'R' && escape_start[1] == 'F')) {
+                    ch = '&';
+                } else if ((escape_len == 2 && escape_start[0] == 'L' && escape_start[1] == 'T')) {
+                    ch = '<';
+                } else if ((escape_len == 2 && escape_start[0] == 'G' && escape_start[1] == 'T')) {
+                    ch = '>';
+                } else if ((escape_len == 2 && escape_start[0] == 'L' && escape_start[1] == 'P')) {
+                    ch = '(';
+                } else if ((escape_len == 2 && escape_start[0] == 'R' && escape_start[1] == 'P')) {
+                    ch = ')';
+                } else if ((escape_len == 1 && escape_start[0] == 'C')) {
+                    ch = ',';
+                } else {
+                    if (escape_len > 1 && escape_start[0] == 'u') {
+                        escape_start++;
+                        escape_len--;
+                        uint64_t val;
+                        if (try_parse_uint(escape_start, escape_len, &val)
+                            && val < UINT32_MAX
+                            && validate_char((uint32_t)val))
+                        {
+                            if (!unicode_iscontrol(val)) {
+                                uint8_t wchr[4];
+                                size_t wchr_len = code_to_utf8(wchr, (uint32_t)val);
+                                PRINT(printer_print_buf(&printer, (const char*)wchr, wchr_len));
+                                len = next_len;
+                                rest = next_rest;
+                                continue;
+                            }
+                        }
+                    }
+                    break; // print the rest of this element raw
+                }
+                PRINT_CH(&printer, ch);
+                len = next_len;
+                rest = next_rest;
+            } else {
+                size_t j = 0;
+                for (;j < len && rest[j] != '$' && rest[j] != '.';j++);
+                if (j == len) {
+                    break;
+                }
+                PRINT(printer_print_buf(&printer, rest, j));
+                rest += j;
+                len -= j;
+            }
+        }
+        PRINT(printer_print_buf(&printer, rest, len));
+    }
+
+    if (printer.out_len < OVERFLOW_MARGIN) {
+        return OverflowOverflow;
+    }
+    *printer.out = '\0';
+    return OverflowOk;
+}
+
+static bool is_symbol_like(const char *s, size_t len) {
+    // rust-demangle definition of symbol like: control characters and space are not symbol-like, all else is
+    for (size_t i = 0; i < len; i++) {
+        char ch = s[i];
+        if (!(ch >= 0x21 && ch <= 0x7e)) {
+            return false;
+        }
+    }
+    return true;
+}
+
+void rust_demangle_demangle(const char *s, struct demangle *res)
+{
+    // During ThinLTO LLVM may import and rename internal symbols, so strip out
+    // those endings first as they're one of the last manglings applied to symbol
+    // names.
+    const char *llvm = ".llvm.";
+    const char *found_llvm = strstr(s, llvm);
+    size_t s_len = strlen(s);
+    if (found_llvm) {
+        const char *all_hex_ptr = found_llvm + strlen(".llvm.");
+        bool all_hex = true;
+        for (;*all_hex_ptr;all_hex_ptr++) {
+            if (!(('0' <= *all_hex_ptr && *all_hex_ptr <= '9') ||
+                  ('A' <= *all_hex_ptr && *all_hex_ptr <= 'F') ||
+                  *all_hex_ptr == '@')) {
+                all_hex = false;
+                break;
+            }
+        }
+
+        if (all_hex) {
+            s_len = found_llvm - s;
+        }
+    }
+
+    const char *suffix;
+    struct demangle_legacy legacy;
+    demangle_status st = rust_demangle_legacy_demangle(s, s_len, &legacy, &suffix);
+    if (st == DemangleOk) {
+        *res = (struct demangle) {
+            .style=DemangleStyleLegacy,
+            .mangled=legacy.mangled,
+            .mangled_len=legacy.mangled_len,
+            .elements=legacy.elements,
+            .original=s,
+            .original_len=s_len,
+            .suffix=suffix,
+            .suffix_len=s_len - (suffix - s),
+        };
+    } else {
+        struct demangle_v0 v0;
+        st = rust_demangle_v0_demangle(s, s_len, &v0, &suffix);
+        if (st == DemangleOk) {
+            *res = (struct demangle) {
+                .style=DemangleStyleV0,
+                .mangled=v0.mangled,
+                .mangled_len=v0.mangled_len,
+                .elements=0,
+                .original=s,
+                .original_len=s_len,
+                .suffix=suffix,
+                .suffix_len=s_len - (suffix - s),
+            };
+        } else {
+            *res = (struct demangle) {
+                .style=DemangleStyleUnknown,
+                .mangled=NULL,
+                .mangled_len=0,
+                .elements=0,
+                .original=s,
+                .original_len=s_len,
+                .suffix=s,
+                .suffix_len=0,
+            };
+        }
+    }
+
+    // Output like LLVM IR adds extra period-delimited words. See if
+    // we are in that case and save the trailing words if so.
+    if (res->suffix_len) {
+        if (res->suffix[0] == '.' && is_symbol_like(res->suffix, res->suffix_len)) {
+            // Keep the suffix
+        } else {
+            // Reset the suffix and invalidate the demangling
+            res->style = DemangleStyleUnknown;
+            res->suffix_len = 0;
+        }
+    }
+}
+
+bool rust_demangle_is_known(struct demangle *res) {
+    return res->style != DemangleStyleUnknown;
+}
+
+overflow_status rust_demangle_display_demangle(struct demangle const *res, char *out, size_t len, bool alternate) {
+    size_t original_len = res->original_len;
+    size_t out_len;
+    switch (res->style) {
+    case DemangleStyleUnknown:
+    if (len < original_len) {
+        return OverflowOverflow;
+    } else {
+        memcpy(out, res->original, original_len);
+        out += original_len;
+        len -= original_len;
+        break;
+    }
+    break;
+    case DemangleStyleLegacy: {
+        struct demangle_legacy legacy = {
+            res->mangled,
+            res->mangled_len,
+            res->elements
+        };
+        if (rust_demangle_legacy_display_demangle(legacy, out, len, alternate) == OverflowOverflow) {
+            return OverflowOverflow;
+        }
+        out_len = strlen(out);
+        out += out_len;
+        len -= out_len;
+        break;
+    }
+    case DemangleStyleV0: {
+        struct demangle_v0 v0 = {
+            res->mangled,
+            res->mangled_len
+        };
+        if (rust_demangle_v0_display_demangle(v0, out, len, alternate) == OverflowOverflow) {
+            return OverflowOverflow;
+        }
+        out_len = strlen(out);
+        out += out_len;
+        len -= out_len;
+        break;
+    }
+    }
+    size_t suffix_len = res->suffix_len;
+    if (len < suffix_len || len - suffix_len < OVERFLOW_MARGIN) {
+        return OverflowOverflow;
+    }
+    memcpy(out, res->suffix, suffix_len);
+    out[suffix_len] = 0;
+    return OverflowOk;
+}
diff --git a/tools/perf/util/demangle-rust-v0.h b/tools/perf/util/demangle-rust-v0.h
new file mode 100644
index 000000000000..d0092818610a
--- /dev/null
+++ b/tools/perf/util/demangle-rust-v0.h
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+// The contents of this file come from the Rust rustc-demangle library, hosted
+// in the <https://github.com/rust-lang/rustc-demangle> repository, licensed
+// under "Apache-2.0 OR MIT". For copyright details, see
+// <https://github.com/rust-lang/rustc-demangle/blob/main/README.md>.
+// Please note that the file should be kept as close as possible to upstream.
+
+#ifndef _H_DEMANGLE_V0_H
+#define _H_DEMANGLE_V0_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <stddef.h>
+
+#if defined(__GNUC__) || defined(__clang__)
+#define DEMANGLE_NODISCARD __attribute__((warn_unused_result))
+#else
+#define DEMANGLE_NODISCARD
+#endif
+
+typedef enum {
+    OverflowOk,
+    OverflowOverflow
+} overflow_status;
+
+enum demangle_style {
+    DemangleStyleUnknown = 0,
+    DemangleStyleLegacy,
+    DemangleStyleV0,
+};
+
+// Not using a union here to make the struct easier to copy-paste if needed.
+struct demangle {
+    enum demangle_style style;
+    // points to the "mangled" part of the name,
+    // not including `ZN` or `R` prefixes.
+    const char *mangled;
+    size_t mangled_len;
+    // In DemangleStyleLegacy, is the number of path elements
+    size_t elements;
+    // while it's called "original", it will not contain `.llvm.9D1C9369@@16` suffixes
+    // that are to be ignored.
+    const char *original;
+    size_t original_len;
+    // Contains the part after the mangled name that is to be outputted,
+    // which can be `.exit.i.i` suffixes LLVM sometimes adds.
+    const char *suffix;
+    size_t suffix_len;
+};
+
+// if the length of the output buffer is less than `output_len-OVERFLOW_MARGIN`,
+// the demangler will return `OverflowOverflow` even if there is no overflow.
+#define OVERFLOW_MARGIN 4
+
+/// Demangle a C string that refers to a Rust symbol and put the demangle intermediate result in `res`.
+/// Beware that `res` contains references into `s`. If `s` is modified (or free'd) before calling
+/// `rust_demangle_display_demangle` behavior is undefined.
+///
+/// Use `rust_demangle_display_demangle` to convert it to an actual string.
+void rust_demangle_demangle(const char *s, struct demangle *res);
+
+/// Write the string in a `struct demangle` into a buffer.
+///
+/// Return `OverflowOk` if the output buffer was sufficiently big, `OverflowOverflow` if it wasn't.
+/// This function is `O(n)` in the length of the input + *output* [$], but the demangled output of demangling a symbol can
+/// be exponentially[$$] large, therefore it is recommended to have a sane bound (`rust-demangle`
+/// uses 1,000,000 bytes) on `len`.
+///
+/// `alternate`, if true, uses the less verbose alternate formatting (Rust `{:#}`) is used, which does not show
+/// symbol hashes and types of constant ints.
+///
+/// [$] It's `O(n * MAX_DEPTH)`, but `MAX_DEPTH` is a constant 300 and therefore it's `O(n)`
+/// [$$] Technically, bounded by `O(n^MAX_DEPTH)`, but this is practically exponential.
+DEMANGLE_NODISCARD overflow_status rust_demangle_display_demangle(struct demangle const *res, char *out, size_t len, bool alternate);
+
+/// Returns true if `res` refers to a known valid Rust demangling style, false if it's an unknown style.
+bool rust_demangle_is_known(struct demangle *res);
+
+#undef DEMANGLE_NODISCARD
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/perf/util/demangle-rust.c b/tools/perf/util/demangle-rust.c
deleted file mode 100644
index a659fc69f73a..000000000000
--- a/tools/perf/util/demangle-rust.c
+++ /dev/null
@@ -1,269 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <string.h>
-#include "debug.h"
-
-#include "demangle-rust.h"
-
-/*
- * Mangled Rust symbols look like this:
- *
- *     _$LT$std..sys..fd..FileDesc$u20$as$u20$core..ops..Drop$GT$::drop::hc68340e1baa4987a
- *
- * The original symbol is:
- *
- *     <std::sys::fd::FileDesc as core::ops::Drop>::drop
- *
- * The last component of the path is a 64-bit hash in lowercase hex, prefixed
- * with "h". Rust does not have a global namespace between crates, an illusion
- * which Rust maintains by using the hash to distinguish things that would
- * otherwise have the same symbol.
- *
- * Any path component not starting with a XID_Start character is prefixed with
- * "_".
- *
- * The following escape sequences are used:
- *
- *     ","  =>  $C$
- *     "@"  =>  $SP$
- *     "*"  =>  $BP$
- *     "&"  =>  $RF$
- *     "<"  =>  $LT$
- *     ">"  =>  $GT$
- *     "("  =>  $LP$
- *     ")"  =>  $RP$
- *     " "  =>  $u20$
- *     "'"  =>  $u27$
- *     "["  =>  $u5b$
- *     "]"  =>  $u5d$
- *     "~"  =>  $u7e$
- *
- * A double ".." means "::" and a single "." means "-".
- *
- * The only characters allowed in the mangled symbol are a-zA-Z0-9 and _.:$
- */
-
-static const char *hash_prefix = "::h";
-static const size_t hash_prefix_len = 3;
-static const size_t hash_len = 16;
-
-static bool is_prefixed_hash(const char *start);
-static bool looks_like_rust(const char *sym, size_t len);
-static bool unescape(const char **in, char **out, const char *seq, char value);
-
-/*
- * INPUT:
- *     sym: symbol that has been through BFD-demangling
- *
- * This function looks for the following indicators:
- *
- *  1. The hash must consist of "h" followed by 16 lowercase hex digits.
- *
- *  2. As a sanity check, the hash must use between 5 and 15 of the 16 possible
- *     hex digits. This is true of 99.9998% of hashes so once in your life you
- *     may see a false negative. The point is to notice path components that
- *     could be Rust hashes but are probably not, like "haaaaaaaaaaaaaaaa". In
- *     this case a false positive (non-Rust symbol has an important path
- *     component removed because it looks like a Rust hash) is worse than a
- *     false negative (the rare Rust symbol is not demangled) so this sets the
- *     balance in favor of false negatives.
- *
- *  3. There must be no characters other than a-zA-Z0-9 and _.:$
- *
- *  4. There must be no unrecognized $-sign sequences.
- *
- *  5. There must be no sequence of three or more dots in a row ("...").
- */
-bool
-rust_is_mangled(const char *sym)
-{
-	size_t len, len_without_hash;
-
-	if (!sym)
-		return false;
-
-	len = strlen(sym);
-	if (len <= hash_prefix_len + hash_len)
-		/* Not long enough to contain "::h" + hash + something else */
-		return false;
-
-	len_without_hash = len - (hash_prefix_len + hash_len);
-	if (!is_prefixed_hash(sym + len_without_hash))
-		return false;
-
-	return looks_like_rust(sym, len_without_hash);
-}
-
-/*
- * A hash is the prefix "::h" followed by 16 lowercase hex digits. The hex
- * digits must comprise between 5 and 15 (inclusive) distinct digits.
- */
-static bool is_prefixed_hash(const char *str)
-{
-	const char *end;
-	bool seen[16];
-	size_t i;
-	int count;
-
-	if (strncmp(str, hash_prefix, hash_prefix_len))
-		return false;
-	str += hash_prefix_len;
-
-	memset(seen, false, sizeof(seen));
-	for (end = str + hash_len; str < end; str++)
-		if (*str >= '0' && *str <= '9')
-			seen[*str - '0'] = true;
-		else if (*str >= 'a' && *str <= 'f')
-			seen[*str - 'a' + 10] = true;
-		else
-			return false;
-
-	/* Count how many distinct digits seen */
-	count = 0;
-	for (i = 0; i < 16; i++)
-		if (seen[i])
-			count++;
-
-	return count >= 5 && count <= 15;
-}
-
-static bool looks_like_rust(const char *str, size_t len)
-{
-	const char *end = str + len;
-
-	while (str < end)
-		switch (*str) {
-		case '$':
-			if (!strncmp(str, "$C$", 3))
-				str += 3;
-			else if (!strncmp(str, "$SP$", 4)
-					|| !strncmp(str, "$BP$", 4)
-					|| !strncmp(str, "$RF$", 4)
-					|| !strncmp(str, "$LT$", 4)
-					|| !strncmp(str, "$GT$", 4)
-					|| !strncmp(str, "$LP$", 4)
-					|| !strncmp(str, "$RP$", 4))
-				str += 4;
-			else if (!strncmp(str, "$u20$", 5)
-					|| !strncmp(str, "$u27$", 5)
-					|| !strncmp(str, "$u5b$", 5)
-					|| !strncmp(str, "$u5d$", 5)
-					|| !strncmp(str, "$u7e$", 5))
-				str += 5;
-			else
-				return false;
-			break;
-		case '.':
-			/* Do not allow three or more consecutive dots */
-			if (!strncmp(str, "...", 3))
-				return false;
-			/* Fall through */
-		case 'a' ... 'z':
-		case 'A' ... 'Z':
-		case '0' ... '9':
-		case '_':
-		case ':':
-			str++;
-			break;
-		default:
-			return false;
-		}
-
-	return true;
-}
-
-/*
- * INPUT:
- *     sym: symbol for which rust_is_mangled(sym) returns true
- *
- * The input is demangled in-place because the mangled name is always longer
- * than the demangled one.
- */
-void
-rust_demangle_sym(char *sym)
-{
-	const char *in;
-	char *out;
-	const char *end;
-
-	if (!sym)
-		return;
-
-	in = sym;
-	out = sym;
-	end = sym + strlen(sym) - (hash_prefix_len + hash_len);
-
-	while (in < end)
-		switch (*in) {
-		case '$':
-			if (!(unescape(&in, &out, "$C$", ',')
-					|| unescape(&in, &out, "$SP$", '@')
-					|| unescape(&in, &out, "$BP$", '*')
-					|| unescape(&in, &out, "$RF$", '&')
-					|| unescape(&in, &out, "$LT$", '<')
-					|| unescape(&in, &out, "$GT$", '>')
-					|| unescape(&in, &out, "$LP$", '(')
-					|| unescape(&in, &out, "$RP$", ')')
-					|| unescape(&in, &out, "$u20$", ' ')
-					|| unescape(&in, &out, "$u27$", '\'')
-					|| unescape(&in, &out, "$u5b$", '[')
-					|| unescape(&in, &out, "$u5d$", ']')
-					|| unescape(&in, &out, "$u7e$", '~'))) {
-				pr_err("demangle-rust: unexpected escape sequence");
-				goto done;
-			}
-			break;
-		case '_':
-			/*
-			 * If this is the start of a path component and the next
-			 * character is an escape sequence, ignore the
-			 * underscore. The mangler inserts an underscore to make
-			 * sure the path component begins with a XID_Start
-			 * character.
-			 */
-			if ((in == sym || in[-1] == ':') && in[1] == '$')
-				in++;
-			else
-				*out++ = *in++;
-			break;
-		case '.':
-			if (in[1] == '.') {
-				/* ".." becomes "::" */
-				*out++ = ':';
-				*out++ = ':';
-				in += 2;
-			} else {
-				/* "." becomes "-" */
-				*out++ = '-';
-				in++;
-			}
-			break;
-		case 'a' ... 'z':
-		case 'A' ... 'Z':
-		case '0' ... '9':
-		case ':':
-			*out++ = *in++;
-			break;
-		default:
-			pr_err("demangle-rust: unexpected character '%c' in symbol\n",
-				*in);
-			goto done;
-		}
-
-done:
-	*out = '\0';
-}
-
-static bool unescape(const char **in, char **out, const char *seq, char value)
-{
-	size_t len = strlen(seq);
-
-	if (strncmp(*in, seq, len))
-		return false;
-
-	**out = value;
-
-	*in += len;
-	*out += 1;
-
-	return true;
-}
diff --git a/tools/perf/util/demangle-rust.h b/tools/perf/util/demangle-rust.h
deleted file mode 100644
index 2fca618b1aa5..000000000000
--- a/tools/perf/util/demangle-rust.h
+++ /dev/null
@@ -1,8 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __PERF_DEMANGLE_RUST
-#define __PERF_DEMANGLE_RUST 1
-
-bool rust_is_mangled(const char *str);
-void rust_demangle_sym(char *str);
-
-#endif /* __PERF_DEMANGLE_RUST */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 8619b6eea62d..057fcf4225ac 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1349,6 +1349,16 @@ struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
 	return dso;
 }
 
+static void __dso__set_long_name_id(struct dso *dso, const char *name, bool name_allocated)
+{
+	if (dso__long_name_allocated(dso))
+		free((char *)dso__long_name(dso));
+
+	RC_CHK_ACCESS(dso)->long_name = name;
+	RC_CHK_ACCESS(dso)->long_name_len = strlen(name);
+	dso__set_long_name_allocated(dso, name_allocated);
+}
+
 static void dso__set_long_name_id(struct dso *dso, const char *name, bool name_allocated)
 {
 	struct dsos *dsos = dso__dsos(dso);
@@ -1362,18 +1372,11 @@ static void dso__set_long_name_id(struct dso *dso, const char *name, bool name_a
 		 * renaming the dso.
 		 */
 		down_write(&dsos->lock);
-	}
-
-	if (dso__long_name_allocated(dso))
-		free((char *)dso__long_name(dso));
-
-	RC_CHK_ACCESS(dso)->long_name = name;
-	RC_CHK_ACCESS(dso)->long_name_len = strlen(name);
-	dso__set_long_name_allocated(dso, name_allocated);
-
-	if (dsos) {
+		__dso__set_long_name_id(dso, name, name_allocated);
 		dsos->sorted = false;
 		up_write(&dsos->lock);
+	} else {
+		__dso__set_long_name_id(dso, name, name_allocated);
 	}
 }
 
@@ -1451,6 +1454,16 @@ void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 	dso__set_long_name_id(dso, name, name_allocated);
 }
 
+static void __dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
+{
+	if (dso__short_name_allocated(dso))
+		free((char *)dso__short_name(dso));
+
+	RC_CHK_ACCESS(dso)->short_name		  = name;
+	RC_CHK_ACCESS(dso)->short_name_len	  = strlen(name);
+	dso__set_short_name_allocated(dso, name_allocated);
+}
+
 void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
 {
 	struct dsos *dsos = dso__dsos(dso);
@@ -1464,17 +1477,11 @@ void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
 		 * renaming the dso.
 		 */
 		down_write(&dsos->lock);
-	}
-	if (dso__short_name_allocated(dso))
-		free((char *)dso__short_name(dso));
-
-	RC_CHK_ACCESS(dso)->short_name		  = name;
-	RC_CHK_ACCESS(dso)->short_name_len	  = strlen(name);
-	dso__set_short_name_allocated(dso, name_allocated);
-
-	if (dsos) {
+		__dso__set_short_name(dso, name, name_allocated);
 		dsos->sorted = false;
 		up_write(&dsos->lock);
+	} else {
+		__dso__set_short_name(dso, name, name_allocated);
 	}
 }
 
diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
index e0998e2a7c4e..4d213017d202 100644
--- a/tools/perf/util/dsos.c
+++ b/tools/perf/util/dsos.c
@@ -157,6 +157,7 @@ static struct dso *__dsos__find_by_longname_id(struct dsos *dsos,
 					       const char *name,
 					       const struct dso_id *id,
 					       bool write_locked)
+	SHARED_LOCKS_REQUIRED(dsos->lock)
 {
 	struct dsos__key key = {
 		.long_name = name,
@@ -262,6 +263,7 @@ static int dsos__find_id_cb(struct dso *dso, void *data)
 
 static struct dso *__dsos__find_id(struct dsos *dsos, const char *name, const struct dso_id *id,
 				   bool cmp_short, bool write_locked)
+	SHARED_LOCKS_REQUIRED(dsos->lock)
 {
 	struct dso *res;
 
@@ -338,6 +340,7 @@ static struct dso *__dsos__addnew_id(struct dsos *dsos, const char *name, const
 }
 
 static struct dso *__dsos__findnew_id(struct dsos *dsos, const char *name, const struct dso_id *id)
+	SHARED_LOCKS_REQUIRED(dsos->lock)
 {
 	struct dso *dso = __dsos__find_id(dsos, name, id, false, /*write_locked=*/true);
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index c23b77f8f854..7544a3104e21 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -77,6 +77,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_HEADER_FEATURE]		= "FEATURE",
 	[PERF_RECORD_COMPRESSED]		= "COMPRESSED",
 	[PERF_RECORD_FINISHED_INIT]		= "FINISHED_INIT",
+	[PERF_RECORD_COMPRESSED2]		= "COMPRESSED2",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -448,12 +449,13 @@ int perf_event__exit_del_thread(const struct perf_tool *tool __maybe_unused,
 
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
 {
-	return fprintf(fp, " offset: %#"PRI_lx64" size: %#"PRI_lx64" flags: %#"PRI_lx64" [%s%s%s]\n",
+	return fprintf(fp, " offset: %#"PRI_lx64" size: %#"PRI_lx64" flags: %#"PRI_lx64" [%s%s%s%s]\n",
 		       event->aux.aux_offset, event->aux.aux_size,
 		       event->aux.flags,
 		       event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
 		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "",
-		       event->aux.flags & PERF_AUX_FLAG_PARTIAL   ? "P" : "");
+		       event->aux.flags & PERF_AUX_FLAG_PARTIAL   ? "P" : "",
+		       event->aux.flags & PERF_AUX_FLAG_COLLISION ? "C" : "");
 }
 
 size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c1a04141aed0..dcd1130502df 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -35,6 +35,7 @@
 #include "util/util.h"
 #include "util/env.h"
 #include "util/intel-tpebs.h"
+#include "util/strbuf.h"
 #include <signal.h>
 #include <unistd.h>
 #include <sched.h>
@@ -183,7 +184,6 @@ void evlist__delete(struct evlist *evlist)
 	if (evlist == NULL)
 		return;
 
-	tpebs_delete();
 	evlist__free_stats(evlist);
 	evlist__munmap(evlist);
 	evlist__close(evlist);
@@ -2468,23 +2468,36 @@ struct evsel *evlist__find_evsel(struct evlist *evlist, int idx)
 	return NULL;
 }
 
-int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf)
+void evlist__format_evsels(struct evlist *evlist, struct strbuf *sb, size_t max_length)
 {
-	struct evsel *evsel;
-	int printed = 0;
+	struct evsel *evsel, *leader = NULL;
+	bool first = true;
 
 	evlist__for_each_entry(evlist, evsel) {
+		struct evsel *new_leader = evsel__leader(evsel);
+
 		if (evsel__is_dummy_event(evsel))
 			continue;
-		if (size > (strlen(evsel__name(evsel)) + (printed ? 2 : 1))) {
-			printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "," : "", evsel__name(evsel));
-		} else {
-			printed += scnprintf(bf + printed, size - printed, "%s...", printed ? "," : "");
-			break;
+
+		if (leader != new_leader && leader && leader->core.nr_members > 1)
+			strbuf_addch(sb, '}');
+
+		if (!first)
+			strbuf_addch(sb, ',');
+
+		if (sb->len > max_length) {
+			strbuf_addstr(sb, "...");
+			return;
 		}
-	}
+		if (leader != new_leader && new_leader->core.nr_members > 1)
+			strbuf_addch(sb, '{');
 
-	return printed;
+		strbuf_addstr(sb, evsel__name(evsel));
+		first = false;
+		leader = new_leader;
+	}
+	if (leader && leader->core.nr_members > 1)
+		strbuf_addch(sb, '}');
 }
 
 void evlist__check_mem_load_aux(struct evlist *evlist)
@@ -2552,34 +2565,56 @@ void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_lis
 	perf_cpu_map__put(user_requested_cpus);
 }
 
-void evlist__uniquify_name(struct evlist *evlist)
+/* Should uniquify be disabled for the evlist? */
+static bool evlist__disable_uniquify(const struct evlist *evlist)
 {
-	char *new_name, empty_attributes[2] = ":", *attributes;
-	struct evsel *pos;
+	struct evsel *counter;
+	struct perf_pmu *last_pmu = NULL;
+	bool first = true;
 
-	if (perf_pmus__num_core_pmus() == 1)
-		return;
+	evlist__for_each_entry(evlist, counter) {
+		/* If PMUs vary then uniquify can be useful. */
+		if (!first && counter->pmu != last_pmu)
+			return false;
+		first = false;
+		if (counter->pmu) {
+			/* Allow uniquify for uncore PMUs. */
+			if (!counter->pmu->is_core)
+				return false;
+			/* Keep hybrid event names uniquified for clarity. */
+			if (perf_pmus__num_core_pmus() > 1)
+				return false;
+		}
+		last_pmu = counter->pmu;
+	}
+	return true;
+}
 
-	evlist__for_each_entry(evlist, pos) {
-		if (!evsel__is_hybrid(pos))
-			continue;
+static bool evlist__set_needs_uniquify(struct evlist *evlist, const struct perf_stat_config *config)
+{
+	struct evsel *counter;
+	bool needs_uniquify = false;
 
-		if (strchr(pos->name, '/'))
-			continue;
+	if (evlist__disable_uniquify(evlist)) {
+		evlist__for_each_entry(evlist, counter)
+			counter->uniquified_name = true;
+		return false;
+	}
+
+	evlist__for_each_entry(evlist, counter) {
+		if (evsel__set_needs_uniquify(counter, config))
+			needs_uniquify = true;
+	}
+	return needs_uniquify;
+}
 
-		attributes = strchr(pos->name, ':');
-		if (attributes)
-			*attributes = '\0';
-		else
-			attributes = empty_attributes;
+void evlist__uniquify_evsel_names(struct evlist *evlist, const struct perf_stat_config *config)
+{
+	if (evlist__set_needs_uniquify(evlist, config)) {
+		struct evsel *pos;
 
-		if (asprintf(&new_name, "%s/%s/%s", pos->pmu ? pos->pmu->name : "",
-			     pos->name, attributes + 1)) {
-			free(pos->name);
-			pos->name = new_name;
-		} else {
-			*attributes = ':';
-		}
+		evlist__for_each_entry(evlist, pos)
+			evsel__uniquify_counter(pos);
 	}
 }
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index edcbf1c10e92..85859708393e 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -19,7 +19,9 @@
 struct pollfd;
 struct thread_map;
 struct perf_cpu_map;
+struct perf_stat_config;
 struct record_opts;
+struct strbuf;
 struct target;
 
 /*
@@ -430,10 +432,10 @@ int event_enable_timer__process(struct event_enable_timer *eet);
 
 struct evsel *evlist__find_evsel(struct evlist *evlist, int idx);
 
-int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf);
+void evlist__format_evsels(struct evlist *evlist, struct strbuf *sb, size_t max_length);
 void evlist__check_mem_load_aux(struct evlist *evlist);
 void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_list);
-void evlist__uniquify_name(struct evlist *evlist);
+void evlist__uniquify_evsel_names(struct evlist *evlist, const struct perf_stat_config *config);
 bool evlist__has_bpf_output(struct evlist *evlist);
 bool evlist__needs_bpf_sb_event(struct evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3c030da2e477..d55482f094bf 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -552,11 +552,11 @@ struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig)
 
 	evsel->exclude_GH = orig->exclude_GH;
 	evsel->sample_read = orig->sample_read;
-	evsel->auto_merge_stats = orig->auto_merge_stats;
 	evsel->collect_stat = orig->collect_stat;
 	evsel->weak_group = orig->weak_group;
 	evsel->use_config_name = orig->use_config_name;
 	evsel->pmu = orig->pmu;
+	evsel->first_wildcard_match = orig->first_wildcard_match;
 
 	if (evsel__copy_config_terms(evsel, orig) < 0)
 		goto out_err;
@@ -1275,9 +1275,10 @@ static void evsel__set_default_freq_period(struct record_opts *opts,
 	}
 }
 
-static bool evsel__is_offcpu_event(struct evsel *evsel)
+bool evsel__is_offcpu_event(struct evsel *evsel)
 {
-	return evsel__is_bpf_output(evsel) && evsel__name_is(evsel, OFFCPU_EVENT);
+	return evsel__is_bpf_output(evsel) && evsel__name_is(evsel, OFFCPU_EVENT) &&
+	       evsel->core.attr.sample_type & PERF_SAMPLE_RAW;
 }
 
 /*
@@ -1425,7 +1426,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 		evsel__set_sample_bit(evsel, CPU);
 	}
 
-	if (opts->sample_address)
+	if (opts->sample_data_src)
 		evsel__set_sample_bit(evsel, DATA_SRC);
 
 	if (opts->sample_phys_addr)
@@ -1440,9 +1441,10 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 		attr->branch_sample_type = opts->branch_stack;
 	}
 
-	if (opts->sample_weight)
+	if (opts->sample_weight || evsel->retire_lat) {
 		arch_evsel__set_sample_weight(evsel);
-
+		evsel->retire_lat = false;
+	}
 	attr->task     = track;
 	attr->mmap     = track;
 	attr->mmap2    = track && !perf_missing_features.mmap2;
@@ -1554,8 +1556,10 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	if (evsel__is_dummy_event(evsel))
 		evsel__reset_sample_bit(evsel, BRANCH_STACK);
 
-	if (evsel__is_offcpu_event(evsel))
+	if (evsel__is_offcpu_event(evsel)) {
 		evsel->core.attr.sample_type &= OFFCPU_SAMPLE_TYPES;
+		attr->inherit = 0;
+	}
 
 	arch__post_evsel_config(evsel, attr);
 }
@@ -1656,6 +1660,8 @@ void evsel__exit(struct evsel *evsel)
 {
 	assert(list_empty(&evsel->core.node));
 	assert(evsel->evlist == NULL);
+	if (evsel__is_retire_lat(evsel))
+		evsel__tpebs_close(evsel);
 	bpf_counter__destroy(evsel);
 	perf_bpf_filter__destroy(evsel);
 	evsel__free_counts(evsel);
@@ -1718,11 +1724,6 @@ static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread)
 	return perf_evsel__read(&evsel->core, cpu_map_idx, thread, count);
 }
 
-static int evsel__read_retire_lat(struct evsel *evsel, int cpu_map_idx, int thread)
-{
-	return tpebs_set_evsel(evsel, cpu_map_idx, thread);
-}
-
 static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
 			     u64 val, u64 ena, u64 run, u64 lost)
 {
@@ -1730,8 +1731,8 @@ static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
 
 	count = perf_counts(counter->counts, cpu_map_idx, thread);
 
-	if (counter->retire_lat) {
-		evsel__read_retire_lat(counter, cpu_map_idx, thread);
+	if (evsel__is_retire_lat(counter)) {
+		evsel__tpebs_read(counter, cpu_map_idx, thread);
 		perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true);
 		return;
 	}
@@ -1889,7 +1890,7 @@ int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread)
 		return evsel__hwmon_pmu_read(evsel, cpu_map_idx, thread);
 
 	if (evsel__is_retire_lat(evsel))
-		return evsel__read_retire_lat(evsel, cpu_map_idx, thread);
+		return evsel__tpebs_read(evsel, cpu_map_idx, thread);
 
 	if (evsel->core.attr.read_format & PERF_FORMAT_GROUP)
 		return evsel__read_group(evsel, cpu_map_idx, thread);
@@ -2576,7 +2577,7 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 	struct perf_cpu cpu;
 
 	if (evsel__is_retire_lat(evsel))
-		return tpebs_start(evsel->evlist);
+		return evsel__tpebs_open(evsel);
 
 	err = __evsel__prepare_open(evsel, cpus, threads);
 	if (err)
@@ -2737,7 +2738,7 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
 void evsel__close(struct evsel *evsel)
 {
 	if (evsel__is_retire_lat(evsel))
-		tpebs_delete();
+		evsel__tpebs_close(evsel);
 	perf_evsel__close(&evsel->core);
 	perf_evsel__free_id(&evsel->core);
 }
@@ -2923,6 +2924,35 @@ static inline bool evsel__has_branch_counters(const struct evsel *evsel)
 	return false;
 }
 
+static int __set_offcpu_sample(struct perf_sample *data)
+{
+	u64 *array = data->raw_data;
+	u32 max_size = data->raw_size, *p32;
+	const void *endp = (void *)array + max_size;
+
+	if (array == NULL)
+		return -EFAULT;
+
+	OVERFLOW_CHECK_u64(array);
+	p32 = (void *)array++;
+	data->pid = p32[0];
+	data->tid = p32[1];
+
+	OVERFLOW_CHECK_u64(array);
+	data->period = *array++;
+
+	OVERFLOW_CHECK_u64(array);
+	data->callchain = (struct ip_callchain *)array++;
+	OVERFLOW_CHECK(array, data->callchain->nr * sizeof(u64), max_size);
+	data->ip = data->callchain->ips[1];
+	array += data->callchain->nr;
+
+	OVERFLOW_CHECK_u64(array);
+	data->cgroup = *array;
+
+	return 0;
+}
+
 int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			struct perf_sample *data)
 {
@@ -3277,6 +3307,9 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 		array = (void *)array + sz;
 	}
 
+	if (evsel__is_offcpu_event(evsel))
+		return __set_offcpu_sample(data);
+
 	return 0;
 }
 
@@ -3752,6 +3785,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
 			return scnprintf(msg, size, "%s",
 	"No hardware sampling interrupt available.\n");
 #endif
+		if (!target__has_cpu(target))
+			return scnprintf(msg, size,
+	"Unsupported event (%s) in per-thread mode, enable system wide with '-a'.",
+					evsel__name(evsel));
 		break;
 	case EBUSY:
 		if (find_process("oprofiled"))
@@ -3917,3 +3954,120 @@ void evsel__remove_from_group(struct evsel *evsel, struct evsel *leader)
 		leader->core.nr_members--;
 	}
 }
+
+bool evsel__set_needs_uniquify(struct evsel *counter, const struct perf_stat_config *config)
+{
+	struct evsel *evsel;
+
+	if (counter->needs_uniquify) {
+		/* Already set. */
+		return true;
+	}
+
+	if (counter->use_config_name || counter->is_libpfm_event) {
+		/* Original name will be used. */
+		return false;
+	}
+
+	if (!config->hybrid_merge && evsel__is_hybrid(counter)) {
+		/* Unique hybrid counters necessary. */
+		counter->needs_uniquify = true;
+		return true;
+	}
+
+	if  (counter->core.attr.type < PERF_TYPE_MAX && counter->core.attr.type != PERF_TYPE_RAW) {
+		/* Legacy event, don't uniquify. */
+		return false;
+	}
+
+	if (counter->pmu && counter->pmu->is_core &&
+	    counter->alternate_hw_config != PERF_COUNT_HW_MAX) {
+		/* A sysfs or json event replacing a legacy event, don't uniquify. */
+		return false;
+	}
+
+	if (config->aggr_mode == AGGR_NONE) {
+		/* Always unique with no aggregation. */
+		counter->needs_uniquify = true;
+		return true;
+	}
+
+	if (counter->first_wildcard_match != NULL) {
+		/*
+		 * If stats are merged then only the first_wildcard_match is
+		 * displayed, there is no need to uniquify this evsel as the
+		 * name won't be shown.
+		 */
+		return false;
+	}
+
+	/*
+	 * Do other non-merged events in the evlist have the same name? If so
+	 * uniquify is necessary.
+	 */
+	evlist__for_each_entry(counter->evlist, evsel) {
+		if (evsel == counter || evsel->first_wildcard_match || evsel->pmu == counter->pmu)
+			continue;
+
+		if (evsel__name_is(counter, evsel__name(evsel))) {
+			counter->needs_uniquify = true;
+			return true;
+		}
+	}
+	return false;
+}
+
+void evsel__uniquify_counter(struct evsel *counter)
+{
+	const char *name, *pmu_name;
+	char *new_name, *config;
+	int ret;
+
+	/* No uniquification necessary. */
+	if (!counter->needs_uniquify)
+		return;
+
+	/* The evsel was already uniquified. */
+	if (counter->uniquified_name)
+		return;
+
+	/* Avoid checking to uniquify twice. */
+	counter->uniquified_name = true;
+
+	name = evsel__name(counter);
+	pmu_name = counter->pmu->name;
+	/* Already prefixed by the PMU name. */
+	if (!strncmp(name, pmu_name, strlen(pmu_name)))
+		return;
+
+	config = strchr(name, '/');
+	if (config) {
+		int len = config - name;
+
+		if (config[1] == '/') {
+			/* case: event// */
+			ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 2);
+		} else {
+			/* case: event/.../ */
+			ret = asprintf(&new_name, "%s/%.*s,%s", pmu_name, len, name, config + 1);
+		}
+	} else {
+		config = strchr(name, ':');
+		if (config) {
+			/* case: event:.. */
+			int len = config - name;
+
+			ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 1);
+		} else {
+			/* case: event */
+			ret = asprintf(&new_name, "%s/%s/", pmu_name, name);
+		}
+	}
+	if (ret > 0) {
+		free(counter->name);
+		counter->name = new_name;
+	} else {
+		/* ENOMEM from asprintf. */
+		counter->uniquified_name = false;
+	}
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index aae431d63d64..6dbc9690e0c9 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -16,6 +16,7 @@
 struct bpf_object;
 struct cgroup;
 struct perf_counts;
+struct perf_stat_config;
 struct perf_stat_evsel;
 union perf_event;
 struct bpf_counter_ops;
@@ -69,6 +70,11 @@ struct evsel {
 		const char		*unit;
 		struct cgroup		*cgrp;
 		const char		*metric_id;
+		/*
+		 * This point to the first evsel with the same name, intended to store the
+		 * aggregated counts in aggregation mode.
+		 */
+		struct evsel		*first_wildcard_match;
 		/* parse modifier helper */
 		int			exclude_GH;
 		int			sample_read;
@@ -77,7 +83,6 @@ struct evsel {
 		bool			percore;
 		bool			precise_max;
 		bool			is_libpfm_event;
-		bool			auto_merge_stats;
 		bool			collect_stat;
 		bool			weak_group;
 		bool			bpf_counter;
@@ -114,7 +119,6 @@ struct evsel {
 	bool			ignore_missing_thread;
 	bool			forced_leader;
 	bool			cmdline_group_boundary;
-	bool			merged_stat;
 	bool			reset_group;
 	bool			errored;
 	bool			needs_auxtrace_mmap;
@@ -177,6 +181,12 @@ struct evsel {
 	/* For tool events */
 	/* Beginning time subtracted when the counter is read. */
 	union {
+		/* Defaults for retirement latency events. */
+		struct _retirement_latency {
+			double mean;
+			double min;
+			double max;
+		} retirement_latency;
 		/* duration_time is a single global time. */
 		__u64 start_time;
 		/*
@@ -542,6 +552,9 @@ void evsel__remove_from_group(struct evsel *evsel, struct evsel *leader);
 
 bool arch_evsel__must_be_in_group(const struct evsel *evsel);
 
+bool evsel__set_needs_uniquify(struct evsel *counter, const struct perf_stat_config *config);
+void evsel__uniquify_counter(struct evsel *counter);
+
 /*
  * Macro to swap the bit-field postition and size.
  * Used when,
@@ -557,4 +570,6 @@ u64 evsel__bitfield_swap_branch_flags(u64 value);
 void evsel__set_config_if_unset(struct perf_pmu *pmu, struct evsel *evsel,
 				const char *config_name, u64 val);
 
+bool evsel__is_offcpu_event(struct evsel *evsel);
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h
index af52a1516d0b..94a1e9cf73d6 100644
--- a/tools/perf/util/evsel_config.h
+++ b/tools/perf/util/evsel_config.h
@@ -48,6 +48,7 @@ struct evsel_config_term {
 		u32	      aux_sample_size;
 		u64	      cfg_chg;
 		char	      *str;
+		int	      cpu;
 	} val;
 	bool weak;
 };
diff --git a/tools/perf/util/fncache.c b/tools/perf/util/fncache.c
index 6225cbc52310..bf9559c55c63 100644
--- a/tools/perf/util/fncache.c
+++ b/tools/perf/util/fncache.c
@@ -1,53 +1,58 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Manage a cache of file names' existence */
+#include <pthread.h>
 #include <stdlib.h>
-#include <unistd.h>
 #include <string.h>
-#include <linux/list.h>
+#include <unistd.h>
+#include <linux/compiler.h>
 #include "fncache.h"
+#include "hashmap.h"
 
-struct fncache {
-	struct hlist_node nd;
-	bool res;
-	char name[];
-};
+static struct hashmap *fncache;
 
-#define FNHSIZE 61
+static size_t fncache__hash(long key, void *ctx __maybe_unused)
+{
+	return str_hash((const char *)key);
+}
 
-static struct hlist_head fncache_hash[FNHSIZE];
+static bool fncache__equal(long key1, long key2, void *ctx __maybe_unused)
+{
+	return strcmp((const char *)key1, (const char *)key2) == 0;
+}
 
-unsigned shash(const unsigned char *s)
+static void fncache__init(void)
 {
-	unsigned h = 0;
-	while (*s)
-		h = 65599 * h + *s++;
-	return h ^ (h >> 16);
+	fncache = hashmap__new(fncache__hash, fncache__equal, /*ctx=*/NULL);
+}
+
+static struct hashmap *fncache__get(void)
+{
+	static pthread_once_t fncache_once = PTHREAD_ONCE_INIT;
+
+	pthread_once(&fncache_once, fncache__init);
+
+	return fncache;
 }
 
 static bool lookup_fncache(const char *name, bool *res)
 {
-	int h = shash((const unsigned char *)name) % FNHSIZE;
-	struct fncache *n;
-
-	hlist_for_each_entry(n, &fncache_hash[h], nd) {
-		if (!strcmp(n->name, name)) {
-			*res = n->res;
-			return true;
-		}
-	}
-	return false;
+	long val;
+
+	if (!hashmap__find(fncache__get(), name, &val))
+		return false;
+
+	*res = (val != 0);
+	return true;
 }
 
 static void update_fncache(const char *name, bool res)
 {
-	struct fncache *n = malloc(sizeof(struct fncache) + strlen(name) + 1);
-	int h = shash((const unsigned char *)name) % FNHSIZE;
-
-	if (!n)
-		return;
-	strcpy(n->name, name);
-	n->res = res;
-	hlist_add_head(&n->nd, &fncache_hash[h]);
+	char *old_key = NULL, *key = strdup(name);
+
+	if (key) {
+		hashmap__set(fncache__get(), key, res, &old_key, /*old_value*/NULL);
+		free(old_key);
+	}
 }
 
 /* No LRU, only use when bounded in some other way. */
diff --git a/tools/perf/util/fncache.h b/tools/perf/util/fncache.h
index fe020beaefb1..b6a0f209493e 100644
--- a/tools/perf/util/fncache.h
+++ b/tools/perf/util/fncache.h
@@ -1,7 +1,6 @@
 #ifndef _FCACHE_H
 #define _FCACHE_H 1
 
-unsigned shash(const unsigned char *s);
 bool file_available(const char *name);
 
 #endif
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index d65228c11412..afc6855327ab 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -336,6 +336,69 @@ static void he_stat__decay(struct he_stat *he_stat)
 	he_stat->latency = (he_stat->latency * 7) / 8;
 }
 
+static int hists__update_mem_stat(struct hists *hists, struct hist_entry *he,
+				  struct mem_info *mi, u64 period)
+{
+	if (hists->nr_mem_stats == 0)
+		return 0;
+
+	if (he->mem_stat == NULL) {
+		he->mem_stat = calloc(hists->nr_mem_stats, sizeof(*he->mem_stat));
+		if (he->mem_stat == NULL)
+			return -1;
+	}
+
+	for (int i = 0; i < hists->nr_mem_stats; i++) {
+		int idx = mem_stat_index(hists->mem_stat_types[i],
+					 mem_info__const_data_src(mi)->val);
+
+		assert(0 <= idx && idx < MEM_STAT_LEN);
+		he->mem_stat[i].entries[idx] += period;
+		hists->mem_stat_total[i].entries[idx] += period;
+	}
+	return 0;
+}
+
+static void hists__add_mem_stat(struct hists *hists, struct hist_entry *dst,
+				struct hist_entry *src)
+{
+	if (hists->nr_mem_stats == 0)
+		return;
+
+	for (int i = 0; i < hists->nr_mem_stats; i++) {
+		for (int k = 0; k < MEM_STAT_LEN; k++)
+			dst->mem_stat[i].entries[k] += src->mem_stat[i].entries[k];
+	}
+}
+
+static int hists__clone_mem_stat(struct hists *hists, struct hist_entry *dst,
+				  struct hist_entry *src)
+{
+	if (hists->nr_mem_stats == 0)
+		return 0;
+
+	dst->mem_stat = calloc(hists->nr_mem_stats, sizeof(*dst->mem_stat));
+	if (dst->mem_stat == NULL)
+		return -1;
+
+	for (int i = 0; i < hists->nr_mem_stats; i++) {
+		for (int k = 0; k < MEM_STAT_LEN; k++)
+			dst->mem_stat[i].entries[k] = src->mem_stat[i].entries[k];
+	}
+	return 0;
+}
+
+static void hists__decay_mem_stat(struct hists *hists, struct hist_entry *he)
+{
+	if (hists->nr_mem_stats == 0)
+		return;
+
+	for (int i = 0; i < hists->nr_mem_stats; i++) {
+		for (int k = 0; k < MEM_STAT_LEN; k++)
+			he->mem_stat[i].entries[k] = (he->mem_stat[i].entries[k] * 7) / 8;
+	}
+}
+
 static void hists__delete_entry(struct hists *hists, struct hist_entry *he);
 
 static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
@@ -350,6 +413,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 	if (symbol_conf.cumulate_callchain)
 		he_stat__decay(he->stat_acc);
 	decay_callchain(he->callchain);
+	hists__decay_mem_stat(hists, he);
 
 	if (!he->depth) {
 		u64 period_diff = prev_period - he->stat.period;
@@ -693,6 +757,10 @@ out:
 		he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
 	if (symbol_conf.cumulate_callchain)
 		he_stat__add_cpumode_period(he->stat_acc, al->cpumode, period);
+	if (hists__update_mem_stat(hists, he, entry->mem_info, period) < 0) {
+		hist_entry__delete(he);
+		return NULL;
+	}
 	return he;
 }
 
@@ -1423,6 +1491,7 @@ void hist_entry__delete(struct hist_entry *he)
 	free_callchain(he->callchain);
 	zfree(&he->trace_output);
 	zfree(&he->raw_data);
+	zfree(&he->mem_stat);
 	ops->free(he);
 }
 
@@ -1572,6 +1641,7 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
 		cmp = hist_entry__collapse_hierarchy(hpp_list, iter, he);
 		if (!cmp) {
 			he_stat__add_stat(&iter->stat, &he->stat);
+			hists__add_mem_stat(hists, iter, he);
 			return iter;
 		}
 
@@ -1613,6 +1683,11 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
 			new->srcfile = NULL;
 	}
 
+	if (hists__clone_mem_stat(hists, new, he) < 0) {
+		hist_entry__delete(new);
+		return NULL;
+	}
+
 	rb_link_node(&new->rb_node_in, parent, p);
 	rb_insert_color_cached(&new->rb_node_in, root, leftmost);
 	return new;
@@ -1695,6 +1770,7 @@ static int hists__collapse_insert_entry(struct hists *hists,
 			he_stat__add_stat(&iter->stat, &he->stat);
 			if (symbol_conf.cumulate_callchain)
 				he_stat__add_stat(iter->stat_acc, he->stat_acc);
+			hists__add_mem_stat(hists, iter, he);
 
 			if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) {
 				struct callchain_cursor *cursor = get_tls_callchain_cursor();
@@ -2978,6 +3054,8 @@ static void hists_evsel__exit(struct evsel *evsel)
 	struct perf_hpp_list_node *node, *tmp;
 
 	hists__delete_all_entries(hists);
+	zfree(&hists->mem_stat_types);
+	zfree(&hists->mem_stat_total);
 
 	list_for_each_entry_safe(node, tmp, &hists->hpp_formats, list) {
 		perf_hpp_list__for_each_format_safe(&node->hpp, fmt, pos) {
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 317d06cca8b8..c64254088fc7 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -9,6 +9,7 @@
 #include "events_stats.h"
 #include "evsel.h"
 #include "map_symbol.h"
+#include "mem-events.h"
 #include "mutex.h"
 #include "sample.h"
 #include "spark.h"
@@ -41,6 +42,7 @@ enum hist_column {
 	HISTC_TIME,
 	HISTC_DSO,
 	HISTC_THREAD,
+	HISTC_TGID,
 	HISTC_COMM,
 	HISTC_CGROUP_ID,
 	HISTC_CGROUP,
@@ -100,6 +102,13 @@ enum hist_column {
 struct thread;
 struct dso;
 
+#define MEM_STAT_LEN  8
+
+struct he_mem_stat {
+	/* meaning of entries depends on enum mem_stat_type */
+	u64			entries[MEM_STAT_LEN];
+};
+
 struct hists {
 	struct rb_root_cached	entries_in_array[2];
 	struct rb_root_cached	*entries_in;
@@ -125,6 +134,9 @@ struct hists {
 	struct perf_hpp_list	*hpp_list;
 	struct list_head	hpp_formats;
 	int			nr_hpp_node;
+	int			nr_mem_stats;
+	enum mem_stat_type	*mem_stat_types;
+	struct he_mem_stat	*mem_stat_total;
 };
 
 #define hists__has(__h, __f) (__h)->hpp_list->__f
@@ -232,6 +244,7 @@ struct hist_entry {
 	} pairs;
 	struct he_stat		stat;
 	struct he_stat		*stat_acc;
+	struct he_mem_stat	*mem_stat;
 	struct map_symbol	ms;
 	struct thread		*thread;
 	struct comm		*comm;
@@ -576,18 +589,25 @@ enum {
 	PERF_HPP__WEIGHT1,
 	PERF_HPP__WEIGHT2,
 	PERF_HPP__WEIGHT3,
+	PERF_HPP__MEM_STAT_OP,
+	PERF_HPP__MEM_STAT_CACHE,
+	PERF_HPP__MEM_STAT_MEMORY,
+	PERF_HPP__MEM_STAT_SNOOP,
+	PERF_HPP__MEM_STAT_DTLB,
 
 	PERF_HPP__MAX_INDEX
 };
 
 void perf_hpp__init(void);
-void perf_hpp__cancel_cumulate(void);
-void perf_hpp__cancel_latency(void);
+void perf_hpp__cancel_cumulate(struct evlist *evlist);
+void perf_hpp__cancel_latency(struct evlist *evlist);
 void perf_hpp__setup_output_field(struct perf_hpp_list *list);
 void perf_hpp__reset_output_field(struct perf_hpp_list *list);
 void perf_hpp__append_sort_keys(struct perf_hpp_list *list);
 int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
 				  struct evlist *evlist);
+int perf_hpp__alloc_mem_stats(struct perf_hpp_list *list,
+			      struct evlist *evlist);
 
 
 bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
@@ -643,6 +663,9 @@ int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		 struct hist_entry *he, hpp_field_fn get_field,
 		 const char *fmtstr, hpp_snprint_fn print_fn,
 		 enum perf_hpp_fmt_type fmtype);
+int hpp__fmt_mem_stat(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		      struct hist_entry *he, enum mem_stat_type mst,
+		      const char *fmtstr, hpp_snprint_fn print_fn);
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 {
diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c
index 3cce77fc8004..c25e7296f1c1 100644
--- a/tools/perf/util/hwmon_pmu.c
+++ b/tools/perf/util/hwmon_pmu.c
@@ -346,42 +346,43 @@ struct perf_pmu *hwmon_pmu__new(struct list_head *pmus, int hwmon_dir, const cha
 {
 	char buf[32];
 	struct hwmon_pmu *hwm;
+	__u32 type = PERF_PMU_TYPE_HWMON_START + strtoul(sysfs_name + 5, NULL, 10);
+
+	if (type > PERF_PMU_TYPE_HWMON_END) {
+		pr_err("Unable to encode hwmon type from %s in valid PMU type\n", sysfs_name);
+		return NULL;
+	}
+
+	snprintf(buf, sizeof(buf), "hwmon_%s", name);
+	fix_name(buf + 6);
 
 	hwm = zalloc(sizeof(*hwm));
 	if (!hwm)
 		return NULL;
 
-	hwm->hwmon_dir_fd = hwmon_dir;
-	hwm->pmu.type = PERF_PMU_TYPE_HWMON_START + strtoul(sysfs_name + 5, NULL, 10);
-	if (hwm->pmu.type > PERF_PMU_TYPE_HWMON_END) {
-		pr_err("Unable to encode hwmon type from %s in valid PMU type\n", sysfs_name);
-		goto err_out;
+	if (perf_pmu__init(&hwm->pmu, type, buf) != 0) {
+		perf_pmu__delete(&hwm->pmu);
+		return NULL;
 	}
-	snprintf(buf, sizeof(buf), "hwmon_%s", name);
-	fix_name(buf + 6);
-	hwm->pmu.name = strdup(buf);
-	if (!hwm->pmu.name)
-		goto err_out;
+
+	hwm->hwmon_dir_fd = hwmon_dir;
 	hwm->pmu.alias_name = strdup(sysfs_name);
-	if (!hwm->pmu.alias_name)
-		goto err_out;
+	if (!hwm->pmu.alias_name) {
+		perf_pmu__delete(&hwm->pmu);
+		return NULL;
+	}
 	hwm->pmu.cpus = perf_cpu_map__new("0");
-	if (!hwm->pmu.cpus)
-		goto err_out;
+	if (!hwm->pmu.cpus) {
+		perf_pmu__delete(&hwm->pmu);
+		return NULL;
+	}
 	INIT_LIST_HEAD(&hwm->pmu.format);
-	INIT_LIST_HEAD(&hwm->pmu.aliases);
 	INIT_LIST_HEAD(&hwm->pmu.caps);
 	hashmap__init(&hwm->events, hwmon_pmu__event_hashmap_hash,
 		      hwmon_pmu__event_hashmap_equal, /*ctx=*/NULL);
 
 	list_add_tail(&hwm->pmu.list, pmus);
 	return &hwm->pmu;
-err_out:
-	free((char *)hwm->pmu.name);
-	free(hwm->pmu.alias_name);
-	free(hwm);
-	close(hwmon_dir);
-	return NULL;
 }
 
 void hwmon_pmu__exit(struct perf_pmu *pmu)
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 4e8a9b172fbc..9b1011fe4826 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -127,6 +127,7 @@ struct intel_pt {
 
 	bool single_pebs;
 	bool sample_pebs;
+	int pebs_data_src_fmt;
 	struct evsel *pebs_evsel;
 
 	u64 evt_sample_type;
@@ -175,6 +176,7 @@ enum switch_state {
 struct intel_pt_pebs_event {
 	struct evsel *evsel;
 	u64 id;
+	int data_src_fmt;
 };
 
 struct intel_pt_queue {
@@ -2272,7 +2274,146 @@ static void intel_pt_add_lbrs(struct branch_stack *br_stack,
 	}
 }
 
-static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel, u64 id)
+#define P(a, b) PERF_MEM_S(a, b)
+#define OP_LH (P(OP, LOAD) | P(LVL, HIT))
+#define LEVEL(x) P(LVLNUM, x)
+#define REM P(REMOTE, REMOTE)
+#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
+
+#define PERF_PEBS_DATA_SOURCE_GRT_MAX	0x10
+#define PERF_PEBS_DATA_SOURCE_GRT_MASK	(PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
+
+/* Based on kernel __intel_pmu_pebs_data_source_grt() and pebs_data_source */
+static const u64 pebs_data_source_grt[PERF_PEBS_DATA_SOURCE_GRT_MAX] = {
+	P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),         /* L3 miss|SNP N/A */
+	OP_LH | P(LVL, L1)  | LEVEL(L1)  | P(SNOOP, NONE),             /* L1 hit|SNP None */
+	OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE),             /* LFB/MAB hit|SNP None */
+	OP_LH | P(LVL, L2)  | LEVEL(L2)  | P(SNOOP, NONE),             /* L2 hit|SNP None */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, NONE),             /* L3 hit|SNP None */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, HIT),              /* L3 hit|SNP Hit */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, HITM),             /* L3 hit|SNP HitM */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, HITM),             /* L3 hit|SNP HitM */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOPX, FWD),             /* L3 hit|SNP Fwd */
+	OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM),   /* Remote L3 hit|SNP HitM */
+	OP_LH | P(LVL, LOC_RAM)  | LEVEL(RAM) | P(SNOOP, HIT),         /* RAM hit|SNP Hit */
+	OP_LH | P(LVL, REM_RAM1) | REM | LEVEL(L3) | P(SNOOP, HIT),    /* Remote L3 hit|SNP Hit */
+	OP_LH | P(LVL, LOC_RAM)  | LEVEL(RAM) | SNOOP_NONE_MISS,       /* RAM hit|SNP None or Miss */
+	OP_LH | P(LVL, REM_RAM1) | LEVEL(RAM) | REM | SNOOP_NONE_MISS, /* Remote RAM hit|SNP None or Miss */
+	OP_LH | P(LVL, IO)  | LEVEL(NA) | P(SNOOP, NONE),              /* I/O hit|SNP None */
+	OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE),              /* Uncached hit|SNP None */
+};
+
+/* Based on kernel __intel_pmu_pebs_data_source_cmt() and pebs_data_source */
+static const u64 pebs_data_source_cmt[PERF_PEBS_DATA_SOURCE_GRT_MAX] = {
+	P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),       /* L3 miss|SNP N/A */
+	OP_LH | P(LVL, L1)  | LEVEL(L1)  | P(SNOOP, NONE),           /* L1 hit|SNP None */
+	OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE),           /* LFB/MAB hit|SNP None */
+	OP_LH | P(LVL, L2)  | LEVEL(L2)  | P(SNOOP, NONE),           /* L2 hit|SNP None */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, NONE),           /* L3 hit|SNP None */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, MISS),           /* L3 hit|SNP Hit */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, HIT),            /* L3 hit|SNP HitM */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOPX, FWD),           /* L3 hit|SNP HitM */
+	OP_LH | P(LVL, L3)  | LEVEL(L3)  | P(SNOOP, HITM),           /* L3 hit|SNP Fwd */
+	OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* Remote L3 hit|SNP HitM */
+	OP_LH | P(LVL, LOC_RAM)  | LEVEL(RAM) | P(SNOOP, NONE),      /* RAM hit|SNP Hit */
+	OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE),                   /* Remote L3 hit|SNP Hit */
+	OP_LH | LEVEL(RAM) | REM | P(SNOOPX, FWD),                   /* RAM hit|SNP None or Miss */
+	OP_LH | LEVEL(RAM) | REM | P(SNOOP, HITM),                   /* Remote RAM hit|SNP None or Miss */
+	OP_LH | P(LVL, IO)  | LEVEL(NA) | P(SNOOP, NONE),            /* I/O hit|SNP None */
+	OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE),            /* Uncached hit|SNP None */
+};
+
+/* Based on kernel pebs_set_tlb_lock() */
+static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock)
+{
+	/*
+	 * TLB access
+	 * 0 = did not miss 2nd level TLB
+	 * 1 = missed 2nd level TLB
+	 */
+	if (tlb)
+		*val |= P(TLB, MISS) | P(TLB, L2);
+	else
+		*val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+	/* locked prefix */
+	if (lock)
+		*val |= P(LOCK, LOCKED);
+}
+
+/* Based on kernel __grt_latency_data() */
+static u64 intel_pt_grt_latency_data(u8 dse, bool tlb, bool lock, bool blk,
+				     const u64 *pebs_data_source)
+{
+	u64 val;
+
+	dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK;
+	val = pebs_data_source[dse];
+
+	pebs_set_tlb_lock(&val, tlb, lock);
+
+	if (blk)
+		val |= P(BLK, DATA);
+	else
+		val |= P(BLK, NA);
+
+	return val;
+}
+
+/* Default value for data source */
+#define PERF_MEM_NA (PERF_MEM_S(OP, NA)    |\
+		     PERF_MEM_S(LVL, NA)   |\
+		     PERF_MEM_S(SNOOP, NA) |\
+		     PERF_MEM_S(LOCK, NA)  |\
+		     PERF_MEM_S(TLB, NA)   |\
+		     PERF_MEM_S(LVLNUM, NA))
+
+enum DATA_SRC_FORMAT {
+	DATA_SRC_FORMAT_ERR  = -1,
+	DATA_SRC_FORMAT_NA   =  0,
+	DATA_SRC_FORMAT_GRT  =  1,
+	DATA_SRC_FORMAT_CMT  =  2,
+};
+
+/* Based on kernel grt_latency_data() and cmt_latency_data */
+static u64 intel_pt_get_data_src(u64 mem_aux_info, int data_src_fmt)
+{
+	switch (data_src_fmt) {
+	case DATA_SRC_FORMAT_GRT: {
+		union {
+			u64 val;
+			struct {
+				unsigned int dse:4;
+				unsigned int locked:1;
+				unsigned int stlb_miss:1;
+				unsigned int fwd_blk:1;
+				unsigned int reserved:25;
+			};
+		} x = {.val = mem_aux_info};
+		return intel_pt_grt_latency_data(x.dse, x.stlb_miss, x.locked, x.fwd_blk,
+						 pebs_data_source_grt);
+	}
+	case DATA_SRC_FORMAT_CMT: {
+		union {
+			u64 val;
+			struct {
+				unsigned int dse:5;
+				unsigned int locked:1;
+				unsigned int stlb_miss:1;
+				unsigned int fwd_blk:1;
+				unsigned int reserved:24;
+			};
+		} x = {.val = mem_aux_info};
+		return intel_pt_grt_latency_data(x.dse, x.stlb_miss, x.locked, x.fwd_blk,
+						 pebs_data_source_cmt);
+	}
+	default:
+		return PERF_MEM_NA;
+	}
+}
+
+static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel,
+					 u64 id, int data_src_fmt)
 {
 	const struct intel_pt_blk_items *items = &ptq->state->items;
 	struct perf_sample sample;
@@ -2393,6 +2534,18 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse
 		}
 	}
 
+	if (sample_type & PERF_SAMPLE_DATA_SRC) {
+		if (items->has_mem_aux_info && data_src_fmt) {
+			if (data_src_fmt < 0) {
+				pr_err("Intel PT missing data_src info\n");
+				return -1;
+			}
+			sample.data_src = intel_pt_get_data_src(items->mem_aux_info, data_src_fmt);
+		} else {
+			sample.data_src = PERF_MEM_NA;
+		}
+	}
+
 	if (sample_type & PERF_SAMPLE_TRANSACTION && items->has_tsx_aux_info) {
 		u64 ax = items->has_rax ? items->rax : 0;
 		/* Refer kernel's intel_hsw_transaction() */
@@ -2413,9 +2566,10 @@ static int intel_pt_synth_single_pebs_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
 	struct evsel *evsel = pt->pebs_evsel;
+	int data_src_fmt = pt->pebs_data_src_fmt;
 	u64 id = evsel->core.id[0];
 
-	return intel_pt_do_synth_pebs_sample(ptq, evsel, id);
+	return intel_pt_do_synth_pebs_sample(ptq, evsel, id, data_src_fmt);
 }
 
 static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
@@ -2440,7 +2594,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 				       hw_id);
 			return intel_pt_synth_single_pebs_sample(ptq);
 		}
-		err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id);
+		err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id, pe->data_src_fmt);
 		if (err)
 			return err;
 	}
@@ -3407,6 +3561,49 @@ static int intel_pt_process_itrace_start(struct intel_pt *pt,
 					event->itrace_start.tid);
 }
 
+/*
+ * Events with data_src are identified by L1_Hit_Indication
+ * refer https://github.com/intel/perfmon
+ */
+static int intel_pt_data_src_fmt(struct intel_pt *pt, struct evsel *evsel)
+{
+	struct perf_env *env = pt->machine->env;
+	int fmt = DATA_SRC_FORMAT_NA;
+
+	if (!env->cpuid)
+		return DATA_SRC_FORMAT_ERR;
+
+	/*
+	 * PEBS-via-PT is only supported on E-core non-hybrid. Of those only
+	 * Gracemont and Crestmont have data_src. Check for:
+	 *	Alderlake N   (Gracemont)
+	 *	Sierra Forest (Crestmont)
+	 *	Grand Ridge   (Crestmont)
+	 */
+
+	if (!strncmp(env->cpuid, "GenuineIntel,6,190,", 19))
+		fmt = DATA_SRC_FORMAT_GRT;
+
+	if (!strncmp(env->cpuid, "GenuineIntel,6,175,", 19) ||
+	    !strncmp(env->cpuid, "GenuineIntel,6,182,", 19))
+		fmt = DATA_SRC_FORMAT_CMT;
+
+	if (fmt == DATA_SRC_FORMAT_NA)
+		return fmt;
+
+	/*
+	 * Only data_src events are:
+	 *	mem-loads	event=0xd0,umask=0x5
+	 *	mem-stores	event=0xd0,umask=0x6
+	 */
+	if (evsel->core.attr.type == PERF_TYPE_RAW &&
+	    ((evsel->core.attr.config & 0xffff) == 0x5d0 ||
+	     (evsel->core.attr.config & 0xffff) == 0x6d0))
+		return fmt;
+
+	return DATA_SRC_FORMAT_NA;
+}
+
 static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt,
 					     union perf_event *event,
 					     struct perf_sample *sample)
@@ -3427,6 +3624,7 @@ static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt,
 
 	ptq->pebs[hw_id].evsel = evsel;
 	ptq->pebs[hw_id].id = sample->id;
+	ptq->pebs[hw_id].data_src_fmt = intel_pt_data_src_fmt(pt, evsel);
 
 	return 0;
 }
@@ -3976,6 +4174,7 @@ static void intel_pt_setup_pebs_events(struct intel_pt *pt)
 			}
 			pt->single_pebs = true;
 			pt->sample_pebs = true;
+			pt->pebs_data_src_fmt = intel_pt_data_src_fmt(pt, evsel);
 			pt->pebs_evsel = evsel;
 		}
 	}
diff --git a/tools/perf/util/intel-tpebs.c b/tools/perf/util/intel-tpebs.c
index 2c421b475b3b..3b92ebf5c112 100644
--- a/tools/perf/util/intel-tpebs.c
+++ b/tools/perf/util/intel-tpebs.c
@@ -3,7 +3,7 @@
  * intel_tpebs.c: Intel TPEBS support
  */
 
-
+#include <api/fs/fs.h>
 #include <sys/param.h>
 #include <subcmd/run-command.h>
 #include <thread.h>
@@ -12,13 +12,17 @@
 #include <linux/zalloc.h>
 #include <linux/err.h>
 #include "sample.h"
+#include "counts.h"
 #include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
+#include "mutex.h"
 #include "session.h"
+#include "stat.h"
 #include "tool.h"
 #include "cpumap.h"
 #include "metricgroup.h"
+#include "stat.h"
 #include <sys/stat.h>
 #include <sys/file.h>
 #include <poll.h>
@@ -27,95 +31,155 @@
 #define PERF_DATA		"-"
 
 bool tpebs_recording;
-static pid_t tpebs_pid = -1;
-static size_t tpebs_event_size;
+enum tpebs_mode tpebs_mode;
 static LIST_HEAD(tpebs_results);
 static pthread_t tpebs_reader_thread;
-static struct child_process *tpebs_cmd;
+static struct child_process tpebs_cmd;
+static int control_fd[2], ack_fd[2];
+static struct mutex tpebs_mtx;
 
 struct tpebs_retire_lat {
 	struct list_head nd;
-	/* Event name */
-	const char *name;
-	/* Event name with the TPEBS modifier R */
-	const char *tpebs_name;
-	/* Count of retire_latency values found in sample data */
-	size_t count;
-	/* Sum of all the retire_latency values in sample data */
-	int sum;
-	/* Average of retire_latency, val = sum / count */
-	double val;
+	/** @evsel: The evsel that opened the retire_lat event. */
+	struct evsel *evsel;
+	/** @event: Event passed to perf record. */
+	char *event;
+	/** @stats: Recorded retirement latency stats. */
+	struct stats stats;
+	/** @last: Last retirement latency read. */
+	uint64_t last;
+	/* Has the event been sent to perf record? */
+	bool started;
 };
 
-static int get_perf_record_args(const char **record_argv, char buf[],
-				const char *cpumap_buf)
+static void tpebs_mtx_init(void)
+{
+	mutex_init(&tpebs_mtx);
+}
+
+static struct mutex *tpebs_mtx_get(void)
 {
-	struct tpebs_retire_lat *e;
-	int i = 0;
+	static pthread_once_t tpebs_mtx_once = PTHREAD_ONCE_INIT;
+
+	pthread_once(&tpebs_mtx_once, tpebs_mtx_init);
+	return &tpebs_mtx;
+}
 
-	pr_debug("tpebs: Prepare perf record for retire_latency\n");
+static struct tpebs_retire_lat *tpebs_retire_lat__find(struct evsel *evsel)
+	EXCLUSIVE_LOCKS_REQUIRED(tpebs_mtx_get());
+
+static int evsel__tpebs_start_perf_record(struct evsel *evsel)
+{
+	const char **record_argv;
+	int tpebs_event_size = 0, i = 0, ret;
+	char control_fd_buf[32];
+	char cpumap_buf[50];
+	struct tpebs_retire_lat *t;
+
+	list_for_each_entry(t, &tpebs_results, nd)
+		tpebs_event_size++;
+
+	record_argv = malloc((10 + 2 * tpebs_event_size) * sizeof(*record_argv));
+	if (!record_argv)
+		return -ENOMEM;
 
 	record_argv[i++] = "perf";
 	record_argv[i++] = "record";
 	record_argv[i++] = "-W";
 	record_argv[i++] = "--synth=no";
-	record_argv[i++] = buf;
 
-	if (!cpumap_buf) {
-		pr_err("tpebs: Require cpumap list to run sampling\n");
-		return -ECANCELED;
-	}
-	/* Use -C when cpumap_buf is not "-1" */
-	if (strcmp(cpumap_buf, "-1")) {
+	scnprintf(control_fd_buf, sizeof(control_fd_buf), "--control=fd:%d,%d",
+		  control_fd[0], ack_fd[1]);
+	record_argv[i++] = control_fd_buf;
+
+	record_argv[i++] = "-o";
+	record_argv[i++] = PERF_DATA;
+
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(evsel->evlist->core.user_requested_cpus)) {
+		cpu_map__snprint(evsel->evlist->core.user_requested_cpus, cpumap_buf,
+				 sizeof(cpumap_buf));
 		record_argv[i++] = "-C";
 		record_argv[i++] = cpumap_buf;
 	}
 
-	list_for_each_entry(e, &tpebs_results, nd) {
+	list_for_each_entry(t, &tpebs_results, nd) {
 		record_argv[i++] = "-e";
-		record_argv[i++] = e->name;
+		record_argv[i++] = t->event;
 	}
+	record_argv[i++] = NULL;
+	assert(i == 10 + 2 * tpebs_event_size || i == 8 + 2 * tpebs_event_size);
+	/* Note, no workload given so system wide is implied. */
+
+	assert(tpebs_cmd.pid == 0);
+	tpebs_cmd.argv = record_argv;
+	tpebs_cmd.out = -1;
+	ret = start_command(&tpebs_cmd);
+	zfree(&tpebs_cmd.argv);
+	list_for_each_entry(t, &tpebs_results, nd)
+		t->started = true;
 
-	record_argv[i++] = "-o";
-	record_argv[i++] = PERF_DATA;
-
-	return 0;
+	return ret;
 }
 
-static int prepare_run_command(const char **argv)
+static bool is_child_pid(pid_t parent, pid_t child)
 {
-	tpebs_cmd = zalloc(sizeof(struct child_process));
-	if (!tpebs_cmd)
-		return -ENOMEM;
-	tpebs_cmd->argv = argv;
-	tpebs_cmd->out = -1;
-	return 0;
+	if (parent < 0 || child < 0)
+		return false;
+
+	while (true) {
+		char path[PATH_MAX];
+		char line[256];
+		FILE *fp;
+
+new_child:
+		if (parent == child)
+			return true;
+
+		if (child <= 0)
+			return false;
+
+		scnprintf(path, sizeof(path), "%s/%d/status", procfs__mountpoint(), child);
+		fp = fopen(path, "r");
+		if (!fp) {
+			/* Presumably the process went away. Assume not a child. */
+			return false;
+		}
+		while (fgets(line, sizeof(line), fp) != NULL) {
+			if (strncmp(line, "PPid:", 5) == 0) {
+				fclose(fp);
+				if (sscanf(line + 5, "%d", &child) != 1) {
+					/* Unexpected error parsing. */
+					return false;
+				}
+				goto new_child;
+			}
+		}
+		/* Unexpected EOF. */
+		fclose(fp);
+		return false;
+	}
 }
 
-static int start_perf_record(int control_fd[], int ack_fd[],
-				const char *cpumap_buf)
+static bool should_ignore_sample(const struct perf_sample *sample, const struct tpebs_retire_lat *t)
 {
-	const char **record_argv;
-	int ret;
-	char buf[32];
+	pid_t workload_pid, sample_pid = sample->pid;
 
-	scnprintf(buf, sizeof(buf), "--control=fd:%d,%d", control_fd[0], ack_fd[1]);
+	/*
+	 * During evlist__purge the evlist will be removed prior to the
+	 * evsel__exit calling evsel__tpebs_close and taking the
+	 * tpebs_mtx. Avoid a segfault by ignoring samples in this case.
+	 */
+	if (t->evsel->evlist == NULL)
+		return true;
 
-	record_argv = calloc(12 + 2 * tpebs_event_size, sizeof(char *));
-	if (!record_argv)
-		return -ENOMEM;
+	workload_pid = t->evsel->evlist->workload.pid;
+	if (workload_pid < 0 || workload_pid == sample_pid)
+		return false;
 
-	ret = get_perf_record_args(record_argv, buf, cpumap_buf);
-	if (ret)
-		goto out;
+	if (!t->evsel->core.attr.inherit)
+		return true;
 
-	ret = prepare_run_command(record_argv);
-	if (ret)
-		goto out;
-	ret = start_command(tpebs_cmd);
-out:
-	free(record_argv);
-	return ret;
+	return !is_child_pid(workload_pid, sample_pid);
 }
 
 static int process_sample_event(const struct perf_tool *tool __maybe_unused,
@@ -124,27 +188,32 @@ static int process_sample_event(const struct perf_tool *tool __maybe_unused,
 				struct evsel *evsel,
 				struct machine *machine __maybe_unused)
 {
-	int ret = 0;
-	const char *evname;
 	struct tpebs_retire_lat *t;
 
-	evname = evsel__name(evsel);
-
+	mutex_lock(tpebs_mtx_get());
+	if (tpebs_cmd.pid == 0) {
+		/* Record has terminated. */
+		mutex_unlock(tpebs_mtx_get());
+		return 0;
+	}
+	t = tpebs_retire_lat__find(evsel);
+	if (!t) {
+		mutex_unlock(tpebs_mtx_get());
+		return -EINVAL;
+	}
+	if (should_ignore_sample(sample, t)) {
+		mutex_unlock(tpebs_mtx_get());
+		return 0;
+	}
 	/*
 	 * Need to handle per core results? We are assuming average retire
 	 * latency value will be used. Save the number of samples and the sum of
 	 * retire latency value for each event.
 	 */
-	list_for_each_entry(t, &tpebs_results, nd) {
-		if (!strcmp(evname, t->name)) {
-			t->count += 1;
-			t->sum += sample->retire_lat;
-			t->val = (double) t->sum / t->count;
-			break;
-		}
-	}
-
-	return ret;
+	t->last = sample->retire_lat;
+	update_stats(&t->stats, sample->retire_lat);
+	mutex_unlock(tpebs_mtx_get());
+	return 0;
 }
 
 static int process_feature_event(struct perf_session *session,
@@ -155,14 +224,13 @@ static int process_feature_event(struct perf_session *session,
 	return 0;
 }
 
-static void *__sample_reader(void *arg)
+static void *__sample_reader(void *arg __maybe_unused)
 {
-	struct child_process *child = arg;
 	struct perf_session *session;
 	struct perf_data data = {
 		.mode = PERF_DATA_MODE_READ,
 		.path = PERF_DATA,
-		.file.fd = child->out,
+		.file.fd = tpebs_cmd.out,
 	};
 	struct perf_tool tool;
 
@@ -180,94 +248,277 @@ static void *__sample_reader(void *arg)
 	return NULL;
 }
 
+static int tpebs_send_record_cmd(const char *msg) EXCLUSIVE_LOCKS_REQUIRED(tpebs_mtx_get())
+{
+	struct pollfd pollfd = { .events = POLLIN, };
+	int ret, len, retries = 0;
+	char ack_buf[8];
+
+	/* Check if the command exited before the send, done with the lock held. */
+	if (tpebs_cmd.pid == 0)
+		return 0;
+
+	/*
+	 * Let go of the lock while sending/receiving as blocking can starve the
+	 * sample reading thread.
+	 */
+	mutex_unlock(tpebs_mtx_get());
+
+	/* Send perf record command.*/
+	len = strlen(msg);
+	ret = write(control_fd[1], msg, len);
+	if (ret != len) {
+		pr_err("perf record control write control message '%s' failed\n", msg);
+		ret = -EPIPE;
+		goto out;
+	}
+
+	if (!strcmp(msg, EVLIST_CTL_CMD_STOP_TAG)) {
+		ret = 0;
+		goto out;
+	}
+
+	/* Wait for an ack. */
+	pollfd.fd = ack_fd[0];
+
+	/*
+	 * We need this poll to ensure the ack_fd PIPE will not hang
+	 * when perf record failed for any reason. The timeout value
+	 * 3000ms is an empirical selection.
+	 */
+again:
+	if (!poll(&pollfd, 1, 500)) {
+		if (check_if_command_finished(&tpebs_cmd)) {
+			ret = 0;
+			goto out;
+		}
+
+		if (retries++ < 6)
+			goto again;
+		pr_err("tpebs failed: perf record ack timeout for '%s'\n", msg);
+		ret = -ETIMEDOUT;
+		goto out;
+	}
+
+	if (!(pollfd.revents & POLLIN)) {
+		if (check_if_command_finished(&tpebs_cmd)) {
+			ret = 0;
+			goto out;
+		}
+
+		pr_err("tpebs failed: did not received an ack for '%s'\n", msg);
+		ret = -EPIPE;
+		goto out;
+	}
+
+	ret = read(ack_fd[0], ack_buf, sizeof(ack_buf));
+	if (ret > 0)
+		ret = strcmp(ack_buf, EVLIST_CTL_CMD_ACK_TAG);
+	else
+		pr_err("tpebs: perf record control ack failed\n");
+out:
+	/* Re-take lock as expected by caller. */
+	mutex_lock(tpebs_mtx_get());
+	return ret;
+}
+
 /*
  * tpebs_stop - stop the sample data read thread and the perf record process.
  */
-static int tpebs_stop(void)
+static int tpebs_stop(void) EXCLUSIVE_LOCKS_REQUIRED(tpebs_mtx_get())
 {
 	int ret = 0;
 
 	/* Like tpebs_start, we should only run tpebs_end once. */
-	if (tpebs_pid != -1) {
-		kill(tpebs_cmd->pid, SIGTERM);
-		tpebs_pid = -1;
+	if (tpebs_cmd.pid != 0) {
+		tpebs_send_record_cmd(EVLIST_CTL_CMD_STOP_TAG);
+		tpebs_cmd.pid = 0;
+		mutex_unlock(tpebs_mtx_get());
 		pthread_join(tpebs_reader_thread, NULL);
-		close(tpebs_cmd->out);
-		ret = finish_command(tpebs_cmd);
+		mutex_lock(tpebs_mtx_get());
+		close(control_fd[0]);
+		close(control_fd[1]);
+		close(ack_fd[0]);
+		close(ack_fd[1]);
+		close(tpebs_cmd.out);
+		ret = finish_command(&tpebs_cmd);
+		tpebs_cmd.pid = 0;
 		if (ret == -ERR_RUN_COMMAND_WAITPID_SIGNAL)
 			ret = 0;
 	}
 	return ret;
 }
 
-/*
- * tpebs_start - start tpebs execution.
- * @evsel_list: retire_latency evsels in this list will be selected and sampled
- * to get the average retire_latency value.
- *
- * This function will be called from evlist level later when evlist__open() is
- * called consistently.
+/**
+ * evsel__tpebs_event() - Create string event encoding to pass to `perf record`.
  */
-int tpebs_start(struct evlist *evsel_list)
+static int evsel__tpebs_event(struct evsel *evsel, char **event)
 {
-	int ret = 0;
-	struct evsel *evsel;
-	char cpumap_buf[50];
+	char *name, *modifier;
+	int ret;
+
+	name = strdup(evsel->name);
+	if (!name)
+		return -ENOMEM;
+
+	modifier = strrchr(name, 'R');
+	if (!modifier) {
+		ret = -EINVAL;
+		goto out;
+	}
+	*modifier = 'p';
+	modifier = strchr(name, ':');
+	if (!modifier)
+		modifier = strrchr(name, '/');
+	if (!modifier) {
+		ret = -EINVAL;
+		goto out;
+	}
+	*modifier = '\0';
+	if (asprintf(event, "%s/name=tpebs_event_%p/%s", name, evsel, modifier + 1) > 0)
+		ret = 0;
+	else
+		ret = -ENOMEM;
+out:
+	if (ret)
+		pr_err("Tpebs event modifier broken '%s'\n", evsel->name);
+	free(name);
+	return ret;
+}
+
+static struct tpebs_retire_lat *tpebs_retire_lat__new(struct evsel *evsel)
+{
+	struct tpebs_retire_lat *result = zalloc(sizeof(*result));
+	int ret;
+
+	if (!result)
+		return NULL;
+
+	ret = evsel__tpebs_event(evsel, &result->event);
+	if (ret) {
+		free(result);
+		return NULL;
+	}
+	result->evsel = evsel;
+	return result;
+}
+
+static void tpebs_retire_lat__delete(struct tpebs_retire_lat *r)
+{
+	zfree(&r->event);
+	free(r);
+}
+
+static struct tpebs_retire_lat *tpebs_retire_lat__find(struct evsel *evsel)
+{
+	struct tpebs_retire_lat *t;
+	unsigned long num;
+	const char *evsel_name;
 
 	/*
-	 * We should only run tpebs_start when tpebs_recording is enabled.
-	 * And we should only run it once with all the required events.
+	 * Evsels will match for evlist with the retirement latency event. The
+	 * name with "tpebs_event_" prefix will be present on events being read
+	 * from `perf record`.
 	 */
-	if (tpebs_pid != -1 || !tpebs_recording)
+	if (evsel__is_retire_lat(evsel)) {
+		list_for_each_entry(t, &tpebs_results, nd) {
+			if (t->evsel == evsel)
+				return t;
+		}
+		return NULL;
+	}
+	evsel_name = strstr(evsel->name, "tpebs_event_");
+	if (!evsel_name) {
+		/* Unexpected that the perf record should have other events. */
+		return NULL;
+	}
+	errno = 0;
+	num = strtoull(evsel_name + 12, NULL, 16);
+	if (errno) {
+		pr_err("Bad evsel for tpebs find '%s'\n", evsel->name);
+		return NULL;
+	}
+	list_for_each_entry(t, &tpebs_results, nd) {
+		if ((unsigned long)t->evsel == num)
+			return t;
+	}
+	return NULL;
+}
+
+/**
+ * evsel__tpebs_prepare - create tpebs data structures ready for opening.
+ * @evsel: retire_latency evsel, all evsels on its list will be prepared.
+ */
+static int evsel__tpebs_prepare(struct evsel *evsel)
+{
+	struct evsel *pos;
+	struct tpebs_retire_lat *tpebs_event;
+
+	mutex_lock(tpebs_mtx_get());
+	tpebs_event = tpebs_retire_lat__find(evsel);
+	if (tpebs_event) {
+		/* evsel, or an identically named one, was already prepared. */
+		mutex_unlock(tpebs_mtx_get());
 		return 0;
+	}
+	tpebs_event = tpebs_retire_lat__new(evsel);
+	if (!tpebs_event) {
+		mutex_unlock(tpebs_mtx_get());
+		return -ENOMEM;
+	}
+	list_add_tail(&tpebs_event->nd, &tpebs_results);
+	mutex_unlock(tpebs_mtx_get());
 
-	cpu_map__snprint(evsel_list->core.user_requested_cpus, cpumap_buf, sizeof(cpumap_buf));
 	/*
-	 * Prepare perf record for sampling event retire_latency before fork and
-	 * prepare workload
+	 * Eagerly prepare all other evsels on the list to try to ensure that by
+	 * open they are all known.
 	 */
-	evlist__for_each_entry(evsel_list, evsel) {
-		int i;
-		char *name;
-		struct tpebs_retire_lat *new;
+	evlist__for_each_entry(evsel->evlist, pos) {
+		int ret;
 
-		if (!evsel->retire_lat)
+		if (pos == evsel || !pos->retire_lat)
 			continue;
 
-		pr_debug("tpebs: Retire_latency of event %s is required\n", evsel->name);
-		for (i = strlen(evsel->name) - 1; i > 0; i--) {
-			if (evsel->name[i] == 'R')
-				break;
-		}
-		if (i <= 0 || evsel->name[i] != 'R') {
-			ret = -1;
-			goto err;
-		}
+		ret = evsel__tpebs_prepare(pos);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
 
-		name = strdup(evsel->name);
-		if (!name) {
-			ret = -ENOMEM;
-			goto err;
-		}
-		name[i] = 'p';
+/**
+ * evsel__tpebs_open - starts tpebs execution.
+ * @evsel: retire_latency evsel, all evsels on its list will be selected. Each
+ *         evsel is sampled to get the average retire_latency value.
+ */
+int evsel__tpebs_open(struct evsel *evsel)
+{
+	int ret;
+	bool tpebs_empty;
 
-		new = zalloc(sizeof(*new));
-		if (!new) {
-			ret = -1;
-			zfree(&name);
-			goto err;
-		}
-		new->name = name;
-		new->tpebs_name = evsel->name;
-		list_add_tail(&new->nd, &tpebs_results);
-		tpebs_event_size += 1;
+	/* We should only run tpebs_start when tpebs_recording is enabled. */
+	if (!tpebs_recording)
+		return 0;
+	/* Only start the events once. */
+	if (tpebs_cmd.pid != 0) {
+		struct tpebs_retire_lat *t;
+		bool valid;
+
+		mutex_lock(tpebs_mtx_get());
+		t = tpebs_retire_lat__find(evsel);
+		valid = t && t->started;
+		mutex_unlock(tpebs_mtx_get());
+		/* May fail as the event wasn't started. */
+		return valid ? 0 : -EBUSY;
 	}
 
-	if (tpebs_event_size > 0) {
-		struct pollfd pollfd = { .events = POLLIN, };
-		int control_fd[2], ack_fd[2], len;
-		char ack_buf[8];
+	ret = evsel__tpebs_prepare(evsel);
+	if (ret)
+		return ret;
 
+	mutex_lock(tpebs_mtx_get());
+	tpebs_empty = list_empty(&tpebs_results);
+	if (!tpebs_empty) {
 		/*Create control and ack fd for --control*/
 		if (pipe(control_fd) < 0) {
 			pr_err("tpebs: Failed to create control fifo");
@@ -280,153 +531,131 @@ int tpebs_start(struct evlist *evsel_list)
 			goto out;
 		}
 
-		ret = start_perf_record(control_fd, ack_fd, cpumap_buf);
+		ret = evsel__tpebs_start_perf_record(evsel);
 		if (ret)
 			goto out;
-		tpebs_pid = tpebs_cmd->pid;
-		if (pthread_create(&tpebs_reader_thread, NULL, __sample_reader, tpebs_cmd)) {
-			kill(tpebs_cmd->pid, SIGTERM);
-			close(tpebs_cmd->out);
-			pr_err("Could not create thread to process sample data.\n");
-			ret = -1;
-			goto out;
-		}
-		/* Wait for perf record initialization.*/
-		len = strlen(EVLIST_CTL_CMD_ENABLE_TAG);
-		ret = write(control_fd[1], EVLIST_CTL_CMD_ENABLE_TAG, len);
-		if (ret != len) {
-			pr_err("perf record control write control message failed\n");
-			goto out;
-		}
-
-		/* wait for an ack */
-		pollfd.fd = ack_fd[0];
-
-		/*
-		 * We need this poll to ensure the ack_fd PIPE will not hang
-		 * when perf record failed for any reason. The timeout value
-		 * 3000ms is an empirical selection.
-		 */
-		if (!poll(&pollfd, 1, 3000)) {
-			pr_err("tpebs failed: perf record ack timeout\n");
-			ret = -1;
-			goto out;
-		}
 
-		if (!(pollfd.revents & POLLIN)) {
-			pr_err("tpebs failed: did not received an ack\n");
+		if (pthread_create(&tpebs_reader_thread, /*attr=*/NULL, __sample_reader,
+				   /*arg=*/NULL)) {
+			kill(tpebs_cmd.pid, SIGTERM);
+			close(tpebs_cmd.out);
+			pr_err("Could not create thread to process sample data.\n");
 			ret = -1;
 			goto out;
 		}
-
-		ret = read(ack_fd[0], ack_buf, sizeof(ack_buf));
-		if (ret > 0)
-			ret = strcmp(ack_buf, EVLIST_CTL_CMD_ACK_TAG);
-		else {
-			pr_err("tpebs: perf record control ack failed\n");
-			goto out;
-		}
+		ret = tpebs_send_record_cmd(EVLIST_CTL_CMD_ENABLE_TAG);
+	}
 out:
-		close(control_fd[0]);
-		close(control_fd[1]);
-		close(ack_fd[0]);
-		close(ack_fd[1]);
+	if (ret) {
+		struct tpebs_retire_lat *t = tpebs_retire_lat__find(evsel);
+
+		list_del_init(&t->nd);
+		tpebs_retire_lat__delete(t);
 	}
-err:
-	if (ret)
-		tpebs_delete();
+	mutex_unlock(tpebs_mtx_get());
 	return ret;
 }
 
-
-int tpebs_set_evsel(struct evsel *evsel, int cpu_map_idx, int thread)
+int evsel__tpebs_read(struct evsel *evsel, int cpu_map_idx, int thread)
 {
-	__u64 val;
-	bool found = false;
+	struct perf_counts_values *count, *old_count = NULL;
 	struct tpebs_retire_lat *t;
-	struct perf_counts_values *count;
+	uint64_t val;
+	int ret;
 
-	/* Non reitre_latency evsel should never enter this function. */
-	if (!evsel__is_retire_lat(evsel))
-		return -1;
+	/* Only set retire_latency value to the first CPU and thread. */
+	if (cpu_map_idx != 0 || thread != 0)
+		return 0;
+
+	if (evsel->prev_raw_counts)
+		old_count = perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
 
-	/*
-	 * Need to stop the forked record to ensure get sampled data from the
-	 * PIPE to process and get non-zero retire_lat value for hybrid.
-	 */
-	tpebs_stop();
 	count = perf_counts(evsel->counts, cpu_map_idx, thread);
 
-	list_for_each_entry(t, &tpebs_results, nd) {
-		if (t->tpebs_name == evsel->name ||
-		    (evsel->metric_id && !strcmp(t->tpebs_name, evsel->metric_id))) {
-			found = true;
+	mutex_lock(tpebs_mtx_get());
+	t = tpebs_retire_lat__find(evsel);
+	/*
+	 * If reading the first tpebs result, send a ping to the record
+	 * process. Allow the sample reader a chance to read by releasing and
+	 * reacquiring the lock.
+	 */
+	if (t && &t->nd == tpebs_results.next) {
+		ret = tpebs_send_record_cmd(EVLIST_CTL_CMD_PING_TAG);
+		mutex_unlock(tpebs_mtx_get());
+		if (ret)
+			return ret;
+		mutex_lock(tpebs_mtx_get());
+	}
+	if (t == NULL || t->stats.n == 0) {
+		/* No sample data, use default. */
+		if (tpebs_recording) {
+			pr_warning_once(
+				"Using precomputed retirement latency data as no samples\n");
+		}
+		val = 0;
+		switch (tpebs_mode) {
+		case TPEBS_MODE__MIN:
+			val = rint(evsel->retirement_latency.min);
+			break;
+		case TPEBS_MODE__MAX:
+			val = rint(evsel->retirement_latency.max);
+			break;
+		default:
+		case TPEBS_MODE__LAST:
+		case TPEBS_MODE__MEAN:
+			val = rint(evsel->retirement_latency.mean);
+			break;
+		}
+	} else {
+		switch (tpebs_mode) {
+		case TPEBS_MODE__MIN:
+			val = t->stats.min;
+			break;
+		case TPEBS_MODE__MAX:
+			val = t->stats.max;
+			break;
+		case TPEBS_MODE__LAST:
+			val = t->last;
+			break;
+		default:
+		case TPEBS_MODE__MEAN:
+			val = rint(t->stats.mean);
 			break;
 		}
 	}
-
-	/* Set ena and run to non-zero */
-	count->ena = count->run = 1;
-	count->lost = 0;
-
-	if (!found) {
-		/*
-		 * Set default value or 0 when retire_latency for this event is
-		 * not found from sampling data (record_tpebs not set or 0
-		 * sample recorded).
-		 */
-		count->val = 0;
-		return 0;
+	mutex_unlock(tpebs_mtx_get());
+
+	if (old_count) {
+		count->val = old_count->val + val;
+		count->run = old_count->run + 1;
+		count->ena = old_count->ena + 1;
+	} else {
+		count->val = val;
+		count->run++;
+		count->ena++;
 	}
-
-	/*
-	 * Only set retire_latency value to the first CPU and thread.
-	 */
-	if (cpu_map_idx == 0 && thread == 0)
-		val = rint(t->val);
-	else
-		val = 0;
-
-	count->val = val;
 	return 0;
 }
 
-static void tpebs_retire_lat__delete(struct tpebs_retire_lat *r)
-{
-	zfree(&r->name);
-	free(r);
-}
-
-
-/*
- * tpebs_delete - delete tpebs related data and stop the created thread and
- * process by calling tpebs_stop().
+/**
+ * evsel__tpebs_close() - delete tpebs related data. If the last event, stop the
+ * created thread and process by calling tpebs_stop().
  *
- * This function is called from evlist_delete() and also from builtin-stat
- * stat_handle_error(). If tpebs_start() is called from places other then perf
- * stat, need to ensure tpebs_delete() is also called to safely free mem and
- * close the data read thread and the forked perf record process.
- *
- * This function is also called in evsel__close() to be symmetric with
- * tpebs_start() being called in evsel__open(). We will update this call site
- * when move tpebs_start() to evlist level.
+ * This function is called in evsel__close() to be symmetric with
+ * evsel__tpebs_open() being called in evsel__open().
  */
-void tpebs_delete(void)
+void evsel__tpebs_close(struct evsel *evsel)
 {
-	struct tpebs_retire_lat *r, *rtmp;
-
-	if (tpebs_pid == -1)
-		return;
-
-	tpebs_stop();
+	struct tpebs_retire_lat *t;
 
-	list_for_each_entry_safe(r, rtmp, &tpebs_results, nd) {
-		list_del_init(&r->nd);
-		tpebs_retire_lat__delete(r);
-	}
+	mutex_lock(tpebs_mtx_get());
+	t = tpebs_retire_lat__find(evsel);
+	if (t) {
+		list_del_init(&t->nd);
+		tpebs_retire_lat__delete(t);
 
-	if (tpebs_cmd) {
-		free(tpebs_cmd);
-		tpebs_cmd = NULL;
+		if (list_empty(&tpebs_results))
+			tpebs_stop();
 	}
+	mutex_unlock(tpebs_mtx_get());
 }
diff --git a/tools/perf/util/intel-tpebs.h b/tools/perf/util/intel-tpebs.h
index 766b3fbd79f1..9475e2e6ea74 100644
--- a/tools/perf/util/intel-tpebs.h
+++ b/tools/perf/util/intel-tpebs.h
@@ -2,34 +2,24 @@
 /*
  * intel_tpebs.h: Intel TEPBS support
  */
-#ifndef INCLUDE__PERF_INTEL_TPEBS_H__
-#define INCLUDE__PERF_INTEL_TPEBS_H__
+#ifndef __INTEL_TPEBS_H
+#define __INTEL_TPEBS_H
 
-#include "stat.h"
-#include "evsel.h"
+struct evlist;
+struct evsel;
 
-#ifdef HAVE_ARCH_X86_64_SUPPORT
+enum tpebs_mode {
+	TPEBS_MODE__MEAN,
+	TPEBS_MODE__MIN,
+	TPEBS_MODE__MAX,
+	TPEBS_MODE__LAST,
+};
 
 extern bool tpebs_recording;
-int tpebs_start(struct evlist *evsel_list);
-void tpebs_delete(void);
-int tpebs_set_evsel(struct evsel *evsel, int cpu_map_idx, int thread);
+extern enum tpebs_mode tpebs_mode;
 
-#else
+int evsel__tpebs_open(struct evsel *evsel);
+void evsel__tpebs_close(struct evsel *evsel);
+int evsel__tpebs_read(struct evsel *evsel, int cpu_map_idx, int thread);
 
-static inline int tpebs_start(struct evlist *evsel_list __maybe_unused)
-{
-	return 0;
-}
-
-static inline void tpebs_delete(void) {};
-
-static inline int tpebs_set_evsel(struct evsel *evsel  __maybe_unused,
-				int cpu_map_idx  __maybe_unused,
-				int thread  __maybe_unused)
-{
-	return 0;
-}
-
-#endif
-#endif
+#endif /* __INTEL_TPEBS_H */
diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h
index b5d916aa49df..59c94190b092 100644
--- a/tools/perf/util/lock-contention.h
+++ b/tools/perf/util/lock-contention.h
@@ -18,6 +18,12 @@ struct lock_filter {
 	char			**slabs;
 };
 
+struct lock_delay {
+	char			*sym;
+	unsigned long		addr;
+	unsigned long		time;
+};
+
 struct lock_stat {
 	struct hlist_node	hash_entry;
 	struct rb_node		rb;		/* used for sorting */
@@ -140,14 +146,17 @@ struct lock_contention {
 	struct machine *machine;
 	struct hlist_head *result;
 	struct lock_filter *filters;
+	struct lock_delay *delays;
 	struct lock_contention_fails fails;
 	struct rb_root cgroups;
+	void *btf;
 	unsigned long map_nr_entries;
 	int max_stack;
 	int stack_skip;
 	int aggr_mode;
 	int owner;
 	int nr_filtered;
+	int nr_delays;
 	bool save_callstack;
 };
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 2531b373f2cf..7ec12c207970 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -20,6 +20,7 @@
 #include "path.h"
 #include "srcline.h"
 #include "symbol.h"
+#include "synthetic-events.h"
 #include "sort.h"
 #include "strlist.h"
 #include "target.h"
@@ -128,23 +129,57 @@ out:
 	return 0;
 }
 
-struct machine *machine__new_host(void)
+static struct machine *__machine__new_host(bool kernel_maps)
 {
 	struct machine *machine = malloc(sizeof(*machine));
 
-	if (machine != NULL) {
-		machine__init(machine, "", HOST_KERNEL_ID);
+	if (!machine)
+		return NULL;
 
-		if (machine__create_kernel_maps(machine) < 0)
-			goto out_delete;
+	machine__init(machine, "", HOST_KERNEL_ID);
 
-		machine->env = &perf_env;
+	if (kernel_maps && machine__create_kernel_maps(machine) < 0) {
+		free(machine);
+		return NULL;
 	}
+	machine->env = &perf_env;
+	return machine;
+}
+
+struct machine *machine__new_host(void)
+{
+	return __machine__new_host(/*kernel_maps=*/true);
+}
+
+static int mmap_handler(const struct perf_tool *tool __maybe_unused,
+			union perf_event *event,
+			struct perf_sample *sample,
+			struct machine *machine)
+{
+	return machine__process_mmap2_event(machine, event, sample);
+}
 
+static int machine__init_live(struct machine *machine, pid_t pid)
+{
+	union perf_event event;
+
+	memset(&event, 0, sizeof(event));
+	return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
+						  mmap_handler, machine, true);
+}
+
+struct machine *machine__new_live(bool kernel_maps, pid_t pid)
+{
+	struct machine *machine = __machine__new_host(kernel_maps);
+
+	if (!machine)
+		return NULL;
+
+	if (machine__init_live(machine, pid)) {
+		machine__delete(machine);
+		return NULL;
+	}
 	return machine;
-out_delete:
-	free(machine);
-	return NULL;
 }
 
 struct machine *machine__new_kallsyms(void)
@@ -1976,7 +2011,7 @@ static void ip__resolve_ams(struct thread *thread,
 	 * Thus, we have to try consecutively until we find a match
 	 * or else, the symbol is unknown
 	 */
-	thread__find_cpumode_addr_location(thread, ip, &al);
+	thread__find_cpumode_addr_location(thread, ip, /*symbols=*/true, &al);
 
 	ams->addr = ip;
 	ams->al_addr = al.addr;
@@ -2078,7 +2113,7 @@ static int add_callchain_ip(struct thread *thread,
 	al.sym = NULL;
 	al.srcline = NULL;
 	if (!cpumode) {
-		thread__find_cpumode_addr_location(thread, ip, &al);
+		thread__find_cpumode_addr_location(thread, ip, symbols, &al);
 	} else {
 		if (ip >= PERF_CONTEXT_MAX) {
 			switch (ip) {
@@ -2106,6 +2141,8 @@ static int add_callchain_ip(struct thread *thread,
 		}
 		if (symbols)
 			thread__find_symbol(thread, *cpumode, ip, &al);
+		else
+			thread__find_map(thread, *cpumode, ip, &al);
 	}
 
 	if (al.sym != NULL) {
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index b56abec84fed..180b369c366c 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -171,6 +171,7 @@ void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
 struct machine *machine__new_host(void);
 struct machine *machine__new_kallsyms(void);
+struct machine *machine__new_live(bool kernel_maps, pid_t pid);
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *machine);
 void machine__delete_threads(struct machine *machine);
diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 0b40d901675e..85b2a93a59ac 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -1082,10 +1082,13 @@ struct map *maps__find(struct maps *maps, u64 ip)
 	while (!done) {
 		down_read(maps__lock(maps));
 		if (maps__maps_by_address_sorted(maps)) {
-			struct map **mapp =
-				bsearch(&ip, maps__maps_by_address(maps), maps__nr_maps(maps),
-					sizeof(*mapp), map__addr_cmp);
+			struct map **mapp = NULL;
+			struct map **maps_by_address = maps__maps_by_address(maps);
+			unsigned int nr_maps = maps__nr_maps(maps);
 
+			if (maps_by_address && nr_maps)
+				mapp = bsearch(&ip, maps_by_address, nr_maps, sizeof(*mapp),
+					       map__addr_cmp);
 			if (mapp)
 				result = map__get(*mapp);
 			done = true;
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 884d9aebce91..80b3069427bc 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -303,15 +303,12 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, char **eve
 	}
 
 	if (cpu_map) {
-		struct perf_cpu_map *online = cpu_map__online();
-
-		if (!perf_cpu_map__equal(cpu_map, online)) {
+		if (!perf_cpu_map__equal(cpu_map, cpu_map__online())) {
 			char buf[200];
 
 			cpu_map__snprint(cpu_map, buf, sizeof(buf));
 			pr_warning("Memory events are enabled on a subset of CPUs: %s\n", buf);
 		}
-		perf_cpu_map__put(online);
 		perf_cpu_map__put(cpu_map);
 	}
 
@@ -680,7 +677,10 @@ do {				\
 			if (lvl & P(LVL, LFB)) stats->ld_fbhit++;
 			if (lvl & P(LVL, L1 )) stats->ld_l1hit++;
 			if (lvl & P(LVL, L2)) {
-				stats->ld_l2hit++;
+				if (snoop & P(SNOOP, HITM))
+					HITM_INC(lcl_hitm);
+				else
+					stats->ld_l2hit++;
 
 				if (snoopx & P(SNOOPX, PEER))
 					PEER_INC(lcl_peer);
@@ -799,3 +799,181 @@ void c2c_add_stats(struct c2c_stats *stats, struct c2c_stats *add)
 	stats->nomap		+= add->nomap;
 	stats->noparse		+= add->noparse;
 }
+
+/*
+ * It returns an index in hist_entry->mem_stat array for the given val which
+ * represents a data-src based on the mem_stat_type.
+ */
+int mem_stat_index(const enum mem_stat_type mst, const u64 val)
+{
+	union perf_mem_data_src src = {
+		.val = val,
+	};
+
+	switch (mst) {
+	case PERF_MEM_STAT_OP:
+		switch (src.mem_op) {
+		case PERF_MEM_OP_LOAD:
+			return MEM_STAT_OP_LOAD;
+		case PERF_MEM_OP_STORE:
+			return MEM_STAT_OP_STORE;
+		case PERF_MEM_OP_LOAD | PERF_MEM_OP_STORE:
+			return MEM_STAT_OP_LDST;
+		default:
+			if (src.mem_op & PERF_MEM_OP_PFETCH)
+				return MEM_STAT_OP_PFETCH;
+			if (src.mem_op & PERF_MEM_OP_EXEC)
+				return MEM_STAT_OP_EXEC;
+			return MEM_STAT_OP_OTHER;
+		}
+	case PERF_MEM_STAT_CACHE:
+		switch (src.mem_lvl_num) {
+		case PERF_MEM_LVLNUM_L1:
+			return MEM_STAT_CACHE_L1;
+		case PERF_MEM_LVLNUM_L2:
+			return MEM_STAT_CACHE_L2;
+		case PERF_MEM_LVLNUM_L3:
+			return MEM_STAT_CACHE_L3;
+		case PERF_MEM_LVLNUM_L4:
+			return MEM_STAT_CACHE_L4;
+		case PERF_MEM_LVLNUM_LFB:
+			return MEM_STAT_CACHE_L1_BUF;
+		case PERF_MEM_LVLNUM_L2_MHB:
+			return MEM_STAT_CACHE_L2_BUF;
+		default:
+			return MEM_STAT_CACHE_OTHER;
+		}
+	case PERF_MEM_STAT_MEMORY:
+		switch (src.mem_lvl_num) {
+		case PERF_MEM_LVLNUM_MSC:
+			return MEM_STAT_MEMORY_MSC;
+		case PERF_MEM_LVLNUM_RAM:
+			return MEM_STAT_MEMORY_RAM;
+		case PERF_MEM_LVLNUM_UNC:
+			return MEM_STAT_MEMORY_UNC;
+		case PERF_MEM_LVLNUM_CXL:
+			return MEM_STAT_MEMORY_CXL;
+		case PERF_MEM_LVLNUM_IO:
+			return MEM_STAT_MEMORY_IO;
+		case PERF_MEM_LVLNUM_PMEM:
+			return MEM_STAT_MEMORY_PMEM;
+		default:
+			return MEM_STAT_MEMORY_OTHER;
+		}
+	case PERF_MEM_STAT_SNOOP:
+		switch (src.mem_snoop) {
+		case PERF_MEM_SNOOP_HIT:
+			return MEM_STAT_SNOOP_HIT;
+		case PERF_MEM_SNOOP_HITM:
+			return MEM_STAT_SNOOP_HITM;
+		case PERF_MEM_SNOOP_MISS:
+			return MEM_STAT_SNOOP_MISS;
+		default:
+			return MEM_STAT_SNOOP_OTHER;
+		}
+	case PERF_MEM_STAT_DTLB:
+		switch (src.mem_dtlb) {
+		case PERF_MEM_TLB_L1 | PERF_MEM_TLB_HIT:
+			return MEM_STAT_DTLB_L1_HIT;
+		case PERF_MEM_TLB_L2 | PERF_MEM_TLB_HIT:
+			return MEM_STAT_DTLB_L2_HIT;
+		case PERF_MEM_TLB_L1 | PERF_MEM_TLB_L2 | PERF_MEM_TLB_HIT:
+			return MEM_STAT_DTLB_ANY_HIT;
+		default:
+			if (src.mem_dtlb & PERF_MEM_TLB_MISS)
+				return MEM_STAT_DTLB_MISS;
+			return MEM_STAT_DTLB_OTHER;
+		}
+	default:
+		break;
+	}
+	return -1;
+}
+
+/* To align output, returned string should be shorter than MEM_STAT_PRINT_LEN */
+const char *mem_stat_name(const enum mem_stat_type mst, const int idx)
+{
+	switch (mst) {
+	case PERF_MEM_STAT_OP:
+		switch (idx) {
+		case MEM_STAT_OP_LOAD:
+			return "Load";
+		case MEM_STAT_OP_STORE:
+			return "Store";
+		case MEM_STAT_OP_LDST:
+			return "Ld+St";
+		case MEM_STAT_OP_PFETCH:
+			return "Pfetch";
+		case MEM_STAT_OP_EXEC:
+			return "Exec";
+		case MEM_STAT_OP_OTHER:
+		default:
+			return "Other";
+		}
+	case PERF_MEM_STAT_CACHE:
+		switch (idx) {
+		case MEM_STAT_CACHE_L1:
+			return "L1";
+		case MEM_STAT_CACHE_L2:
+			return "L2";
+		case MEM_STAT_CACHE_L3:
+			return "L3";
+		case MEM_STAT_CACHE_L4:
+			return "L4";
+		case MEM_STAT_CACHE_L1_BUF:
+			return "L1-buf";
+		case MEM_STAT_CACHE_L2_BUF:
+			return "L2-buf";
+		case MEM_STAT_CACHE_OTHER:
+		default:
+			return "Other";
+		}
+	case PERF_MEM_STAT_MEMORY:
+		switch (idx) {
+		case MEM_STAT_MEMORY_RAM:
+			return "RAM";
+		case MEM_STAT_MEMORY_MSC:
+			return "MSC";
+		case MEM_STAT_MEMORY_UNC:
+			return "Uncach";
+		case MEM_STAT_MEMORY_CXL:
+			return "CXL";
+		case MEM_STAT_MEMORY_IO:
+			return "IO";
+		case MEM_STAT_MEMORY_PMEM:
+			return "PMEM";
+		case MEM_STAT_MEMORY_OTHER:
+		default:
+			return "Other";
+		}
+	case PERF_MEM_STAT_SNOOP:
+		switch (idx) {
+		case MEM_STAT_SNOOP_HIT:
+			return "Hit";
+		case MEM_STAT_SNOOP_HITM:
+			return "HitM";
+		case MEM_STAT_SNOOP_MISS:
+			return "Miss";
+		case MEM_STAT_SNOOP_OTHER:
+		default:
+			return "Other";
+		}
+	case PERF_MEM_STAT_DTLB:
+		switch (idx) {
+		case MEM_STAT_DTLB_L1_HIT:
+			return "L1-Hit";
+		case MEM_STAT_DTLB_L2_HIT:
+			return "L2-Hit";
+		case MEM_STAT_DTLB_ANY_HIT:
+			return "L?-Hit";
+		case MEM_STAT_DTLB_MISS:
+			return "Miss";
+		case MEM_STAT_DTLB_OTHER:
+		default:
+			return "Other";
+		}
+	default:
+		break;
+	}
+	return "N/A";
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index a5c19d39ee37..5b98076904b0 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -89,4 +89,61 @@ struct hist_entry;
 int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi);
 void c2c_add_stats(struct c2c_stats *stats, struct c2c_stats *add);
 
+enum mem_stat_type {
+	PERF_MEM_STAT_OP,
+	PERF_MEM_STAT_CACHE,
+	PERF_MEM_STAT_MEMORY,
+	PERF_MEM_STAT_SNOOP,
+	PERF_MEM_STAT_DTLB,
+};
+
+#define MEM_STAT_PRINT_LEN  7  /* 1 space + 5 digits + 1 percent sign */
+
+enum mem_stat_op {
+	MEM_STAT_OP_LOAD,
+	MEM_STAT_OP_STORE,
+	MEM_STAT_OP_LDST,
+	MEM_STAT_OP_PFETCH,
+	MEM_STAT_OP_EXEC,
+	MEM_STAT_OP_OTHER,
+};
+
+enum mem_stat_cache {
+	MEM_STAT_CACHE_L1,
+	MEM_STAT_CACHE_L2,
+	MEM_STAT_CACHE_L3,
+	MEM_STAT_CACHE_L4,
+	MEM_STAT_CACHE_L1_BUF,
+	MEM_STAT_CACHE_L2_BUF,
+	MEM_STAT_CACHE_OTHER,
+};
+
+enum mem_stat_memory {
+	MEM_STAT_MEMORY_RAM,
+	MEM_STAT_MEMORY_MSC,
+	MEM_STAT_MEMORY_UNC,
+	MEM_STAT_MEMORY_CXL,
+	MEM_STAT_MEMORY_IO,
+	MEM_STAT_MEMORY_PMEM,
+	MEM_STAT_MEMORY_OTHER,
+};
+
+enum mem_stat_snoop {
+	MEM_STAT_SNOOP_HIT,
+	MEM_STAT_SNOOP_HITM,
+	MEM_STAT_SNOOP_MISS,
+	MEM_STAT_SNOOP_OTHER,
+};
+
+enum mem_stat_dtlb {
+	MEM_STAT_DTLB_L1_HIT,
+	MEM_STAT_DTLB_L2_HIT,
+	MEM_STAT_DTLB_ANY_HIT,
+	MEM_STAT_DTLB_MISS,
+	MEM_STAT_DTLB_OTHER,
+};
+
+int mem_stat_index(const enum mem_stat_type mst, const u64 data_src);
+const char *mem_stat_name(const enum mem_stat_type mst, const int idx);
+
 #endif /* __PERF_MEM_EVENTS_H */
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 46920ebadfd1..43d35f956a33 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -353,7 +353,7 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids,
 	return 0;
 }
 
-static bool match_metric(const char *metric_or_groups, const char *sought)
+static bool match_metric_or_groups(const char *metric_or_groups, const char *sought)
 {
 	int len;
 	char *m;
@@ -369,18 +369,19 @@ static bool match_metric(const char *metric_or_groups, const char *sought)
 	    (metric_or_groups[len] == 0 || metric_or_groups[len] == ';'))
 		return true;
 	m = strchr(metric_or_groups, ';');
-	return m && match_metric(m + 1, sought);
+	return m && match_metric_or_groups(m + 1, sought);
 }
 
-static bool match_pm_metric(const struct pmu_metric *pm, const char *pmu, const char *metric)
+static bool match_pm_metric_or_groups(const struct pmu_metric *pm, const char *pmu,
+				      const char *metric_or_groups)
 {
 	const char *pm_pmu = pm->pmu ?: "cpu";
 
 	if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu))
 		return false;
 
-	return match_metric(pm->metric_group, metric) ||
-	       match_metric(pm->metric_name, metric);
+	return match_metric_or_groups(pm->metric_group, metric_or_groups) ||
+	       match_metric_or_groups(pm->metric_name, metric_or_groups);
 }
 
 /** struct mep - RB-tree node for building printing information. */
@@ -395,6 +396,7 @@ struct mep {
 	const char *metric_expr;
 	const char *metric_threshold;
 	const char *metric_unit;
+	const char *pmu_name;
 };
 
 static int mep_cmp(struct rb_node *rb_node, const void *entry)
@@ -475,6 +477,7 @@ static int metricgroup__add_to_mep_groups(const struct pmu_metric *pm,
 			me->metric_expr = pm->metric_expr;
 			me->metric_threshold = pm->metric_threshold;
 			me->metric_unit = pm->unit;
+			me->pmu_name = pm->pmu;
 		}
 	}
 	free(omg);
@@ -550,7 +553,8 @@ void metricgroup__print(const struct print_callbacks *print_cb, void *print_stat
 				me->metric_long_desc,
 				me->metric_expr,
 				me->metric_threshold,
-				me->metric_unit);
+				me->metric_unit,
+				me->pmu_name);
 		next = rb_next(node);
 		rblist__remove_node(&groups, node);
 	}
@@ -802,11 +806,6 @@ struct metricgroup_add_iter_data {
 	const struct pmu_metrics_table *table;
 };
 
-static bool metricgroup__find_metric(const char *pmu,
-				     const char *metric,
-				     const struct pmu_metrics_table *table,
-				     struct pmu_metric *pm);
-
 static int add_metric(struct list_head *metric_list,
 		      const struct pmu_metric *pm,
 		      const char *modifier,
@@ -818,6 +817,16 @@ static int add_metric(struct list_head *metric_list,
 		      const struct visited_metric *visited,
 		      const struct pmu_metrics_table *table);
 
+static int metricgroup__find_metric_callback(const struct pmu_metric *pm,
+					     const struct pmu_metrics_table *table  __maybe_unused,
+					     void *vdata)
+{
+	struct pmu_metric *copied_pm = vdata;
+
+	memcpy(copied_pm, pm, sizeof(*pm));
+	return 0;
+}
+
 /**
  * resolve_metric - Locate metrics within the root metric and recursively add
  *                    references to them.
@@ -838,7 +847,7 @@ static int add_metric(struct list_head *metric_list,
  *       architecture perf is running upon.
  */
 static int resolve_metric(struct list_head *metric_list,
-			  const char *pmu,
+			  struct perf_pmu *pmu,
 			  const char *modifier,
 			  bool metric_no_group,
 			  bool metric_no_threshold,
@@ -868,7 +877,9 @@ static int resolve_metric(struct list_head *metric_list,
 	hashmap__for_each_entry(root_metric->pctx->ids, cur, bkt) {
 		struct pmu_metric pm;
 
-		if (metricgroup__find_metric(pmu, cur->pkey, table, &pm)) {
+		if (pmu_metrics_table__find_metric(table, pmu, cur->pkey,
+						   metricgroup__find_metric_callback,
+						   &pm) != PMU_METRICS__NOT_FOUND) {
 			pending = realloc(pending,
 					(pending_cnt + 1) * sizeof(struct to_resolve));
 			if (!pending)
@@ -1019,7 +1030,12 @@ static int __add_metric(struct list_head *metric_list,
 	}
 	if (!ret) {
 		/* Resolve referenced metrics. */
-		const char *pmu = pm->pmu ?: "cpu";
+		struct perf_pmu *pmu;
+
+		if (pm->pmu && pm->pmu[0] != '\0')
+			pmu = perf_pmus__find(pm->pmu);
+		else
+			pmu = perf_pmus__scan_core(/*pmu=*/ NULL);
 
 		ret = resolve_metric(metric_list, pmu, modifier, metric_no_group,
 				     metric_no_threshold, user_requested_cpu_list,
@@ -1036,44 +1052,6 @@ static int __add_metric(struct list_head *metric_list,
 	return ret;
 }
 
-struct metricgroup__find_metric_data {
-	const char *pmu;
-	const char *metric;
-	struct pmu_metric *pm;
-};
-
-static int metricgroup__find_metric_callback(const struct pmu_metric *pm,
-					     const struct pmu_metrics_table *table  __maybe_unused,
-					     void *vdata)
-{
-	struct metricgroup__find_metric_data *data = vdata;
-	const char *pm_pmu = pm->pmu ?: "cpu";
-
-	if (strcmp(data->pmu, "all") && strcmp(pm_pmu, data->pmu))
-		return 0;
-
-	if (!match_metric(pm->metric_name, data->metric))
-		return 0;
-
-	memcpy(data->pm, pm, sizeof(*pm));
-	return 1;
-}
-
-static bool metricgroup__find_metric(const char *pmu,
-				     const char *metric,
-				     const struct pmu_metrics_table *table,
-				     struct pmu_metric *pm)
-{
-	struct metricgroup__find_metric_data data = {
-		.pmu = pmu,
-		.metric = metric,
-		.pm = pm,
-	};
-
-	return pmu_metrics_table__for_each_metric(table, metricgroup__find_metric_callback, &data)
-		? true : false;
-}
-
 static int add_metric(struct list_head *metric_list,
 		      const struct pmu_metric *pm,
 		      const char *modifier,
@@ -1119,7 +1097,7 @@ static int metricgroup__add_metric_sys_event_iter(const struct pmu_metric *pm,
 	struct metricgroup_add_iter_data *d = data;
 	int ret;
 
-	if (!match_pm_metric(pm, d->pmu, d->metric_name))
+	if (!match_pm_metric_or_groups(pm, d->pmu, d->metric_name))
 		return 0;
 
 	ret = add_metric(d->metric_list, pm, d->modifier, d->metric_no_group,
@@ -1200,9 +1178,9 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm,
 	struct metricgroup__add_metric_data *data = vdata;
 	int ret = 0;
 
-	if (pm->metric_expr && match_pm_metric(pm, data->pmu, data->metric_name)) {
+	if (pm->metric_expr && match_pm_metric_or_groups(pm, data->pmu, data->metric_name)) {
 		bool metric_no_group = data->metric_no_group ||
-			match_metric(pm->metricgroup_no_group, data->metric_name);
+			match_metric_or_groups(pm->metricgroup_no_group, data->metric_name);
 
 		data->has_match = true;
 		ret = add_metric(data->list, pm, data->modifier, metric_no_group,
@@ -1723,29 +1701,32 @@ int metricgroup__parse_groups_test(struct evlist *evlist,
 
 struct metricgroup__has_metric_data {
 	const char *pmu;
-	const char *metric;
+	const char *metric_or_groups;
 };
-static int metricgroup__has_metric_callback(const struct pmu_metric *pm,
-					    const struct pmu_metrics_table *table __maybe_unused,
-					    void *vdata)
+static int metricgroup__has_metric_or_groups_callback(const struct pmu_metric *pm,
+						      const struct pmu_metrics_table *table
+							__maybe_unused,
+						      void *vdata)
 {
 	struct metricgroup__has_metric_data *data = vdata;
 
-	return match_pm_metric(pm, data->pmu, data->metric) ? 1 : 0;
+	return match_pm_metric_or_groups(pm, data->pmu, data->metric_or_groups) ? 1 : 0;
 }
 
-bool metricgroup__has_metric(const char *pmu, const char *metric)
+bool metricgroup__has_metric_or_groups(const char *pmu, const char *metric_or_groups)
 {
 	const struct pmu_metrics_table *table = pmu_metrics_table__find();
 	struct metricgroup__has_metric_data data = {
 		.pmu = pmu,
-		.metric = metric,
+		.metric_or_groups = metric_or_groups,
 	};
 
 	if (!table)
 		return false;
 
-	return pmu_metrics_table__for_each_metric(table, metricgroup__has_metric_callback, &data)
+	return pmu_metrics_table__for_each_metric(table,
+						  metricgroup__has_metric_or_groups_callback,
+						  &data)
 		? true : false;
 }
 
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 779f6ede1b51..a04ac1afa6cc 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -85,7 +85,7 @@ int metricgroup__parse_groups_test(struct evlist *evlist,
 				   struct rblist *metric_events);
 
 void metricgroup__print(const struct print_callbacks *print_cb, void *print_state);
-bool metricgroup__has_metric(const char *pmu, const char *metric);
+bool metricgroup__has_metric_or_groups(const char *pmu, const char *metric_or_groups);
 unsigned int metricgroups__topdown_max_level(void);
 int arch_get_runtimeparam(const struct pmu_metric *pm);
 void metricgroup__rblist_exit(struct rblist *metric_events);
diff --git a/tools/perf/util/mutex.h b/tools/perf/util/mutex.h
index 62d258c71ded..38458f00846f 100644
--- a/tools/perf/util/mutex.h
+++ b/tools/perf/util/mutex.h
@@ -43,6 +43,12 @@
 #define EXCLUSIVE_LOCK_FUNCTION(...)  __attribute__((exclusive_lock_function(__VA_ARGS__)))
 
 /*
+ * Documents functions that acquire a shared (reader) lock in the body of a
+ * function, and do not release it.
+ */
+#define SHARED_LOCK_FUNCTION(...)  __attribute__((shared_lock_function(__VA_ARGS__)))
+
+/*
  * Documents functions that expect a lock to be held on entry to the function,
  * and release it in the body of the function.
  */
@@ -55,6 +61,9 @@
 /* Documents a function that expects a mutex to be held prior to entry. */
 #define EXCLUSIVE_LOCKS_REQUIRED(...) __attribute__((exclusive_locks_required(__VA_ARGS__)))
 
+/* Documents a function that expects a shared (reader) lock to be held prior to entry. */
+#define SHARED_LOCKS_REQUIRED(...) __attribute__((shared_locks_required(__VA_ARGS__)))
+
 /* Turns off thread safety checking within the body of a particular function. */
 #define NO_THREAD_SAFETY_ANALYSIS __attribute__((no_thread_safety_analysis))
 
@@ -66,9 +75,11 @@
 #define LOCKS_EXCLUDED(...)
 #define LOCK_RETURNED(x)
 #define EXCLUSIVE_LOCK_FUNCTION(...)
+#define SHARED_LOCK_FUNCTION(...)
 #define UNLOCK_FUNCTION(...)
 #define EXCLUSIVE_TRYLOCK_FUNCTION(...)
 #define EXCLUSIVE_LOCKS_REQUIRED(...)
+#define SHARED_LOCKS_REQUIRED(...)
 #define NO_THREAD_SAFETY_ANALYSIS
 
 #endif
diff --git a/tools/perf/util/off_cpu.h b/tools/perf/util/off_cpu.h
index 2dd67c60f211..64bf763ddf50 100644
--- a/tools/perf/util/off_cpu.h
+++ b/tools/perf/util/off_cpu.h
@@ -13,9 +13,10 @@ struct record_opts;
 #define OFFCPU_SAMPLE_TYPES  (PERF_SAMPLE_IDENTIFIER | PERF_SAMPLE_IP | \
 			      PERF_SAMPLE_TID | PERF_SAMPLE_TIME | \
 			      PERF_SAMPLE_ID | PERF_SAMPLE_CPU | \
-			      PERF_SAMPLE_PERIOD | PERF_SAMPLE_CALLCHAIN | \
+			      PERF_SAMPLE_PERIOD | PERF_SAMPLE_RAW | \
 			      PERF_SAMPLE_CGROUP)
 
+#define OFFCPU_THRESH 500000000ULL
 
 #ifdef HAVE_BPF_SKEL
 int off_cpu_prepare(struct evlist *evlist, struct target *target,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 5152fd5a6ead..2380de56a207 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -7,6 +7,7 @@
 #include <errno.h>
 #include <sys/ioctl.h>
 #include <sys/param.h>
+#include "cpumap.h"
 #include "term.h"
 #include "env.h"
 #include "evlist.h"
@@ -28,6 +29,7 @@
 #include "util/evsel_config.h"
 #include "util/event.h"
 #include "util/bpf-filter.h"
+#include "util/stat.h"
 #include "util/util.h"
 #include "tracepoint.h"
 
@@ -179,6 +181,26 @@ static char *get_config_name(const struct parse_events_terms *head_terms)
 	return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_NAME);
 }
 
+static struct perf_cpu_map *get_config_cpu(const struct parse_events_terms *head_terms)
+{
+	struct parse_events_term *term;
+	struct perf_cpu_map *cpus = NULL;
+
+	if (!head_terms)
+		return NULL;
+
+	list_for_each_entry(term, &head_terms->terms, list) {
+		if (term->type_term == PARSE_EVENTS__TERM_TYPE_CPU) {
+			struct perf_cpu_map *cpu = perf_cpu_map__new_int(term->val.num);
+
+			perf_cpu_map__merge(&cpus, cpu);
+			perf_cpu_map__put(cpu);
+		}
+	}
+
+	return cpus;
+}
+
 /**
  * fix_raw - For each raw term see if there is an event (aka alias) in pmu that
  *           matches the raw's string value. If the string value matches an
@@ -228,25 +250,55 @@ __add_event(struct list_head *list, int *idx,
 	    struct perf_event_attr *attr,
 	    bool init_attr,
 	    const char *name, const char *metric_id, struct perf_pmu *pmu,
-	    struct list_head *config_terms, bool auto_merge_stats,
+	    struct list_head *config_terms, struct evsel *first_wildcard_match,
 	    struct perf_cpu_map *cpu_list, u64 alternate_hw_config)
 {
 	struct evsel *evsel;
-	struct perf_cpu_map *cpus = perf_cpu_map__is_empty(cpu_list) && pmu ? pmu->cpus : cpu_list;
+	bool is_pmu_core;
+	struct perf_cpu_map *cpus;
 
-	cpus = perf_cpu_map__get(cpus);
-	if (pmu)
-		perf_pmu__warn_invalid_formats(pmu);
+	/*
+	 * Ensure the first_wildcard_match's PMU matches that of the new event
+	 * being added. Otherwise try to match with another event further down
+	 * the evlist.
+	 */
+	if (first_wildcard_match) {
+		struct evsel *pos = list_prev_entry(first_wildcard_match, core.node);
+
+		first_wildcard_match = NULL;
+		list_for_each_entry_continue(pos, list, core.node) {
+			if (perf_pmu__name_no_suffix_match(pos->pmu, pmu->name)) {
+				first_wildcard_match = pos;
+				break;
+			}
+			if (pos->pmu->is_core && (!pmu || pmu->is_core)) {
+				first_wildcard_match = pos;
+				break;
+			}
+		}
+	}
 
-	if (pmu && (attr->type == PERF_TYPE_RAW || attr->type >= PERF_TYPE_MAX)) {
-		perf_pmu__warn_invalid_config(pmu, attr->config, name,
-					      PERF_PMU_FORMAT_VALUE_CONFIG, "config");
-		perf_pmu__warn_invalid_config(pmu, attr->config1, name,
-					      PERF_PMU_FORMAT_VALUE_CONFIG1, "config1");
-		perf_pmu__warn_invalid_config(pmu, attr->config2, name,
-					      PERF_PMU_FORMAT_VALUE_CONFIG2, "config2");
-		perf_pmu__warn_invalid_config(pmu, attr->config3, name,
-					      PERF_PMU_FORMAT_VALUE_CONFIG3, "config3");
+	if (pmu) {
+		is_pmu_core = pmu->is_core;
+		cpus = perf_cpu_map__get(perf_cpu_map__is_empty(cpu_list) ? pmu->cpus : cpu_list);
+		perf_pmu__warn_invalid_formats(pmu);
+		if (attr->type == PERF_TYPE_RAW || attr->type >= PERF_TYPE_MAX) {
+			perf_pmu__warn_invalid_config(pmu, attr->config, name,
+						PERF_PMU_FORMAT_VALUE_CONFIG, "config");
+			perf_pmu__warn_invalid_config(pmu, attr->config1, name,
+						PERF_PMU_FORMAT_VALUE_CONFIG1, "config1");
+			perf_pmu__warn_invalid_config(pmu, attr->config2, name,
+						PERF_PMU_FORMAT_VALUE_CONFIG2, "config2");
+			perf_pmu__warn_invalid_config(pmu, attr->config3, name,
+						PERF_PMU_FORMAT_VALUE_CONFIG3, "config3");
+		}
+	} else {
+		is_pmu_core = (attr->type == PERF_TYPE_HARDWARE ||
+			       attr->type == PERF_TYPE_HW_CACHE);
+		if (perf_cpu_map__is_empty(cpu_list))
+			cpus = is_pmu_core ? perf_cpu_map__new_online_cpus() : NULL;
+		else
+			cpus = perf_cpu_map__get(cpu_list);
 	}
 	if (init_attr)
 		event_attr_init(attr);
@@ -261,10 +313,10 @@ __add_event(struct list_head *list, int *idx,
 	evsel->core.cpus = cpus;
 	evsel->core.own_cpus = perf_cpu_map__get(cpus);
 	evsel->core.requires_cpu = pmu ? pmu->is_uncore : false;
-	evsel->core.is_pmu_core = pmu ? pmu->is_core : false;
-	evsel->auto_merge_stats = auto_merge_stats;
+	evsel->core.is_pmu_core = is_pmu_core;
 	evsel->pmu = pmu;
 	evsel->alternate_hw_config = alternate_hw_config;
+	evsel->first_wildcard_match = first_wildcard_match;
 
 	if (name)
 		evsel->name = strdup(name);
@@ -287,7 +339,7 @@ struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr,
 {
 	return __add_event(/*list=*/NULL, &idx, attr, /*init_attr=*/false, name,
 			   metric_id, pmu, /*config_terms=*/NULL,
-			   /*auto_merge_stats=*/false, /*cpu_list=*/NULL,
+			   /*first_wildcard_match=*/NULL, /*cpu_list=*/NULL,
 			   /*alternate_hw_config=*/PERF_COUNT_HW_MAX);
 }
 
@@ -298,7 +350,7 @@ static int add_event(struct list_head *list, int *idx,
 {
 	return __add_event(list, idx, attr, /*init_attr*/true, name, metric_id,
 			   /*pmu=*/NULL, config_terms,
-			   /*auto_merge_stats=*/false, /*cpu_list=*/NULL,
+			   /*first_wildcard_match=*/NULL, /*cpu_list=*/NULL,
 			   alternate_hw_config) ? 0 : -ENOMEM;
 }
 
@@ -423,7 +475,7 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 static int parse_events_add_pmu(struct parse_events_state *parse_state,
 				struct list_head *list, struct perf_pmu *pmu,
 				const struct parse_events_terms *const_parsed_terms,
-				bool auto_merge_stats, u64 alternate_hw_config);
+				struct evsel *first_wildcard_match, u64 alternate_hw_config);
 
 int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			   struct parse_events_state *parse_state,
@@ -433,11 +485,13 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 	bool found_supported = false;
 	const char *config_name = get_config_name(parsed_terms);
 	const char *metric_id = get_config_metric_id(parsed_terms);
+	struct perf_cpu_map *cpus = get_config_cpu(parsed_terms);
+	int ret = 0;
+	struct evsel *first_wildcard_match = NULL;
 
 	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
 		LIST_HEAD(config_terms);
 		struct perf_event_attr attr;
-		int ret;
 
 		if (parse_events__filter_pmu(parse_state, pmu))
 			continue;
@@ -449,10 +503,13 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			 */
 			ret = parse_events_add_pmu(parse_state, list, pmu,
 						   parsed_terms,
-						   perf_pmu__auto_merge_stats(pmu),
+						   first_wildcard_match,
 						   /*alternate_hw_config=*/PERF_COUNT_HW_MAX);
 			if (ret)
-				return ret;
+				goto out_err;
+			if (first_wildcard_match == NULL)
+				first_wildcard_match =
+					container_of(list->prev, struct evsel, core.node);
 			continue;
 		}
 
@@ -472,21 +529,29 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 
 		if (parsed_terms) {
 			if (config_attr(&attr, parsed_terms, parse_state->error,
-					config_term_common))
-				return -EINVAL;
-
-			if (get_config_terms(parsed_terms, &config_terms))
-				return -ENOMEM;
+					config_term_common)) {
+				ret = -EINVAL;
+				goto out_err;
+			}
+			if (get_config_terms(parsed_terms, &config_terms)) {
+				ret = -ENOMEM;
+				goto out_err;
+			}
 		}
 
 		if (__add_event(list, idx, &attr, /*init_attr*/true, config_name ?: name,
-				metric_id, pmu, &config_terms, /*auto_merge_stats=*/false,
-				/*cpu_list=*/NULL,
-				/*alternate_hw_config=*/PERF_COUNT_HW_MAX) == NULL)
-			return -ENOMEM;
+				metric_id, pmu, &config_terms, first_wildcard_match,
+				cpus, /*alternate_hw_config=*/PERF_COUNT_HW_MAX) == NULL)
+			ret = -ENOMEM;
 
+		if (first_wildcard_match == NULL)
+			first_wildcard_match = container_of(list->prev, struct evsel, core.node);
 		free_config_terms(&config_terms);
+		if (ret)
+			goto out_err;
 	}
+out_err:
+	perf_cpu_map__put(cpus);
 	return found_supported ? 0 : -EINVAL;
 }
 
@@ -805,6 +870,7 @@ const char *parse_events__term_type_str(enum parse_events__term_type term_type)
 		[PARSE_EVENTS__TERM_TYPE_RAW]                   = "raw",
 		[PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE]          = "legacy-cache",
 		[PARSE_EVENTS__TERM_TYPE_HARDWARE]              = "hardware",
+		[PARSE_EVENTS__TERM_TYPE_CPU]			= "cpu",
 	};
 	if ((unsigned int)term_type >= __PARSE_EVENTS__TERM_TYPE_NR)
 		return "unknown term";
@@ -834,6 +900,7 @@ config_term_avail(enum parse_events__term_type term_type, struct parse_events_er
 	case PARSE_EVENTS__TERM_TYPE_METRIC_ID:
 	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
 	case PARSE_EVENTS__TERM_TYPE_PERCORE:
+	case PARSE_EVENTS__TERM_TYPE_CPU:
 		return true;
 	case PARSE_EVENTS__TERM_TYPE_USER:
 	case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
@@ -981,6 +1048,15 @@ do {									   \
 			return -EINVAL;
 		}
 		break;
+	case PARSE_EVENTS__TERM_TYPE_CPU:
+		CHECK_TYPE_VAL(NUM);
+		if (term->val.num >= (u64)cpu__max_present_cpu().cpu) {
+			parse_events_error__handle(err, term->err_val,
+						strdup("too big"),
+						NULL);
+			return -EINVAL;
+		}
+		break;
 	case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
 	case PARSE_EVENTS__TERM_TYPE_USER:
 	case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
@@ -1108,6 +1184,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_RAW:
 	case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
 	case PARSE_EVENTS__TERM_TYPE_HARDWARE:
+	case PARSE_EVENTS__TERM_TYPE_CPU:
 	default:
 		if (err) {
 			parse_events_error__handle(err, term->err_term,
@@ -1242,6 +1319,7 @@ do {								\
 		case PARSE_EVENTS__TERM_TYPE_RAW:
 		case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
 		case PARSE_EVENTS__TERM_TYPE_HARDWARE:
+		case PARSE_EVENTS__TERM_TYPE_CPU:
 		default:
 			break;
 		}
@@ -1296,6 +1374,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct parse_events_terms *head
 		case PARSE_EVENTS__TERM_TYPE_RAW:
 		case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
 		case PARSE_EVENTS__TERM_TYPE_HARDWARE:
+		case PARSE_EVENTS__TERM_TYPE_CPU:
 		default:
 			break;
 		}
@@ -1335,11 +1414,13 @@ int parse_events_add_tracepoint(struct parse_events_state *parse_state,
 static int __parse_events_add_numeric(struct parse_events_state *parse_state,
 				struct list_head *list,
 				struct perf_pmu *pmu, u32 type, u32 extended_type,
-				u64 config, const struct parse_events_terms *head_config)
+				u64 config, const struct parse_events_terms *head_config,
+				struct evsel *first_wildcard_match)
 {
 	struct perf_event_attr attr;
 	LIST_HEAD(config_terms);
 	const char *name, *metric_id;
+	struct perf_cpu_map *cpus;
 	int ret;
 
 	memset(&attr, 0, sizeof(attr));
@@ -1361,10 +1442,11 @@ static int __parse_events_add_numeric(struct parse_events_state *parse_state,
 
 	name = get_config_name(head_config);
 	metric_id = get_config_metric_id(head_config);
+	cpus = get_config_cpu(head_config);
 	ret = __add_event(list, &parse_state->idx, &attr, /*init_attr*/true, name,
-			  metric_id, pmu, &config_terms, /*auto_merge_stats=*/false,
-			  /*cpu_list=*/NULL, /*alternate_hw_config=*/PERF_COUNT_HW_MAX
-		) == NULL ? -ENOMEM : 0;
+			metric_id, pmu, &config_terms, first_wildcard_match,
+			cpus, /*alternate_hw_config=*/PERF_COUNT_HW_MAX) ? 0 : -ENOMEM;
+	perf_cpu_map__put(cpus);
 	free_config_terms(&config_terms);
 	return ret;
 }
@@ -1380,6 +1462,7 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 
 	/* Wildcards on numeric values are only supported by core PMUs. */
 	if (wildcard && perf_pmus__supports_extended_type()) {
+		struct evsel *first_wildcard_match = NULL;
 		while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
 			int ret;
 
@@ -1389,15 +1472,20 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 
 			ret = __parse_events_add_numeric(parse_state, list, pmu,
 							 type, pmu->type,
-							 config, head_config);
+							 config, head_config,
+							 first_wildcard_match);
 			if (ret)
 				return ret;
+			if (first_wildcard_match == NULL)
+				first_wildcard_match =
+					container_of(list->prev, struct evsel, core.node);
 		}
 		if (found_supported)
 			return 0;
 	}
 	return __parse_events_add_numeric(parse_state, list, perf_pmus__find_by_type(type),
-					type, /*extended_type=*/0, config, head_config);
+					type, /*extended_type=*/0, config, head_config,
+					/*first_wildcard_match=*/NULL);
 }
 
 static bool config_term_percore(struct list_head *config_terms)
@@ -1415,7 +1503,7 @@ static bool config_term_percore(struct list_head *config_terms)
 static int parse_events_add_pmu(struct parse_events_state *parse_state,
 				struct list_head *list, struct perf_pmu *pmu,
 				const struct parse_events_terms *const_parsed_terms,
-				bool auto_merge_stats, u64 alternate_hw_config)
+				struct evsel *first_wildcard_match, u64 alternate_hw_config)
 {
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
@@ -1424,6 +1512,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 	LIST_HEAD(config_terms);
 	struct parse_events_terms parsed_terms;
 	bool alias_rewrote_terms = false;
+	struct perf_cpu_map *term_cpu = NULL;
 
 	if (verbose > 1) {
 		struct strbuf sb;
@@ -1451,7 +1540,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 		evsel = __add_event(list, &parse_state->idx, &attr,
 				    /*init_attr=*/true, /*name=*/NULL,
 				    /*metric_id=*/NULL, pmu,
-				    /*config_terms=*/NULL, auto_merge_stats,
+				    /*config_terms=*/NULL, first_wildcard_match,
 				    /*cpu_list=*/NULL, alternate_hw_config);
 		return evsel ? 0 : -ENOMEM;
 	}
@@ -1518,11 +1607,12 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 		return -EINVAL;
 	}
 
+	term_cpu = get_config_cpu(&parsed_terms);
 	evsel = __add_event(list, &parse_state->idx, &attr, /*init_attr=*/true,
 			    get_config_name(&parsed_terms),
 			    get_config_metric_id(&parsed_terms), pmu,
-			    &config_terms, auto_merge_stats, /*cpu_list=*/NULL,
-			    alternate_hw_config);
+			    &config_terms, first_wildcard_match, term_cpu, alternate_hw_config);
+	perf_cpu_map__put(term_cpu);
 	if (!evsel) {
 		parse_events_terms__exit(&parsed_terms);
 		return -ENOMEM;
@@ -1539,6 +1629,10 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state,
 	evsel->scale = info.scale;
 	evsel->per_pkg = info.per_pkg;
 	evsel->snapshot = info.snapshot;
+	evsel->retirement_latency.mean = info.retirement_latency_mean;
+	evsel->retirement_latency.min = info.retirement_latency_min;
+	evsel->retirement_latency.max = info.retirement_latency_max;
+
 	return 0;
 }
 
@@ -1554,6 +1648,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 	int ok = 0;
 	const char *config;
 	struct parse_events_terms parsed_terms;
+	struct evsel *first_wildcard_match = NULL;
 
 	*listp = NULL;
 
@@ -1586,17 +1681,14 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 	INIT_LIST_HEAD(list);
 
 	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-		bool auto_merge_stats;
-
 		if (parse_events__filter_pmu(parse_state, pmu))
 			continue;
 
 		if (!perf_pmu__have_event(pmu, event_name))
 			continue;
 
-		auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
 		if (!parse_events_add_pmu(parse_state, list, pmu,
-					  &parsed_terms, auto_merge_stats, hw_config)) {
+					  &parsed_terms, first_wildcard_match, hw_config)) {
 			struct strbuf sb;
 
 			strbuf_init(&sb, /*hint=*/ 0);
@@ -1605,11 +1697,13 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			strbuf_release(&sb);
 			ok++;
 		}
+		if (first_wildcard_match == NULL)
+			first_wildcard_match = container_of(list->prev, struct evsel, core.node);
 	}
 
 	if (parse_state->fake_pmu) {
 		if (!parse_events_add_pmu(parse_state, list, perf_pmus__fake_pmu(), &parsed_terms,
-					  /*auto_merge_stats=*/true, hw_config)) {
+					 first_wildcard_match, hw_config)) {
 			struct strbuf sb;
 
 			strbuf_init(&sb, /*hint=*/ 0);
@@ -1640,6 +1734,7 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state
 	struct perf_pmu *pmu;
 	int ok = 0;
 	char *help;
+	struct evsel *first_wildcard_match = NULL;
 
 	*listp = malloc(sizeof(**listp));
 	if (!*listp)
@@ -1650,14 +1745,14 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state
 	/* Attempt to add to list assuming event_or_pmu is a PMU name. */
 	pmu = perf_pmus__find(event_or_pmu);
 	if (pmu && !parse_events_add_pmu(parse_state, *listp, pmu, const_parsed_terms,
-					 /*auto_merge_stats=*/false,
+					 first_wildcard_match,
 					 /*alternate_hw_config=*/PERF_COUNT_HW_MAX))
 		return 0;
 
 	if (parse_state->fake_pmu) {
 		if (!parse_events_add_pmu(parse_state, *listp, perf_pmus__fake_pmu(),
 					  const_parsed_terms,
-					  /*auto_merge_stats=*/false,
+					  first_wildcard_match,
 					  /*alternate_hw_config=*/PERF_COUNT_HW_MAX))
 			return 0;
 	}
@@ -1667,15 +1762,16 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state
 	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
 		if (!parse_events__filter_pmu(parse_state, pmu) &&
 		    perf_pmu__wildcard_match(pmu, event_or_pmu)) {
-			bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
-
 			if (!parse_events_add_pmu(parse_state, *listp, pmu,
 						  const_parsed_terms,
-						  auto_merge_stats,
+						  first_wildcard_match,
 						  /*alternate_hw_config=*/PERF_COUNT_HW_MAX)) {
 				ok++;
 				parse_state->wild_card_pmus = true;
 			}
+			if (first_wildcard_match == NULL)
+				first_wildcard_match =
+					container_of((*listp)->prev, struct evsel, core.node);
 		}
 	}
 	if (ok)
@@ -2196,14 +2292,23 @@ int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filte
 	if (ret2 < 0)
 		return ret;
 
-	if (ret2 && warn_if_reordered && !parse_state.wild_card_pmus)
-		pr_warning("WARNING: events were regrouped to match PMUs\n");
-
 	/*
 	 * Add list to the evlist even with errors to allow callers to clean up.
 	 */
 	evlist__splice_list_tail(evlist, &parse_state.list);
 
+	if (ret2 && warn_if_reordered && !parse_state.wild_card_pmus) {
+		pr_warning("WARNING: events were regrouped to match PMUs\n");
+
+		if (verbose > 0) {
+			struct strbuf sb = STRBUF_INIT;
+
+			evlist__uniquify_evsel_names(evlist, &stat_config);
+			evlist__format_evsels(evlist, &sb, 2048);
+			pr_debug("evlist after sorting/fixing: '%s'\n", sb.buf);
+			strbuf_release(&sb);
+		}
+	}
 	if (!ret) {
 		struct evsel *last;
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index e176a34ab088..ab242f671031 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -80,7 +80,8 @@ enum parse_events__term_type {
 	PARSE_EVENTS__TERM_TYPE_RAW,
 	PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE,
 	PARSE_EVENTS__TERM_TYPE_HARDWARE,
-#define	__PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_HARDWARE + 1)
+	PARSE_EVENTS__TERM_TYPE_CPU,
+#define	__PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_CPU + 1)
 };
 
 struct parse_events_term {
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 7ed86e3e34e3..4af7b9c1f44d 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -335,6 +335,7 @@ aux-output		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
 aux-action		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_ACTION); }
 aux-sample-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); }
 metric-id		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); }
+cpu			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CPU); }
 cpu-cycles|cycles				{ return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
 stalled-cycles-frontend|idle-cycles-frontend	{ return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
 stalled-cycles-backend|idle-cycles-backend	{ return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b7ebac5ab1d1..609828513f6c 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -27,6 +27,7 @@
 #include <util/pmu-flex.h>
 #include "parse-events.h"
 #include "print-events.h"
+#include "hashmap.h"
 #include "header.h"
 #include "string2.h"
 #include "strbuf.h"
@@ -66,8 +67,6 @@ struct perf_pmu_alias {
 	char *topic;
 	/** @terms: Owned list of the original parsed parameters. */
 	struct parse_events_terms terms;
-	/** @list: List element of struct perf_pmu aliases. */
-	struct list_head list;
 	/**
 	 * @pmu_name: The name copied from the json struct pmu_event. This can
 	 * differ from the PMU name as it won't have suffixes.
@@ -77,6 +76,12 @@ struct perf_pmu_alias {
 	char unit[UNIT_MAX_LEN+1];
 	/** @scale: Value to scale read counter values by. */
 	double scale;
+	/** @retirement_latency_mean: Value to be given for unsampled retirement latency mean. */
+	double retirement_latency_mean;
+	/** @retirement_latency_min: Value to be given for unsampled retirement latency min. */
+	double retirement_latency_min;
+	/** @retirement_latency_max: Value to be given for unsampled retirement latency max. */
+	double retirement_latency_max;
 	/**
 	 * @per_pkg: Does the file
 	 * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.per-pkg or
@@ -257,7 +262,7 @@ static int pmu_format(struct perf_pmu *pmu, int dirfd, const char *name, bool ea
 	return 0;
 }
 
-int perf_pmu__convert_scale(const char *scale, char **end, double *sval)
+static int parse_double(const char *scale, char **end, double *sval)
 {
 	char *lc;
 	int ret = 0;
@@ -294,6 +299,11 @@ out:
 	return ret;
 }
 
+int perf_pmu__convert_scale(const char *scale, char **end, double *sval)
+{
+	return parse_double(scale, end, sval);
+}
+
 static int perf_pmu__parse_scale(struct perf_pmu *pmu, struct perf_pmu_alias *alias)
 {
 	struct stat st;
@@ -407,25 +417,33 @@ static void perf_pmu__parse_snapshot(struct perf_pmu *pmu, struct perf_pmu_alias
 }
 
 /* Delete an alias entry. */
-static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+static void perf_pmu_free_alias(struct perf_pmu_alias *alias)
 {
-	zfree(&newalias->name);
-	zfree(&newalias->desc);
-	zfree(&newalias->long_desc);
-	zfree(&newalias->topic);
-	zfree(&newalias->pmu_name);
-	parse_events_terms__exit(&newalias->terms);
-	free(newalias);
+	if (!alias)
+		return;
+
+	zfree(&alias->name);
+	zfree(&alias->desc);
+	zfree(&alias->long_desc);
+	zfree(&alias->topic);
+	zfree(&alias->pmu_name);
+	parse_events_terms__exit(&alias->terms);
+	free(alias);
 }
 
 static void perf_pmu__del_aliases(struct perf_pmu *pmu)
 {
-	struct perf_pmu_alias *alias, *tmp;
+	struct hashmap_entry *entry;
+	size_t bkt;
 
-	list_for_each_entry_safe(alias, tmp, &pmu->aliases, list) {
-		list_del(&alias->list);
-		perf_pmu_free_alias(alias);
-	}
+	if (!pmu->aliases)
+		return;
+
+	hashmap__for_each_entry(pmu->aliases, entry, bkt)
+		perf_pmu_free_alias(entry->pvalue);
+
+	hashmap__free(pmu->aliases);
+	pmu->aliases = NULL;
 }
 
 static struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu,
@@ -433,35 +451,37 @@ static struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu,
 						   bool load)
 {
 	struct perf_pmu_alias *alias;
+	bool has_sysfs_event;
+	char event_file_name[FILENAME_MAX + 8];
 
-	if (load && !pmu->sysfs_aliases_loaded) {
-		bool has_sysfs_event;
-		char event_file_name[FILENAME_MAX + 8];
+	if (hashmap__find(pmu->aliases, name, &alias))
+		return alias;
 
-		/*
-		 * Test if alias/event 'name' exists in the PMU's sysfs/events
-		 * directory. If not skip parsing the sysfs aliases. Sysfs event
-		 * name must be all lower or all upper case.
-		 */
-		scnprintf(event_file_name, sizeof(event_file_name), "events/%s", name);
-		for (size_t i = 7, n = 7 + strlen(name); i < n; i++)
-			event_file_name[i] = tolower(event_file_name[i]);
+	if (!load || pmu->sysfs_aliases_loaded)
+		return NULL;
 
-		has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name);
-		if (!has_sysfs_event) {
-			for (size_t i = 7, n = 7 + strlen(name); i < n; i++)
-				event_file_name[i] = toupper(event_file_name[i]);
+	/*
+	 * Test if alias/event 'name' exists in the PMU's sysfs/events
+	 * directory. If not skip parsing the sysfs aliases. Sysfs event
+	 * name must be all lower or all upper case.
+	 */
+	scnprintf(event_file_name, sizeof(event_file_name), "events/%s", name);
+	for (size_t i = 7, n = 7 + strlen(name); i < n; i++)
+		event_file_name[i] = tolower(event_file_name[i]);
 
-			has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name);
-		}
-		if (has_sysfs_event)
-			pmu_aliases_parse(pmu);
+	has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name);
+	if (!has_sysfs_event) {
+		for (size_t i = 7, n = 7 + strlen(name); i < n; i++)
+			event_file_name[i] = toupper(event_file_name[i]);
 
+		has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name);
 	}
-	list_for_each_entry(alias, &pmu->aliases, list) {
-		if (!strcasecmp(alias->name, name))
+	if (has_sysfs_event) {
+		pmu_aliases_parse(pmu);
+		if (hashmap__find(pmu->aliases, name, &alias))
 			return alias;
 	}
+
 	return NULL;
 }
 
@@ -525,6 +545,18 @@ static int update_alias(const struct pmu_event *pe,
 		if (!ret)
 			snprintf(data->alias->unit, sizeof(data->alias->unit), "%s", unit);
 	}
+	if (!ret && pe->retirement_latency_mean) {
+		ret = parse_double(pe->retirement_latency_mean, NULL,
+					      &data->alias->retirement_latency_mean);
+	}
+	if (!ret && pe->retirement_latency_min) {
+		ret = parse_double(pe->retirement_latency_min, NULL,
+					      &data->alias->retirement_latency_min);
+	}
+	if (!ret && pe->retirement_latency_max) {
+		ret = parse_double(pe->retirement_latency_max, NULL,
+					      &data->alias->retirement_latency_max);
+	}
 	return ret;
 }
 
@@ -532,8 +564,8 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 				const char *desc, const char *val, FILE *val_fd,
 			        const struct pmu_event *pe, enum event_source src)
 {
-	struct perf_pmu_alias *alias;
-	int ret;
+	struct perf_pmu_alias *alias, *old_alias;
+	int ret = 0;
 	const char *long_desc = NULL, *topic = NULL, *unit = NULL, *pmu_name = NULL;
 	bool deprecated = false, perpkg = false;
 
@@ -562,6 +594,24 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 	alias->per_pkg = perpkg;
 	alias->snapshot = false;
 	alias->deprecated = deprecated;
+	alias->retirement_latency_mean = 0.0;
+	alias->retirement_latency_min = 0.0;
+	alias->retirement_latency_max = 0.0;
+
+	if (!ret && pe && pe->retirement_latency_mean) {
+		ret = parse_double(pe->retirement_latency_mean, NULL,
+				   &alias->retirement_latency_mean);
+	}
+	if (!ret && pe && pe->retirement_latency_min) {
+		ret = parse_double(pe->retirement_latency_min, NULL,
+				   &alias->retirement_latency_min);
+	}
+	if (!ret && pe && pe->retirement_latency_max) {
+		ret = parse_double(pe->retirement_latency_max, NULL,
+				   &alias->retirement_latency_max);
+	}
+	if (ret)
+		return ret;
 
 	ret = parse_events_terms(&alias->terms, val, val_fd);
 	if (ret) {
@@ -607,7 +657,8 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 		break;
 
 	}
-	list_add_tail(&alias->list, &pmu->aliases);
+	hashmap__set(pmu->aliases, alias->name, alias, /*old_key=*/ NULL, &old_alias);
+	perf_pmu_free_alias(old_alias);
 	return 0;
 }
 
@@ -1095,43 +1146,77 @@ perf_pmu__arch_init(struct perf_pmu *pmu)
 		pmu->mem_events = perf_mem_events;
 }
 
+/* Variant of str_hash that does tolower on each character. */
+static size_t aliases__hash(long key, void *ctx __maybe_unused)
+{
+	const char *s = (const char *)key;
+	size_t h = 0;
+
+	while (*s) {
+		h = h * 31 + tolower(*s);
+		s++;
+	}
+	return h;
+}
+
+static bool aliases__equal(long key1, long key2, void *ctx __maybe_unused)
+{
+	return strcasecmp((const char *)key1, (const char *)key2) == 0;
+}
+
+int perf_pmu__init(struct perf_pmu *pmu, __u32 type, const char *name)
+{
+	pmu->type = type;
+	INIT_LIST_HEAD(&pmu->format);
+	INIT_LIST_HEAD(&pmu->caps);
+
+	pmu->name = strdup(name);
+	if (!pmu->name)
+		return -ENOMEM;
+
+	pmu->aliases = hashmap__new(aliases__hash, aliases__equal, /*ctx=*/ NULL);
+	if (!pmu->aliases)
+		return -ENOMEM;
+
+	return 0;
+}
+
 struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *name,
 				  bool eager_load)
 {
 	struct perf_pmu *pmu;
-	__u32 type;
 
 	pmu = zalloc(sizeof(*pmu));
 	if (!pmu)
 		return NULL;
 
-	pmu->name = strdup(name);
-	if (!pmu->name)
-		goto err;
+	if (perf_pmu__init(pmu, PERF_PMU_TYPE_FAKE, name) != 0) {
+		perf_pmu__delete(pmu);
+		return NULL;
+	}
 
 	/*
 	 * Read type early to fail fast if a lookup name isn't a PMU. Ensure
 	 * that type value is successfully assigned (return 1).
 	 */
-	if (perf_pmu__scan_file_at(pmu, dirfd, "type", "%u", &type) != 1)
-		goto err;
-
-	INIT_LIST_HEAD(&pmu->format);
-	INIT_LIST_HEAD(&pmu->aliases);
-	INIT_LIST_HEAD(&pmu->caps);
+	if (perf_pmu__scan_file_at(pmu, dirfd, "type", "%u", &pmu->type) != 1) {
+		perf_pmu__delete(pmu);
+		return NULL;
+	}
 
 	/*
 	 * The pmu data we store & need consists of the pmu
 	 * type value and format definitions. Load both right
 	 * now.
 	 */
-	if (pmu_format(pmu, dirfd, name, eager_load))
-		goto err;
+	if (pmu_format(pmu, dirfd, name, eager_load)) {
+		perf_pmu__delete(pmu);
+		return NULL;
+	}
 
 	pmu->is_core = is_pmu_core(name);
 	pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core);
 
-	pmu->type = type;
 	pmu->is_uncore = pmu_is_uncore(dirfd, name);
 	if (pmu->is_uncore)
 		pmu->id = pmu_id(name);
@@ -1153,10 +1238,6 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 		pmu_aliases_parse_eager(pmu, dirfd);
 
 	return pmu;
-err:
-	zfree(&pmu->name);
-	free(pmu);
-	return NULL;
 }
 
 /* Creates the PMU when sysfs scanning fails. */
@@ -1178,7 +1259,7 @@ struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pm
 	pmu->cpus = cpu_map__online();
 
 	INIT_LIST_HEAD(&pmu->format);
-	INIT_LIST_HEAD(&pmu->aliases);
+	pmu->aliases = hashmap__new(aliases__hash, aliases__equal, /*ctx=*/ NULL);
 	INIT_LIST_HEAD(&pmu->caps);
 	list_add_tail(&pmu->list, core_pmus);
 	return pmu;
@@ -1429,7 +1510,7 @@ static int pmu_config_term(const struct perf_pmu *pmu,
 			break;
 		case PARSE_EVENTS__TERM_TYPE_USER: /* Not hardcoded. */
 			return -EINVAL;
-		case PARSE_EVENTS__TERM_TYPE_NAME ... PARSE_EVENTS__TERM_TYPE_HARDWARE:
+		case PARSE_EVENTS__TERM_TYPE_NAME ... PARSE_EVENTS__TERM_TYPE_CPU:
 			/* Skip non-config terms. */
 			break;
 		default:
@@ -1678,6 +1759,9 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_
 	info->unit     = NULL;
 	info->scale    = 0.0;
 	info->snapshot = false;
+	info->retirement_latency_mean = 0.0;
+	info->retirement_latency_min = 0.0;
+	info->retirement_latency_max = 0.0;
 
 	if (perf_pmu__is_hwmon(pmu)) {
 		ret = hwmon_pmu__check_alias(head_terms, info, err);
@@ -1711,6 +1795,10 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_
 		if (term->alternate_hw_config)
 			*alternate_hw_config = term->val.num;
 
+		info->retirement_latency_mean = alias->retirement_latency_mean;
+		info->retirement_latency_min = alias->retirement_latency_min;
+		info->retirement_latency_max = alias->retirement_latency_max;
+
 		list_del_init(&term->list);
 		parse_events_term__delete(term);
 	}
@@ -1804,6 +1892,7 @@ int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_call
 		"aux-output",
 		"aux-action=(pause|resume|start-paused)",
 		"aux-sample-size=number",
+		"cpu=number",
 	};
 	struct perf_pmu_format *format;
 	int ret;
@@ -1930,13 +2019,14 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 			     void *state, pmu_event_callback cb)
 {
 	char buf[1024];
-	struct perf_pmu_alias *event;
 	struct pmu_event_info info = {
 		.pmu = pmu,
 		.event_type_desc = "Kernel PMU event",
 	};
 	int ret = 0;
 	struct strbuf sb;
+	struct hashmap_entry *entry;
+	size_t bkt;
 
 	if (perf_pmu__is_hwmon(pmu))
 		return hwmon_pmu__for_each_event(pmu, state, cb);
@@ -1944,7 +2034,8 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 	strbuf_init(&sb, /*hint=*/ 0);
 	pmu_aliases_parse(pmu);
 	pmu_add_cpu_aliases(pmu);
-	list_for_each_entry(event, &pmu->aliases, list) {
+	hashmap__for_each_entry(pmu->aliases, entry, bkt) {
+		struct perf_pmu_alias *event = entry->pvalue;
 		size_t buf_used, pmu_name_len;
 
 		if (perf_pmu__is_tool(pmu) && tool_pmu__skip_event(event->name))
@@ -2052,6 +2143,9 @@ static bool perf_pmu___name_match(const struct perf_pmu *pmu, const char *to_mat
 	for (size_t i = 0; i < ARRAY_SIZE(names); i++) {
 		const char *name = names[i];
 
+		if (!name)
+			continue;
+
 		if (wildcard && perf_pmu__match_wildcard_uncore(name, to_match))
 			return true;
 		if (!wildcard && perf_pmu__match_ignoring_suffix_uncore(name, to_match))
@@ -2211,6 +2305,17 @@ static void perf_pmu__del_caps(struct perf_pmu *pmu)
 	}
 }
 
+struct perf_pmu_caps *perf_pmu__get_cap(struct perf_pmu *pmu, const char *name)
+{
+	struct perf_pmu_caps *caps;
+
+	list_for_each_entry(caps, &pmu->caps, list) {
+		if (!strcmp(caps->name, name))
+			return caps;
+	}
+	return NULL;
+}
+
 /*
  * Reading/parsing the given pmu capabilities, which should be located at:
  * /sys/bus/event_source/devices/<dev>/caps as sysfs group attributes.
@@ -2401,6 +2506,9 @@ int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename,
 
 void perf_pmu__delete(struct perf_pmu *pmu)
 {
+	if (!pmu)
+		return;
+
 	if (perf_pmu__is_hwmon(pmu))
 		hwmon_pmu__exit(pmu);
 
@@ -2418,14 +2526,16 @@ void perf_pmu__delete(struct perf_pmu *pmu)
 
 const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config)
 {
-	struct perf_pmu_alias *event;
+	struct hashmap_entry *entry;
+	size_t bkt;
 
 	if (!pmu)
 		return NULL;
 
 	pmu_aliases_parse(pmu);
 	pmu_add_cpu_aliases(pmu);
-	list_for_each_entry(event, &pmu->aliases, list) {
+	hashmap__for_each_entry(pmu->aliases, entry, bkt) {
+		struct perf_pmu_alias *event = entry->pvalue;
 		struct perf_event_attr attr = {.config = 0,};
 
 		int ret = perf_pmu__config(pmu, &attr, &event->terms, /*apply_hardcoded=*/true,
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index b93014cc3670..71b8636fd07d 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -14,6 +14,7 @@
 #include "mem-events.h"
 
 struct evsel_config_term;
+struct hashmap;
 struct perf_cpu_map;
 struct print_callbacks;
 
@@ -125,7 +126,7 @@ struct perf_pmu {
 	 * event read from <sysfs>/bus/event_source/devices/<name>/events/ or
 	 * from json events in pmu-events.c.
 	 */
-	struct list_head aliases;
+	struct hashmap *aliases;
 	/**
 	 * @events_table: The events table for json events in pmu-events.c.
 	 */
@@ -194,6 +195,9 @@ struct perf_pmu {
 struct perf_pmu_info {
 	const char *unit;
 	double scale;
+	double retirement_latency_mean;
+	double retirement_latency_min;
+	double retirement_latency_max;
 	bool per_pkg;
 	bool snapshot;
 };
@@ -274,6 +278,8 @@ bool pmu_uncore_identifier_match(const char *compat, const char *id);
 
 int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
 
+struct perf_pmu_caps *perf_pmu__get_cap(struct perf_pmu *pmu, const char *name);
+
 int perf_pmu__caps_parse(struct perf_pmu *pmu);
 
 void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
@@ -289,6 +295,7 @@ int perf_pmu__pathname_scnprintf(char *buf, size_t size,
 int perf_pmu__event_source_devices_fd(void);
 int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags);
 
+int perf_pmu__init(struct perf_pmu *pmu, __u32 type, const char *name);
 struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name,
 				  bool eager_load);
 struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index b99292de7669..3bbd26fec78a 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -727,14 +727,21 @@ struct perf_pmu *evsel__find_pmu(const struct evsel *evsel)
 	legacy_core_type =
 		evsel->core.attr.type == PERF_TYPE_HARDWARE ||
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE;
-	if (!pmu && legacy_core_type) {
-		if (perf_pmus__supports_extended_type()) {
-			u32 type = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT;
+	if (!pmu && legacy_core_type && perf_pmus__supports_extended_type()) {
+		u32 type = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT;
 
-			pmu = perf_pmus__find_by_type(type);
-		} else {
-			pmu = perf_pmus__find_core_pmu();
-		}
+		pmu = perf_pmus__find_by_type(type);
+	}
+	if (!pmu && (legacy_core_type || evsel->core.attr.type == PERF_TYPE_RAW)) {
+		/*
+		 * For legacy events, if there was no extended type info then
+		 * assume the PMU is the first core PMU.
+		 *
+		 * On architectures like ARM there is no sysfs PMU with type
+		 * PERF_TYPE_RAW, assume the RAW events are going to be handled
+		 * by the first core PMU.
+		 */
+		pmu = perf_pmus__find_core_pmu();
 	}
 	((struct evsel *)evsel)->pmu = pmu;
 	return pmu;
diff --git a/tools/perf/util/print-events.h b/tools/perf/util/print-events.h
index 445efa1636c1..8f19c2bea64a 100644
--- a/tools/perf/util/print-events.h
+++ b/tools/perf/util/print-events.h
@@ -25,7 +25,8 @@ struct print_callbacks {
 			const char *long_desc,
 			const char *expr,
 			const char *threshold,
-			const char *unit);
+			const char *unit,
+			const char *pmu_name);
 	bool (*skip_duplicate_pmus)(void *print_state);
 };
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index f3c05da25b4a..321c333877fa 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -626,6 +626,92 @@ static int pyrf_thread_map__setup_types(void)
 	return PyType_Ready(&pyrf_thread_map__type);
 }
 
+struct pyrf_counts_values {
+	PyObject_HEAD
+
+	struct perf_counts_values values;
+};
+
+static const char pyrf_counts_values__doc[] = PyDoc_STR("perf counts values object.");
+
+static void pyrf_counts_values__delete(struct pyrf_counts_values *pcounts_values)
+{
+	Py_TYPE(pcounts_values)->tp_free((PyObject *)pcounts_values);
+}
+
+#define counts_values_member_def(member, ptype, help) \
+	{ #member, ptype, \
+	  offsetof(struct pyrf_counts_values, values.member), \
+	  0, help }
+
+static PyMemberDef pyrf_counts_values_members[] = {
+	counts_values_member_def(val, T_ULONG, "Value of event"),
+	counts_values_member_def(ena, T_ULONG, "Time for which enabled"),
+	counts_values_member_def(run, T_ULONG, "Time for which running"),
+	counts_values_member_def(id, T_ULONG, "Unique ID for an event"),
+	counts_values_member_def(lost, T_ULONG, "Num of lost samples"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_counts_values_get_values(struct pyrf_counts_values *self, void *closure)
+{
+	PyObject *vals = PyList_New(5);
+
+	if (!vals)
+		return NULL;
+	for (int i = 0; i < 5; i++)
+		PyList_SetItem(vals, i, PyLong_FromLong(self->values.values[i]));
+
+	return vals;
+}
+
+static int pyrf_counts_values_set_values(struct pyrf_counts_values *self, PyObject *list,
+					 void *closure)
+{
+	Py_ssize_t size;
+	PyObject *item = NULL;
+
+	if (!PyList_Check(list)) {
+		PyErr_SetString(PyExc_TypeError, "Value assigned must be a list");
+		return -1;
+	}
+
+	size = PyList_Size(list);
+	for (Py_ssize_t i = 0; i < size; i++) {
+		item = PyList_GetItem(list, i);
+		if (!PyLong_Check(item)) {
+			PyErr_SetString(PyExc_TypeError, "List members should be numbers");
+			return -1;
+		}
+		self->values.values[i] = PyLong_AsLong(item);
+	}
+
+	return 0;
+}
+
+static PyGetSetDef pyrf_counts_values_getset[] = {
+	{"values", (getter)pyrf_counts_values_get_values, (setter)pyrf_counts_values_set_values,
+		"Name field", NULL},
+	{ .name = NULL, },
+};
+
+static PyTypeObject pyrf_counts_values__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.counts_values",
+	.tp_basicsize	= sizeof(struct pyrf_counts_values),
+	.tp_dealloc	= (destructor)pyrf_counts_values__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_counts_values__doc,
+	.tp_members	= pyrf_counts_values_members,
+	.tp_getset	= pyrf_counts_values_getset,
+};
+
+static int pyrf_counts_values__setup_types(void)
+{
+	pyrf_counts_values__type.tp_new = PyType_GenericNew;
+	return PyType_Ready(&pyrf_counts_values__type);
+}
+
 struct pyrf_evsel {
 	PyObject_HEAD
 
@@ -781,6 +867,58 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
 	return Py_None;
 }
 
+static PyObject *pyrf_evsel__cpus(struct pyrf_evsel *pevsel)
+{
+	struct pyrf_cpu_map *pcpu_map = PyObject_New(struct pyrf_cpu_map, &pyrf_cpu_map__type);
+
+	if (pcpu_map)
+		pcpu_map->cpus = perf_cpu_map__get(pevsel->evsel.core.cpus);
+
+	return (PyObject *)pcpu_map;
+}
+
+static PyObject *pyrf_evsel__threads(struct pyrf_evsel *pevsel)
+{
+	struct pyrf_thread_map *pthread_map =
+		PyObject_New(struct pyrf_thread_map, &pyrf_thread_map__type);
+
+	if (pthread_map)
+		pthread_map->threads = perf_thread_map__get(pevsel->evsel.core.threads);
+
+	return (PyObject *)pthread_map;
+}
+
+static PyObject *pyrf_evsel__read(struct pyrf_evsel *pevsel,
+				  PyObject *args, PyObject *kwargs)
+{
+	struct evsel *evsel = &pevsel->evsel;
+	int cpu = 0, cpu_idx, thread = 0, thread_idx;
+	struct perf_counts_values counts;
+	struct pyrf_counts_values *count_values = PyObject_New(struct pyrf_counts_values,
+							       &pyrf_counts_values__type);
+
+	if (!count_values)
+		return NULL;
+
+	if (!PyArg_ParseTuple(args, "ii", &cpu, &thread))
+		return NULL;
+
+	cpu_idx = perf_cpu_map__idx(evsel->core.cpus, (struct perf_cpu){.cpu = cpu});
+	if (cpu_idx < 0) {
+		PyErr_Format(PyExc_TypeError, "CPU %d is not part of evsel's CPUs", cpu);
+		return NULL;
+	}
+	thread_idx = perf_thread_map__idx(evsel->core.threads, thread);
+	if (cpu_idx < 0) {
+		PyErr_Format(PyExc_TypeError, "Thread %d is not part of evsel's threads",
+			     thread);
+		return NULL;
+	}
+	perf_evsel__read(&(evsel->core), cpu_idx, thread_idx, &counts);
+	count_values->values = counts;
+	return (PyObject *)count_values;
+}
+
 static PyObject *pyrf_evsel__str(PyObject *self)
 {
 	struct pyrf_evsel *pevsel = (void *)self;
@@ -799,6 +937,24 @@ static PyMethodDef pyrf_evsel__methods[] = {
 		.ml_flags = METH_VARARGS | METH_KEYWORDS,
 		.ml_doc	  = PyDoc_STR("open the event selector file descriptor table.")
 	},
+	{
+		.ml_name  = "cpus",
+		.ml_meth  = (PyCFunction)pyrf_evsel__cpus,
+		.ml_flags = METH_NOARGS,
+		.ml_doc	  = PyDoc_STR("CPUs the event is to be used with.")
+	},
+	{
+		.ml_name  = "threads",
+		.ml_meth  = (PyCFunction)pyrf_evsel__threads,
+		.ml_flags = METH_NOARGS,
+		.ml_doc	  = PyDoc_STR("threads the event is to be used with.")
+	},
+	{
+		.ml_name  = "read",
+		.ml_meth  = (PyCFunction)pyrf_evsel__read,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("read counters")
+	},
 	{ .ml_name = NULL, }
 };
 
@@ -1054,6 +1210,16 @@ static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist,
 	return Py_None;
 }
 
+static PyObject *pyrf_evlist__close(struct pyrf_evlist *pevlist)
+{
+	struct evlist *evlist = &pevlist->evlist;
+
+	evlist__close(evlist);
+
+	Py_INCREF(Py_None);
+	return Py_None;
+}
+
 static PyObject *pyrf_evlist__config(struct pyrf_evlist *pevlist)
 {
 	struct record_opts opts = {
@@ -1113,6 +1279,12 @@ static PyMethodDef pyrf_evlist__methods[] = {
 		.ml_doc	  = PyDoc_STR("open the file descriptors.")
 	},
 	{
+		.ml_name  = "close",
+		.ml_meth  = (PyCFunction)pyrf_evlist__close,
+		.ml_flags = METH_NOARGS,
+		.ml_doc	  = PyDoc_STR("close the file descriptors.")
+	},
+	{
 		.ml_name  = "poll",
 		.ml_meth  = (PyCFunction)pyrf_evlist__poll,
 		.ml_flags = METH_VARARGS | METH_KEYWORDS,
@@ -1442,7 +1614,8 @@ PyMODINIT_FUNC PyInit_perf(void)
 	    pyrf_evlist__setup_types() < 0 ||
 	    pyrf_evsel__setup_types() < 0 ||
 	    pyrf_thread_map__setup_types() < 0 ||
-	    pyrf_cpu_map__setup_types() < 0)
+	    pyrf_cpu_map__setup_types() < 0 ||
+	    pyrf_counts_values__setup_types() < 0)
 		return module;
 
 	/* The page_size is placed in util object. */
@@ -1487,6 +1660,9 @@ PyMODINIT_FUNC PyInit_perf(void)
 	Py_INCREF(&pyrf_cpu_map__type);
 	PyModule_AddObject(module, "cpu_map", (PyObject*)&pyrf_cpu_map__type);
 
+	Py_INCREF(&pyrf_counts_values__type);
+	PyModule_AddObject(module, "counts_values", (PyObject *)&pyrf_counts_values__type);
+
 	dict = PyModule_GetDict(module);
 	if (dict == NULL)
 		goto error;
diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
index a6566134e09e..ea3a6c4657ee 100644
--- a/tools/perf/util/record.h
+++ b/tools/perf/util/record.h
@@ -28,6 +28,7 @@ struct record_opts {
 	bool	      sample_time_set;
 	bool	      sample_cpu;
 	bool	      sample_identifier;
+	bool	      sample_data_src;
 	bool	      period;
 	bool	      period_set;
 	bool	      running_time;
@@ -79,6 +80,7 @@ struct record_opts {
 	int	      synth;
 	int	      threads_spec;
 	const char    *threads_user_spec;
+	u64	      off_cpu_thresh_ns;
 };
 
 extern const char * const *record_usage;
diff --git a/tools/perf/util/rwsem.c b/tools/perf/util/rwsem.c
index 5109167f27f7..9d26832398db 100644
--- a/tools/perf/util/rwsem.c
+++ b/tools/perf/util/rwsem.c
@@ -27,6 +27,7 @@ int exit_rwsem(struct rw_semaphore *sem)
 }
 
 int down_read(struct rw_semaphore *sem)
+	NO_THREAD_SAFETY_ANALYSIS
 {
 #if RWS_ERRORCHECK
 	mutex_lock(&sem->mtx);
@@ -37,6 +38,7 @@ int down_read(struct rw_semaphore *sem)
 }
 
 int up_read(struct rw_semaphore *sem)
+	NO_THREAD_SAFETY_ANALYSIS
 {
 #if RWS_ERRORCHECK
 	mutex_unlock(&sem->mtx);
@@ -47,6 +49,7 @@ int up_read(struct rw_semaphore *sem)
 }
 
 int down_write(struct rw_semaphore *sem)
+	NO_THREAD_SAFETY_ANALYSIS
 {
 #if RWS_ERRORCHECK
 	mutex_lock(&sem->mtx);
@@ -57,6 +60,7 @@ int down_write(struct rw_semaphore *sem)
 }
 
 int up_write(struct rw_semaphore *sem)
+	NO_THREAD_SAFETY_ANALYSIS
 {
 #if RWS_ERRORCHECK
 	mutex_unlock(&sem->mtx);
diff --git a/tools/perf/util/rwsem.h b/tools/perf/util/rwsem.h
index ef5cbc31d967..b102d8143181 100644
--- a/tools/perf/util/rwsem.h
+++ b/tools/perf/util/rwsem.h
@@ -10,7 +10,7 @@
  */
 #define RWS_ERRORCHECK 0
 
-struct rw_semaphore {
+struct LOCKABLE rw_semaphore {
 #if RWS_ERRORCHECK
 	struct mutex mtx;
 #else
@@ -21,10 +21,10 @@ struct rw_semaphore {
 int init_rwsem(struct rw_semaphore *sem);
 int exit_rwsem(struct rw_semaphore *sem);
 
-int down_read(struct rw_semaphore *sem);
-int up_read(struct rw_semaphore *sem);
+int down_read(struct rw_semaphore *sem) SHARED_LOCK_FUNCTION(sem);
+int up_read(struct rw_semaphore *sem) UNLOCK_FUNCTION(sem);
 
-int down_write(struct rw_semaphore *sem);
-int up_write(struct rw_semaphore *sem);
+int down_write(struct rw_semaphore *sem) EXCLUSIVE_LOCK_FUNCTION(sem);
+int up_write(struct rw_semaphore *sem) UNLOCK_FUNCTION(sem);
 
 #endif /* _PERF_RWSEM_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 60fb9997ea0d..a320672c264e 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1400,7 +1400,9 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	int err;
 
 	perf_sample__init(&sample, /*all=*/true);
-	if (event->header.type != PERF_RECORD_COMPRESSED || perf_tool__compressed_is_stub(tool))
+	if ((event->header.type != PERF_RECORD_COMPRESSED &&
+	     event->header.type != PERF_RECORD_COMPRESSED2) ||
+	    perf_tool__compressed_is_stub(tool))
 		dump_event(session->evlist, event, file_offset, &sample, file_path);
 
 	/* These events are processed right away */
@@ -1481,6 +1483,7 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		err = tool->feature(session, event);
 		break;
 	case PERF_RECORD_COMPRESSED:
+	case PERF_RECORD_COMPRESSED2:
 		err = tool->compressed(session, event, file_offset, file_path);
 		if (err)
 			dump_event(session->evlist, event, file_offset, &sample, file_path);
@@ -1639,8 +1642,17 @@ static s64 perf_session__process_event(struct perf_session *session,
 	if (session->header.needs_swap)
 		event_swap(event, evlist__sample_id_all(evlist));
 
-	if (event->header.type >= PERF_RECORD_HEADER_MAX)
-		return -EINVAL;
+	if (event->header.type >= PERF_RECORD_HEADER_MAX) {
+		/* perf should not support unaligned event, stop here. */
+		if (event->header.size % sizeof(u64))
+			return -EINVAL;
+
+		/* This perf is outdated and does not support the latest event type. */
+		ui__warning("Unsupported header type %u, please consider updating perf.\n",
+			    event->header.type);
+		/* Skip unsupported event by returning its size. */
+		return event->header.size;
+	}
 
 	events_stats__inc(&evlist->stats, event->header.type);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index c51049087e4e..45e654653960 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -141,6 +141,43 @@ struct sort_entry sort_thread = {
 	.se_width_idx	= HISTC_THREAD,
 };
 
+/* --sort tgid */
+
+static int64_t
+sort__tgid_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return thread__pid(right->thread) - thread__pid(left->thread);
+}
+
+static int hist_entry__tgid_snprintf(struct hist_entry *he, char *bf,
+				       size_t size, unsigned int width)
+{
+	int tgid = thread__pid(he->thread);
+	const char *comm = NULL;
+
+	/* display comm of the thread-group leader */
+	if (thread__pid(he->thread) == thread__tid(he->thread)) {
+		comm = thread__comm_str(he->thread);
+	} else {
+		struct maps *maps = thread__maps(he->thread);
+		struct thread *leader = machine__find_thread(maps__machine(maps),
+							     tgid, tgid);
+		if (leader) {
+			comm = thread__comm_str(leader);
+			thread__put(leader);
+		}
+	}
+	width = max(7U, width) - 8;
+	return repsep_snprintf(bf, size, "%7d:%-*.*s", tgid, width, width, comm ?: "");
+}
+
+struct sort_entry sort_tgid = {
+	.se_header	= "   Tgid:Command",
+	.se_cmp		= sort__tgid_cmp,
+	.se_snprintf	= hist_entry__tgid_snprintf,
+	.se_width_idx	= HISTC_TGID,
+};
+
 /* --sort simd */
 
 static int64_t
@@ -2508,6 +2545,7 @@ static void sort_dimension_add_dynamic_header(struct sort_dimension *sd)
 
 static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_PID, "pid", sort_thread),
+	DIM(SORT_TGID, "tgid", sort_tgid),
 	DIM(SORT_COMM, "comm", sort_comm),
 	DIM(SORT_DSO, "dso", sort_dso),
 	DIM(SORT_SYM, "symbol", sort_sym),
@@ -2598,9 +2636,11 @@ struct hpp_dimension {
 	struct perf_hpp_fmt	*fmt;
 	int			taken;
 	int			was_taken;
+	int			mem_mode;
 };
 
 #define DIM(d, n) { .name = n, .fmt = &perf_hpp__format[d], }
+#define DIM_MEM(d, n) { .name = n, .fmt = &perf_hpp__format[d], .mem_mode = 1, }
 
 static struct hpp_dimension hpp_sort_dimensions[] = {
 	DIM(PERF_HPP__OVERHEAD, "overhead"),
@@ -2620,8 +2660,15 @@ static struct hpp_dimension hpp_sort_dimensions[] = {
 	DIM(PERF_HPP__WEIGHT2, "ins_lat"),
 	DIM(PERF_HPP__WEIGHT3, "retire_lat"),
 	DIM(PERF_HPP__WEIGHT3, "p_stage_cyc"),
+	/* used for output only when SORT_MODE__MEM */
+	DIM_MEM(PERF_HPP__MEM_STAT_OP, "op"),
+	DIM_MEM(PERF_HPP__MEM_STAT_CACHE, "cache"),
+	DIM_MEM(PERF_HPP__MEM_STAT_MEMORY, "memory"),
+	DIM_MEM(PERF_HPP__MEM_STAT_SNOOP, "snoop"),
+	DIM_MEM(PERF_HPP__MEM_STAT_DTLB, "dtlb"),
 };
 
+#undef DIM_MEM
 #undef DIM
 
 struct hpp_sort_entry {
@@ -2641,18 +2688,22 @@ void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 }
 
 static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			      struct hists *hists, int line __maybe_unused,
+			      struct hists *hists, int line,
 			      int *span __maybe_unused)
 {
 	struct hpp_sort_entry *hse;
 	size_t len = fmt->user_len;
+	const char *hdr = "";
+
+	if (line == hists->hpp_list->nr_header_lines - 1)
+		hdr = fmt->name;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
 	if (!len)
 		len = hists__col_len(hists, hse->se->se_width_idx);
 
-	return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name);
+	return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, hdr);
 }
 
 static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
@@ -2884,9 +2935,10 @@ static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd,
 }
 
 static int __sort_dimension__add_hpp_output(struct sort_dimension *sd,
-					    struct perf_hpp_list *list)
+					    struct perf_hpp_list *list,
+					    int level)
 {
-	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, 0);
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, level);
 
 	if (hse == NULL)
 		return -1;
@@ -3495,12 +3547,13 @@ static int __hpp_dimension__add(struct hpp_dimension *hd,
 }
 
 static int __sort_dimension__add_output(struct perf_hpp_list *list,
-					struct sort_dimension *sd)
+					struct sort_dimension *sd,
+					int level)
 {
 	if (sd->taken)
 		return 0;
 
-	if (__sort_dimension__add_hpp_output(sd, list) < 0)
+	if (__sort_dimension__add_hpp_output(sd, list, level) < 0)
 		return -1;
 
 	sd->taken = 1;
@@ -3508,14 +3561,15 @@ static int __sort_dimension__add_output(struct perf_hpp_list *list,
 }
 
 static int __hpp_dimension__add_output(struct perf_hpp_list *list,
-				       struct hpp_dimension *hd)
+				       struct hpp_dimension *hd,
+				       int level)
 {
 	struct perf_hpp_fmt *fmt;
 
 	if (hd->taken)
 		return 0;
 
-	fmt = __hpp_dimension__alloc_hpp(hd, 0);
+	fmt = __hpp_dimension__alloc_hpp(hd, level);
 	if (!fmt)
 		return -1;
 
@@ -3532,7 +3586,7 @@ int hpp_dimension__add_output(unsigned col, bool implicit)
 	hd = &hpp_sort_dimensions[col];
 	if (implicit && !hd->was_taken)
 		return 0;
-	return __hpp_dimension__add_output(&perf_hpp_list, hd);
+	return __hpp_dimension__add_output(&perf_hpp_list, hd, /*level=*/0);
 }
 
 int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
@@ -3601,15 +3655,6 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 		return __sort_dimension__add(sd, list, level);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
-		struct hpp_dimension *hd = &hpp_sort_dimensions[i];
-
-		if (strncasecmp(tok, hd->name, strlen(tok)))
-			continue;
-
-		return __hpp_dimension__add(hd, list, level);
-	}
-
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
 		struct sort_dimension *sd = &bstack_sort_dimensions[i];
 
@@ -3651,6 +3696,15 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 		return 0;
 	}
 
+	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
+		struct hpp_dimension *hd = &hpp_sort_dimensions[i];
+
+		if (strncasecmp(tok, hd->name, strlen(tok)))
+			continue;
+
+		return __hpp_dimension__add(hd, list, level);
+	}
+
 	if (!add_dynamic_entry(evlist, tok, level))
 		return 0;
 
@@ -4000,7 +4054,7 @@ void sort__setup_elide(FILE *output)
 	}
 }
 
-int output_field_add(struct perf_hpp_list *list, const char *tok)
+int output_field_add(struct perf_hpp_list *list, const char *tok, int *level)
 {
 	unsigned int i;
 
@@ -4013,16 +4067,25 @@ int output_field_add(struct perf_hpp_list *list, const char *tok)
 		if (!strcasecmp(tok, "weight"))
 			ui__warning("--fields weight shows the average value unlike in the --sort key.\n");
 
-		return __hpp_dimension__add_output(list, hd);
+		if (hd->mem_mode && sort__mode != SORT_MODE__MEMORY)
+			continue;
+
+		return __hpp_dimension__add_output(list, hd, *level);
 	}
 
+	/*
+	 * A non-output field will increase level so that it can be in a
+	 * different hierarchy.
+	 */
+	(*level)++;
+
 	for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
 		struct sort_dimension *sd = &common_sort_dimensions[i];
 
 		if (!sd->name || strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		return __sort_dimension__add_output(list, sd);
+		return __sort_dimension__add_output(list, sd, *level);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -4034,7 +4097,7 @@ int output_field_add(struct perf_hpp_list *list, const char *tok)
 		if (sort__mode != SORT_MODE__BRANCH)
 			return -EINVAL;
 
-		return __sort_dimension__add_output(list, sd);
+		return __sort_dimension__add_output(list, sd, *level);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
@@ -4046,7 +4109,7 @@ int output_field_add(struct perf_hpp_list *list, const char *tok)
 		if (sort__mode != SORT_MODE__MEMORY)
 			return -EINVAL;
 
-		return __sort_dimension__add_output(list, sd);
+		return __sort_dimension__add_output(list, sd, *level);
 	}
 
 	return -ESRCH;
@@ -4056,10 +4119,11 @@ static int setup_output_list(struct perf_hpp_list *list, char *str)
 {
 	char *tmp, *tok;
 	int ret = 0;
+	int level = 0;
 
 	for (tok = strtok_r(str, ", ", &tmp);
 			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		ret = output_field_add(list, tok);
+		ret = output_field_add(list, tok, &level);
 		if (ret == -EINVAL) {
 			ui__error("Invalid --fields key: `%s'", tok);
 			break;
@@ -4149,6 +4213,10 @@ int setup_sorting(struct evlist *evlist)
 	if (err < 0)
 		return err;
 
+	err = perf_hpp__alloc_mem_stats(&perf_hpp_list, evlist);
+	if (err < 0)
+		return err;
+
 	/* copy sort keys to output fields */
 	perf_hpp__setup_output_field(&perf_hpp_list);
 	/* and then copy output fields to sort keys */
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 180d36a2bea3..a742ab7f3c67 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -73,6 +73,7 @@ enum sort_type {
 	SORT_SYM_OFFSET,
 	SORT_ANNOTATE_DATA_TYPE_CACHELINE,
 	SORT_PARALLELISM,
+	SORT_TGID,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
@@ -146,7 +147,7 @@ void reset_dimensions(void);
 int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 			struct evlist *evlist,
 			int level);
-int output_field_add(struct perf_hpp_list *list, const char *tok);
+int output_field_add(struct perf_hpp_list *list, const char *tok, int *level);
 int64_t
 sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t
diff --git a/tools/perf/util/srccode.c b/tools/perf/util/srccode.c
index 476e99896d5e..0f4907843ac1 100644
--- a/tools/perf/util/srccode.c
+++ b/tools/perf/util/srccode.c
@@ -16,7 +16,7 @@
 #include "srccode.h"
 #include "debug.h"
 #include <internal/lib.h> // page_size
-#include "fncache.h"
+#include "hashmap.h"
 
 #define MAXSRCCACHE (32*1024*1024)
 #define MAXSRCFILES     64
@@ -92,7 +92,7 @@ static struct srcfile *find_srcfile(char *fn)
 	struct srcfile *h;
 	int fd;
 	unsigned long sz;
-	unsigned hval = shash((unsigned char *)fn) % SRC_HTAB_SZ;
+	size_t hval = str_hash(fn) % SRC_HTAB_SZ;
 
 	hlist_for_each_entry (h, &srcfile_htab[hval], hash_nd) {
 		if (!strcmp(fn, h->fn)) {
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index e852ac0d9847..729ad5cd52cb 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -798,40 +798,28 @@ static void abs_printout(struct perf_stat_config *config,
 	print_cgroup(config, os, evsel->cgrp);
 }
 
-static bool is_mixed_hw_group(struct evsel *counter)
-{
-	struct evlist *evlist = counter->evlist;
-	u32 pmu_type = counter->core.attr.type;
-	struct evsel *pos;
-
-	if (counter->core.nr_members < 2)
-		return false;
-
-	evlist__for_each_entry(evlist, pos) {
-		/* software events can be part of any hardware group */
-		if (pos->core.attr.type == PERF_TYPE_SOFTWARE)
-			continue;
-		if (pmu_type == PERF_TYPE_SOFTWARE) {
-			pmu_type = pos->core.attr.type;
-			continue;
-		}
-		if (pmu_type != pos->core.attr.type)
-			return true;
-	}
-
-	return false;
-}
-
-static bool evlist__has_hybrid(struct evlist *evlist)
+static bool evlist__has_hybrid_pmus(struct evlist *evlist)
 {
 	struct evsel *evsel;
+	struct perf_pmu *last_core_pmu = NULL;
 
 	if (perf_pmus__num_core_pmus() == 1)
 		return false;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->core.is_pmu_core)
+		if (evsel->core.is_pmu_core) {
+			struct perf_pmu *pmu = evsel__find_pmu(evsel);
+
+			if (pmu == last_core_pmu)
+				continue;
+
+			if (last_core_pmu == NULL) {
+				last_core_pmu = pmu;
+				continue;
+			}
+			/* A distinct core PMU. */
 			return true;
+		}
 	}
 
 	return false;
@@ -872,10 +860,8 @@ static void printout(struct perf_stat_config *config, struct outstate *os,
 		ok = false;
 
 		if (counter->supported) {
-			if (!evlist__has_hybrid(counter->evlist)) {
+			if (!evlist__has_hybrid_pmus(counter->evlist)) {
 				config->print_free_counters_hint = 1;
-				if (is_mixed_hw_group(counter))
-					config->print_mixed_hw_group_error = 1;
 			}
 		}
 	}
@@ -929,61 +915,6 @@ static void printout(struct perf_stat_config *config, struct outstate *os,
 	}
 }
 
-static void evsel__uniquify_counter(struct evsel *counter)
-{
-	const char *name, *pmu_name;
-	char *new_name, *config;
-	int ret;
-
-	/* No uniquification necessary. */
-	if (!counter->needs_uniquify)
-		return;
-
-	/* The evsel was already uniquified. */
-	if (counter->uniquified_name)
-		return;
-
-	/* Avoid checking to uniquify twice. */
-	counter->uniquified_name = true;
-
-	name = evsel__name(counter);
-	pmu_name = counter->pmu->name;
-	/* Already prefixed by the PMU name. */
-	if (!strncmp(name, pmu_name, strlen(pmu_name)))
-		return;
-
-	config = strchr(name, '/');
-	if (config) {
-		int len = config - name;
-
-		if (config[1] == '/') {
-			/* case: event// */
-			ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 2);
-		} else {
-			/* case: event/.../ */
-			ret = asprintf(&new_name, "%s/%.*s,%s", pmu_name, len, name, config + 1);
-		}
-	} else {
-		config = strchr(name, ':');
-		if (config) {
-			/* case: event:.. */
-			int len = config - name;
-
-			ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 1);
-		} else {
-			/* case: event */
-			ret = asprintf(&new_name, "%s/%s/", pmu_name, name);
-		}
-	}
-	if (ret > 0) {
-		free(counter->name);
-		counter->name = new_name;
-	} else {
-		/* ENOMEM from asprintf. */
-		counter->uniquified_name = false;
-	}
-}
-
 /**
  * should_skip_zero_count() - Check if the event should print 0 values.
  * @config: The perf stat configuration (including aggregation mode).
@@ -1022,8 +953,16 @@ static bool should_skip_zero_counter(struct perf_stat_config *config,
 		return true;
 
 	/*
-	 * Many tool events are only gathered on the first index, skip other
-	 * zero values.
+	 * In per-thread mode the aggr_map and aggr_get_id functions may be
+	 * NULL, assume all 0 values should be output in that case.
+	 */
+	if (!config->aggr_map || !config->aggr_get_id)
+		return false;
+
+	/*
+	 * Tool events may be gathered on all logical CPUs, for example
+	 * system_time, but for many the first index is the only one used, for
+	 * example num_cores. Don't skip for the first index.
 	 */
 	if (evsel__is_tool(counter)) {
 		struct aggr_cpu_id own_id =
@@ -1031,15 +970,12 @@ static bool should_skip_zero_counter(struct perf_stat_config *config,
 
 		return !aggr_cpu_id__equal(id, &own_id);
 	}
-
 	/*
-	 * Skip value 0 when it's an uncore event and the given aggr id
-	 * does not belong to the PMU cpumask.
+	 * Skip value 0 when the counter's cpumask doesn't match the given aggr
+	 * id.
 	 */
-	if (!counter->pmu || !counter->pmu->is_uncore)
-		return false;
 
-	perf_cpu_map__for_each_cpu(cpu, idx, counter->pmu->cpus) {
+	perf_cpu_map__for_each_cpu(cpu, idx, counter->core.cpus) {
 		struct aggr_cpu_id own_id = config->aggr_get_id(config, cpu);
 
 		if (aggr_cpu_id__equal(id, &own_id))
@@ -1066,10 +1002,15 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
 	os->evsel = counter;
 
 	/* Skip already merged uncore/hybrid events */
-	if (counter->merged_stat)
-		return;
-
-	evsel__uniquify_counter(counter);
+	if (config->aggr_mode != AGGR_NONE) {
+		if (evsel__is_hybrid(counter)) {
+			if (config->hybrid_merge && counter->first_wildcard_match != NULL)
+				return;
+		} else {
+			if (counter->first_wildcard_match != NULL)
+				return;
+		}
+	}
 
 	val = aggr->counts.val;
 	ena = aggr->counts.ena;
@@ -1575,11 +1516,6 @@ static void print_footer(struct perf_stat_config *config)
 "	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
 "	perf stat ...\n"
 "	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
-
-	if (config->print_mixed_hw_group_error)
-		fprintf(output,
-			"The events in group usually have to be from "
-			"the same PMU. Try reorganizing the group.\n");
 }
 
 static void print_percore(struct perf_stat_config *config,
@@ -1650,96 +1586,6 @@ static void print_cgroup_counter(struct perf_stat_config *config, struct evlist
 		print_metric_end(config, os);
 }
 
-/* Should uniquify be disabled for the evlist? */
-static bool evlist__disable_uniquify(const struct evlist *evlist)
-{
-	struct evsel *counter;
-	struct perf_pmu *last_pmu = NULL;
-	bool first = true;
-
-	evlist__for_each_entry(evlist, counter) {
-		/* If PMUs vary then uniquify can be useful. */
-		if (!first && counter->pmu != last_pmu)
-			return false;
-		first = false;
-		if (counter->pmu) {
-			/* Allow uniquify for uncore PMUs. */
-			if (!counter->pmu->is_core)
-				return false;
-			/* Keep hybrid event names uniquified for clarity. */
-			if (perf_pmus__num_core_pmus() > 1)
-				return false;
-		}
-	}
-	return true;
-}
-
-static void evsel__set_needs_uniquify(struct evsel *counter, const struct perf_stat_config *config)
-{
-	struct evsel *evsel;
-
-	if (counter->merged_stat) {
-		/* Counter won't be shown. */
-		return;
-	}
-
-	if (counter->use_config_name || counter->is_libpfm_event) {
-		/* Original name will be used. */
-		return;
-	}
-
-	if (!config->hybrid_merge && evsel__is_hybrid(counter)) {
-		/* Unique hybrid counters necessary. */
-		counter->needs_uniquify = true;
-		return;
-	}
-
-	if  (counter->core.attr.type < PERF_TYPE_MAX && counter->core.attr.type != PERF_TYPE_RAW) {
-		/* Legacy event, don't uniquify. */
-		return;
-	}
-
-	if (counter->pmu && counter->pmu->is_core &&
-	    counter->alternate_hw_config != PERF_COUNT_HW_MAX) {
-		/* A sysfs or json event replacing a legacy event, don't uniquify. */
-		return;
-	}
-
-	if (config->aggr_mode == AGGR_NONE) {
-		/* Always unique with no aggregation. */
-		counter->needs_uniquify = true;
-		return;
-	}
-
-	/*
-	 * Do other non-merged events in the evlist have the same name? If so
-	 * uniquify is necessary.
-	 */
-	evlist__for_each_entry(counter->evlist, evsel) {
-		if (evsel == counter || evsel->merged_stat)
-			continue;
-
-		if (evsel__name_is(counter, evsel__name(evsel))) {
-			counter->needs_uniquify = true;
-			return;
-		}
-	}
-}
-
-static void evlist__set_needs_uniquify(struct evlist *evlist, const struct perf_stat_config *config)
-{
-	struct evsel *counter;
-
-	if (evlist__disable_uniquify(evlist)) {
-		evlist__for_each_entry(evlist, counter)
-			counter->uniquified_name = true;
-		return;
-	}
-
-	evlist__for_each_entry(evlist, counter)
-		evsel__set_needs_uniquify(counter, config);
-}
-
 void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
 			    struct target *_target, struct timespec *ts,
 			    int argc, const char **argv)
@@ -1751,7 +1597,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf
 		.first = true,
 	};
 
-	evlist__set_needs_uniquify(evlist, config);
+	evlist__uniquify_evsel_names(evlist, config);
 
 	if (config->iostat_run)
 		evlist->selected = evlist__first(evlist);
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 1f7abd8754c7..355a7d5c8ab8 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -535,35 +535,6 @@ static int evsel__merge_aggr_counters(struct evsel *evsel, struct evsel *alias)
 
 	return 0;
 }
-/*
- * Events should have the same name, scale, unit, cgroup but on different core
- * PMUs or on different but matching uncore PMUs.
- */
-static bool evsel__is_alias(struct evsel *evsel_a, struct evsel *evsel_b)
-{
-	if (strcmp(evsel__name(evsel_a), evsel__name(evsel_b)))
-		return false;
-
-	if (evsel_a->scale != evsel_b->scale)
-		return false;
-
-	if (evsel_a->cgrp != evsel_b->cgrp)
-		return false;
-
-	if (strcmp(evsel_a->unit, evsel_b->unit))
-		return false;
-
-	if (evsel__is_clock(evsel_a) != evsel__is_clock(evsel_b))
-		return false;
-
-	if (evsel_a->pmu == evsel_b->pmu || evsel_a->pmu == NULL || evsel_b->pmu == NULL)
-		return false;
-
-	if (evsel_a->pmu->is_core)
-		return evsel_b->pmu->is_core;
-
-	return perf_pmu__name_no_suffix_match(evsel_a->pmu, evsel_b->pmu->name);
-}
 
 static void evsel__merge_aliases(struct evsel *evsel)
 {
@@ -572,10 +543,9 @@ static void evsel__merge_aliases(struct evsel *evsel)
 
 	alias = list_prepare_entry(evsel, &(evlist->core.entries), core.node);
 	list_for_each_entry_continue(alias, &evlist->core.entries, core.node) {
-		/* Merge the same events on different PMUs. */
-		if (evsel__is_alias(evsel, alias)) {
+		if (alias->first_wildcard_match == evsel) {
+			/* Merge the same events on different PMUs. */
 			evsel__merge_aggr_counters(evsel, alias);
-			alias->merged_stat = true;
 		}
 	}
 }
@@ -588,11 +558,7 @@ static bool evsel__should_merge_hybrid(const struct evsel *evsel,
 
 static void evsel__merge_stats(struct evsel *evsel, struct perf_stat_config *config)
 {
-	/* this evsel is already merged */
-	if (evsel->merged_stat)
-		return;
-
-	if (evsel->auto_merge_stats || evsel__should_merge_hybrid(evsel, config))
+	if (!evsel->pmu || !evsel->pmu->is_core || evsel__should_merge_hybrid(evsel, config))
 		evsel__merge_aliases(evsel);
 }
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 2fda9acd7374..1bcd7634bf47 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -100,7 +100,6 @@ struct perf_stat_config {
 	int			 times;
 	int			 run_count;
 	int			 print_free_counters_hint;
-	int			 print_mixed_hw_group_error;
 	const char		*csv_sep;
 	struct stats		*walltime_nsecs_stats;
 	struct rusage		 ru_data;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index fbf6d0f73af9..01818abd02df 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -13,10 +13,6 @@
 #include "maps.h"
 #include "symbol.h"
 #include "symsrc.h"
-#include "demangle-cxx.h"
-#include "demangle-ocaml.h"
-#include "demangle-java.h"
-#include "demangle-rust.h"
 #include "machine.h"
 #include "vdso.h"
 #include "debug.h"
@@ -279,62 +275,6 @@ static int elf_read_program_header(Elf *elf, u64 vaddr, GElf_Phdr *phdr)
 	return -1;
 }
 
-static bool want_demangle(bool is_kernel_sym)
-{
-	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
-}
-
-/*
- * Demangle C++ function signature, typically replaced by demangle-cxx.cpp
- * version.
- */
-#ifndef HAVE_CXA_DEMANGLE_SUPPORT
-char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused,
-		       bool modifiers __maybe_unused)
-{
-#ifdef HAVE_LIBBFD_SUPPORT
-	int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0);
-
-	return bfd_demangle(NULL, str, flags);
-#elif defined(HAVE_CPLUS_DEMANGLE_SUPPORT)
-	int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0);
-
-	return cplus_demangle(str, flags);
-#else
-	return NULL;
-#endif
-}
-#endif /* !HAVE_CXA_DEMANGLE_SUPPORT */
-
-static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
-{
-	char *demangled = NULL;
-
-	/*
-	 * We need to figure out if the object was created from C++ sources
-	 * DWARF DW_compile_unit has this, but we don't always have access
-	 * to it...
-	 */
-	if (!want_demangle(dso__kernel(dso) || kmodule))
-		return demangled;
-
-	demangled = cxx_demangle_sym(elf_name, verbose > 0, verbose > 0);
-	if (demangled == NULL) {
-		demangled = ocaml_demangle_sym(elf_name);
-		if (demangled == NULL) {
-			demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
-		}
-	}
-	else if (rust_is_mangled(demangled))
-		/*
-		    * Input to Rust demangling is the BFD-demangled
-		    * name which it Rust-demangles in place.
-		    */
-		rust_demangle_sym(demangled);
-
-	return demangled;
-}
-
 struct rel_info {
 	u32		nr_entries;
 	u32		*sorted;
@@ -620,7 +560,7 @@ static bool get_plt_got_name(GElf_Shdr *shdr, size_t i,
 	/* Get the associated symbol */
 	gelf_getsym(di->dynsym_data, vr->sym_idx, &sym);
 	sym_name = elf_sym__name(&sym, di->dynstr_data);
-	demangled = demangle_sym(di->dso, 0, sym_name);
+	demangled = dso__demangle_sym(di->dso, /*kmodule=*/0, sym_name);
 	if (demangled != NULL)
 		sym_name = demangled;
 
@@ -818,7 +758,7 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss)
 		gelf_getsym(syms, get_rel_symidx(&ri, idx), &sym);
 
 		elf_name = elf_sym__name(&sym, symstrs);
-		demangled = demangle_sym(dso, 0, elf_name);
+		demangled = dso__demangle_sym(dso, /*kmodule=*/0, elf_name);
 		if (demangled)
 			elf_name = demangled;
 		if (*elf_name)
@@ -847,11 +787,6 @@ out_elf_end:
 	return 0;
 }
 
-char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
-{
-	return demangle_sym(dso, kmodule, elf_name);
-}
-
 /*
  * Align offset to 4 bytes as needed for note name and descriptor data.
  */
@@ -1840,7 +1775,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 			}
 		}
 
-		demangled = demangle_sym(dso, kmodule, elf_name);
+		demangled = dso__demangle_sym(dso, kmodule, elf_name);
 		if (demangled != NULL)
 			elf_name = demangled;
 
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index c6f369b5d893..c73fe2e09fe9 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -90,11 +90,23 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 {
 	FILE *fp;
 	int ret = -1;
-	bool need_swap = false;
+	bool need_swap = false, elf32;
 	u8 e_ident[EI_NIDENT];
-	size_t buf_size;
-	void *buf;
 	int i;
+	union {
+		struct {
+			Elf32_Ehdr ehdr32;
+			Elf32_Phdr *phdr32;
+		};
+		struct {
+			Elf64_Ehdr ehdr64;
+			Elf64_Phdr *phdr64;
+		};
+	} hdrs;
+	void *phdr;
+	size_t phdr_size;
+	void *buf = NULL;
+	size_t buf_size = 0;
 
 	fp = fopen(filename, "r");
 	if (fp == NULL)
@@ -108,117 +120,79 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 		goto out;
 
 	need_swap = check_need_swap(e_ident[EI_DATA]);
+	elf32 = e_ident[EI_CLASS] == ELFCLASS32;
 
-	/* for simplicity */
-	fseek(fp, 0, SEEK_SET);
-
-	if (e_ident[EI_CLASS] == ELFCLASS32) {
-		Elf32_Ehdr ehdr;
-		Elf32_Phdr *phdr;
-
-		if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
-			goto out;
+	if (fread(elf32 ? (void *)&hdrs.ehdr32 : (void *)&hdrs.ehdr64,
+		  elf32 ? sizeof(hdrs.ehdr32) : sizeof(hdrs.ehdr64),
+		  1, fp) != 1)
+		goto out;
 
-		if (need_swap) {
-			ehdr.e_phoff = bswap_32(ehdr.e_phoff);
-			ehdr.e_phentsize = bswap_16(ehdr.e_phentsize);
-			ehdr.e_phnum = bswap_16(ehdr.e_phnum);
+	if (need_swap) {
+		if (elf32) {
+			hdrs.ehdr32.e_phoff = bswap_32(hdrs.ehdr32.e_phoff);
+			hdrs.ehdr32.e_phentsize = bswap_16(hdrs.ehdr32.e_phentsize);
+			hdrs.ehdr32.e_phnum = bswap_16(hdrs.ehdr32.e_phnum);
+		} else {
+			hdrs.ehdr64.e_phoff = bswap_64(hdrs.ehdr64.e_phoff);
+			hdrs.ehdr64.e_phentsize = bswap_16(hdrs.ehdr64.e_phentsize);
+			hdrs.ehdr64.e_phnum = bswap_16(hdrs.ehdr64.e_phnum);
 		}
+	}
+	phdr_size = elf32 ? hdrs.ehdr32.e_phentsize * hdrs.ehdr32.e_phnum
+			  : hdrs.ehdr64.e_phentsize * hdrs.ehdr64.e_phnum;
+	phdr = malloc(phdr_size);
+	if (phdr == NULL)
+		goto out;
 
-		buf_size = ehdr.e_phentsize * ehdr.e_phnum;
-		buf = malloc(buf_size);
-		if (buf == NULL)
-			goto out;
-
-		fseek(fp, ehdr.e_phoff, SEEK_SET);
-		if (fread(buf, buf_size, 1, fp) != 1)
-			goto out_free;
-
-		for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
-			void *tmp;
-			long offset;
-
-			if (need_swap) {
-				phdr->p_type = bswap_32(phdr->p_type);
-				phdr->p_offset = bswap_32(phdr->p_offset);
-				phdr->p_filesz = bswap_32(phdr->p_filesz);
-			}
-
-			if (phdr->p_type != PT_NOTE)
-				continue;
-
-			buf_size = phdr->p_filesz;
-			offset = phdr->p_offset;
-			tmp = realloc(buf, buf_size);
-			if (tmp == NULL)
-				goto out_free;
-
-			buf = tmp;
-			fseek(fp, offset, SEEK_SET);
-			if (fread(buf, buf_size, 1, fp) != 1)
-				goto out_free;
+	fseek(fp, elf32 ? hdrs.ehdr32.e_phoff : hdrs.ehdr64.e_phoff, SEEK_SET);
+	if (fread(phdr, phdr_size, 1, fp) != 1)
+		goto out_free;
 
-			ret = read_build_id(buf, buf_size, bid, need_swap);
-			if (ret == 0) {
-				ret = bid->size;
-				break;
-			}
-		}
-	} else {
-		Elf64_Ehdr ehdr;
-		Elf64_Phdr *phdr;
+	if (elf32)
+		hdrs.phdr32 = phdr;
+	else
+		hdrs.phdr64 = phdr;
 
-		if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
-			goto out;
+	for (i = 0; i < elf32 ? hdrs.ehdr32.e_phnum : hdrs.ehdr64.e_phnum; i++) {
+		size_t p_filesz;
 
 		if (need_swap) {
-			ehdr.e_phoff = bswap_64(ehdr.e_phoff);
-			ehdr.e_phentsize = bswap_16(ehdr.e_phentsize);
-			ehdr.e_phnum = bswap_16(ehdr.e_phnum);
+			if (elf32) {
+				hdrs.phdr32[i].p_type = bswap_32(hdrs.phdr32[i].p_type);
+				hdrs.phdr32[i].p_offset = bswap_32(hdrs.phdr32[i].p_offset);
+				hdrs.phdr32[i].p_filesz = bswap_32(hdrs.phdr32[i].p_offset);
+			} else {
+				hdrs.phdr64[i].p_type = bswap_32(hdrs.phdr64[i].p_type);
+				hdrs.phdr64[i].p_offset = bswap_64(hdrs.phdr64[i].p_offset);
+				hdrs.phdr64[i].p_filesz = bswap_64(hdrs.phdr64[i].p_filesz);
+			}
 		}
+		if ((elf32 ? hdrs.phdr32[i].p_type : hdrs.phdr64[i].p_type) != PT_NOTE)
+			continue;
 
-		buf_size = ehdr.e_phentsize * ehdr.e_phnum;
-		buf = malloc(buf_size);
-		if (buf == NULL)
-			goto out;
-
-		fseek(fp, ehdr.e_phoff, SEEK_SET);
-		if (fread(buf, buf_size, 1, fp) != 1)
-			goto out_free;
-
-		for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
+		p_filesz = elf32 ? hdrs.phdr32[i].p_filesz : hdrs.phdr64[i].p_filesz;
+		if (p_filesz > buf_size) {
 			void *tmp;
-			long offset;
-
-			if (need_swap) {
-				phdr->p_type = bswap_32(phdr->p_type);
-				phdr->p_offset = bswap_64(phdr->p_offset);
-				phdr->p_filesz = bswap_64(phdr->p_filesz);
-			}
-
-			if (phdr->p_type != PT_NOTE)
-				continue;
 
-			buf_size = phdr->p_filesz;
-			offset = phdr->p_offset;
+			buf_size = p_filesz;
 			tmp = realloc(buf, buf_size);
 			if (tmp == NULL)
 				goto out_free;
-
 			buf = tmp;
-			fseek(fp, offset, SEEK_SET);
-			if (fread(buf, buf_size, 1, fp) != 1)
-				goto out_free;
+		}
+		fseek(fp, elf32 ? hdrs.phdr32[i].p_offset : hdrs.phdr64[i].p_offset, SEEK_SET);
+		if (fread(buf, p_filesz, 1, fp) != 1)
+			goto out_free;
 
-			ret = read_build_id(buf, buf_size, bid, need_swap);
-			if (ret == 0) {
-				ret = bid->size;
-				break;
-			}
+		ret = read_build_id(buf, p_filesz, bid, need_swap);
+		if (ret == 0) {
+			ret = bid->size;
+			break;
 		}
 	}
 out_free:
 	free(buf);
+	free(phdr);
 out:
 	fclose(fp);
 	return ret;
@@ -381,13 +355,6 @@ void symbol__elf_init(void)
 {
 }
 
-char *dso__demangle_sym(struct dso *dso __maybe_unused,
-			int kmodule __maybe_unused,
-			const char *elf_name __maybe_unused)
-{
-	return NULL;
-}
-
 bool filename__has_section(const char *filename __maybe_unused, const char *sec __maybe_unused)
 {
 	return false;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 11540219481b..8b30c6f16a9e 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -19,6 +19,11 @@
 #include "build-id.h"
 #include "cap.h"
 #include "cpumap.h"
+#include "debug.h"
+#include "demangle-cxx.h"
+#include "demangle-java.h"
+#include "demangle-ocaml.h"
+#include "demangle-rust-v0.h"
 #include "dso.h"
 #include "util.h" // lsdir()
 #include "debug.h"
@@ -36,6 +41,7 @@
 #include "header.h"
 #include "path.h"
 #include <linux/ctype.h>
+#include <linux/log2.h>
 #include <linux/zalloc.h>
 
 #include <elf.h>
@@ -98,10 +104,12 @@ static enum dso_binary_type binary_type_symtab[] = {
 
 #define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab)
 
-static bool symbol_type__filter(char symbol_type)
+static bool symbol_type__filter(char __symbol_type)
 {
-	symbol_type = toupper(symbol_type);
-	return symbol_type == 'T' || symbol_type == 'W' || symbol_type == 'D' || symbol_type == 'B';
+	// Since 'U' == undefined and 'u' == unique global symbol, we can't use toupper there
+	char symbol_type = toupper(__symbol_type);
+	return symbol_type == 'T' || symbol_type == 'W' || symbol_type == 'D' || symbol_type == 'B' ||
+	       __symbol_type == 'u' || __symbol_type == 'l';
 }
 
 static int prefix_underscores_count(const char *str)
@@ -2646,3 +2654,79 @@ int symbol__validate_sym_arguments(void)
 	}
 	return 0;
 }
+
+static bool want_demangle(bool is_kernel_sym)
+{
+	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
+}
+
+/*
+ * Demangle C++ function signature, typically replaced by demangle-cxx.cpp
+ * version.
+ */
+#ifndef HAVE_CXA_DEMANGLE_SUPPORT
+char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused,
+		       bool modifiers __maybe_unused)
+{
+#ifdef HAVE_LIBBFD_SUPPORT
+	int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0);
+
+	return bfd_demangle(NULL, str, flags);
+#elif defined(HAVE_CPLUS_DEMANGLE_SUPPORT)
+	int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0);
+
+	return cplus_demangle(str, flags);
+#else
+	return NULL;
+#endif
+}
+#endif /* !HAVE_CXA_DEMANGLE_SUPPORT */
+
+char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
+{
+	struct demangle rust_demangle = {
+		.style = DemangleStyleUnknown,
+	};
+	char *demangled = NULL;
+
+	/*
+	 * We need to figure out if the object was created from C++ sources
+	 * DWARF DW_compile_unit has this, but we don't always have access
+	 * to it...
+	 */
+	if (!want_demangle((dso && dso__kernel(dso)) || kmodule))
+		return demangled;
+
+	rust_demangle_demangle(elf_name, &rust_demangle);
+	if (rust_demangle_is_known(&rust_demangle)) {
+		/* A rust mangled name. */
+		if (rust_demangle.mangled_len == 0)
+			return demangled;
+
+		for (size_t buf_len = roundup_pow_of_two(rust_demangle.mangled_len * 2);
+		     buf_len < 1024 * 1024; buf_len += 32) {
+			char *tmp = realloc(demangled, buf_len);
+
+			if (!tmp) {
+				/* Failure to grow output buffer, return what is there. */
+				return demangled;
+			}
+			demangled = tmp;
+			if (rust_demangle_display_demangle(&rust_demangle, demangled, buf_len,
+							   /*alternate=*/true) == OverflowOk)
+				return demangled;
+		}
+		/* Buffer exceeded sensible bounds, return what is there. */
+		return demangled;
+	}
+
+	demangled = cxx_demangle_sym(elf_name, verbose > 0, verbose > 0);
+	if (demangled)
+		return demangled;
+
+	demangled = ocaml_demangle_sym(elf_name);
+	if (demangled)
+		return demangled;
+
+	return java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
+}
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 89585f53c1d5..ffb48cc2103f 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -410,7 +410,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bo
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
-					struct addr_location *al)
+					bool symbols, struct addr_location *al)
 {
 	size_t i;
 	const u8 cpumodes[] = {
@@ -421,7 +421,11 @@ void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
 	};
 
 	for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
-		thread__find_symbol(thread, cpumodes[i], addr, al);
+		if (symbols)
+			thread__find_symbol(thread, cpumodes[i], addr, al);
+		else
+			thread__find_map(thread, cpumodes[i], addr, al);
+
 		if (al->map)
 			break;
 	}
@@ -471,6 +475,7 @@ uint16_t thread__e_machine(struct thread *thread, struct machine *machine)
 
 		if (parent) {
 			e_machine = thread__e_machine(parent, machine);
+			thread__put(parent);
 			thread__set_e_machine(thread, e_machine);
 			return e_machine;
 		}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index cd574a896418..2b90bbed7a61 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -126,7 +126,7 @@ struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode,
 				      u64 addr, struct addr_location *al);
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
-					struct addr_location *al);
+					bool symbols, struct addr_location *al);
 
 int thread__memcpy(struct thread *thread, struct machine *machine,
 		   void *buf, u64 ip, int len, bool *is64bit);
diff --git a/tools/perf/util/tool.c b/tools/perf/util/tool.c
index 3b7f390f26eb..37bd8ac63b01 100644
--- a/tools/perf/util/tool.c
+++ b/tools/perf/util/tool.c
@@ -43,8 +43,15 @@ static int perf_session__process_compressed_event(struct perf_session *session,
 		decomp->size = decomp_last_rem;
 	}
 
-	src = (void *)event + sizeof(struct perf_record_compressed);
-	src_size = event->pack.header.size - sizeof(struct perf_record_compressed);
+	if (event->header.type == PERF_RECORD_COMPRESSED) {
+		src = (void *)event + sizeof(struct perf_record_compressed);
+		src_size = event->pack.header.size - sizeof(struct perf_record_compressed);
+	} else if (event->header.type == PERF_RECORD_COMPRESSED2) {
+		src = (void *)event + sizeof(struct perf_record_compressed2);
+		src_size = event->pack2.data_size;
+	} else {
+		return -1;
+	}
 
 	decomp_size = zstd_decompress_stream(session->active_decomp->zstd_decomp, src, src_size,
 				&(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem);
diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c
index 97b327d1ce4a..4630b8cc8e52 100644
--- a/tools/perf/util/tool_pmu.c
+++ b/tools/perf/util/tool_pmu.c
@@ -486,8 +486,14 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread)
 		delta_start *= 1000000000 / ticks_per_sec;
 	}
 	count->val    = delta_start;
-	count->ena    = count->run = delta_start;
 	count->lost   = 0;
+	/*
+	 * The values of enabled and running must make a ratio of 100%. The
+	 * exact values don't matter as long as they are non-zero to avoid
+	 * issues with evsel__count_has_error.
+	 */
+	count->ena++;
+	count->run++;
 	return 0;
 }
 
@@ -496,19 +502,12 @@ struct perf_pmu *tool_pmu__new(void)
 	struct perf_pmu *tool = zalloc(sizeof(struct perf_pmu));
 
 	if (!tool)
-		goto out;
-	tool->name = strdup("tool");
-	if (!tool->name) {
-		zfree(&tool);
-		goto out;
-	}
+		return NULL;
 
-	tool->type = PERF_PMU_TYPE_TOOL;
-	INIT_LIST_HEAD(&tool->aliases);
-	INIT_LIST_HEAD(&tool->caps);
-	INIT_LIST_HEAD(&tool->format);
+	if (perf_pmu__init(tool, PERF_PMU_TYPE_TOOL, "tool") != 0) {
+		perf_pmu__delete(tool);
+		return NULL;
+	}
 	tool->events_table = find_core_events_table("common", "common");
-
-out:
 	return tool;
 }
diff --git a/tools/perf/util/trace.h b/tools/perf/util/trace.h
new file mode 100644
index 000000000000..fa8d480527a2
--- /dev/null
+++ b/tools/perf/util/trace.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef UTIL_TRACE_H
+#define UTIL_TRACE_H
+
+#include <stdio.h>  /* for FILE */
+
+enum trace_summary_mode {
+	SUMMARY__NONE = 0,
+	SUMMARY__BY_TOTAL,
+	SUMMARY__BY_THREAD,
+	SUMMARY__BY_CGROUP,
+};
+
+#ifdef HAVE_BPF_SKEL
+
+int trace_prepare_bpf_summary(enum trace_summary_mode mode);
+void trace_start_bpf_summary(void);
+void trace_end_bpf_summary(void);
+int trace_print_bpf_summary(FILE *fp);
+void trace_cleanup_bpf_summary(void);
+
+#else /* !HAVE_BPF_SKEL */
+
+static inline int trace_prepare_bpf_summary(enum trace_summary_mode mode __maybe_unused)
+{
+	return -1;
+}
+static inline void trace_start_bpf_summary(void) {}
+static inline void trace_end_bpf_summary(void) {}
+static inline int trace_print_bpf_summary(FILE *fp __maybe_unused)
+{
+	return 0;
+}
+static inline void trace_cleanup_bpf_summary(void) {}
+
+#endif /* HAVE_BPF_SKEL */
+
+#endif /* UTIL_TRACE_H */
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index 387f3df8b988..31a2d73c963f 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -67,6 +67,7 @@ cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o
 cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o
 cxl_core-$(CONFIG_CXL_MCE) += $(CXL_CORE_SRC)/mce.o
 cxl_core-$(CONFIG_CXL_FEATURES) += $(CXL_CORE_SRC)/features.o
+cxl_core-$(CONFIG_CXL_EDAC_MEM_FEATURES) += $(CXL_CORE_SRC)/edac.o
 cxl_core-y += config_check.o
 cxl_core-y += cxl_core_test.o
 cxl_core-y += cxl_core_exports.o
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index 1c3336095923..8a5815ca870d 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -1527,5 +1527,6 @@ MODULE_PARM_DESC(interleave_arithmetic, "Modulo:0, XOR:1");
 module_init(cxl_test_init);
 module_exit(cxl_test_exit);
 MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("cxl_test: setup module");
 MODULE_IMPORT_NS("ACPI");
 MODULE_IMPORT_NS("CXL");
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index bf9caa908f89..0f1d91f57ba3 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -1909,4 +1909,5 @@ static struct platform_driver cxl_mock_mem_driver = {
 
 module_platform_driver(cxl_mock_mem_driver);
 MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("cxl_test: mem device mock module");
 MODULE_IMPORT_NS("CXL");
diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c
index af2594e4f35d..1989ae020df3 100644
--- a/tools/testing/cxl/test/mock.c
+++ b/tools/testing/cxl/test/mock.c
@@ -312,5 +312,6 @@ void __wrap_cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device
 EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dport_init_ras_reporting, "CXL");
 
 MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("cxl_test: emulation module");
 MODULE_IMPORT_NS("ACPI");
 MODULE_IMPORT_NS("CXL");
diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config
index e70c502a16df..422e186cf3cf 100644
--- a/tools/testing/kunit/configs/all_tests.config
+++ b/tools/testing/kunit/configs/all_tests.config
@@ -10,7 +10,6 @@ CONFIG_KUNIT_EXAMPLE_TEST=y
 CONFIG_KUNIT_ALL_TESTS=y
 
 CONFIG_FORTIFY_SOURCE=y
-CONFIG_INIT_STACK_ALL_PATTERN=y
 
 CONFIG_IIO=y
 
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 6aa11cd3db42..339b31e6a6b5 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -205,7 +205,7 @@ export KHDR_INCLUDES
 
 all:
 	@ret=1;							\
-	for TARGET in $(TARGETS); do				\
+	for TARGET in $(TARGETS) $(INSTALL_DEP_TARGETS); do	\
 		BUILD_TARGET=$$BUILD/$$TARGET;			\
 		mkdir $$BUILD_TARGET  -p;			\
 		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET	\
diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c
index 69f81cb555ca..d93f68024cc6 100644
--- a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c
+++ b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c
@@ -57,15 +57,15 @@ int BPF_PROG(test_percpu_load, struct cgroup *cgrp, const char *path)
 SEC("tp_btf/cgroup_mkdir")
 int BPF_PROG(test_percpu_helper, struct cgroup *cgrp, const char *path)
 {
-	struct cgroup_rstat_cpu *rstat;
+	struct css_rstat_cpu *rstat;
 	__u32 cpu;
 
 	cpu = bpf_get_smp_processor_id();
-	rstat = (struct cgroup_rstat_cpu *)bpf_per_cpu_ptr(
+	rstat = (struct css_rstat_cpu *)bpf_per_cpu_ptr(
 			cgrp->self.rstat_cpu, cpu);
 	if (rstat) {
 		/* READ_ONCE */
-		*(volatile int *)rstat;
+		*(volatile long *)rstat;
 	}
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
index e6c248e3ae54..e9e918cdf31f 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
@@ -385,7 +385,7 @@ int bpf_testmod_fentry_ok;
 
 noinline ssize_t
 bpf_testmod_test_read(struct file *file, struct kobject *kobj,
-		      struct bin_attribute *bin_attr,
+		      const struct bin_attribute *bin_attr,
 		      char *buf, loff_t off, size_t len)
 {
 	struct bpf_testmod_test_read_ctx ctx = {
@@ -465,7 +465,7 @@ ALLOW_ERROR_INJECTION(bpf_testmod_test_read, ERRNO);
 
 noinline ssize_t
 bpf_testmod_test_write(struct file *file, struct kobject *kobj,
-		      struct bin_attribute *bin_attr,
+		      const struct bin_attribute *bin_attr,
 		      char *buf, loff_t off, size_t len)
 {
 	struct bpf_testmod_test_write_ctx ctx = {
@@ -567,7 +567,7 @@ static void testmod_unregister_uprobe(void)
 
 static ssize_t
 bpf_testmod_uprobe_write(struct file *file, struct kobject *kobj,
-			 struct bin_attribute *bin_attr,
+			 const struct bin_attribute *bin_attr,
 			 char *buf, loff_t off, size_t len)
 {
 	unsigned long offset = 0;
diff --git a/tools/testing/selftests/damon/_damon_sysfs.py b/tools/testing/selftests/damon/_damon_sysfs.py
index 1e587e0b1a39..5b1cb6b3ce4e 100644
--- a/tools/testing/selftests/damon/_damon_sysfs.py
+++ b/tools/testing/selftests/damon/_damon_sysfs.py
@@ -15,6 +15,10 @@ if sysfs_root is None:
     print('Seems sysfs not mounted?')
     exit(ksft_skip)
 
+if not os.path.exists(sysfs_root):
+    print('Seems DAMON disabled?')
+    exit(ksft_skip)
+
 def write_file(path, string):
     "Returns error string if failed, or None otherwise"
     string = '%s' % string
diff --git a/tools/testing/selftests/drivers/net/hw/config b/tools/testing/selftests/drivers/net/hw/config
new file mode 100644
index 000000000000..88ae719e6f8f
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/config
@@ -0,0 +1,5 @@
+CONFIG_IPV6=y
+CONFIG_IPV6_GRE=y
+CONFIG_NET_IPGRE=y
+CONFIG_NET_IPGRE_DEMUX=y
+CONFIG_VXLAN=y
diff --git a/tools/testing/selftests/drivers/net/hw/tso.py b/tools/testing/selftests/drivers/net/hw/tso.py
index e1ecb92f79d9..3370827409aa 100755
--- a/tools/testing/selftests/drivers/net/hw/tso.py
+++ b/tools/testing/selftests/drivers/net/hw/tso.py
@@ -39,7 +39,7 @@ def run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso):
     port = rand_port()
     listen_cmd = f"socat -{ipver} -t 2 -u TCP-LISTEN:{port},reuseport /dev/null,ignoreeof"
 
-    with bkg(listen_cmd, host=cfg.remote) as nc:
+    with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as nc:
         wait_port_listen(port, host=cfg.remote)
 
         if ipver == "4":
@@ -216,7 +216,7 @@ def main() -> None:
             ("",            "6", "tx-tcp6-segmentation",          None),
             ("vxlan",        "", "tx-udp_tnl-segmentation",       ("vxlan",  True,  "id 100 dstport 4789 noudpcsum")),
             ("vxlan_csum",   "", "tx-udp_tnl-csum-segmentation",  ("vxlan",  False, "id 100 dstport 4789 udpcsum")),
-            ("gre",         "4", "tx-gre-segmentation",           ("ipgre",  False,  "")),
+            ("gre",         "4", "tx-gre-segmentation",           ("gre",    False,  "")),
             ("gre",         "6", "tx-gre-segmentation",           ("ip6gre", False,  "")),
         )
 
diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index b6cfe0a4b7df..dbbcc5eb3dce 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -112,9 +112,12 @@ struct comm_pipes {
 
 static int setup_comm_pipes(struct comm_pipes *comm_pipes)
 {
-	if (pipe(comm_pipes->child_ready) < 0)
+	if (pipe(comm_pipes->child_ready) < 0) {
+		ksft_perror("pipe()");
 		return -errno;
+	}
 	if (pipe(comm_pipes->parent_ready) < 0) {
+		ksft_perror("pipe()");
 		close(comm_pipes->child_ready[0]);
 		close(comm_pipes->child_ready[1]);
 		return -errno;
@@ -207,13 +210,14 @@ static void do_test_cow_in_parent(char *mem, size_t size, bool do_mprotect,
 
 	ret = setup_comm_pipes(&comm_pipes);
 	if (ret) {
-		ksft_test_result_fail("pipe() failed\n");
+		log_test_result(KSFT_FAIL);
 		return;
 	}
 
 	ret = fork();
 	if (ret < 0) {
-		ksft_test_result_fail("fork() failed\n");
+		ksft_perror("fork() failed");
+		log_test_result(KSFT_FAIL);
 		goto close_comm_pipes;
 	} else if (!ret) {
 		exit(fn(mem, size, &comm_pipes));
@@ -228,9 +232,18 @@ static void do_test_cow_in_parent(char *mem, size_t size, bool do_mprotect,
 		 * write-faults by directly mapping pages writable.
 		 */
 		ret = mprotect(mem, size, PROT_READ);
-		ret |= mprotect(mem, size, PROT_READ|PROT_WRITE);
 		if (ret) {
-			ksft_test_result_fail("mprotect() failed\n");
+			ksft_perror("mprotect() failed");
+			log_test_result(KSFT_FAIL);
+			write(comm_pipes.parent_ready[1], "0", 1);
+			wait(&ret);
+			goto close_comm_pipes;
+		}
+
+		ret = mprotect(mem, size, PROT_READ|PROT_WRITE);
+		if (ret) {
+			ksft_perror("mprotect() failed");
+			log_test_result(KSFT_FAIL);
 			write(comm_pipes.parent_ready[1], "0", 1);
 			wait(&ret);
 			goto close_comm_pipes;
@@ -248,16 +261,16 @@ static void do_test_cow_in_parent(char *mem, size_t size, bool do_mprotect,
 		ret = -EINVAL;
 
 	if (!ret) {
-		ksft_test_result_pass("No leak from parent into child\n");
+		log_test_result(KSFT_PASS);
 	} else if (xfail) {
 		/*
 		 * With hugetlb, some vmsplice() tests are currently expected to
 		 * fail because (a) harder to fix and (b) nobody really cares.
 		 * Flag them as expected failure for now.
 		 */
-		ksft_test_result_xfail("Leak from parent into child\n");
+		log_test_result(KSFT_XFAIL);
 	} else {
-		ksft_test_result_fail("Leak from parent into child\n");
+		log_test_result(KSFT_FAIL);
 	}
 close_comm_pipes:
 	close_comm_pipes(&comm_pipes);
@@ -306,26 +319,29 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size,
 
 	ret = setup_comm_pipes(&comm_pipes);
 	if (ret) {
-		ksft_test_result_fail("pipe() failed\n");
+		log_test_result(KSFT_FAIL);
 		goto free;
 	}
 
 	if (pipe(fds) < 0) {
-		ksft_test_result_fail("pipe() failed\n");
+		ksft_perror("pipe() failed");
+		log_test_result(KSFT_FAIL);
 		goto close_comm_pipes;
 	}
 
 	if (before_fork) {
 		transferred = vmsplice(fds[1], &iov, 1, 0);
 		if (transferred <= 0) {
-			ksft_test_result_fail("vmsplice() failed\n");
+			ksft_print_msg("vmsplice() failed\n");
+			log_test_result(KSFT_FAIL);
 			goto close_pipe;
 		}
 	}
 
 	ret = fork();
 	if (ret < 0) {
-		ksft_test_result_fail("fork() failed\n");
+		ksft_perror("fork() failed\n");
+		log_test_result(KSFT_FAIL);
 		goto close_pipe;
 	} else if (!ret) {
 		write(comm_pipes.child_ready[1], "0", 1);
@@ -339,7 +355,8 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size,
 	if (!before_fork) {
 		transferred = vmsplice(fds[1], &iov, 1, 0);
 		if (transferred <= 0) {
-			ksft_test_result_fail("vmsplice() failed\n");
+			ksft_perror("vmsplice() failed");
+			log_test_result(KSFT_FAIL);
 			wait(&ret);
 			goto close_pipe;
 		}
@@ -348,7 +365,8 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size,
 	while (read(comm_pipes.child_ready[0], &buf, 1) != 1)
 		;
 	if (munmap(mem, size) < 0) {
-		ksft_test_result_fail("munmap() failed\n");
+		ksft_perror("munmap() failed");
+		log_test_result(KSFT_FAIL);
 		goto close_pipe;
 	}
 	write(comm_pipes.parent_ready[1], "0", 1);
@@ -356,7 +374,8 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size,
 	/* Wait until the child is done writing. */
 	wait(&ret);
 	if (!WIFEXITED(ret)) {
-		ksft_test_result_fail("wait() failed\n");
+		ksft_perror("wait() failed");
+		log_test_result(KSFT_FAIL);
 		goto close_pipe;
 	}
 
@@ -364,22 +383,23 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size,
 	for (total = 0; total < transferred; total += cur) {
 		cur = read(fds[0], new + total, transferred - total);
 		if (cur < 0) {
-			ksft_test_result_fail("read() failed\n");
+			ksft_perror("read() failed");
+			log_test_result(KSFT_FAIL);
 			goto close_pipe;
 		}
 	}
 
 	if (!memcmp(old, new, transferred)) {
-		ksft_test_result_pass("No leak from child into parent\n");
+		log_test_result(KSFT_PASS);
 	} else if (xfail) {
 		/*
 		 * With hugetlb, some vmsplice() tests are currently expected to
 		 * fail because (a) harder to fix and (b) nobody really cares.
 		 * Flag them as expected failure for now.
 		 */
-		ksft_test_result_xfail("Leak from child into parent\n");
+		log_test_result(KSFT_XFAIL);
 	} else {
-		ksft_test_result_fail("Leak from child into parent\n");
+		log_test_result(KSFT_FAIL);
 	}
 close_pipe:
 	close(fds[0]);
@@ -416,13 +436,14 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork)
 
 	ret = setup_comm_pipes(&comm_pipes);
 	if (ret) {
-		ksft_test_result_fail("pipe() failed\n");
+		log_test_result(KSFT_FAIL);
 		return;
 	}
 
 	file = tmpfile();
 	if (!file) {
-		ksft_test_result_fail("tmpfile() failed\n");
+		ksft_perror("tmpfile() failed");
+		log_test_result(KSFT_FAIL);
 		goto close_comm_pipes;
 	}
 	fd = fileno(file);
@@ -430,14 +451,16 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork)
 
 	tmp = malloc(size);
 	if (!tmp) {
-		ksft_test_result_fail("malloc() failed\n");
+		ksft_print_msg("malloc() failed\n");
+		log_test_result(KSFT_FAIL);
 		goto close_file;
 	}
 
 	/* Skip on errors, as we might just lack kernel support. */
 	ret = io_uring_queue_init(1, &ring, 0);
 	if (ret < 0) {
-		ksft_test_result_skip("io_uring_queue_init() failed\n");
+		ksft_print_msg("io_uring_queue_init() failed\n");
+		log_test_result(KSFT_SKIP);
 		goto free_tmp;
 	}
 
@@ -452,7 +475,8 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork)
 	iov.iov_len = size;
 	ret = io_uring_register_buffers(&ring, &iov, 1);
 	if (ret) {
-		ksft_test_result_skip("io_uring_register_buffers() failed\n");
+		ksft_print_msg("io_uring_register_buffers() failed\n");
+		log_test_result(KSFT_SKIP);
 		goto queue_exit;
 	}
 
@@ -463,7 +487,8 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork)
 		 */
 		ret = fork();
 		if (ret < 0) {
-			ksft_test_result_fail("fork() failed\n");
+			ksft_perror("fork() failed");
+			log_test_result(KSFT_FAIL);
 			goto unregister_buffers;
 		} else if (!ret) {
 			write(comm_pipes.child_ready[1], "0", 1);
@@ -483,10 +508,17 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork)
 		 * if the page is mapped R/O vs. R/W).
 		 */
 		ret = mprotect(mem, size, PROT_READ);
+		if (ret) {
+			ksft_perror("mprotect() failed");
+			log_test_result(KSFT_FAIL);
+			goto unregister_buffers;
+		}
+
 		clear_softdirty();
-		ret |= mprotect(mem, size, PROT_READ | PROT_WRITE);
+		ret = mprotect(mem, size, PROT_READ | PROT_WRITE);
 		if (ret) {
-			ksft_test_result_fail("mprotect() failed\n");
+			ksft_perror("mprotect() failed");
+			log_test_result(KSFT_FAIL);
 			goto unregister_buffers;
 		}
 	}
@@ -498,25 +530,29 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork)
 	memset(mem, 0xff, size);
 	sqe = io_uring_get_sqe(&ring);
 	if (!sqe) {
-		ksft_test_result_fail("io_uring_get_sqe() failed\n");
+		ksft_print_msg("io_uring_get_sqe() failed\n");
+		log_test_result(KSFT_FAIL);
 		goto quit_child;
 	}
 	io_uring_prep_write_fixed(sqe, fd, mem, size, 0, 0);
 
 	ret = io_uring_submit(&ring);
 	if (ret < 0) {
-		ksft_test_result_fail("io_uring_submit() failed\n");
+		ksft_print_msg("io_uring_submit() failed\n");
+		log_test_result(KSFT_FAIL);
 		goto quit_child;
 	}
 
 	ret = io_uring_wait_cqe(&ring, &cqe);
 	if (ret < 0) {
-		ksft_test_result_fail("io_uring_wait_cqe() failed\n");
+		ksft_print_msg("io_uring_wait_cqe() failed\n");
+		log_test_result(KSFT_FAIL);
 		goto quit_child;
 	}
 
 	if (cqe->res != size) {
-		ksft_test_result_fail("write_fixed failed\n");
+		ksft_print_msg("write_fixed failed\n");
+		log_test_result(KSFT_FAIL);
 		goto quit_child;
 	}
 	io_uring_cqe_seen(&ring, cqe);
@@ -526,15 +562,18 @@ static void do_test_iouring(char *mem, size_t size, bool use_fork)
 	while (total < size) {
 		cur = pread(fd, tmp + total, size - total, total);
 		if (cur < 0) {
-			ksft_test_result_fail("pread() failed\n");
+			ksft_print_msg("pread() failed\n");
+			log_test_result(KSFT_FAIL);
 			goto quit_child;
 		}
 		total += cur;
 	}
 
 	/* Finally, check if we read what we expected. */
-	ksft_test_result(!memcmp(mem, tmp, size),
-			 "Longterm R/W pin is reliable\n");
+	if (!memcmp(mem, tmp, size))
+		log_test_result(KSFT_PASS);
+	else
+		log_test_result(KSFT_FAIL);
 
 quit_child:
 	if (use_fork) {
@@ -582,19 +621,21 @@ static void do_test_ro_pin(char *mem, size_t size, enum ro_pin_test test,
 	int ret;
 
 	if (gup_fd < 0) {
-		ksft_test_result_skip("gup_test not available\n");
+		ksft_print_msg("gup_test not available\n");
+		log_test_result(KSFT_SKIP);
 		return;
 	}
 
 	tmp = malloc(size);
 	if (!tmp) {
-		ksft_test_result_fail("malloc() failed\n");
+		ksft_print_msg("malloc() failed\n");
+		log_test_result(KSFT_FAIL);
 		return;
 	}
 
 	ret = setup_comm_pipes(&comm_pipes);
 	if (ret) {
-		ksft_test_result_fail("pipe() failed\n");
+		log_test_result(KSFT_FAIL);
 		goto free_tmp;
 	}
 
@@ -609,7 +650,8 @@ static void do_test_ro_pin(char *mem, size_t size, enum ro_pin_test test,
 		 */
 		ret = fork();
 		if (ret < 0) {
-			ksft_test_result_fail("fork() failed\n");
+			ksft_perror("fork() failed");
+			log_test_result(KSFT_FAIL);
 			goto close_comm_pipes;
 		} else if (!ret) {
 			write(comm_pipes.child_ready[1], "0", 1);
@@ -646,7 +688,8 @@ static void do_test_ro_pin(char *mem, size_t size, enum ro_pin_test test,
 		clear_softdirty();
 		ret |= mprotect(mem, size, PROT_READ | PROT_WRITE);
 		if (ret) {
-			ksft_test_result_fail("mprotect() failed\n");
+			ksft_perror("mprotect() failed");
+			log_test_result(KSFT_FAIL);
 			goto close_comm_pipes;
 		}
 		break;
@@ -661,9 +704,11 @@ static void do_test_ro_pin(char *mem, size_t size, enum ro_pin_test test,
 	ret = ioctl(gup_fd, PIN_LONGTERM_TEST_START, &args);
 	if (ret) {
 		if (errno == EINVAL)
-			ksft_test_result_skip("PIN_LONGTERM_TEST_START failed\n");
+			ret = KSFT_SKIP;
 		else
-			ksft_test_result_fail("PIN_LONGTERM_TEST_START failed\n");
+			ret = KSFT_FAIL;
+		ksft_perror("PIN_LONGTERM_TEST_START failed");
+		log_test_result(ret);
 		goto wait;
 	}
 
@@ -676,22 +721,26 @@ static void do_test_ro_pin(char *mem, size_t size, enum ro_pin_test test,
 	 */
 	tmp_val = (__u64)(uintptr_t)tmp;
 	ret = ioctl(gup_fd, PIN_LONGTERM_TEST_READ, &tmp_val);
-	if (ret)
-		ksft_test_result_fail("PIN_LONGTERM_TEST_READ failed\n");
-	else
-		ksft_test_result(!memcmp(mem, tmp, size),
-				 "Longterm R/O pin is reliable\n");
+	if (ret) {
+		ksft_perror("PIN_LONGTERM_TEST_READ failed");
+		log_test_result(KSFT_FAIL);
+	} else {
+		if (!memcmp(mem, tmp, size))
+			log_test_result(KSFT_PASS);
+		else
+			log_test_result(KSFT_FAIL);
+	}
 
 	ret = ioctl(gup_fd, PIN_LONGTERM_TEST_STOP);
 	if (ret)
-		ksft_print_msg("[INFO] PIN_LONGTERM_TEST_STOP failed\n");
+		ksft_perror("PIN_LONGTERM_TEST_STOP failed");
 wait:
 	switch (test) {
 	case RO_PIN_TEST_SHARED:
 		write(comm_pipes.parent_ready[1], "0", 1);
 		wait(&ret);
 		if (!WIFEXITED(ret))
-			ksft_print_msg("[INFO] wait() failed\n");
+			ksft_perror("wait() failed");
 		break;
 	default:
 		break;
@@ -746,14 +795,16 @@ static void do_run_with_base_page(test_fn fn, bool swapout)
 	mem = mmap(NULL, pagesize, PROT_READ | PROT_WRITE,
 		   MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	if (mem == MAP_FAILED) {
-		ksft_test_result_fail("mmap() failed\n");
+		ksft_perror("mmap() failed");
+		log_test_result(KSFT_FAIL);
 		return;
 	}
 
 	ret = madvise(mem, pagesize, MADV_NOHUGEPAGE);
 	/* Ignore if not around on a kernel. */
 	if (ret && errno != EINVAL) {
-		ksft_test_result_fail("MADV_NOHUGEPAGE failed\n");
+		ksft_perror("MADV_NOHUGEPAGE failed");
+		log_test_result(KSFT_FAIL);
 		goto munmap;
 	}
 
@@ -763,7 +814,8 @@ static void do_run_with_base_page(test_fn fn, bool swapout)
 	if (swapout) {
 		madvise(mem, pagesize, MADV_PAGEOUT);
 		if (!pagemap_is_swapped(pagemap_fd, mem)) {
-			ksft_test_result_skip("MADV_PAGEOUT did not work, is swap enabled?\n");
+			ksft_print_msg("MADV_PAGEOUT did not work, is swap enabled?\n");
+			log_test_result(KSFT_SKIP);
 			goto munmap;
 		}
 	}
@@ -775,13 +827,13 @@ munmap:
 
 static void run_with_base_page(test_fn fn, const char *desc)
 {
-	ksft_print_msg("[RUN] %s ... with base page\n", desc);
+	log_test_start("%s ... with base page", desc);
 	do_run_with_base_page(fn, false);
 }
 
 static void run_with_base_page_swap(test_fn fn, const char *desc)
 {
-	ksft_print_msg("[RUN] %s ... with swapped out base page\n", desc);
+	log_test_start("%s ... with swapped out base page", desc);
 	do_run_with_base_page(fn, true);
 }
 
@@ -807,7 +859,8 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize)
 	mmap_mem = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
 			MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	if (mmap_mem == MAP_FAILED) {
-		ksft_test_result_fail("mmap() failed\n");
+		ksft_perror("mmap() failed");
+		log_test_result(KSFT_FAIL);
 		return;
 	}
 
@@ -816,7 +869,8 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize)
 
 	ret = madvise(mem, thpsize, MADV_HUGEPAGE);
 	if (ret) {
-		ksft_test_result_fail("MADV_HUGEPAGE failed\n");
+		ksft_perror("MADV_HUGEPAGE failed");
+		log_test_result(KSFT_FAIL);
 		goto munmap;
 	}
 
@@ -826,7 +880,8 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize)
 	 */
 	mem[0] = 1;
 	if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) {
-		ksft_test_result_skip("Did not get a THP populated\n");
+		ksft_print_msg("Did not get a THP populated\n");
+		log_test_result(KSFT_SKIP);
 		goto munmap;
 	}
 	memset(mem, 1, thpsize);
@@ -846,12 +901,14 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize)
 		 */
 		ret = mprotect(mem + pagesize, pagesize, PROT_READ);
 		if (ret) {
-			ksft_test_result_fail("mprotect() failed\n");
+			ksft_perror("mprotect() failed");
+			log_test_result(KSFT_FAIL);
 			goto munmap;
 		}
 		ret = mprotect(mem + pagesize, pagesize, PROT_READ | PROT_WRITE);
 		if (ret) {
-			ksft_test_result_fail("mprotect() failed\n");
+			ksft_perror("mprotect() failed");
+			log_test_result(KSFT_FAIL);
 			goto munmap;
 		}
 		break;
@@ -863,7 +920,8 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize)
 		 */
 		ret = madvise(mem + pagesize, thpsize - pagesize, MADV_DONTNEED);
 		if (ret) {
-			ksft_test_result_fail("MADV_DONTNEED failed\n");
+			ksft_perror("MADV_DONTNEED failed");
+			log_test_result(KSFT_FAIL);
 			goto munmap;
 		}
 		size = pagesize;
@@ -877,13 +935,15 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize)
 		mremap_mem = mmap(NULL, mremap_size, PROT_NONE,
 				  MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 		if (mremap_mem == MAP_FAILED) {
-			ksft_test_result_fail("mmap() failed\n");
+			ksft_perror("mmap() failed");
+			log_test_result(KSFT_FAIL);
 			goto munmap;
 		}
 		tmp = mremap(mem + mremap_size, mremap_size, mremap_size,
 			     MREMAP_MAYMOVE | MREMAP_FIXED, mremap_mem);
 		if (tmp != mremap_mem) {
-			ksft_test_result_fail("mremap() failed\n");
+			ksft_perror("mremap() failed");
+			log_test_result(KSFT_FAIL);
 			goto munmap;
 		}
 		size = mremap_size;
@@ -896,12 +956,14 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize)
 		 */
 		ret = madvise(mem + pagesize, thpsize - pagesize, MADV_DONTFORK);
 		if (ret) {
-			ksft_test_result_fail("MADV_DONTFORK failed\n");
+			ksft_perror("MADV_DONTFORK failed");
+			log_test_result(KSFT_FAIL);
 			goto munmap;
 		}
 		ret = fork();
 		if (ret < 0) {
-			ksft_test_result_fail("fork() failed\n");
+			ksft_perror("fork() failed");
+			log_test_result(KSFT_FAIL);
 			goto munmap;
 		} else if (!ret) {
 			exit(0);
@@ -910,7 +972,8 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize)
 		/* Allow for sharing all pages again. */
 		ret = madvise(mem + pagesize, thpsize - pagesize, MADV_DOFORK);
 		if (ret) {
-			ksft_test_result_fail("MADV_DOFORK failed\n");
+			ksft_perror("MADV_DOFORK failed");
+			log_test_result(KSFT_FAIL);
 			goto munmap;
 		}
 		break;
@@ -924,7 +987,8 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize)
 	case THP_RUN_SINGLE_PTE_SWAPOUT:
 		madvise(mem, size, MADV_PAGEOUT);
 		if (!range_is_swapped(mem, size)) {
-			ksft_test_result_skip("MADV_PAGEOUT did not work, is swap enabled?\n");
+			ksft_print_msg("MADV_PAGEOUT did not work, is swap enabled?\n");
+			log_test_result(KSFT_SKIP);
 			goto munmap;
 		}
 		break;
@@ -941,56 +1005,56 @@ munmap:
 
 static void run_with_thp(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with THP (%zu kB)\n",
+	log_test_start("%s ... with THP (%zu kB)",
 		desc, size / 1024);
 	do_run_with_thp(fn, THP_RUN_PMD, size);
 }
 
 static void run_with_thp_swap(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with swapped-out THP (%zu kB)\n",
+	log_test_start("%s ... with swapped-out THP (%zu kB)",
 		desc, size / 1024);
 	do_run_with_thp(fn, THP_RUN_PMD_SWAPOUT, size);
 }
 
 static void run_with_pte_mapped_thp(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with PTE-mapped THP (%zu kB)\n",
+	log_test_start("%s ... with PTE-mapped THP (%zu kB)",
 		desc, size / 1024);
 	do_run_with_thp(fn, THP_RUN_PTE, size);
 }
 
 static void run_with_pte_mapped_thp_swap(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with swapped-out, PTE-mapped THP (%zu kB)\n",
+	log_test_start("%s ... with swapped-out, PTE-mapped THP (%zu kB)",
 		desc, size / 1024);
 	do_run_with_thp(fn, THP_RUN_PTE_SWAPOUT, size);
 }
 
 static void run_with_single_pte_of_thp(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with single PTE of THP (%zu kB)\n",
+	log_test_start("%s ... with single PTE of THP (%zu kB)",
 		desc, size / 1024);
 	do_run_with_thp(fn, THP_RUN_SINGLE_PTE, size);
 }
 
 static void run_with_single_pte_of_thp_swap(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with single PTE of swapped-out THP (%zu kB)\n",
+	log_test_start("%s ... with single PTE of swapped-out THP (%zu kB)",
 		desc, size / 1024);
 	do_run_with_thp(fn, THP_RUN_SINGLE_PTE_SWAPOUT, size);
 }
 
 static void run_with_partial_mremap_thp(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with partially mremap()'ed THP (%zu kB)\n",
+	log_test_start("%s ... with partially mremap()'ed THP (%zu kB)",
 		desc, size / 1024);
 	do_run_with_thp(fn, THP_RUN_PARTIAL_MREMAP, size);
 }
 
 static void run_with_partial_shared_thp(test_fn fn, const char *desc, size_t size)
 {
-	ksft_print_msg("[RUN] %s ... with partially shared THP (%zu kB)\n",
+	log_test_start("%s ... with partially shared THP (%zu kB)",
 		desc, size / 1024);
 	do_run_with_thp(fn, THP_RUN_PARTIAL_SHARED, size);
 }
@@ -1000,14 +1064,15 @@ static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize)
 	int flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB;
 	char *mem, *dummy;
 
-	ksft_print_msg("[RUN] %s ... with hugetlb (%zu kB)\n", desc,
+	log_test_start("%s ... with hugetlb (%zu kB)", desc,
 		       hugetlbsize / 1024);
 
 	flags |= __builtin_ctzll(hugetlbsize) << MAP_HUGE_SHIFT;
 
 	mem = mmap(NULL, hugetlbsize, PROT_READ | PROT_WRITE, flags, -1, 0);
 	if (mem == MAP_FAILED) {
-		ksft_test_result_skip("need more free huge pages\n");
+		ksft_perror("need more free huge pages");
+		log_test_result(KSFT_SKIP);
 		return;
 	}
 
@@ -1020,7 +1085,8 @@ static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize)
 	 */
 	dummy = mmap(NULL, hugetlbsize, PROT_READ | PROT_WRITE, flags, -1, 0);
 	if (dummy == MAP_FAILED) {
-		ksft_test_result_skip("need more free huge pages\n");
+		ksft_perror("need more free huge pages");
+		log_test_result(KSFT_SKIP);
 		goto munmap;
 	}
 	munmap(dummy, hugetlbsize);
@@ -1226,7 +1292,7 @@ static void do_test_anon_thp_collapse(char *mem, size_t size,
 
 	ret = setup_comm_pipes(&comm_pipes);
 	if (ret) {
-		ksft_test_result_fail("pipe() failed\n");
+		log_test_result(KSFT_FAIL);
 		return;
 	}
 
@@ -1236,12 +1302,14 @@ static void do_test_anon_thp_collapse(char *mem, size_t size,
 	 */
 	ret = mprotect(mem + pagesize, pagesize, PROT_READ);
 	if (ret) {
-		ksft_test_result_fail("mprotect() failed\n");
+		ksft_perror("mprotect() failed");
+		log_test_result(KSFT_FAIL);
 		goto close_comm_pipes;
 	}
 	ret = mprotect(mem + pagesize, pagesize, PROT_READ | PROT_WRITE);
 	if (ret) {
-		ksft_test_result_fail("mprotect() failed\n");
+		ksft_perror("mprotect() failed");
+		log_test_result(KSFT_FAIL);
 		goto close_comm_pipes;
 	}
 
@@ -1250,8 +1318,8 @@ static void do_test_anon_thp_collapse(char *mem, size_t size,
 		/* Collapse before actually COW-sharing the page. */
 		ret = madvise(mem, size, MADV_COLLAPSE);
 		if (ret) {
-			ksft_test_result_skip("MADV_COLLAPSE failed: %s\n",
-					      strerror(errno));
+			ksft_perror("MADV_COLLAPSE failed");
+			log_test_result(KSFT_SKIP);
 			goto close_comm_pipes;
 		}
 		break;
@@ -1262,7 +1330,8 @@ static void do_test_anon_thp_collapse(char *mem, size_t size,
 		/* Don't COW-share the upper part of the THP. */
 		ret = madvise(mem + size / 2, size / 2, MADV_DONTFORK);
 		if (ret) {
-			ksft_test_result_fail("MADV_DONTFORK failed\n");
+			ksft_perror("MADV_DONTFORK failed");
+			log_test_result(KSFT_FAIL);
 			goto close_comm_pipes;
 		}
 		break;
@@ -1270,7 +1339,8 @@ static void do_test_anon_thp_collapse(char *mem, size_t size,
 		/* Don't COW-share the lower part of the THP. */
 		ret = madvise(mem, size / 2, MADV_DONTFORK);
 		if (ret) {
-			ksft_test_result_fail("MADV_DONTFORK failed\n");
+			ksft_perror("MADV_DONTFORK failed");
+			log_test_result(KSFT_FAIL);
 			goto close_comm_pipes;
 		}
 		break;
@@ -1280,7 +1350,8 @@ static void do_test_anon_thp_collapse(char *mem, size_t size,
 
 	ret = fork();
 	if (ret < 0) {
-		ksft_test_result_fail("fork() failed\n");
+		ksft_perror("fork() failed");
+		log_test_result(KSFT_FAIL);
 		goto close_comm_pipes;
 	} else if (!ret) {
 		switch (test) {
@@ -1314,7 +1385,8 @@ static void do_test_anon_thp_collapse(char *mem, size_t size,
 		 */
 		ret = madvise(mem, size, MADV_DOFORK);
 		if (ret) {
-			ksft_test_result_fail("MADV_DOFORK failed\n");
+			ksft_perror("MADV_DOFORK failed");
+			log_test_result(KSFT_FAIL);
 			write(comm_pipes.parent_ready[1], "0", 1);
 			wait(&ret);
 			goto close_comm_pipes;
@@ -1324,8 +1396,8 @@ static void do_test_anon_thp_collapse(char *mem, size_t size,
 		/* Collapse before anyone modified the COW-shared page. */
 		ret = madvise(mem, size, MADV_COLLAPSE);
 		if (ret) {
-			ksft_test_result_skip("MADV_COLLAPSE failed: %s\n",
-					      strerror(errno));
+			ksft_perror("MADV_COLLAPSE failed");
+			log_test_result(KSFT_SKIP);
 			write(comm_pipes.parent_ready[1], "0", 1);
 			wait(&ret);
 			goto close_comm_pipes;
@@ -1345,7 +1417,10 @@ static void do_test_anon_thp_collapse(char *mem, size_t size,
 	else
 		ret = -EINVAL;
 
-	ksft_test_result(!ret, "No leak from parent into child\n");
+	if (!ret)
+		log_test_result(KSFT_PASS);
+	else
+		log_test_result(KSFT_FAIL);
 close_comm_pipes:
 	close_comm_pipes(&comm_pipes);
 }
@@ -1430,7 +1505,7 @@ static void run_anon_thp_test_cases(void)
 	for (i = 0; i < ARRAY_SIZE(anon_thp_test_cases); i++) {
 		struct test_case const *test_case = &anon_thp_test_cases[i];
 
-		ksft_print_msg("[RUN] %s\n", test_case->desc);
+		log_test_start("%s", test_case->desc);
 		do_run_with_thp(test_case->fn, THP_RUN_PMD, pmdsize);
 	}
 }
@@ -1453,8 +1528,10 @@ static void test_cow(char *mem, const char *smem, size_t size)
 	memset(mem, 0xff, size);
 
 	/* See if we still read the old values via the other mapping. */
-	ksft_test_result(!memcmp(smem, old, size),
-			 "Other mapping not modified\n");
+	if (!memcmp(smem, old, size))
+		log_test_result(KSFT_PASS);
+	else
+		log_test_result(KSFT_FAIL);
 	free(old);
 }
 
@@ -1472,18 +1549,20 @@ static void run_with_zeropage(non_anon_test_fn fn, const char *desc)
 {
 	char *mem, *smem, tmp;
 
-	ksft_print_msg("[RUN] %s ... with shared zeropage\n", desc);
+	log_test_start("%s ... with shared zeropage", desc);
 
 	mem = mmap(NULL, pagesize, PROT_READ | PROT_WRITE,
 		   MAP_PRIVATE | MAP_ANON, -1, 0);
 	if (mem == MAP_FAILED) {
-		ksft_test_result_fail("mmap() failed\n");
+		ksft_perror("mmap() failed");
+		log_test_result(KSFT_FAIL);
 		return;
 	}
 
 	smem = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0);
 	if (smem == MAP_FAILED) {
-		ksft_test_result_fail("mmap() failed\n");
+		ksft_perror("mmap() failed");
+		log_test_result(KSFT_FAIL);
 		goto munmap;
 	}
 
@@ -1504,10 +1583,11 @@ static void run_with_huge_zeropage(non_anon_test_fn fn, const char *desc)
 	size_t mmap_size;
 	int ret;
 
-	ksft_print_msg("[RUN] %s ... with huge zeropage\n", desc);
+	log_test_start("%s ... with huge zeropage", desc);
 
 	if (!has_huge_zeropage) {
-		ksft_test_result_skip("Huge zeropage not enabled\n");
+		ksft_print_msg("Huge zeropage not enabled\n");
+		log_test_result(KSFT_SKIP);
 		return;
 	}
 
@@ -1516,13 +1596,15 @@ static void run_with_huge_zeropage(non_anon_test_fn fn, const char *desc)
 	mmap_mem = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
 			MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	if (mmap_mem == MAP_FAILED) {
-		ksft_test_result_fail("mmap() failed\n");
+		ksft_perror("mmap() failed");
+		log_test_result(KSFT_FAIL);
 		return;
 	}
 	mmap_smem = mmap(NULL, mmap_size, PROT_READ,
 			 MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	if (mmap_smem == MAP_FAILED) {
-		ksft_test_result_fail("mmap() failed\n");
+		ksft_perror("mmap() failed");
+		log_test_result(KSFT_FAIL);
 		goto munmap;
 	}
 
@@ -1531,9 +1613,15 @@ static void run_with_huge_zeropage(non_anon_test_fn fn, const char *desc)
 	smem = (char *)(((uintptr_t)mmap_smem + pmdsize) & ~(pmdsize - 1));
 
 	ret = madvise(mem, pmdsize, MADV_HUGEPAGE);
+	if (ret != 0) {
+		ksft_perror("madvise()");
+		log_test_result(KSFT_FAIL);
+		goto munmap;
+	}
 	ret |= madvise(smem, pmdsize, MADV_HUGEPAGE);
-	if (ret) {
-		ksft_test_result_fail("MADV_HUGEPAGE failed\n");
+	if (ret != 0) {
+		ksft_perror("madvise()");
+		log_test_result(KSFT_FAIL);
 		goto munmap;
 	}
 
@@ -1562,29 +1650,33 @@ static void run_with_memfd(non_anon_test_fn fn, const char *desc)
 	char *mem, *smem, tmp;
 	int fd;
 
-	ksft_print_msg("[RUN] %s ... with memfd\n", desc);
+	log_test_start("%s ... with memfd", desc);
 
 	fd = memfd_create("test", 0);
 	if (fd < 0) {
-		ksft_test_result_fail("memfd_create() failed\n");
+		ksft_perror("memfd_create() failed");
+		log_test_result(KSFT_FAIL);
 		return;
 	}
 
 	/* File consists of a single page filled with zeroes. */
 	if (fallocate(fd, 0, 0, pagesize)) {
-		ksft_test_result_fail("fallocate() failed\n");
+		ksft_perror("fallocate() failed");
+		log_test_result(KSFT_FAIL);
 		goto close;
 	}
 
 	/* Create a private mapping of the memfd. */
 	mem = mmap(NULL, pagesize, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
 	if (mem == MAP_FAILED) {
-		ksft_test_result_fail("mmap() failed\n");
+		ksft_perror("mmap() failed");
+		log_test_result(KSFT_FAIL);
 		goto close;
 	}
 	smem = mmap(NULL, pagesize, PROT_READ, MAP_SHARED, fd, 0);
 	if (smem == MAP_FAILED) {
-		ksft_test_result_fail("mmap() failed\n");
+		ksft_perror("mmap() failed");
+		log_test_result(KSFT_FAIL);
 		goto munmap;
 	}
 
@@ -1607,35 +1699,40 @@ static void run_with_tmpfile(non_anon_test_fn fn, const char *desc)
 	FILE *file;
 	int fd;
 
-	ksft_print_msg("[RUN] %s ... with tmpfile\n", desc);
+	log_test_start("%s ... with tmpfile", desc);
 
 	file = tmpfile();
 	if (!file) {
-		ksft_test_result_fail("tmpfile() failed\n");
+		ksft_perror("tmpfile() failed");
+		log_test_result(KSFT_FAIL);
 		return;
 	}
 
 	fd = fileno(file);
 	if (fd < 0) {
-		ksft_test_result_skip("fileno() failed\n");
+		ksft_perror("fileno() failed");
+		log_test_result(KSFT_SKIP);
 		return;
 	}
 
 	/* File consists of a single page filled with zeroes. */
 	if (fallocate(fd, 0, 0, pagesize)) {
-		ksft_test_result_fail("fallocate() failed\n");
+		ksft_perror("fallocate() failed");
+		log_test_result(KSFT_FAIL);
 		goto close;
 	}
 
 	/* Create a private mapping of the memfd. */
 	mem = mmap(NULL, pagesize, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
 	if (mem == MAP_FAILED) {
-		ksft_test_result_fail("mmap() failed\n");
+		ksft_perror("mmap() failed");
+		log_test_result(KSFT_FAIL);
 		goto close;
 	}
 	smem = mmap(NULL, pagesize, PROT_READ, MAP_SHARED, fd, 0);
 	if (smem == MAP_FAILED) {
-		ksft_test_result_fail("mmap() failed\n");
+		ksft_perror("mmap() failed");
+		log_test_result(KSFT_FAIL);
 		goto munmap;
 	}
 
@@ -1659,20 +1756,22 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc,
 	char *mem, *smem, tmp;
 	int fd;
 
-	ksft_print_msg("[RUN] %s ... with memfd hugetlb (%zu kB)\n", desc,
+	log_test_start("%s ... with memfd hugetlb (%zu kB)", desc,
 		       hugetlbsize / 1024);
 
 	flags |= __builtin_ctzll(hugetlbsize) << MFD_HUGE_SHIFT;
 
 	fd = memfd_create("test", flags);
 	if (fd < 0) {
-		ksft_test_result_skip("memfd_create() failed\n");
+		ksft_perror("memfd_create() failed");
+		log_test_result(KSFT_SKIP);
 		return;
 	}
 
 	/* File consists of a single page filled with zeroes. */
 	if (fallocate(fd, 0, 0, hugetlbsize)) {
-		ksft_test_result_skip("need more free huge pages\n");
+		ksft_perror("need more free huge pages");
+		log_test_result(KSFT_SKIP);
 		goto close;
 	}
 
@@ -1680,12 +1779,14 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc,
 	mem = mmap(NULL, hugetlbsize, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd,
 		   0);
 	if (mem == MAP_FAILED) {
-		ksft_test_result_skip("need more free huge pages\n");
+		ksft_perror("need more free huge pages");
+		log_test_result(KSFT_SKIP);
 		goto close;
 	}
 	smem = mmap(NULL, hugetlbsize, PROT_READ, MAP_SHARED, fd, 0);
 	if (smem == MAP_FAILED) {
-		ksft_test_result_fail("mmap() failed\n");
+		ksft_perror("mmap() failed");
+		log_test_result(KSFT_FAIL);
 		goto munmap;
 	}
 
@@ -1771,7 +1872,6 @@ static int tests_per_non_anon_test_case(void)
 
 int main(int argc, char **argv)
 {
-	int err;
 	struct thp_settings default_settings;
 
 	ksft_print_header();
@@ -1811,9 +1911,5 @@ int main(int argc, char **argv)
 		thp_restore_settings();
 	}
 
-	err = ksft_get_fail_cnt();
-	if (err)
-		ksft_exit_fail_msg("%d out of %d tests failed\n",
-				   err, ksft_test_num());
-	ksft_exit_pass();
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c
index 0cd9d236649d..93af3d3760f9 100644
--- a/tools/testing/selftests/mm/guard-regions.c
+++ b/tools/testing/selftests/mm/guard-regions.c
@@ -1453,8 +1453,21 @@ TEST_F(guard_regions, uffd)
 
 	/* Set up uffd. */
 	uffd = userfaultfd(0);
-	if (uffd == -1 && errno == EPERM)
-		ksft_exit_skip("No userfaultfd permissions, try running as root.\n");
+	if (uffd == -1) {
+		switch (errno) {
+		case EPERM:
+			SKIP(return, "No userfaultfd permissions, try running as root.");
+			break;
+		case ENOSYS:
+			SKIP(return, "userfaultfd is not supported/not enabled.");
+			break;
+		default:
+			ksft_exit_fail_msg("userfaultfd failed with %s\n",
+					   strerror(errno));
+			break;
+		}
+	}
+
 	ASSERT_NE(uffd, -1);
 
 	ASSERT_EQ(ioctl(uffd, UFFDIO_API, &api), 0);
diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c
index d50ada0c7dbf..8a97ac5176a4 100644
--- a/tools/testing/selftests/mm/gup_longterm.c
+++ b/tools/testing/selftests/mm/gup_longterm.c
@@ -93,33 +93,48 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
 	__fsword_t fs_type = get_fs_type(fd);
 	bool should_work;
 	char *mem;
+	int result = KSFT_PASS;
 	int ret;
 
+	if (fd < 0) {
+		result = KSFT_FAIL;
+		goto report;
+	}
+
 	if (ftruncate(fd, size)) {
 		if (errno == ENOENT) {
 			skip_test_dodgy_fs("ftruncate()");
 		} else {
-			ksft_test_result_fail("ftruncate() failed (%s)\n", strerror(errno));
+			ksft_print_msg("ftruncate() failed (%s)\n",
+				       strerror(errno));
+			result = KSFT_FAIL;
+			goto report;
 		}
 		return;
 	}
 
 	if (fallocate(fd, 0, 0, size)) {
-		if (size == pagesize)
-			ksft_test_result_fail("fallocate() failed (%s)\n", strerror(errno));
-		else
-			ksft_test_result_skip("need more free huge pages\n");
-		return;
+		if (size == pagesize) {
+			ksft_print_msg("fallocate() failed (%s)\n", strerror(errno));
+			result = KSFT_FAIL;
+		} else {
+			ksft_print_msg("need more free huge pages\n");
+			result = KSFT_SKIP;
+		}
+		goto report;
 	}
 
 	mem = mmap(NULL, size, PROT_READ | PROT_WRITE,
 		   shared ? MAP_SHARED : MAP_PRIVATE, fd, 0);
 	if (mem == MAP_FAILED) {
-		if (size == pagesize || shared)
-			ksft_test_result_fail("mmap() failed (%s)\n", strerror(errno));
-		else
-			ksft_test_result_skip("need more free huge pages\n");
-		return;
+		if (size == pagesize || shared) {
+			ksft_print_msg("mmap() failed (%s)\n", strerror(errno));
+			result = KSFT_FAIL;
+		} else {
+			ksft_print_msg("need more free huge pages\n");
+			result = KSFT_SKIP;
+		}
+		goto report;
 	}
 
 	/* Fault in the page such that GUP-fast can pin it directly. */
@@ -134,7 +149,8 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
 		 */
 		ret = mprotect(mem, size, PROT_READ);
 		if (ret) {
-			ksft_test_result_fail("mprotect() failed (%s)\n", strerror(errno));
+			ksft_print_msg("mprotect() failed (%s)\n", strerror(errno));
+			result = KSFT_FAIL;
 			goto munmap;
 		}
 		/* FALLTHROUGH */
@@ -147,12 +163,14 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
 				type == TEST_TYPE_RW_FAST;
 
 		if (gup_fd < 0) {
-			ksft_test_result_skip("gup_test not available\n");
+			ksft_print_msg("gup_test not available\n");
+			result = KSFT_SKIP;
 			break;
 		}
 
 		if (rw && shared && fs_is_unknown(fs_type)) {
-			ksft_test_result_skip("Unknown filesystem\n");
+			ksft_print_msg("Unknown filesystem\n");
+			result = KSFT_SKIP;
 			return;
 		}
 		/*
@@ -169,14 +187,19 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
 		args.flags |= rw ? PIN_LONGTERM_TEST_FLAG_USE_WRITE : 0;
 		ret = ioctl(gup_fd, PIN_LONGTERM_TEST_START, &args);
 		if (ret && errno == EINVAL) {
-			ksft_test_result_skip("PIN_LONGTERM_TEST_START failed (EINVAL)n");
+			ksft_print_msg("PIN_LONGTERM_TEST_START failed (EINVAL)n");
+			result = KSFT_SKIP;
 			break;
 		} else if (ret && errno == EFAULT) {
-			ksft_test_result(!should_work, "Should have failed\n");
+			if (should_work)
+				result = KSFT_FAIL;
+			else
+				result = KSFT_PASS;
 			break;
 		} else if (ret) {
-			ksft_test_result_fail("PIN_LONGTERM_TEST_START failed (%s)\n",
-					      strerror(errno));
+			ksft_print_msg("PIN_LONGTERM_TEST_START failed (%s)\n",
+				       strerror(errno));
+			result = KSFT_FAIL;
 			break;
 		}
 
@@ -189,7 +212,10 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
 		 * some previously unsupported filesystems, we might want to
 		 * perform some additional tests for possible data corruptions.
 		 */
-		ksft_test_result(should_work, "Should have worked\n");
+		if (should_work)
+			result = KSFT_PASS;
+		else
+			result = KSFT_FAIL;
 		break;
 	}
 #ifdef LOCAL_CONFIG_HAVE_LIBURING
@@ -199,8 +225,9 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
 
 		/* io_uring always pins pages writable. */
 		if (shared && fs_is_unknown(fs_type)) {
-			ksft_test_result_skip("Unknown filesystem\n");
-			return;
+			ksft_print_msg("Unknown filesystem\n");
+			result = KSFT_SKIP;
+			goto report;
 		}
 		should_work = !shared ||
 			      fs_supports_writable_longterm_pinning(fs_type);
@@ -208,8 +235,9 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
 		/* Skip on errors, as we might just lack kernel support. */
 		ret = io_uring_queue_init(1, &ring, 0);
 		if (ret < 0) {
-			ksft_test_result_skip("io_uring_queue_init() failed (%s)\n",
-					      strerror(-ret));
+			ksft_print_msg("io_uring_queue_init() failed (%s)\n",
+				       strerror(-ret));
+			result = KSFT_SKIP;
 			break;
 		}
 		/*
@@ -222,17 +250,28 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
 		/* Only new kernels return EFAULT. */
 		if (ret && (errno == ENOSPC || errno == EOPNOTSUPP ||
 			    errno == EFAULT)) {
-			ksft_test_result(!should_work, "Should have failed (%s)\n",
-					 strerror(errno));
+			if (should_work) {
+				ksft_print_msg("Should have failed (%s)\n",
+					       strerror(errno));
+				result = KSFT_FAIL;
+			} else {
+				result = KSFT_PASS;
+			}
 		} else if (ret) {
 			/*
 			 * We might just lack support or have insufficient
 			 * MEMLOCK limits.
 			 */
-			ksft_test_result_skip("io_uring_register_buffers() failed (%s)\n",
-					      strerror(-ret));
+			ksft_print_msg("io_uring_register_buffers() failed (%s)\n",
+				       strerror(-ret));
+			result = KSFT_SKIP;
 		} else {
-			ksft_test_result(should_work, "Should have worked\n");
+			if (should_work) {
+				result = KSFT_PASS;
+			} else {
+				ksft_print_msg("Should have worked\n");
+				result = KSFT_FAIL;
+			}
 			io_uring_unregister_buffers(&ring);
 		}
 
@@ -246,6 +285,8 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
 
 munmap:
 	munmap(mem, size);
+report:
+	log_test_result(result);
 }
 
 typedef void (*test_fn)(int fd, size_t size);
@@ -254,13 +295,11 @@ static void run_with_memfd(test_fn fn, const char *desc)
 {
 	int fd;
 
-	ksft_print_msg("[RUN] %s ... with memfd\n", desc);
+	log_test_start("%s ... with memfd", desc);
 
 	fd = memfd_create("test", 0);
-	if (fd < 0) {
-		ksft_test_result_fail("memfd_create() failed (%s)\n", strerror(errno));
-		return;
-	}
+	if (fd < 0)
+		ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno));
 
 	fn(fd, pagesize);
 	close(fd);
@@ -271,23 +310,23 @@ static void run_with_tmpfile(test_fn fn, const char *desc)
 	FILE *file;
 	int fd;
 
-	ksft_print_msg("[RUN] %s ... with tmpfile\n", desc);
+	log_test_start("%s ... with tmpfile", desc);
 
 	file = tmpfile();
 	if (!file) {
-		ksft_test_result_fail("tmpfile() failed (%s)\n", strerror(errno));
-		return;
-	}
-
-	fd = fileno(file);
-	if (fd < 0) {
-		ksft_test_result_fail("fileno() failed (%s)\n", strerror(errno));
-		goto close;
+		ksft_print_msg("tmpfile() failed (%s)\n", strerror(errno));
+		fd = -1;
+	} else {
+		fd = fileno(file);
+		if (fd < 0) {
+			ksft_print_msg("fileno() failed (%s)\n", strerror(errno));
+		}
 	}
 
 	fn(fd, pagesize);
-close:
-	fclose(file);
+
+	if (file)
+		fclose(file);
 }
 
 static void run_with_local_tmpfile(test_fn fn, const char *desc)
@@ -295,22 +334,22 @@ static void run_with_local_tmpfile(test_fn fn, const char *desc)
 	char filename[] = __FILE__"_tmpfile_XXXXXX";
 	int fd;
 
-	ksft_print_msg("[RUN] %s ... with local tmpfile\n", desc);
+	log_test_start("%s ... with local tmpfile", desc);
 
 	fd = mkstemp(filename);
-	if (fd < 0) {
-		ksft_test_result_fail("mkstemp() failed (%s)\n", strerror(errno));
-		return;
-	}
+	if (fd < 0)
+		ksft_print_msg("mkstemp() failed (%s)\n", strerror(errno));
 
 	if (unlink(filename)) {
-		ksft_test_result_fail("unlink() failed (%s)\n", strerror(errno));
-		goto close;
+		ksft_print_msg("unlink() failed (%s)\n", strerror(errno));
+		close(fd);
+		fd = -1;
 	}
 
 	fn(fd, pagesize);
-close:
-	close(fd);
+
+	if (fd >= 0)
+		close(fd);
 }
 
 static void run_with_memfd_hugetlb(test_fn fn, const char *desc,
@@ -319,15 +358,14 @@ static void run_with_memfd_hugetlb(test_fn fn, const char *desc,
 	int flags = MFD_HUGETLB;
 	int fd;
 
-	ksft_print_msg("[RUN] %s ... with memfd hugetlb (%zu kB)\n", desc,
+	log_test_start("%s ... with memfd hugetlb (%zu kB)", desc,
 		       hugetlbsize / 1024);
 
 	flags |= __builtin_ctzll(hugetlbsize) << MFD_HUGE_SHIFT;
 
 	fd = memfd_create("test", flags);
 	if (fd < 0) {
-		ksft_test_result_skip("memfd_create() failed (%s)\n", strerror(errno));
-		return;
+		ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno));
 	}
 
 	fn(fd, hugetlbsize);
@@ -455,7 +493,7 @@ static int tests_per_test_case(void)
 
 int main(int argc, char **argv)
 {
-	int i, err;
+	int i;
 
 	pagesize = getpagesize();
 	nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes,
@@ -469,9 +507,5 @@ int main(int argc, char **argv)
 	for (i = 0; i < ARRAY_SIZE(test_cases); i++)
 		run_test_case(&test_cases[i]);
 
-	err = ksft_get_fail_cnt();
-	if (err)
-		ksft_exit_fail_msg("%d out of %d tests failed\n",
-				   err, ksft_test_num());
-	ksft_exit_pass();
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/mm/madv_populate.c b/tools/testing/selftests/mm/madv_populate.c
index ef7d911da13e..b6fabd5c27ed 100644
--- a/tools/testing/selftests/mm/madv_populate.c
+++ b/tools/testing/selftests/mm/madv_populate.c
@@ -172,12 +172,12 @@ static void test_populate_read(void)
 	if (addr == MAP_FAILED)
 		ksft_exit_fail_msg("mmap failed\n");
 	ksft_test_result(range_is_not_populated(addr, SIZE),
-			 "range initially not populated\n");
+			 "read range initially not populated\n");
 
 	ret = madvise(addr, SIZE, MADV_POPULATE_READ);
 	ksft_test_result(!ret, "MADV_POPULATE_READ\n");
 	ksft_test_result(range_is_populated(addr, SIZE),
-			 "range is populated\n");
+			 "read range is populated\n");
 
 	munmap(addr, SIZE);
 }
@@ -194,12 +194,12 @@ static void test_populate_write(void)
 	if (addr == MAP_FAILED)
 		ksft_exit_fail_msg("mmap failed\n");
 	ksft_test_result(range_is_not_populated(addr, SIZE),
-			 "range initially not populated\n");
+			 "write range initially not populated\n");
 
 	ret = madvise(addr, SIZE, MADV_POPULATE_WRITE);
 	ksft_test_result(!ret, "MADV_POPULATE_WRITE\n");
 	ksft_test_result(range_is_populated(addr, SIZE),
-			 "range is populated\n");
+			 "write range is populated\n");
 
 	munmap(addr, SIZE);
 }
@@ -247,19 +247,19 @@ static void test_softdirty(void)
 	/* Clear any softdirty bits. */
 	clear_softdirty();
 	ksft_test_result(range_is_not_softdirty(addr, SIZE),
-			 "range is not softdirty\n");
+			 "cleared range is not softdirty\n");
 
 	/* Populating READ should set softdirty. */
 	ret = madvise(addr, SIZE, MADV_POPULATE_READ);
-	ksft_test_result(!ret, "MADV_POPULATE_READ\n");
+	ksft_test_result(!ret, "softdirty MADV_POPULATE_READ\n");
 	ksft_test_result(range_is_not_softdirty(addr, SIZE),
-			 "range is not softdirty\n");
+			 "range is not softdirty after MADV_POPULATE_READ\n");
 
 	/* Populating WRITE should set softdirty. */
 	ret = madvise(addr, SIZE, MADV_POPULATE_WRITE);
-	ksft_test_result(!ret, "MADV_POPULATE_WRITE\n");
+	ksft_test_result(!ret, "softdirty MADV_POPULATE_WRITE\n");
 	ksft_test_result(range_is_softdirty(addr, SIZE),
-			 "range is softdirty\n");
+			 "range is softdirty after MADV_POPULATE_WRITE \n");
 
 	munmap(addr, SIZE);
 }
diff --git a/tools/testing/selftests/mm/mlock2-tests.c b/tools/testing/selftests/mm/mlock2-tests.c
index 7f0d50fa361d..3e90ff37e336 100644
--- a/tools/testing/selftests/mm/mlock2-tests.c
+++ b/tools/testing/selftests/mm/mlock2-tests.c
@@ -196,7 +196,7 @@ static void test_mlock_lock(void)
 		ksft_exit_fail_msg("munlock(): %s\n", strerror(errno));
 	}
 
-	ksft_test_result(!unlock_lock_check(map), "%s: Locked\n", __func__);
+	ksft_test_result(!unlock_lock_check(map), "%s: Unlocked\n", __func__);
 	munmap(map, 2 * page_size);
 }
 
diff --git a/tools/testing/selftests/mm/pfnmap.c b/tools/testing/selftests/mm/pfnmap.c
index 8a9d19b6020c..866ac023baf5 100644
--- a/tools/testing/selftests/mm/pfnmap.c
+++ b/tools/testing/selftests/mm/pfnmap.c
@@ -12,6 +12,8 @@
 #include <stdint.h>
 #include <unistd.h>
 #include <errno.h>
+#include <stdio.h>
+#include <ctype.h>
 #include <fcntl.h>
 #include <signal.h>
 #include <setjmp.h>
@@ -43,14 +45,62 @@ static int test_read_access(char *addr, size_t size, size_t pagesize)
 			/* Force a read that the compiler cannot optimize out. */
 			*((volatile char *)(addr + offs));
 	}
-	if (signal(SIGSEGV, signal_handler) == SIG_ERR)
+	if (signal(SIGSEGV, SIG_DFL) == SIG_ERR)
 		return -EINVAL;
 
 	return ret;
 }
 
+static int find_ram_target(off_t *phys_addr,
+		unsigned long long pagesize)
+{
+	unsigned long long start, end;
+	char line[80], *end_ptr;
+	FILE *file;
+
+	/* Search /proc/iomem for the first suitable "System RAM" range. */
+	file = fopen("/proc/iomem", "r");
+	if (!file)
+		return -errno;
+
+	while (fgets(line, sizeof(line), file)) {
+		/* Ignore any child nodes. */
+		if (!isalnum(line[0]))
+			continue;
+
+		if (!strstr(line, "System RAM\n"))
+			continue;
+
+		start = strtoull(line, &end_ptr, 16);
+		/* Skip over the "-" */
+		end_ptr++;
+		/* Make end "exclusive". */
+		end = strtoull(end_ptr, NULL, 16) + 1;
+
+		/* Actual addresses are not exported */
+		if (!start && !end)
+			break;
+
+		/* We need full pages. */
+		start = (start + pagesize - 1) & ~(pagesize - 1);
+		end &= ~(pagesize - 1);
+
+		if (start != (off_t)start)
+			break;
+
+		/* We need two pages. */
+		if (end > start + 2 * pagesize) {
+			fclose(file);
+			*phys_addr = start;
+			return 0;
+		}
+	}
+	return -ENOENT;
+}
+
 FIXTURE(pfnmap)
 {
+	off_t phys_addr;
 	size_t pagesize;
 	int dev_mem_fd;
 	char *addr1;
@@ -63,14 +113,17 @@ FIXTURE_SETUP(pfnmap)
 {
 	self->pagesize = getpagesize();
 
+	/* We'll require two physical pages throughout our tests ... */
+	if (find_ram_target(&self->phys_addr, self->pagesize))
+		SKIP(return, "Cannot find ram target in '/proc/iomem'\n");
+
 	self->dev_mem_fd = open("/dev/mem", O_RDONLY);
 	if (self->dev_mem_fd < 0)
 		SKIP(return, "Cannot open '/dev/mem'\n");
 
-	/* We'll require the first two pages throughout our tests ... */
 	self->size1 = self->pagesize * 2;
 	self->addr1 = mmap(NULL, self->size1, PROT_READ, MAP_SHARED,
-			   self->dev_mem_fd, 0);
+			   self->dev_mem_fd, self->phys_addr);
 	if (self->addr1 == MAP_FAILED)
 		SKIP(return, "Cannot mmap '/dev/mem'\n");
 
@@ -129,7 +182,7 @@ TEST_F(pfnmap, munmap_split)
 	 */
 	self->size2 = self->pagesize;
 	self->addr2 = mmap(NULL, self->pagesize, PROT_READ, MAP_SHARED,
-			   self->dev_mem_fd, 0);
+			   self->dev_mem_fd, self->phys_addr);
 	ASSERT_NE(self->addr2, MAP_FAILED);
 }
 
diff --git a/tools/testing/selftests/mm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c
index cd5174d735be..a41bc1234b37 100644
--- a/tools/testing/selftests/mm/thuge-gen.c
+++ b/tools/testing/selftests/mm/thuge-gen.c
@@ -127,7 +127,7 @@ void test_mmap(unsigned long size, unsigned flags)
 
 	show(size);
 	ksft_test_result(size == getpagesize() || (before - after) == NUM_PAGES,
-			 "%s mmap %lu\n", __func__, size);
+			 "%s mmap %lu %x\n", __func__, size, flags);
 
 	if (munmap(map, size * NUM_PAGES))
 		ksft_exit_fail_msg("%s: unmap %s\n", __func__, strerror(errno));
@@ -165,7 +165,7 @@ void test_shmget(unsigned long size, unsigned flags)
 
 	show(size);
 	ksft_test_result(size == getpagesize() || (before - after) == NUM_PAGES,
-			 "%s: mmap %lu\n", __func__, size);
+			 "%s: mmap %lu %x\n", __func__, size, flags);
 	if (shmdt(map))
 		ksft_exit_fail_msg("%s: shmdt: %s\n", __func__, strerror(errno));
 }
diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh
index 1f92e8caceac..325de53966b6 100755
--- a/tools/testing/selftests/mm/va_high_addr_switch.sh
+++ b/tools/testing/selftests/mm/va_high_addr_switch.sh
@@ -7,23 +7,20 @@
 # real test to check that the kernel is configured to support at least 5
 # pagetable levels.
 
-# 1 means the test failed
-exitcode=1
-
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 
-fail()
+skip()
 {
 	echo "$1"
-	exit $exitcode
+	exit $ksft_skip
 }
 
 check_supported_x86_64()
 {
 	local config="/proc/config.gz"
 	[[ -f "${config}" ]] || config="/boot/config-$(uname -r)"
-	[[ -f "${config}" ]] || fail "Cannot find kernel config in /proc or /boot"
+	[[ -f "${config}" ]] || skip "Cannot find kernel config in /proc or /boot"
 
 	# gzip -dcfq automatically handles both compressed and plaintext input.
 	# See man 1 gzip under '-f'.
@@ -33,11 +30,9 @@ check_supported_x86_64()
 		else {print 1}; exit}' /proc/cpuinfo 2>/dev/null)
 
 	if [[ "${pg_table_levels}" -lt 5 ]]; then
-		echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test"
-		exit $ksft_skip
+		skip "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test"
 	elif [[ "${cpu_supports_pl5}" -ne 0 ]]; then
-		echo "$0: CPU does not have the necessary la57 flag to support page table level 5"
-		exit $ksft_skip
+		skip "$0: CPU does not have the necessary la57 flag to support page table level 5"
 	fi
 }
 
@@ -45,24 +40,21 @@ check_supported_ppc64()
 {
 	local config="/proc/config.gz"
 	[[ -f "${config}" ]] || config="/boot/config-$(uname -r)"
-	[[ -f "${config}" ]] || fail "Cannot find kernel config in /proc or /boot"
+	[[ -f "${config}" ]] || skip "Cannot find kernel config in /proc or /boot"
 
 	local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2)
 	if [[ "${pg_table_levels}" -lt 5 ]]; then
-		echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test"
-		exit $ksft_skip
+		skip "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test"
 	fi
 
 	local mmu_support=$(grep -m1 "mmu" /proc/cpuinfo | awk '{print $3}')
 	if [[ "$mmu_support" != "radix" ]]; then
-		echo "$0: System does not use Radix MMU, required for 5-level paging"
-		exit $ksft_skip
+		skip "$0: System does not use Radix MMU, required for 5-level paging"
 	fi
 
 	local hugepages_total=$(awk '/HugePages_Total/ {print $2}' /proc/meminfo)
 	if [[ "${hugepages_total}" -eq 0 ]]; then
-		echo "$0: HugePages are not enabled, required for some tests"
-		exit $ksft_skip
+		skip "$0: HugePages are not enabled, required for some tests"
 	fi
 }
 
diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c
index 1357e2d6a7b6..61d7bf1f8c62 100644
--- a/tools/testing/selftests/mm/vm_util.c
+++ b/tools/testing/selftests/mm/vm_util.c
@@ -439,7 +439,7 @@ int open_procmap(pid_t pid, struct procmap_fd *procmap_out)
 	sprintf(path, "/proc/%d/maps", pid);
 	procmap_out->query.size = sizeof(procmap_out->query);
 	procmap_out->fd = open(path, O_RDONLY);
-	if (procmap_out < 0)
+	if (procmap_out->fd < 0)
 		ret = -errno;
 
 	return ret;
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index 9211ba640d9c..adb5d294a220 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -3,6 +3,7 @@
 #include <stdbool.h>
 #include <sys/mman.h>
 #include <err.h>
+#include <stdarg.h>
 #include <strings.h> /* ffsl() */
 #include <unistd.h> /* _SC_PAGESIZE */
 #include "../kselftest.h"
@@ -95,6 +96,25 @@ static inline int open_self_procmap(struct procmap_fd *procmap_out)
 	return open_procmap(pid, procmap_out);
 }
 
+/* These helpers need to be inline to match the kselftest.h idiom. */
+static char test_name[1024];
+
+static inline void log_test_start(const char *name, ...)
+{
+	va_list args;
+	va_start(args, name);
+
+	vsnprintf(test_name, sizeof(test_name), name, args);
+	ksft_print_msg("[RUN] %s\n", test_name);
+
+	va_end(args);
+}
+
+static inline void log_test_result(int result)
+{
+	ksft_test_result_report(result, "%s\n", test_name);
+}
+
 /*
  * On ppc64 this will only work with radix 2M hugepage size
  */
diff --git a/tools/testing/selftests/net/netfilter/nft_concat_range.sh b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
index efea93cf23d4..cd12b8b5ac0e 100755
--- a/tools/testing/selftests/net/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
@@ -378,7 +378,7 @@ display		net,port,proto
 type_spec	ipv4_addr . inet_service . inet_proto
 chain_spec	ip daddr . udp dport . meta l4proto
 dst		addr4 port proto
-src
+src		 
 start		1
 count		9
 src_delta	9
@@ -419,6 +419,7 @@ table inet filter {
 
 	set test {
 		type ${type_spec}
+		counter
 		flags interval,timeout
 	}
 
@@ -1158,9 +1159,18 @@ del() {
 	fi
 }
 
-# Return packet count from 'test' counter in 'inet filter' table
+# Return packet count for elem $1 from 'test' counter in 'inet filter' table
 count_packets() {
 	found=0
+	for token in $(nft reset element inet filter test "${1}" ); do
+		[ ${found} -eq 1 ] && echo "${token}" && return
+		[ "${token}" = "packets" ] && found=1
+	done
+}
+
+# Return packet count from 'test' counter in 'inet filter' table
+count_packets_nomatch() {
+	found=0
 	for token in $(nft list counter inet filter test); do
 		[ ${found} -eq 1 ] && echo "${token}" && return
 		[ "${token}" = "packets" ] && found=1
@@ -1206,6 +1216,10 @@ perf() {
 
 # Set MAC addresses, send single packet, check that it matches, reset counter
 send_match() {
+	local elem="$1"
+
+	shift
+
 	ip link set veth_a address "$(format_mac "${1}")"
 	ip -n B link set veth_b address "$(format_mac "${2}")"
 
@@ -1216,7 +1230,7 @@ send_match() {
 		eval src_"$f"=\$\(format_\$f "${2}"\)
 	done
 	eval send_\$proto
-	if [ "$(count_packets)" != "1" ]; then
+	if [ "$(count_packets "$elem")" != "1" ]; then
 		err "${proto} packet to:"
 		err "  $(for f in ${dst}; do
 			 eval format_\$f "${1}"; printf ' '; done)"
@@ -1242,7 +1256,7 @@ send_nomatch() {
 		eval src_"$f"=\$\(format_\$f "${2}"\)
 	done
 	eval send_\$proto
-	if [ "$(count_packets)" != "0" ]; then
+	if [ "$(count_packets_nomatch)" != "0" ]; then
 		err "${proto} packet to:"
 		err "  $(for f in ${dst}; do
 			 eval format_\$f "${1}"; printf ' '; done)"
@@ -1255,6 +1269,42 @@ send_nomatch() {
 	fi
 }
 
+maybe_send_nomatch() {
+	local elem="$1"
+	local what="$4"
+
+	[ $((RANDOM%20)) -gt 0 ] && return
+
+	dst_addr4="$2"
+	dst_port="$3"
+	send_udp
+
+	if [ "$(count_packets_nomatch)" != "0" ]; then
+		err "Packet to $dst_addr4:$dst_port did match $what"
+		err "$(nft -a list ruleset)"
+		return 1
+	fi
+}
+
+maybe_send_match() {
+	local elem="$1"
+	local what="$4"
+
+	[ $((RANDOM%20)) -gt 0 ] && return
+
+	dst_addr4="$2"
+	dst_port="$3"
+	send_udp
+
+	if [ "$(count_packets "{ $elem }")" != "1" ]; then
+		err "Packet to $dst_addr4:$dst_port did not match $what"
+		err "$(nft -a list ruleset)"
+		return 1
+	fi
+	nft reset counter inet filter test >/dev/null
+	nft reset element inet filter test "{ $elem }" >/dev/null
+}
+
 # Correctness test template:
 # - add ranged element, check that packets match it
 # - check that packets outside range don't match it
@@ -1262,6 +1312,8 @@ send_nomatch() {
 test_correctness_main() {
 	range_size=1
 	for i in $(seq "${start}" $((start + count))); do
+		local elem=""
+
 		end=$((start + range_size))
 
 		# Avoid negative or zero-sized port ranges
@@ -1272,15 +1324,16 @@ test_correctness_main() {
 		srcstart=$((start + src_delta))
 		srcend=$((end + src_delta))
 
-		add "$(format)" || return 1
+		elem="$(format)"
+		add "$elem" || return 1
 		for j in $(seq "$start" $((range_size / 2 + 1)) ${end}); do
-			send_match "${j}" $((j + src_delta)) || return 1
+			send_match "$elem" "${j}" $((j + src_delta)) || return 1
 		done
 		send_nomatch $((end + 1)) $((end + 1 + src_delta)) || return 1
 
 		# Delete elements now and then
 		if [ $((i % 3)) -eq 0 ]; then
-			del "$(format)" || return 1
+			del "$elem" || return 1
 			for j in $(seq "$start" \
 				   $((range_size / 2 + 1)) ${end}); do
 				send_nomatch "${j}" $((j + src_delta)) \
@@ -1572,14 +1625,17 @@ test_timeout() {
 
 	range_size=1
 	for i in $(seq "$start" $((start + count))); do
+		local elem=""
+
 		end=$((start + range_size))
 		srcstart=$((start + src_delta))
 		srcend=$((end + src_delta))
 
-		add "$(format)" || return 1
+		elem="$(format)"
+		add "$elem" || return 1
 
 		for j in $(seq "$start" $((range_size / 2 + 1)) ${end}); do
-			send_match "${j}" $((j + src_delta)) || return 1
+			send_match "$elem" "${j}" $((j + src_delta)) || return 1
 		done
 
 		range_size=$((range_size + 1))
@@ -1737,7 +1793,7 @@ test_bug_reload() {
 		srcend=$((end + src_delta))
 
 		for j in $(seq "$start" $((range_size / 2 + 1)) ${end}); do
-			send_match "${j}" $((j + src_delta)) || return 1
+			send_match "$(format)" "${j}" $((j + src_delta)) || return 1
 		done
 
 		range_size=$((range_size + 1))
@@ -1756,22 +1812,34 @@ test_bug_net_port_proto_match() {
 	range_size=1
 	for i in $(seq 1 10); do
 		for j in $(seq 1 20) ; do
-			elem=$(printf "10.%d.%d.0/24 . %d1-%d0 . 6-17 " ${i} ${j} ${i} "$((i+1))")
+			local dport=$j
+
+			elem=$(printf "10.%d.%d.0/24 . %d-%d0 . 6-17 " ${i} ${j} ${dport} "$((dport+1))")
+
+			# too slow, do not test all addresses
+			maybe_send_nomatch "$elem" $(printf "10.%d.%d.1" $i $j) $(printf "%d1" $((dport+1))) "before add" || return 1
 
 			nft "add element inet filter test { $elem }" || return 1
+
+			maybe_send_match "$elem" $(printf "10.%d.%d.1" $i $j) $(printf "%d" $dport) "after add" || return 1
+
 			nft "get element inet filter test { $elem }" | grep -q "$elem"
 			if [ $? -ne 0 ];then
 				local got=$(nft "get element inet filter test { $elem }")
 				err "post-add: should have returned $elem but got $got"
 				return 1
 			fi
+
+			maybe_send_nomatch "$elem" $(printf "10.%d.%d.1" $i $j) $(printf "%d1" $((dport+1))) "out-of-range" || return 1
 		done
 	done
 
 	# recheck after set was filled
 	for i in $(seq 1 10); do
 		for j in $(seq 1 20) ; do
-			elem=$(printf "10.%d.%d.0/24 . %d1-%d0 . 6-17 " ${i} ${j} ${i} "$((i+1))")
+			local dport=$j
+
+			elem=$(printf "10.%d.%d.0/24 . %d-%d0 . 6-17 " ${i} ${j} ${dport} "$((dport+1))")
 
 			nft "get element inet filter test { $elem }" | grep -q "$elem"
 			if [ $? -ne 0 ];then
@@ -1779,6 +1847,9 @@ test_bug_net_port_proto_match() {
 				err "post-fill: should have returned $elem but got $got"
 				return 1
 			fi
+
+			maybe_send_match "$elem" $(printf "10.%d.%d.1" $i $j) $(printf "%d" $dport) "recheck" || return 1
+			maybe_send_nomatch "$elem" $(printf "10.%d.%d.1" $i $j) $(printf "%d1" $((dport+1))) "recheck out-of-range" || return 1
 		done
 	done
 
@@ -1786,9 +1857,10 @@ test_bug_net_port_proto_match() {
 	for i in $(seq 1 10); do
 		for j in $(seq 1 20) ; do
 			local rnd=$((RANDOM%10))
+			local dport=$j
 			local got=""
 
-			elem=$(printf "10.%d.%d.0/24 . %d1-%d0 . 6-17 " ${i} ${j} ${i} "$((i+1))")
+			elem=$(printf "10.%d.%d.0/24 . %d-%d0 . 6-17 " ${i} ${j} ${dport} "$((dport+1))")
 			if [ $rnd -gt 0 ];then
 				continue
 			fi
@@ -1799,6 +1871,8 @@ test_bug_net_port_proto_match() {
 				err "post-delete: query for $elem returned $got instead of error."
 				return 1
 			fi
+
+			maybe_send_nomatch "$elem" $(printf "10.%d.%d.1" $i $j) $(printf "%d" $dport) "match after deletion" || return 1
 		done
 	done
 
@@ -1817,7 +1891,7 @@ test_bug_avx2_mismatch()
 	dst_addr6="$a2"
 	send_icmp6
 
-	if [ "$(count_packets)" -gt "0" ]; then
+	if [ "$(count_packets "{ icmpv6 . $a1 }")" -gt "0" ]; then
 		err "False match for $a2"
 		return 1
 	fi
diff --git a/tools/testing/selftests/net/netfilter/nft_nat.sh b/tools/testing/selftests/net/netfilter/nft_nat.sh
index 9e39de26455f..a954754b99b3 100755
--- a/tools/testing/selftests/net/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/net/netfilter/nft_nat.sh
@@ -866,6 +866,24 @@ EOF
 	ip netns exec "$ns0" nft delete table $family nat
 }
 
+file_cmp()
+{
+	local infile="$1"
+	local outfile="$2"
+
+	if ! cmp "$infile" "$outfile";then
+		echo -n "Infile "
+		ls -l "$infile"
+		echo -n "Outfile "
+		ls -l "$outfile"
+		echo "ERROR: in and output file mismatch when checking $msg" 1>&1
+		ret=1
+		return 1
+	fi
+
+	return 0
+}
+
 test_stateless_nat_ip()
 {
 	local lret=0
@@ -966,11 +984,7 @@ EOF
 
 	wait
 
-	if ! cmp "$INFILE" "$OUTFILE";then
-		ls -l "$INFILE" "$OUTFILE"
-		echo "ERROR: in and output file mismatch when checking udp with stateless nat" 1>&2
-		lret=1
-	fi
+	file_cmp "$INFILE" "$OUTFILE" "udp with stateless nat" || lret=1
 
 	:> "$OUTFILE"
 
@@ -991,6 +1005,62 @@ EOF
 	return $lret
 }
 
+test_dnat_clash()
+{
+	local lret=0
+
+	if ! socat -h > /dev/null 2>&1;then
+		echo "SKIP: Could not run dnat clash test without socat tool"
+		[ $ret -eq 0 ] && ret=$ksft_skip
+		return $ksft_skip
+	fi
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+flush ruleset
+table ip dnat-test {
+ chain prerouting {
+  type nat hook prerouting priority dstnat; policy accept;
+  ip daddr 10.0.2.1 udp dport 1234 counter dnat to 10.0.1.1:1234
+ }
+}
+EOF
+	if [ $? -ne 0 ]; then
+		echo "SKIP: Could not add dnat rules"
+		[ $ret -eq 0 ] && ret=$ksft_skip
+		return $ksft_skip
+	fi
+
+	local udpdaddr="10.0.2.1"
+	for i in 1 2;do
+		echo "PING $udpdaddr" > "$INFILE"
+		echo "PONG 10.0.1.1 step $i" | ip netns exec "$ns0" timeout 3 socat STDIO UDP4-LISTEN:1234,bind=10.0.1.1 > "$OUTFILE" 2>/dev/null &
+		local lpid=$!
+
+		busywait $BUSYWAIT_TIMEOUT listener_ready "$ns0" 1234 "-u"
+
+		result=$(ip netns exec "$ns1" timeout 3 socat STDIO UDP4-SENDTO:"$udpdaddr:1234,sourceport=4321" < "$INFILE")
+		udpdaddr="10.0.1.1"
+
+		if [ "$result" != "PONG 10.0.1.1 step $i" ] ; then
+			echo "ERROR: failed to test udp $ns1 to $ns2 with dnat rule step $i, result: \"$result\"" 1>&2
+			lret=1
+			ret=1
+		fi
+
+		wait
+
+		file_cmp "$INFILE" "$OUTFILE" "udp dnat step $i" || lret=1
+
+		:> "$OUTFILE"
+	done
+
+	test $lret -eq 0 && echo "PASS: IP dnat clash $ns1:$ns2"
+
+	ip netns exec "$ns0" nft flush ruleset
+
+	return $lret
+}
+
 # ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99
 for i in "$ns0" "$ns1" "$ns2" ;do
 ip netns exec "$i" nft -f /dev/stdin <<EOF
@@ -1147,6 +1217,7 @@ $test_inet_nat && test_redirect6 inet
 
 test_port_shadowing
 test_stateless_nat_ip
+test_dnat_clash
 
 if [ $ret -ne 0 ];then
 	echo -n "FAIL: "
diff --git a/tools/testing/selftests/net/ovpn/ovpn-cli.c b/tools/testing/selftests/net/ovpn/ovpn-cli.c
index de9c26f98b2e..9201f2905f2c 100644
--- a/tools/testing/selftests/net/ovpn/ovpn-cli.c
+++ b/tools/testing/selftests/net/ovpn/ovpn-cli.c
@@ -2166,6 +2166,7 @@ static int ovpn_parse_cmd_args(struct ovpn_ctx *ovpn, int argc, char *argv[])
 
 		ovpn->peers_file = argv[4];
 
+		ovpn->sa_family = AF_INET;
 		if (argc > 5 && !strcmp(argv[5], "ipv6"))
 			ovpn->sa_family = AF_INET6;
 		break;
diff --git a/tools/testing/selftests/net/ovpn/test-large-mtu.sh b/tools/testing/selftests/net/ovpn/test-large-mtu.sh
new file mode 100755
index 000000000000..ce2a2cb64f72
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-large-mtu.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+MTU="1500"
+
+source test.sh
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index f6e45e62da3a..441feb21aa5a 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -1461,4 +1461,9 @@ static inline int __call_mmap_prepare(struct file *file,
 	return file->f_op->mmap_prepare(desc);
 }
 
+static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma)
+{
+	(void)vma;
+}
+
 #endif	/* __MM_VMA_INTERNAL_H */